{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Sklearn" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Bike Sharing Demand Problem\n", "The problem at [kaggle.com](https://www.kaggle.com/c/bike-sharing-demand).\n", "Based on historical data on bicycle rental and weather conditions, it is necessary to evaluate the demand for bicycle rental.\n", "\n", "In the original problem statement, there are 11 features available: https://www.kaggle.com/c/prudential-life-insurance-assessment/data\n", "\n", "The feature set contains both real, categorical, and binary data.\n", "\n", "For the demonstration, a training sample bike_sharing_demand.csv is used from the original data.\n", "\n", "Задача на kaggle: \n", "По историческим данным о прокате велосипедов и погодным условиям необходимо оценить спрос на прокат велосипедов.\n", "В исходной постановке задачи доступно 11 признаков: https://www.kaggle.com/c/prudential-life-insurance-assessment/data\n", "В наборе признаков присутсвуют вещественные, категориальные, и бинарные данные. \n", "Для демонстрации используется обучающая выборка из исходных данных train.csv, файлы для работы прилагаются.\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import warnings\n", "warnings.filterwarnings('ignore')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Libraries" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from sklearn import model_selection, linear_model, metrics\n", "\n", "import numpy as np\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 112, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Populating the interactive namespace from numpy and matplotlib\n" ] } ], "source": [ "%pylab inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Dataset load\n", "We load data into dataframe. " ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "raw_data = pd.read_csv('bike_sharing_demand.csv', header = 0, sep = ',')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
datetimeseasonholidayworkingdayweathertempatemphumiditywindspeedcasualregisteredcount
02011-01-01 00:00:0010019.8414.395810.031316
12011-01-01 01:00:0010019.0213.635800.083240
22011-01-01 02:00:0010019.0213.635800.052732
32011-01-01 03:00:0010019.8414.395750.031013
42011-01-01 04:00:0010019.8414.395750.0011
\n", "
" ], "text/plain": [ " datetime season holiday workingday weather temp atemp \\\n", "0 2011-01-01 00:00:00 1 0 0 1 9.84 14.395 \n", "1 2011-01-01 01:00:00 1 0 0 1 9.02 13.635 \n", "2 2011-01-01 02:00:00 1 0 0 1 9.02 13.635 \n", "3 2011-01-01 03:00:00 1 0 0 1 9.84 14.395 \n", "4 2011-01-01 04:00:00 1 0 0 1 9.84 14.395 \n", "\n", " humidity windspeed casual registered count \n", "0 81 0.0 3 13 16 \n", "1 80 0.0 8 32 40 \n", "2 80 0.0 5 27 32 \n", "3 75 0.0 3 10 13 \n", "4 75 0.0 0 1 1 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "***datetime*** - hourly date + timestamp \n", "\n", "***season*** - 1 = spring, 2 = summer, 3 = fall, 4 = winter \n", "\n", "***holiday*** - whether the day is considered a holiday\n", "\n", "***workingday*** - whether the day is neither a weekend nor holiday\n", "\n", "***weather*** - 1: Clear, Few clouds, Partly cloudy, Partly cloudy\n", "2: Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist\n", "3: Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds\n", "4: Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog \n", " \n", "***temp*** - temperature in Celsius\n", "\n", "***atemp*** - \"feels like\" temperature in Celsius\n", "\n", "***humidity*** - relative humidity\n", "\n", "***windspeed*** - wind speed\n", "\n", "***casual*** - number of non-registered user rentals initiated\n", "\n", "***registered*** - number of registered user rentals initiated\n", "\n", "***count*** - number of total bike rentals, **the target label**" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(10886, 12)\n" ] } ], "source": [ "print(raw_data.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let us check is any **values that are missing** in dataset. If so, we need to process to fill them in." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data.isnull().values.any()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The negative result shows there are no missed data cells/ values." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Data preprocessing" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Типы признаков" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 10886 entries, 0 to 10885\n", "Data columns (total 12 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 datetime 10886 non-null object \n", " 1 season 10886 non-null int64 \n", " 2 holiday 10886 non-null int64 \n", " 3 workingday 10886 non-null int64 \n", " 4 weather 10886 non-null int64 \n", " 5 temp 10886 non-null float64\n", " 6 atemp 10886 non-null float64\n", " 7 humidity 10886 non-null int64 \n", " 8 windspeed 10886 non-null float64\n", " 9 casual 10886 non-null int64 \n", " 10 registered 10886 non-null int64 \n", " 11 count 10886 non-null int64 \n", "dtypes: float64(3), int64(8), object(1)\n", "memory usage: 1020.7+ KB\n" ] } ], "source": [ "raw_data.info()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We may see here that almost all the data are presented as numbers, whether integers or floating point ones.\n", "#### Transform into the *datetime* type\n", "So, let's transform **datetime** feature (of a type *object*) into the *datetime* type in the dataframe:" ] }, { "cell_type": "code", "execution_count": 111, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
