Created
July 6, 2015 16:30
-
-
Save dschien/66b8764c4ad1b7ed4f33 to your computer and use it in GitHub Desktop.
sklearn.linear_model.LinearRegression vs statsmodel OLS
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import pandas as pd\n", | |
"import numpy as np\n", | |
"import scipy as sp\n", | |
"import statsmodels.api as sm\n", | |
"import matplotlib.pyplot as plt\n", | |
"from sklearn.linear_model import LinearRegression\n", | |
"%matplotlib inline" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"# Data from R ISLR package - write.csv(Boston, \"Boston.csv\", col.names = FALSE)\n", | |
"boston_df = pd.read_csv(\"../../r/Boston.csv\")" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 12, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"(47.117263854857882,\n", | |
" array([ -3.05335819e+09, 3.05335819e+09, 9.31299461e-02,\n", | |
" -3.29341722e+00]))" | |
] | |
}, | |
"execution_count": 12, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"# fitting medv ~ lstat + I(lstat^2)\n", | |
"boston_df[\"lstat^2\"] = boston_df[\"lstat\"] ** 2\n", | |
"# fitting medv ~ poly(lstat,4). We already have lstat^2 and lstat from previous\n", | |
"boston_df[\"lstat^4\"] = np.power(boston_df[\"lstat\"], 4)\n", | |
"boston_df[\"lstat^3\"] = np.power(boston_df[\"lstat\"], 4)\n", | |
"X = boston_df[[\"lstat^4\", \"lstat^3\", \"lstat^2\", \"lstat\"]]\n", | |
"y = boston_df[\"medv\"]\n", | |
"reg7 = LinearRegression()\n", | |
"reg7.fit(X, y)\n", | |
"(reg7.intercept_, reg7.coef_)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 14, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"# X = boston_df[[\"lstat^4\", \"lstat^3\", \"lstat^2\", \"lstat\"]]\n", | |
"X = sm.add_constant(X)\n", | |
"# X = boston_df[[1., \"lstat^4\", \"lstat^3\", \"lstat^2\", \"lstat\"]]\n", | |
"ols = sm.OLS(y,X).fit()\n", | |
"# ols.summary()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 11, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"False" | |
] | |
}, | |
"execution_count": 11, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"eps = 0.0000000001\n", | |
"np.all(np.abs(ols.params.values[1:] - reg7.coef_) < eps)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 13, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([ -1.17513710e-05, -1.17509020e-05, 9.23027375e-02,\n", | |
" -3.27115207e+00])" | |
] | |
}, | |
"execution_count": 13, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"ols.params.values[1:]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.9" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment