{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "import seaborn as sns" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "tips = sns.load_dataset('tips')" ] }, { "cell_type": "code", "execution_count": 4, "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", "
total_billtipsexsmokerdaytimesize
016.991.01FemaleNoSunDinner2
110.341.66MaleNoSunDinner3
221.013.50MaleNoSunDinner3
323.683.31MaleNoSunDinner2
424.593.61FemaleNoSunDinner4
\n", "
" ], "text/plain": [ " total_bill tip sex smoker day time size\n", "0 16.99 1.01 Female No Sun Dinner 2\n", "1 10.34 1.66 Male No Sun Dinner 3\n", "2 21.01 3.50 Male No Sun Dinner 3\n", "3 23.68 3.31 Male No Sun Dinner 2\n", "4 24.59 3.61 Female No Sun Dinner 4" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tips.head()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "import statsmodels.formula.api as smf" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "model = smf.ols('tip ~ total_bill', data=tips)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "results = model.fit()" ] }, { "cell_type": "code", "execution_count": 13, "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", "
OLS Regression Results
Dep. Variable: tip R-squared: 0.457
Model: OLS Adj. R-squared: 0.454
Method: Least Squares F-statistic: 203.4
Date: Fri, 11 May 2018 Prob (F-statistic): 6.69e-34
Time: 18:19:28 Log-Likelihood: -350.54
No. Observations: 244 AIC: 705.1
Df Residuals: 242 BIC: 712.1
Df Model: 1
Covariance Type: nonrobust
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
coef std err t P>|t| [0.025 0.975]
Intercept 0.9203 0.160 5.761 0.000 0.606 1.235
total_bill 0.1050 0.007 14.260 0.000 0.091 0.120
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Omnibus: 20.185 Durbin-Watson: 2.151
Prob(Omnibus): 0.000 Jarque-Bera (JB): 37.750
Skew: 0.443 Prob(JB): 6.35e-09
Kurtosis: 4.711 Cond. No. 53.0
" ], "text/plain": [ "\n", "\"\"\"\n", " OLS Regression Results \n", "==============================================================================\n", "Dep. Variable: tip R-squared: 0.457\n", "Model: OLS Adj. R-squared: 0.454\n", "Method: Least Squares F-statistic: 203.4\n", "Date: Fri, 11 May 2018 Prob (F-statistic): 6.69e-34\n", "Time: 18:19:28 Log-Likelihood: -350.54\n", "No. Observations: 244 AIC: 705.1\n", "Df Residuals: 242 BIC: 712.1\n", "Df Model: 1 \n", "Covariance Type: nonrobust \n", "==============================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "Intercept 0.9203 0.160 5.761 0.000 0.606 1.235\n", "total_bill 0.1050 0.007 14.260 0.000 0.091 0.120\n", "==============================================================================\n", "Omnibus: 20.185 Durbin-Watson: 2.151\n", "Prob(Omnibus): 0.000 Jarque-Bera (JB): 37.750\n", "Skew: 0.443 Prob(JB): 6.35e-09\n", "Kurtosis: 4.711 Cond. No. 53.0\n", "==============================================================================\n", "\n", "Warnings:\n", "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", "\"\"\"" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "results.summary()" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Intercept 0.920270\n", "total_bill 0.105025\n", "dtype: float64" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "results.params" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "from sklearn import linear_model" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "lr = linear_model.LinearRegression()" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "Expected 2D array, got 1D array instead:\narray=[ 16.99 10.34 21.01 23.68 24.59 25.29 8.77 26.88 15.04 14.78\n 10.27 35.26 15.42 18.43 14.83 21.58 10.33 16.29 16.97 20.65\n 17.92 20.29 15.77 39.42 19.82 17.81 13.37 12.69 21.7 19.65\n 9.55 18.35 15.06 20.69 17.78 24.06 16.31 16.93 18.69 31.27\n 16.04 17.46 13.94 9.68 30.4 18.29 22.23 32.4 28.55 18.04\n 12.54 10.29 34.81 9.94 25.56 19.49 38.01 26.41 11.24 48.27\n 20.29 13.81 11.02 18.29 17.59 20.08 16.45 3.07 20.23 15.01\n 12.02 17.07 26.86 25.28 14.73 10.51 17.92 27.2 22.76 17.29\n 19.44 16.66 10.07 32.68 15.98 34.83 13.03 18.28 24.71 21.16\n 28.97 22.49 5.75 16.32 22.75 40.17 27.28 12.03 21.01 12.46\n 11.35 15.38 44.3 22.42 20.92 15.36 20.49 25.21 18.24 14.31 14.\n 7.25 38.07 23.95 25.71 17.31 29.93 10.65 12.43 24.08 11.69\n 13.42 14.26 15.95 12.48 29.8 8.52 14.52 11.38 22.82 19.08\n 20.27 11.17 12.26 18.26 8.51 10.33 14.15 16. 13.16 17.47\n 34.3 41.19 27.05 16.43 8.35 18.64 11.87 9.78 7.51 14.07\n 13.13 17.26 24.55 19.77 29.85 48.17 25. 