Skip to content

Instantly share code, notes, and snippets.

@decisionstats

decisionstats/linear regression in python

Created March 13, 2017 12:34
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save decisionstats/8ac83dbe4dd08808af3d9c0869259cf6 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save decisionstats/8ac83dbe4dd08808af3d9c0869259cf6 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
linear regression in python
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import statsmodels.formula.api as sm"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris=pd.read_csv(\"http://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"iris =iris.drop('Unnamed: 0', 1)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Sepal.Length</th>\n",
" <th>Sepal.Width</th>\n",
" <th>Petal.Length</th>\n",
" <th>Petal.Width</th>\n",
" <th>Species</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Sepal.Length Sepal.Width Petal.Length Petal.Width Species\n",
"0 5.1 3.5 1.4 0.2 setosa\n",
"1 4.9 3.0 1.4 0.2 setosa\n",
"2 4.7 3.2 1.3 0.2 setosa\n",
"3 4.6 3.1 1.5 0.2 setosa\n",
"4 5.0 3.6 1.4 0.2 setosa"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"iris.head()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris.columns=['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width',\n",
" 'Species']"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width',\n",
" 'Species'],\n",
" dtype='object')"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"iris.columns"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"result = sm.ols(formula=\"Sepal_Length ~ Petal_Length + Sepal_Width + Petal_Width + Species\", data=iris)\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x9bafe10>"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result.fit()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<table class=\"simpletable\">\n",
"<caption>OLS Regression Results</caption>\n",
"<tr>\n",
" <th>Dep. Variable:</th> <td>Sepal_Length</td> <th> R-squared: </th> <td> 0.867</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Model:</th> <td>OLS</td> <th> Adj. R-squared: </th> <td> 0.863</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Method:</th> <td>Least Squares</td> <th> F-statistic: </th> <td> 188.3</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Date:</th> <td>Mon, 13 Mar 2017</td> <th> Prob (F-statistic):</th> <td>2.67e-61</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Time:</th> <td>17:56:48</td> <th> Log-Likelihood: </th> <td> -32.558</td>\n",
"</tr>\n",
"<tr>\n",
" <th>No. Observations:</th> <td> 150</td> <th> AIC: </th> <td> 77.12</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Residuals:</th> <td> 144</td> <th> BIC: </th> <td> 95.18</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Model:</th> <td> 5</td> <th> </th> <td> </td> \n",
"</tr>\n",
"<tr>\n",
" <th>Covariance Type:</th> <td>nonrobust</td> <th> </th> <td> </td> \n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <td></td> <th>coef</th> <th>std err</th> <th>t</th> <th>P>|t|</th> <th>[95.0% Conf. Int.]</th> \n",
"</tr>\n",
"<tr>\n",
" <th>Intercept</th> <td> 2.1713</td> <td> 0.280</td> <td> 7.760</td> <td> 0.000</td> <td> 1.618 2.724</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Species[T.versicolor]</th> <td> -0.7236</td> <td> 0.240</td> <td> -3.013</td> <td> 0.003</td> <td> -1.198 -0.249</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Species[T.virginica]</th> <td> -1.0235</td> <td> 0.334</td> <td> -3.067</td> <td> 0.003</td> <td> -1.683 -0.364</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Petal_Length</th> <td> 0.8292</td> <td> 0.069</td> <td> 12.101</td> <td> 0.000</td> <td> 0.694 0.965</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Sepal_Width</th> <td> 0.4959</td> <td> 0.086</td> <td> 5.761</td> <td> 0.000</td> <td> 0.326 0.666</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Petal_Width</th> <td> -0.3152</td> <td> 0.151</td> <td> -2.084</td> <td> 0.039</td> <td> -0.614 -0.016</td>\n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <th>Omnibus:</th> <td> 0.418</td> <th> Durbin-Watson: </th> <td> 1.966</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(Omnibus):</th> <td> 0.811</td> <th> Jarque-Bera (JB): </th> <td> 0.572</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Skew:</th> <td>-0.060</td> <th> Prob(JB): </th> <td> 0.751</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Kurtosis:</th> <td> 2.722</td> <th> Cond. No. </th> <td> 94.0</td>\n",