datetimeseasonholidayworkingdayweathertempatemphumiditywindspeedcasualregisteredcountmonthhour
43202011-10-12 01:00:00401322.9626.515838.99812810101
73552012-05-05 20:00:00200124.6028.7907816.9979100209309520
98542012-10-14 23:00:00400222.9626.5156819.001227781051023
\n", "
" ], "text/plain": [ " datetime season holiday workingday weather temp atemp \\\n", "4320 2011-10-12 01:00:00 4 0 1 3 22.96 26.515 \n", "7355 2012-05-05 20:00:00 2 0 0 1 24.60 28.790 \n", "9854 2012-10-14 23:00:00 4 0 0 2 22.96 26.515 \n", "\n", " humidity windspeed casual registered count month hour \n", "4320 83 8.9981 2 8 10 10 1 \n", "7355 78 16.9979 100 209 309 5 20 \n", "9854 68 19.0012 27 78 105 10 23 " ] }, "execution_count": 111, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data.datetime = raw_data.datetime.apply(pd.to_datetime)\n", "raw_data.sample(3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 2 new features from datetime\n", "Based on that transformed feature we calculate 2 new features: **month** and **hour** of the event (rental)." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "raw_data['month'] = raw_data.datetime.apply(lambda x : x.month)\n", "raw_data['hour'] = raw_data.datetime.apply(lambda x : x.hour)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
datetimeseasonholidayworkingdayweathertempatemphumiditywindspeedcasualregisteredcountmonthhour
68642012-04-04 08:00:00201218.0421.970727.00153165368448
62902012-02-18 08:00:0010019.0213.635870.0000109210228
37652011-09-07 20:00:00301326.2428.790896.003239396920
\n", "
" ], "text/plain": [ " datetime season holiday workingday weather temp atemp \\\n", "6864 2012-04-04 08:00:00 2 0 1 2 18.04 21.970 \n", "6290 2012-02-18 08:00:00 1 0 0 1 9.02 13.635 \n", "3765 2011-09-07 20:00:00 3 0 1 3 26.24 28.790 \n", "\n", " humidity windspeed casual registered count month hour \n", "6864 72 7.0015 31 653 684 4 8 \n", "6290 87 0.0000 10 92 102 2 8 \n", "3765 89 6.0032 3 93 96 9 20 " ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data.sample(3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Splitting the model into the train and test sets.\n", "Note that the data are **time dependent**, **time spread**. So we might get the train data of earlier period and evaluate the built estimator on the test set of later period. Since the data are sorted by time, we just cut of the last 1000 rows and use them as a test set. " ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "train_data = raw_data.iloc[:-1000, :]\n", "hold_out_test_data = raw_data.iloc[-1000:, :]" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(10886, 14) (9886, 14) (1000, 14)\n" ] } ], "source": [ "print(raw_data.shape, train_data.shape, hold_out_test_data.shape)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "train period from 2011-01-01 00:00:00 to 2012-10-16 06:00:00\n", "evaluation period from 2012-10-16 07:00:00 to 2012-12-19 23:00:00\n" ] } ], "source": [ "print('train period from {} to {}'.format(train_data.datetime.min(), train_data.datetime.max()))\n", "print('evaluation period from {} to {}'.format(hold_out_test_data.datetime.min(), hold_out_test_data.datetime.max()))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Data and target function\n", "We cut off the target, column **count** from the rest of dataset.\n", "\n", "We also cut off the **datetime** data column since it's now only an object identifier." ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "# training dataset\n", "train_labels = train_data['count'].values\n", "train_data = train_data.drop(['datetime', 'count'], axis = 1)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "# test dataset\n", "test_labels = hold_out_test_data['count'].values\n", "test_data = hold_out_test_data.drop(['datetime', 'count'], axis = 1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Let's visualize the target function (label) at the train and test sets.\n", "Remember that target label (**count**) shows how many bikes were rented at that time spot (hour)." ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5, 1.0, 'test data')" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "pylab.figure(figsize = (16, 6))\n", "\n", "pylab.subplot(1,2,1)\n", "pylab.hist(train_labels)\n", "pylab.title('train data')\n", "\n", "pylab.subplot(1,2,2)\n", "pylab.hist(test_labels)\n", "pylab.title('test data')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Numeric features\n", "In this post we work only with numeric features. Let's separate them." ] }, { "cell_type": "code", "execution_count": 110, "metadata": {}, "outputs": [], "source": [ "numeric_columns = ['temp', 'atemp', 'humidity',\\\n", "'windspeed', 'casual', 'registered', 'month', 'hour']" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "train_data = train_data[numeric_columns]\n", "test_data = test_data[numeric_columns]" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
tempatemphumiditywindspeedcasualregisteredmonthhour
09.8414.395810.031310
19.0213.635800.083211
29.0213.635800.052712
39.8414.395750.031013
49.8414.395750.00114
\n", "
" ], "text/plain": [ " temp atemp humidity windspeed casual registered month hour\n", "0 9.84 14.395 81 0.0 3 13 1 0\n", "1 9.02 13.635 80 0.0 8 32 1 1\n", "2 9.02 13.635 80 0.0 5 27 1 2\n", "3 9.84 14.395 75 0.0 3 10 1 3\n", "4 9.84 14.395 75 0.0 0 1 1 4" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_data.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### We now train a model with SGDRegressor\n", "SGDRegressor develops a model based on [Stochastic Gradient Descent](/linear-regression-stochastic-gradient-descent/).\n", "\n", "We supply the default paramets for the regressor model." ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'alpha': 0.0001,\n", " 'average': False,\n", " 'early_stopping': False,\n", " 'epsilon': 0.1,\n", " 'eta0': 0.01,\n", " 'fit_intercept': True,\n", " 'l1_ratio': 0.15,\n", " 'learning_rate': 'invscaling',\n", " 'loss': 'squared_loss',\n", " 'max_iter': 5,\n", " 'n_iter_no_change': 5,\n", " 'penalty': 'l2',\n", " 'power_t': 0.25,\n", " 'random_state': 0,\n", " 'shuffle': True,\n", " 'tol': 0.001,\n", " 'validation_fraction': 0.1,\n", " 'verbose': 0,\n", " 'warm_start': False}" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "regressor = linear_model.SGDRegressor(random_state = 0, max_iter=5)\n", "regressor.get_params()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "1. Train the model `regressor.fit()` \n", "2. Estimate the model with MAE `mean_absolute_error`" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "data": { "text/plain": [ "9340385490952.236" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "regressor.fit(train_data, train_labels)\n", "metrics.mean_absolute_error(test_labels, regressor.predict(test_data))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The number is too big...\n", "\n", "Let's output the targets and model predictions:" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Target\n", " [525 835 355 222 228 325 328 308 346 446]\n" ] } ], "source": [ "print('Target\\n', test_labels[:10])" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Prediction\n", " [1.47320172e+13 2.64787988e+13 1.23495857e+13 1.35429951e+13\n", " 1.25998915e+13 1.74809610e+13 1.75786549e+13 2.11426913e+13\n", " 1.96417926e+13 2.32672606e+13]\n" ] } ], "source": [ "print('Prediction\\n', regressor.predict(test_data)[:10])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The model predicts super big numbers. It should not be this way.\n", "\n", "Let's take a look at the regression coefficients." ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([ 1.12866511e+10, 6.68434729e+10, -7.05920006e+10, -2.09051100e+10,\n", " 1.65497847e+11, 2.92967602e+10, -6.71456293e+10, 8.32559786e+10])" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "regressor.coef_" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "The regression model coefficients are too high. This might happen if the features differ in scale. \n", "### Scaling the features" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [], "source": [ "from sklearn.preprocessing import StandardScaler" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We separately apply **StandardScaler** to the train and test data." ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [], "source": [ "# create StandardScaler and train/fit it\n", "scaler = StandardScaler()\n", "scaler.fit(train_data, train_labels)\n", "scaled_train_data = scaler.transform(train_data)\n", "scaled_test_data = scaler.transform(test_data)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "After we've got scaled data we train the model again." ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "data": { "text/plain": [ "0.11793762963431514" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "regressor.fit(scaled_train_data, train_labels)\n", "metrics.mean_absolute_error(test_labels, regressor.predict(scaled_test_data))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The error is in this case is very low. \n", "\n", "If we output targets and predictions (below), we see that the model has done a good estimation. The distance is less than 1 bike." ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[525 835 355 222 228 325 328 308 346 446]\n" ] } ], "source": [ "print(test_labels[:10])" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[524.83, 834.83, 354.86, 221.89, 227.84, 324.88, 327.9, 307.93, 345.9, 445.9]" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(map(lambda x : round(x, 2), regressor.predict(scaled_test_data)[:10]))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### The regression result is suspiciously good\n", "We take a look at the coefficients and see that almost all of the weights are too small." ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "regressor.coef_\n", " [1.41, -1.41, 0.01, -0.04, 50.86, 148.0, -0.01, 0.01]\n" ] } ], "source": [ "#print(regressor.coef_)\n", "map_obj = map(lambda x : round(x, 2), regressor.coef_)\n", "print('regressor.coef_\\n', list(map_obj))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "What are the features with non-small weights, 50.86, 148.0 ? \n", "\n", "*Casual* and *register* features are." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### How does the bike rental system work?\n", "The bike rental system works as follows: both registered and unregistered users can use the system. In this case, column **registered** represent the number of registered users who use the system. The **casual** column shows the number of users who have not registered but also want to rent a bike. \n", "\n", "Let's output the values of the target function and see the following pattern: if the **value of these two columns (*registered* and *casual*) is added together, we get our target label**." ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([16, 40, 32, 13, 1, 1, 2, 3, 8, 14], dtype=int64)" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_labels[:10]" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.all(train_data.registered + train_data.casual == train_labels)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This was our mistake. We indeed used the features in dataset (**casual**, **registered**) that replicate the target, **count**. \n", "\n", "So we cut off these data (columns) from train and test sets to properly build regession model." ] }, { "cell_type": "code", "execution_count": 106, "metadata": {}, "outputs": [ { "ename": "KeyError", "evalue": "\"['casual' 'registered'] not found in axis\"", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtrain_data\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdrop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'casual'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'registered'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minplace\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mtest_data\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdrop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'casual'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'registered'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minplace\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36mdrop\u001b[1;34m(self, labels, axis, index, columns, level, inplace, errors)\u001b[0m\n\u001b[0;32m 4161\u001b[0m \u001b[0mweight\u001b[0m \u001b[1;36m1.0\u001b[0m \u001b[1;36m0.8\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4162\u001b[0m \"\"\"\n\u001b[1;32m-> 4163\u001b[1;33m return super().drop(\n\u001b[0m\u001b[0;32m 4164\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4165\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36mdrop\u001b[1;34m(self, labels, axis, index, columns, level, inplace, errors)\u001b[0m\n\u001b[0;32m 3885\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m \u001b[1;32min\u001b[0m \u001b[0maxes\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3886\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mlabels\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3887\u001b[1;33m \u001b[0mobj\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_drop_axis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlevel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0merrors\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3888\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3889\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m_drop_axis\u001b[1;34m(self, labels, axis, level, errors)\u001b[0m\n\u001b[0;32m 3919\u001b[0m \u001b[0mnew_axis\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdrop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlevel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0merrors\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3920\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3921\u001b[1;33m \u001b[0mnew_axis\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdrop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0merrors\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3922\u001b[0m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreindex\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[1;33m{\u001b[0m\u001b[0maxis_name\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mnew_axis\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3923\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mdrop\u001b[1;34m(self, labels, errors)\u001b[0m\n\u001b[0;32m 5280\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mmask\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0many\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5281\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0merrors\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[1;34m\"ignore\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5282\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"{labels[mask]} not found in axis\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5283\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m~\u001b[0m\u001b[0mmask\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5284\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdelete\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mKeyError\u001b[0m: \"['casual' 'registered'] not found in axis\"" ] } ], "source": [ "train_data.drop(['casual', 'registered'], axis = 1, inplace = True)\n", "test_data.drop(['casual', 'registered'], axis = 1, inplace = True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We scale the features with the new dataset and train/fit the model and estimate by MAE." ] }, { "cell_type": "code", "execution_count": 72, "metadata": {}, "outputs": [], "source": [ "scaler.fit(train_data, train_labels)\n", "scaled_train_data = scaler.transform(train_data)\n", "scaled_test_data = scaler.transform(test_data)" ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "data": { "text/plain": [ "121.81123864993025" ] }, "execution_count": 73, "metadata": {}, "output_type": "execute_result" } ], "source": [ "regressor.fit(scaled_train_data, train_labels)\n", "metrics.mean_absolute_error(test_labels, regressor.predict(scaled_test_data))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The above MAE is more realistic.\n", "\n", "The all model weights are influence the model predictions." ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[31.03, 29.96, -41.93, 6.17, 14.08, 49.6]\n" ] } ], "source": [ "print(list(map(lambda x : round(x, 2), regressor.coef_)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Pipeline\n", "\n", "Up to now we were solving the problem with default parameters of the regressor model. Now we have a certain base-level model.\n", "\n", "Now we will select optimal parameters for a regressor model.\n", "\n", "Yet to train/fit the model we need to scale [only] a train dataset. Since we use cross-validation (CV) we'll need to scale each CV training dataset at each CV step. Therefore we make a **Pipeline**. Pipeline implies transformation chains. Particulary it'll include 2 chains: (1) scaling and (2) regressotion itself at each iteration. *Sklearn* library does allow us to do both scaling of at each iteration and CV thru **Pipeline** module." ] }, { "cell_type": "code", "execution_count": 75, "metadata": {}, "outputs": [], "source": [ "from sklearn.pipeline import Pipeline" ] }, { "cell_type": "code", "execution_count": 76, "metadata": {}, "outputs": [], "source": [ "# make a pipeline from two steps: scaling and classification\n", "pipeline = Pipeline(steps = [('scaling', scaler), ('regression', regressor)])\n", "# both methods `scaler` and `regressor` should posess methods fit() and perdict()" ] }, { "cell_type": "code", "execution_count": 78, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "data": { "text/plain": [ "121.81123864993025" ] }, "execution_count": 78, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pipeline.fit(train_data, train_labels)\n", "metrics.mean_absolute_error(test_labels, pipeline.predict(test_data))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The error (above) remained the same. Pipeline works well.\n", "### Parameters selection\n", "We select parameters by grid. \n", "\n", "In the case of using Pipeline, we need to refer to the model parameters using the extended name. \n", "\n", "First, we need to specify the name of the step, then a double underscore goes, then the name of the parameter itself follows." ] }, { "cell_type": "code", "execution_count": 79, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dict_keys(['memory', 'steps', 'verbose', 'scaling', 'regression', 'scaling__copy', 'scaling__with_mean', 'scaling__with_std', 'regression__alpha', 'regression__average', 'regression__early_stopping', 'regression__epsilon', 'regression__eta0', 'regression__fit_intercept', 'regression__l1_ratio', 'regression__learning_rate', 'regression__loss', 'regression__max_iter', 'regression__n_iter_no_change', 'regression__penalty', 'regression__power_t', 'regression__random_state', 'regression__shuffle', 'regression__tol', 'regression__validation_fraction', 'regression__verbose', 'regression__warm_start'])" ] }, "execution_count": 79, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pipeline.get_params().keys()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We compose a dictionary of parameters to choose from." ] }, { "cell_type": "code", "execution_count": 90, "metadata": {}, "outputs": [], "source": [ "parameters_grid = {\n", " 'regression__loss' : ['huber', 'epsilon_insensitive', 'squared_loss', ],\n", " 'regression__max_iter' : [3, 5, 10, 50], \n", " 'regression__penalty' : ['l1', 'l2', 'none'],\n", " 'regression__alpha' : [0.0001, 0.01],\n", " 'scaling__with_mean' : [0., 0.5], #\n", "}" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We build a CV grid and pass the **pipeline** object into it along with **parameters_grid** and others.\n", "\n", " - Parameter **scoring** defines the kind of error that we score parameters at." ] }, { "cell_type": "code", "execution_count": 91, "metadata": {}, "outputs": [], "source": [ "grid_cv = model_selection.GridSearchCV(pipeline, parameters_grid, scoring = 'neg_mean_absolute_error', cv = 4)" ] }, { "cell_type": "code", "execution_count": 92, "metadata": { "scrolled": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Wall time: 22.6 s\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1208: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n", " warnings.warn(\"Maximum number of iteration reached before \"\n" ] }, { "data": { "text/plain": [ "GridSearchCV(cv=4,\n", " estimator=Pipeline(steps=[('scaling', StandardScaler()),\n", " ('regression',\n", " SGDRegressor(max_iter=5,\n", " random_state=0))]),\n", " param_grid={'regression__alpha': [0.0001, 0.01],\n", " 'regression__loss': ['huber', 'epsilon_insensitive',\n", " 'squared_loss'],\n", " 'regression__max_iter': [3, 5, 10, 50],\n", " 'regression__penalty': ['l1', 'l2', 'none'],\n", " 'scaling__with_mean': [0.0, 0.5]},\n", " scoring='neg_mean_absolute_error')" ] }, "execution_count": 92, "metadata": {}, "output_type": "execute_result" } ], "source": [ "%%time\n", "grid_cv.fit(train_data, train_labels)" ] }, { "cell_type": "code", "execution_count": 94, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "-108.61772632999148\n", "{'regression__alpha': 0.01, 'regression__loss': 'squared_loss', 'regression__max_iter': 3, 'regression__penalty': 'l2', 'scaling__with_mean': 0.0}\n" ] } ], "source": [ "print(grid_cv.best_score_)\n", "print(grid_cv.best_params_)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Results of the CV grid parameters search\n", "The CV parameters grid shows good result - `neg_mean_absolute_error`: -108.62 \n", "\n", "We are ok with 3 iterations - `regression__max_iter`: 3 \n", "\n", "Regularization parameter - `regression__alpha`: 0.01\n", "\n", "Regularization type is L2, Ridge - `regression__penalty`: 'l2'\n", "\n", "As to the scaling, the best is with mean at the point 0 - `scaling__with_mean`: 0.0" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Score a model by the deferred test\n", "Calcualte the MAE of *griv_CV* best estimator." ] }, { "cell_type": "code", "execution_count": 96, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "119.98978845935379" ] }, "execution_count": 96, "metadata": {}, "output_type": "execute_result" } ], "source": [ "metrics.mean_absolute_error(test_labels, grid_cv.best_estimator_.predict(test_data))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This error is less than one of the base model.\n", "\n", "Yet, the MAE is at a certain point. What is the mean value of the test labels/targets?" ] }, { "cell_type": "code", "execution_count": 98, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "232.159" ] }, "execution_count": 98, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.mean(test_labels)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "So, even though we've decreased the error from 122 to 120, since the mean is 232, the model has not underwent a good improvment." ] }, { "cell_type": "code", "execution_count": 101, "metadata": {}, "outputs": [], "source": [ "test_predictions = grid_cv.best_estimator_.predict(test_data)" ] }, { "cell_type": "code", "execution_count": 99, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[525 835 355 222 228 325 328 308 346 446]\n" ] } ], "source": [ "print(test_labels[:10])" ] }, { "cell_type": "code", "execution_count": 102, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[139.60470681 159.80765341 207.55935972 237.76288054 257.83836668\n", " 267.44558034 272.49537469 297.70688522 304.29818873 313.58821156]\n" ] } ], "source": [ "print(test_predictions[:10])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The target and predictions of grid_cv differ siginificantly. \n", "\n", "### Targets-predictions grapth\n", "We display a graph of our objects in the space of the correct values of the target label vs our predictions. When we plot a graph in such a space a good model should have the following: a cloud of points in the diagonal area. It turns out that our predictions should coincide with the target label therefore the diagonal points should transpire." ] }, { "cell_type": "code", "execution_count": 105, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(-100.0, 1100.0)" ] }, "execution_count": 105, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "pylab.figure(figsize=(16, 6))\n", "# No parameters model setting \n", "pylab.subplot(1,2,1)\n", "pylab.grid(True)\n", "pylab.scatter(train_labels, pipeline.predict(train_data), alpha=0.5, color = 'red')\n", "pylab.scatter(test_labels, pipeline.predict(test_data), alpha=0.5, color = 'blue')\n", "pylab.title('No parameters model setting')\n", "pylab.xlim(-100,1100)\n", "pylab.ylim(-100,1100)\n", "\n", "# Grid search model setting \n", "pylab.subplot(1,2,2)\n", "pylab.grid(True)\n", "pylab.scatter(train_labels, grid_cv.best_estimator_.predict(train_data), alpha=0.5, color = 'red')\n", "pylab.scatter(test_labels, grid_cv.best_estimator_.predict(test_data), alpha=0.5, color = 'blue')\n", "pylab.title('Grid search model setting')\n", "pylab.xlim(-100,1100)\n", "pylab.ylim(-100,1100)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "From the graph above we see that we have built a not very good model. \n", "\n", "We see that our point clouds does not look like a diagonal. Moreover, point clouds when using a model without parameter selection and point clouds when using a model with parameter selection are not of much differece. That is, our model is quite weak, and optimization by parameters did not profit much. \n", "\n", "### Conclusion\n", "In this post we touched a baseline, that is an initial regression model that works only on numerical features. We learned how to do scaling, how to build transformation chains. \n", "\n", "In the followin posts we will try to improve this model by adding all the other features to it." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.5" } }, "nbformat": 4, "nbformat_minor": 1 }