13.39 16.49 21.5\n 12.66 16.21 13.81 17.51 24.52 20.76 31.71 10.59 10.63 50.81\n 15.81 7.25 31.85 16.82 32.9 17.89 14.48 9.6 34.63 34.65\n 23.33 45.35 23.17 40.55 20.69 20.9 30.46 18.15 23.1 15.69\n 19.81 28.44 15.48 16.58 7.56 10.34 43.11 13. 13.51 18.71\n 12.74 13. 16.4 20.53 16.47 26.59 38.73 24.27 12.76 30.06\n 25.89 48.33 13.27 28.17 12.9 28.15 11.59 7.74 30.14 12.16\n 13.42 8.58 15.98 13.42 16.27 10.09 20.45 13.28 22.12 24.01\n 15.69 11.61 10.77 15.53 10.07 12.6 32.83 35.83 29.03 27.18\n 22.67 17.82 18.78].\nReshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mValueError\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[0mpredicted\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtips\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'total_bill'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtips\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'tip'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\base.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m 480\u001b[0m \u001b[0mn_jobs_\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 481\u001b[0m X, y = check_X_y(X, y, accept_sparse=['csr', 'csc', 'coo'],\n\u001b[1;32m--> 482\u001b[1;33m y_numeric=True, multi_output=True)\n\u001b[0m\u001b[0;32m 483\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 484\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0msample_weight\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0matleast_1d\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36mcheck_X_y\u001b[1;34m(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)\u001b[0m\n\u001b[0;32m 571\u001b[0m X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite,\n\u001b[0;32m 572\u001b[0m \u001b[0mensure_2d\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mallow_nd\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mensure_min_samples\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 573\u001b[1;33m ensure_min_features, warn_on_dtype, estimator)\n\u001b[0m\u001b[0;32m 574\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mmulti_output\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 575\u001b[0m y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False,\n", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[1;34m(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)\u001b[0m\n\u001b[0;32m 439\u001b[0m \u001b[1;34m\"Reshape your data either using array.reshape(-1, 1) if \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 440\u001b[0m \u001b[1;34m\"your data has a single feature or array.reshape(1, -1) \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 441\u001b[1;33m \"if it contains a single sample.\".format(array))\n\u001b[0m\u001b[0;32m 442\u001b[0m \u001b[0marray\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0matleast_2d\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 443\u001b[0m \u001b[1;31m# To ensure that array flags are maintained\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mValueError\u001b[0m: Expected 2D array, got 1D array instead:\narray=[ 16.99 10.34 21.01 23.68 24.59 25.29 8.77 26.88 15.04 14.78\n 10.27 35.26 15.42 18.43 14.83 21.58 10.33 16.29 16.97 20.65\n 17.92 20.29 15.77 39.42 19.82 17.81 13.37 12.69 21.7 19.65\n 9.55 18.35 15.06 20.69 17.78 24.06 16.31 16.93 18.69 31.27\n 16.04 17.46 13.94 9.68 30.4 18.29 22.23 32.4 28.55 18.04\n 12.54 10.29 34.81 9.94 25.56 19.49 38.01 26.41 11.24 48.27\n 20.29 13.81 11.02 18.29 17.59 20.08 16.45 3.07 20.23 15.01\n 12.02 17.07 26.86 25.28 14.73 10.51 17.92 27.2 22.76 17.29\n 19.44 16.66 10.07 32.68 15.98 34.83 13.03 18.28 24.71 21.16\n 28.97 22.49 5.75 16.32 22.75 40.17 27.28 12.03 21.01 12.46\n 11.35 15.38 44.3 22.42 20.92 15.36 20.49 25.21 18.24 14.31 14.\n 7.25 38.07 23.95 25.71 17.31 29.93 10.65 12.43 24.08 11.69\n 13.42 14.26 15.95 12.48 29.8 8.52 14.52 11.38 22.82 19.08\n 20.27 11.17 12.26 18.26 8.51 10.33 14.15 16. 13.16 17.47\n 34.3 41.19 27.05 16.43 8.35 18.64 11.87 9.78 7.51 14.07\n 13.13 17.26 24.55 19.77 29.85 48.17 25. 13.39 16.49 21.5\n 12.66 16.21 13.81 17.51 24.52 20.76 31.71 10.59 10.63 50.81\n 15.81 7.25 31.85 16.82 32.9 17.89 14.48 9.6 34.63 34.65\n 23.33 45.35 23.17 40.55 20.69 20.9 30.46 18.15 23.1 15.69\n 19.81 28.44 15.48 16.58 7.56 10.34 43.11 13. 13.51 18.71\n 12.74 13. 16.4 20.53 16.47 26.59 38.73 24.27 12.76 30.06\n 25.89 48.33 13.27 28.17 12.9 28.15 11.59 7.74 30.14 12.16\n 13.42 8.58 15.98 13.42 16.27 10.09 20.45 13.28 22.12 24.01\n 15.69 11.61 10.77 15.53 10.07 12.6 32.83 35.83 29.03 27.18\n 22.67 17.82 18.78].\nReshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample." ] } ], "source": [ "predicted = lr.fit(X=tips['total_bill'], y=tips['tip'])" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "predicted = lr.fit(X=tips['total_bill'].values.reshape(-1, 1),\n", " y=tips['tip'])" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([ 0.10502452])" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predicted.coef_" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.92026961355467352" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predicted.intercept_" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['total_bill', 'tip', 'sex', 'smoker', 'day', 'time', 'size'], dtype='object')" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tips.columns" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "model = smf.ols('tip ~ total_bill + sex', data=tips).fit()" ] }, { "cell_type": "code", "execution_count": 23, "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", "
OLS Regression Results
Dep. Variable: tip R-squared: 0.457
Model: OLS Adj. R-squared: 0.452
Method: Least Squares F-statistic: 101.3
Date: Fri, 11 May 2018 Prob (F-statistic): 1.18e-32
Time: 18:20:35 Log-Likelihood: -350.52
No. Observations: 244 AIC: 707.0
Df Residuals: 241 BIC: 717.5
Df Model: 2
Covariance Type: nonrobust
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
coef std err t P>|t| [0.025 0.975]
Intercept 0.9067 0.175 5.182 0.000 0.562 1.251
sex[T.Female] 0.0266 0.138 0.192 0.848 -0.246 0.299
total_bill 0.1052 0.007 14.110 0.000 0.091 0.120
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Omnibus: 20.499 Durbin-Watson: 2.149
Prob(Omnibus): 0.000 Jarque-Bera (JB): 38.652
Skew: 0.447 Prob(JB): 4.05e-09
Kurtosis: 4.733 Cond. No. 63.0
" ], "text/plain": [ "\n", "\"\"\"\n", " OLS Regression Results \n", "==============================================================================\n", "Dep. Variable: tip R-squared: 0.457\n", "Model: OLS Adj. R-squared: 0.452\n", "Method: Least Squares F-statistic: 101.3\n", "Date: Fri, 11 May 2018 Prob (F-statistic): 1.18e-32\n", "Time: 18:20:35 Log-Likelihood: -350.52\n", "No. Observations: 244 AIC: 707.0\n", "Df Residuals: 241 BIC: 717.5\n", "Df Model: 2 \n", "Covariance Type: nonrobust \n", "=================================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", "---------------------------------------------------------------------------------\n", "Intercept 0.9067 0.175 5.182 0.000 0.562 1.251\n", "sex[T.Female] 0.0266 0.138 0.192 0.848 -0.246 0.299\n", "total_bill 0.1052 0.007 14.110 0.000 0.091 0.120\n", "==============================================================================\n", "Omnibus: 20.499 Durbin-Watson: 2.149\n", "Prob(Omnibus): 0.000 Jarque-Bera (JB): 38.652\n", "Skew: 0.447 Prob(JB): 4.05e-09\n", "Kurtosis: 4.733 Cond. No. 63.0\n", "==============================================================================\n", "\n", "Warnings:\n", "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", "\"\"\"" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.summary()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "lr = linear_model.LinearRegression()" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "could not convert string to float: 'Female'", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mValueError\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[0mpredicted\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtips\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'total_bill'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'sex'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtips\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'tip'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\base.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m 480\u001b[0m \u001b[0mn_jobs_\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 481\u001b[0m X, y = check_X_y(X, y, accept_sparse=['csr', 'csc', 'coo'],\n\u001b[1;32m--> 482\u001b[1;33m y_numeric=True, multi_output=True)\n\u001b[0m\u001b[0;32m 483\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 484\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0msample_weight\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0matleast_1d\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36mcheck_X_y\u001b[1;34m(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)\u001b[0m\n\u001b[0;32m 571\u001b[0m X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite,\n\u001b[0;32m 572\u001b[0m \u001b[0mensure_2d\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mallow_nd\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mensure_min_samples\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 573\u001b[1;33m ensure_min_features, warn_on_dtype, estimator)\n\u001b[0m\u001b[0;32m 574\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mmulti_output\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 575\u001b[0m y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False,\n", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[1;34m(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)\u001b[0m\n\u001b[0;32m 446\u001b[0m \u001b[1;31m# make sure we actually converted to numeric:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 447\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mdtype_numeric\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0marray\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkind\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m\"O\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 448\u001b[1;33m \u001b[0marray\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0marray\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfloat64\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 449\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mallow_nd\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0marray\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m3\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 450\u001b[0m raise ValueError(\"Found array with dim %d. %s expected <= 2.\"\n", "\u001b[1;31mValueError\u001b[0m: could not convert string to float: 'Female'" ] } ], "source": [ "predicted = lr.fit(tips[['total_bill', 'sex']], tips['tip'])" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "tips_dummy = pd.get_dummies(tips[['total_bill', 'sex', 'tip']])" ] }, { "cell_type": "code", "execution_count": 27, "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", "
total_billtipsex_Malesex_Female
016.991.0101
110.341.6610
221.013.5010
323.683.3110
424.593.6101
\n", "
" ], "text/plain": [ " total_bill tip sex_Male sex_Female\n", "0 16.99 1.01 0 1\n", "1 10.34 1.66 1 0\n", "2 21.01 3.50 1 0\n", "3 23.68 3.31 1 0\n", "4 24.59 3.61 0 1" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tips_dummy.head()" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 244 entries, 0 to 243\n", "Data columns (total 7 columns):\n", "total_bill 244 non-null float64\n", "tip 244 non-null float64\n", "sex 244 non-null category\n", "smoker 244 non-null category\n", "day 244 non-null category\n", "time 244 non-null category\n", "size 244 non-null int64\n", "dtypes: category(4), float64(2), int64(1)\n", "memory usage: 7.2 KB\n" ] } ], "source": [ "tips.info()" ] }, { "cell_type": "code", "execution_count": 29, "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", "
tiptotal_billsex_Female
01.0116.991
11.6610.340
23.5021.010
33.3123.680
43.6124.591
\n", "
" ], "text/plain": [ " tip total_bill sex_Female\n", "0 1.01 16.99 1\n", "1 1.66 10.34 0\n", "2 3.50 21.01 0\n", "3 3.31 23.68 0\n", "4 3.61 24.59 1" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tips_dummy = pd.get_dummies(tips[['tip', 'total_bill', 'sex']], drop_first=True)\n", "tips_dummy.head()" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "predicted = lr.fit(tips_dummy.iloc[:, 1:], tips_dummy['tip'])" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([ 0.10523236, 0.02660871])" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predicted.coef_" ] }, { "cell_type": "code", "execution_count": 33, "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", "
tiptotal_billsex_Female
01.0116.991
11.6610.340
23.5021.010
33.3123.680
43.6124.591
\n", "
" ], "text/plain": [ " tip total_bill sex_Female\n", "0 1.01 16.99 1\n", "1 1.66 10.34 0\n", "2 3.50 21.01 0\n", "3 3.31 23.68 0\n", "4 3.61 24.59 1" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tips_dummy.head()" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "from patsy import dmatrices" ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "response, predictors = dmatrices('tip ~ total_bill + sex', data = tips)" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [], "source": [ "#response" ] }, { "cell_type": "code", "execution_count": 39, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "#predictors" ] }, { "cell_type": "code", "execution_count": 40, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "predicted = lr.fit(predictors, response)" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 0. , 0.02660871, 0.10523236]])" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predicted.coef_" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 4 }