"</tr>\n",
"</table>"
],
"text/plain": [
"<class 'statsmodels.iolib.summary.Summary'>\n",
"\"\"\"\n",
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: Sepal_Length R-squared: 0.867\n",
"Model: OLS Adj. R-squared: 0.863\n",
"Method: Least Squares F-statistic: 188.3\n",
"Date: Mon, 13 Mar 2017 Prob (F-statistic): 2.67e-61\n",
"Time: 17:56:48 Log-Likelihood: -32.558\n",
"No. Observations: 150 AIC: 77.12\n",
"Df Residuals: 144 BIC: 95.18\n",
"Df Model: 5 \n",
"Covariance Type: nonrobust \n",
"=========================================================================================\n",
" coef std err t P>|t| [95.0% Conf. Int.]\n",
"-----------------------------------------------------------------------------------------\n",
"Intercept 2.1713 0.280 7.760 0.000 1.618 2.724\n",
"Species[T.versicolor] -0.7236 0.240 -3.013 0.003 -1.198 -0.249\n",
"Species[T.virginica] -1.0235 0.334 -3.067 0.003 -1.683 -0.364\n",
"Petal_Length 0.8292 0.069 12.101 0.000 0.694 0.965\n",
"Sepal_Width 0.4959 0.086 5.761 0.000 0.326 0.666\n",
"Petal_Width -0.3152 0.151 -2.084 0.039 -0.614 -0.016\n",
"==============================================================================\n",
"Omnibus: 0.418 Durbin-Watson: 1.966\n",
"Prob(Omnibus): 0.811 Jarque-Bera (JB): 0.572\n",
"Skew: -0.060 Prob(JB): 0.751\n",
"Kurtosis: 2.722 Cond. No. 94.0\n",
"==============================================================================\n",
"\n",
"Warnings:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
"\"\"\""
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result.fit().summary()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Intercept 2.171266\n",
"Species[T.versicolor] -0.723562\n",
"Species[T.virginica] -1.023498\n",
"Petal_Length 0.829244\n",
"Sepal_Width 0.495889\n",
"Petal_Width -0.315155\n",
"dtype: float64"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result.fit().params"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>student_resid</th>\n",
" <th>unadj_p</th>\n",
" <th>bonf(p)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.312689</td>\n",
" <td>0.754973</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.473016</td>\n",
" <td>0.636923</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-0.240279</td>\n",
" <td>0.810458</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-0.956277</td>\n",
" <td>0.340546</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-0.178770</td>\n",
" <td>0.858371</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0.036712</td>\n",
" <td>0.970765</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>-1.066895</td>\n",
" <td>0.287817</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>-0.125127</td>\n",
" <td>0.900599</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>-1.021792</td>\n",
" <td>0.308605</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>-0.068824</td>\n",
" <td>0.945226</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>0.703086</td>\n",
" <td>0.483145</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>-1.058507</td>\n",
" <td>0.291609</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>0.038433</td>\n",
" <td>0.969396</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>-0.792571</td>\n",
" <td>0.429341</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>2.431167</td>\n",
" <td>0.016288</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>0.778864</td>\n",
" <td>0.437347</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1.142357</td>\n",
" <td>0.255215</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>0.416300</td>\n",
" <td>0.677815</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1.089623</td>\n",
" <td>0.277712</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>-0.346136</td>\n",
" <td>0.729749</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>0.645498</td>\n",
" <td>0.519639</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>-0.078552</td>\n",
" <td>0.937498</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>-0.405720</td>\n",
" <td>0.685554</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>0.133053</td>\n",
" <td>0.894339</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>-1.904722</td>\n",
" <td>0.058824</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>0.255775</td>\n",
" <td>0.798492</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>-0.190906</td>\n",
" <td>0.848870</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>0.368833</td>\n",
" <td>0.712798</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>0.805113</td>\n",
" <td>0.422091</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>-1.063322</td>\n",
" <td>0.289428</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>0.540764</td>\n",
" <td>0.589512</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>-1.229878</td>\n",
" <td>0.220762</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
" <td>0.814912</td>\n",
" <td>0.416478</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>1.054229</td>\n",
" <td>0.293556</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124</th>\n",
" <td>-0.491062</td>\n",
" <td>0.624135</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
" <td>0.191377</td>\n",
" <td>0.848501</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>126</th>\n",
" <td>0.833707</td>\n",
" <td>0.405837</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>-0.104393</td>\n",
" <td>0.917003</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>-0.388983</td>\n",
" <td>0.697868</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>129</th>\n",
" <td>0.878534</td>\n",
" <td>0.381128</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>1.353238</td>\n",
" <td>0.178115</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>131</th>\n",
" <td>0.653646</td>\n",
" <td>0.514390</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>132</th>\n",
" <td>-0.286276</td>\n",
" <td>0.775081</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>133</th>\n",
" <td>0.024680</td>\n",
" <td>0.980344</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>-1.876542</td>\n",
" <td>0.062619</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>2.474327</td>\n",
" <td>0.014518</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>-1.413807</td>\n",
" <td>0.159592</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>-0.924181</td>\n",
" <td>0.356949</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>138</th>\n",
" <td>-0.161519</td>\n",
" <td>0.871913</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139</th>\n",
" <td>1.319446</td>\n",
" <td>0.189129</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>0.425193</td>\n",
" <td>0.671335</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>141</th>\n",
" <td>2.426542</td>\n",
" <td>0.016488</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>142</th>\n",
" <td>-1.048813</td>\n",
" <td>0.296034</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>143</th>\n",
" <td>-0.337894</td>\n",
" <td>0.735939</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>144</th>\n",
" <td>-0.077141</td>\n",
" <td>0.938619</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
" <td>1.606589</td>\n",
" <td>0.110351</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>1.215637</td>\n",
" <td>0.226126</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>0.602340</td>\n",
" <td>0.547902</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>-1.294716</td>\n",
" <td>0.197505</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>149</th>\n",
" <td>-1.321604</td>\n",
" <td>0.188411</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>150 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" student_resid unadj_p bonf(p)\n",
"0 0.312689 0.754973 1.0\n",
"1 0.473016 0.636923 1.0\n",
"2 -0.240279 0.810458 1.0\n",
"3 -0.956277 0.340546 1.0\n",
"4 -0.178770 0.858371 1.0\n",
"5 0.036712 0.970765 1.0\n",
"6 -1.066895 0.287817 1.0\n",
"7 -0.125127 0.900599 1.0\n",
"8 -1.021792 0.308605 1.0\n",
"9 -0.068824 0.945226 1.0\n",
"10 0.703086 0.483145 1.0\n",
"11 -1.058507 0.291609 1.0\n",
"12 0.038433 0.969396 1.0\n",
"13 -0.792571 0.429341 1.0\n",
"14 2.431167 0.016288 1.0\n",
