{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Statsmodel"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:46.919419",
"start_time": "2016-04-03T01:31:43.859040"
},
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import statsmodels.api as sm\n",
"import statsmodels.formula.api as smf\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:46.957835",
"start_time": "2016-04-03T01:31:46.921186"
},
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" sepal_length | \n",
" sepal_width | \n",
" petal_length | \n",
" petal_width | \n",
" species | \n",
"
\n",
" \n",
" \n",
" \n",
" | 145 | \n",
" 6.7 | \n",
" 3.0 | \n",
" 5.2 | \n",
" 2.3 | \n",
" virginica | \n",
"
\n",
" \n",
" | 146 | \n",
" 6.3 | \n",
" 2.5 | \n",
" 5.0 | \n",
" 1.9 | \n",
" virginica | \n",
"
\n",
" \n",
" | 147 | \n",
" 6.5 | \n",
" 3.0 | \n",
" 5.2 | \n",
" 2.0 | \n",
" virginica | \n",
"
\n",
" \n",
" | 148 | \n",
" 6.2 | \n",
" 3.4 | \n",
" 5.4 | \n",
" 2.3 | \n",
" virginica | \n",
"
\n",
" \n",
" | 149 | \n",
" 5.9 | \n",
" 3.0 | \n",
" 5.1 | \n",
" 1.8 | \n",
" virginica | \n",
"
\n",
" \n",
"
\n",
"
\n",
"OLS Regression Results\n",
"\n",
" | Dep. Variable: | sepal_length | R-squared: | 0.957 | \n",
"
\n",
"\n",
" | Model: | OLS | Adj. R-squared: | 0.956 | \n",
"
\n",
"\n",
" | Method: | Least Squares | F-statistic: | 3277. | \n",
"
\n",
"\n",
" | Date: | Sun, 03 Apr 2016 | Prob (F-statistic): | 2.42e-103 | \n",
"
\n",
"\n",
" | Time: | 01:31:50 | Log-Likelihood: | -243.98 | \n",
"
\n",
"\n",
" | No. Observations: | 150 | AIC: | 490.0 | \n",
"
\n",
"\n",
" | Df Residuals: | 149 | BIC: | 493.0 | \n",
"
\n",
"\n",
" | Df Model: | 1 | | | \n",
"
\n",
"\n",
" | Covariance Type: | nonrobust | | | \n",
"
\n",
"
\n",
"\n",
"\n",
" | coef | std err | t | P>|t| | [95.0% Conf. Int.] | \n",
"
\n",
"\n",
" | sepal_width | 1.8690 | 0.033 | 57.246 | 0.000 | 1.804 1.934 | \n",
"
\n",
"
\n",
"\n",
"\n",
" | Omnibus: | 18.144 | Durbin-Watson: | 0.427 | \n",
"
\n",
"\n",
" | Prob(Omnibus): | 0.000 | Jarque-Bera (JB): | 7.909 | \n",
"
\n",
"\n",
" | Skew: | -0.338 | Prob(JB): | 0.0192 | \n",
"
\n",
"\n",
" | Kurtosis: | 2.101 | Cond. No. | 1.00 | \n",
"
\n",
"
"
],
"text/plain": [
"\n",
"\"\"\"\n",
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: sepal_length R-squared: 0.957\n",
"Model: OLS Adj. R-squared: 0.956\n",
"Method: Least Squares F-statistic: 3277.\n",
"Date: Sun, 03 Apr 2016 Prob (F-statistic): 2.42e-103\n",
"Time: 01:31:50 Log-Likelihood: -243.98\n",
"No. Observations: 150 AIC: 490.0\n",
"Df Residuals: 149 BIC: 493.0\n",
"Df Model: 1 \n",
"Covariance Type: nonrobust \n",
"===============================================================================\n",
" coef std err t P>|t| [95.0% Conf. Int.]\n",
"-------------------------------------------------------------------------------\n",
"sepal_width 1.8690 0.033 57.246 0.000 1.804 1.934\n",
"==============================================================================\n",
"Omnibus: 18.144 Durbin-Watson: 0.427\n",
"Prob(Omnibus): 0.000 Jarque-Bera (JB): 7.909\n",
"Skew: -0.338 Prob(JB): 0.0192\n",
"Kurtosis: 2.101 Cond. No. 1.00\n",
"==============================================================================\n",
"\n",
"Warnings:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
"\"\"\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fitted.summary()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.069467",
"start_time": "2016-04-03T01:31:51.057906"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"sepal_width 1.869009\n",
"dtype: float64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fitted.params"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.077310",
"start_time": "2016-04-03T01:31:51.072416"
},
"collapsed": false
},
"outputs": [],
"source": [
"def attrs(obj):\n",
" return [a for a in dir(obj) if not a.startswith(\"_\")]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.096021",
"start_time": "2016-04-03T01:31:51.080053"
},
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Pretty printing has been turned OFF\n"
]
}
],
"source": [
"%pprint"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## model と 学習済みモデル"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.106290",
"start_time": "2016-04-03T01:31:51.099023"
},
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"['data', 'df_model', 'df_resid', 'endog', 'endog_names', 'exog', 'exog_names', 'fit', 'fit_regularized', 'from_formula', 'hessian', 'information', 'initialize', 'k_constant', 'loglike', 'nobs', 'normalized_cov_params', 'pinv_wexog', 'predict', 'rank', 'score', 'weights', 'wendog', 'wexog', 'wexog_singular_values', 'whiten']"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"attrs(model)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.116904",
"start_time": "2016-04-03T01:31:51.109746"
},
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"['HC0_se', 'HC1_se', 'HC2_se', 'HC3_se', 'aic', 'bic', 'bse', 'centered_tss', 'compare_f_test', 'compare_lm_test', 'compare_lr_test', 'condition_number', 'conf_int', 'conf_int_el', 'cov_HC0', 'cov_HC1', 'cov_HC2', 'cov_HC3', 'cov_kwds', 'cov_params', 'cov_type', 'df_model', 'df_resid', 'diagn', 'eigenvals', 'el_test', 'ess', 'f_pvalue', 'f_test', 'fittedvalues', 'fvalue', 'get_influence', 'get_robustcov_results', 'initialize', 'k_constant', 'llf', 'load', 'model', 'mse_model', 'mse_resid', 'mse_total', 'nobs', 'normalized_cov_params', 'outlier_test', 'params', 'predict', 'pvalues', 'remove_data', 'resid', 'resid_pearson', 'rsquared', 'rsquared_adj', 'save', 'scale', 'ssr', 'summary', 'summary2', 't_test', 'tvalues', 'uncentered_tss', 'use_t', 'wald_test', 'wresid']"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"attrs(fitted)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## statsmodel api"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.126951",
"start_time": "2016-04-03T01:31:51.119806"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['GEE', 'GLM', 'GLS', 'GLSAR', 'OLS', 'RLM', 'WLS']"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(sm) if a.isupper()]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.300108",
"start_time": "2016-04-03T01:31:51.292737"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['GEE', 'GLM', 'GLS', 'GLSAR', 'Logit', 'MNLogit', 'MixedLM', 'NegativeBinomial', 'NominalGEE', 'OLS', 'OrdinalGEE', 'PHReg', 'Poisson', 'ProbPlot', 'Probit', 'QuantReg', 'RLM', 'WLS']"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(sm) if a[0].isupper()]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:51.447306",
"start_time": "2016-04-03T01:31:51.440455"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['add_constant', 'categorical', 'cov_struct', 'datasets', 'distributions', 'emplike', 'families', 'formula', 'genmod', 'graphics', 'iolib', 'load', 'nonparametric', 'qqline', 'qqplot', 'qqplot_2samples', 'regression', 'robust', 'show_versions', 'stats', 'test', 'tools', 'tsa', 'version', 'webdoc']"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(sm) if a.islower()]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## statsmodels formula api"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:53.741339",
"start_time": "2016-04-03T01:31:53.729179"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['GEE', 'GLM', 'GLS', 'GLSAR', 'OLS', 'RLM', 'WLS']"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(smf) if a.isupper()]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:54.252237",
"start_time": "2016-04-03T01:31:54.245937"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['GEE', 'GLM', 'GLS', 'GLSAR', 'Logit', 'MNLogit', 'MixedLM', 'NegativeBinomial', 'NominalGEE', 'OLS', 'OrdinalGEE', 'PHReg', 'Poisson', 'Probit', 'QuantReg', 'RLM', 'WLS']"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(smf) if a[0].isupper()]"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:54.750466",
"start_time": "2016-04-03T01:31:54.741854"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['gee', 'glm', 'gls', 'glsar', 'logit', 'mixedlm', 'mnlogit', 'negativebinomial', 'nominal_gee', 'ols', 'ordinal_gee', 'phreg', 'poisson', 'probit', 'quantreg', 'rlm', 'wls']"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(smf) if a.islower()]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## statsmodels"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:56.161870",
"start_time": "2016-04-03T01:31:56.158773"
},
"collapsed": true
},
"outputs": [],
"source": [
"import statsmodels"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:56.413189",
"start_time": "2016-04-03T01:31:56.405499"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(statsmodels) if a.isupper()]"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:56.604257",
"start_time": "2016-04-03T01:31:56.598834"
},
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"['CacheWriteWarning', 'ConvergenceWarning', 'InvalidTestWarning', 'IterationLimitWarning', 'NoseWrapper', 'Tester']"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(statsmodels) if a[0].isupper()]"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:57.106223",
"start_time": "2016-04-03T01:31:57.101025"
},
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"['api', 'base', 'compat', 'datasets', 'discrete', 'distributions', 'duration', 'emplike', 'errstate', 'formula', 'genmod', 'graphics', 'info', 'iolib', 'nonparametric', 'print_function', 'regression', 'robust', 'sandbox', 'simplefilter', 'stats', 'test', 'tools', 'tsa', 'version']"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[a for a in attrs(statsmodels) if a.islower()]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:31:58.260213",
"start_time": "2016-04-03T01:31:58.253929"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"{'mathtext.bf', 'mathtext.rm', 'text.latex.preamble', 'text.hinting', 'ytick.minor.size', 'figure.titlesize', 'agg.path.chunksize', 'mathtext.fontset', 'mathtext.fallback_to_cm', 'text.hinting_factor', 'mathtext.tt', 'mathtext.cal', 'xtick.labelsize', 'mathtext.it', 'text.color', 'legend.handletextpad', 'legend.fontsize', 'axes.formatter.use_mathtext', 'figure.figsize', 'xtick.minor.size', 'text.dvipnghack', 'text.antialiased', 'errorbar.capsize', 'axes.titlesize', 'text.latex.unicode', 'lines.markersize', 'text.latex.preview', 'xtick.major.size', 'mathtext.default', 'axes.labelsize', 'ytick.labelsize', 'ps.papersize', 'boxplot.flierprops.markersize', 'mathtext.sf', 'ytick.major.size', 'font.size', 'text.usetex'}"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"{k for k in plt.rcParams.keys() if \"text\" in k} | {k for k in plt.rcParams.keys() if \"size\" in k}"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"ExecuteTime": {
"end_time": "2016-04-03T01:37:51.285439",
"start_time": "2016-04-03T01:37:50.291540"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" 5.0 | \n",
" 4.0 | \n",
" 6.0 | \n",
" 7.0 | \n",
" 8.0 | \n",
"
\n",
" \n",
" | \n",
" setosa | \n",
" versicolor | \n",
" virginica | \n",
" setosa | \n",
" versicolor | \n",
" virginica | \n",
" setosa | \n",
" versicolor | \n",
" virginica | \n",
" setosa | \n",
" versicolor | \n",
" virginica | \n",
" setosa | \n",
" versicolor | \n",
" virginica | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.310897 | \n",
" 0.310897 | \n",
" 0.310897 | \n",
" 0.352564 | \n",
" 0.352564 | \n",
" 0.352564 | \n",
" 0.798077 | \n",
" 0.798077 | \n",
" 0.798077 | \n",
" 0.961538 | \n",
" 0.961538 | \n",
" 0.961538 | \n",
"
\n",
" \n",
" | 1 | \n",
" 0.000000 | \n",
" 0.846445 | \n",
" 0.979003 | \n",
" 0.000000 | \n",
" 0.993421 | \n",
" 1.000000 | \n",
" 0.000000 | \n",
" 0.079141 | \n",
" 0.608166 | \n",
" 0.000000 | \n",
" 0.006579 | \n",
" 0.342105 | \n",
" 0.000000 | \n",
" 0.006579 | \n",
" 0.013158 | \n",
"
\n",
" \n",
" | 2 | \n",
" 0.301282 | \n",
" 0.301282 | \n",
" 0.301282 | \n",
" 0.032051 | \n",
" 0.032051 | \n",
" 0.032051 | \n",
" 0.435897 | \n",
" 0.435897 | \n",
" 0.435897 | \n",
" 0.153846 | \n",
" 0.153846 | \n",
" 0.153846 | \n",
" 0.038462 | \n",
" 0.038462 | \n",
" 0.038462 | \n",
"
\n",
" \n",
" | 3 | \n",
" 0.839866 | \n",
" 0.125980 | \n",
" 0.020997 | \n",
" 0.986842 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.072562 | \n",
" 0.522446 | \n",
" 0.391834 | \n",
" 0.000000 | \n",
" 0.328947 | \n",
" 0.657895 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.986842 | \n",
"
\n",
" \n",
"
\n",
"