"15 0.778864 0.437347 1.0\n",
"16 1.142357 0.255215 1.0\n",
"17 0.416300 0.677815 1.0\n",
"18 1.089623 0.277712 1.0\n",
"19 -0.346136 0.729749 1.0\n",
"20 0.645498 0.519639 1.0\n",
"21 -0.078552 0.937498 1.0\n",
"22 -0.405720 0.685554 1.0\n",
"23 0.133053 0.894339 1.0\n",
"24 -1.904722 0.058824 1.0\n",
"25 0.255775 0.798492 1.0\n",
"26 -0.190906 0.848870 1.0\n",
"27 0.368833 0.712798 1.0\n",
"28 0.805113 0.422091 1.0\n",
"29 -1.063322 0.289428 1.0\n",
".. ... ... ...\n",
"120 0.540764 0.589512 1.0\n",
"121 -1.229878 0.220762 1.0\n",
"122 0.814912 0.416478 1.0\n",
"123 1.054229 0.293556 1.0\n",
"124 -0.491062 0.624135 1.0\n",
"125 0.191377 0.848501 1.0\n",
"126 0.833707 0.405837 1.0\n",
"127 -0.104393 0.917003 1.0\n",
"128 -0.388983 0.697868 1.0\n",
"129 0.878534 0.381128 1.0\n",
"130 1.353238 0.178115 1.0\n",
"131 0.653646 0.514390 1.0\n",
"132 -0.286276 0.775081 1.0\n",
"133 0.024680 0.980344 1.0\n",
"134 -1.876542 0.062619 1.0\n",
"135 2.474327 0.014518 1.0\n",
"136 -1.413807 0.159592 1.0\n",
"137 -0.924181 0.356949 1.0\n",
"138 -0.161519 0.871913 1.0\n",
"139 1.319446 0.189129 1.0\n",
"140 0.425193 0.671335 1.0\n",
"141 2.426542 0.016488 1.0\n",
"142 -1.048813 0.296034 1.0\n",
"143 -0.337894 0.735939 1.0\n",
"144 -0.077141 0.938619 1.0\n",
"145 1.606589 0.110351 1.0\n",
"146 1.215637 0.226126 1.0\n",
"147 0.602340 0.547902 1.0\n",
"148 -1.294716 0.197505 1.0\n",
"149 -1.321604 0.188411 1.0\n",
"\n",
"[150 rows x 3 columns]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result.fit().outlier_test(method='bonf', alpha=0.05)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['HC0_se',\n",
" 'HC1_se',\n",
" 'HC2_se',\n",
" 'HC3_se',\n",
" '_HCCM',\n",
" '__class__',\n",
" '__delattr__',\n",
" '__dict__',\n",
" '__dir__',\n",
" '__doc__',\n",
" '__eq__',\n",
" '__format__',\n",
" '__ge__',\n",
" '__getattribute__',\n",
" '__gt__',\n",
" '__hash__',\n",
" '__init__',\n",
" '__le__',\n",
" '__lt__',\n",
" '__module__',\n",
" '__ne__',\n",
" '__new__',\n",
" '__reduce__',\n",
" '__reduce_ex__',\n",
" '__repr__',\n",
" '__setattr__',\n",
" '__sizeof__',\n",
" '__str__',\n",
" '__subclasshook__',\n",
" '__weakref__',\n",
" '_cache',\n",
" '_data_attr',\n",
" '_get_robustcov_results',\n",
" '_is_nested',\n",
" '_wexog_singular_values',\n",
" 'aic',\n",
" 'bic',\n",
" 'bse',\n",
" 'centered_tss',\n",
" 'compare_f_test',\n",
" 'compare_lm_test',\n",
" 'compare_lr_test',\n",
" 'condition_number',\n",
" 'conf_int',\n",
" 'conf_int_el',\n",
" 'cov_HC0',\n",
" 'cov_HC1',\n",
" 'cov_HC2',\n",
" 'cov_HC3',\n",
" 'cov_kwds',\n",
" 'cov_params',\n",
" 'cov_type',\n",
" 'df_model',\n",
" 'df_resid',\n",
" 'eigenvals',\n",
" 'el_test',\n",
" 'ess',\n",
" 'f_pvalue',\n",
" 'f_test',\n",
" 'fittedvalues',\n",
" 'fvalue',\n",
" 'get_influence',\n",
" 'get_robustcov_results',\n",
" 'initialize',\n",
" 'k_constant',\n",
" 'llf',\n",
" 'load',\n",
" 'model',\n",
" 'mse_model',\n",
" 'mse_resid',\n",
" 'mse_total',\n",
" 'nobs',\n",
" 'normalized_cov_params',\n",
" 'outlier_test',\n",
" 'params',\n",
" 'predict',\n",
" 'pvalues',\n",
" 'remove_data',\n",
" 'resid',\n",
" 'resid_pearson',\n",
" 'rsquared',\n",
" 'rsquared_adj',\n",
" 'save',\n",
" 'scale',\n",
" 'ssr',\n",
" 'summary',\n",
" 'summary2',\n",
" 't_test',\n",
" 'tvalues',\n",
" 'uncentered_tss',\n",
" 'use_t',\n",
" 'wald_test',\n",
" 'wresid']"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dir(result.fit())"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Bad data points (bonf(p) < 0.05):\n",
"Empty DataFrame\n",
"Columns: [student_resid, unadj_p, bonf(p)]\n",
"Index: []\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\Dell\\Anaconda3\\lib\\site-packages\\ipykernel\\__main__.py:3: FutureWarning: icol(i) is deprecated. Please use .iloc[:,i]\n",
" app.launch_new_instance()\n"
]
}
],
"source": [
"test=result.fit().outlier_test()\n",
"print ('Bad data points (bonf(p) < 0.05):')\n",
"print (test[test.icol(2) < 0.05])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"anaconda-cloud": {},
"kernelspec": {
"display_name": "Python [conda root]",
"language": "python",
"name": "conda-root-py"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 1
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment