{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "04_Chapter04.ipynb",
"provenance": [],
"toc_visible": true,
"include_colab_link": true
},
"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": "3.7.3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QwCP4URihbil",
"colab_type": "text"
},
"source": [
"## Chapter 4 - Generalized Linear Models: Model Fitting and Inference"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "GQeT5h9SMAIZ",
"colab": {},
"outputId": "1d7fac02-0eed-4bea-c5a6-9d9bbab4b92f"
},
"source": [
"import warnings\n",
"\n",
"import pandas as pd\n",
"import proplot as plot\n",
"import seaborn as sns\n",
"import statsmodels.api as sm\n",
"import statsmodels.formula.api as smf\n",
"from patsy import dmatrices\n",
"from scipy import stats\n",
"\n",
"warnings.filterwarnings(\"ignore\")\n",
"%pylab inline\n",
"\n",
"\n",
"plt.rcParams[\"axes.labelweight\"] = \"bold\"\n",
"plt.rcParams[\"font.weight\"] = \"bold\""
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Populating the interactive namespace from numpy and matplotlib\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "VeC-rT1MMAIq",
"colab": {},
"outputId": "fcc7fcbd-d528-4e36-af16-6ad466bbf15a"
},
"source": [
"crabs_df = pd.read_csv(\"../data/Crabs.tsv.gz\", sep=\"\\t\")\n",
"crabs_df.head()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" crab | \n",
" y | \n",
" weight | \n",
" width | \n",
" color | \n",
" spine | \n",
"
\n",
" \n",
" \n",
" \n",
" | 1 | \n",
" 1 | \n",
" 8 | \n",
" 3.05 | \n",
" 28.3 | \n",
" 2 | \n",
" 3 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" 0 | \n",
" 1.55 | \n",
" 22.5 | \n",
" 3 | \n",
" 3 | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" 9 | \n",
" 2.30 | \n",
" 26.0 | \n",
" 1 | \n",
" 1 | \n",
"
\n",
" \n",
" | 4 | \n",
" 4 | \n",
" 0 | \n",
" 2.10 | \n",
" 24.8 | \n",
" 3 | \n",
" 3 | \n",
"
\n",
" \n",
" | 5 | \n",
" 5 | \n",
" 4 | \n",
" 2.60 | \n",
" 26.0 | \n",
" 3 | \n",
" 3 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"tags": [],
"image/png": {
"height": 750,
"width": 750
}
}
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "CeYDZmSOMAJP",
"colab": {},
"outputId": "c2da0f54-5258-4718-ab8b-9ecde2af68ef"
},
"source": [
"from statsmodels.stats.anova import anova_lm\n",
"\n",
"fit1 = smf.ols(formula=\"\"\"price ~ size + new + baths + beds\"\"\", data=house_df).fit()\n",
"fit2 = smf.ols(\n",
" formula=\"\"\"price ~ (size + new + baths + beds)**2\"\"\", data=house_df\n",
").fit()\n",
"fit3 = smf.ols(\n",
" formula=\"\"\"price ~ (size + new + baths + beds)**3\"\"\", data=house_df\n",
").fit()\n",
"fit6 = smf.ols(\n",
" formula=\"\"\"price ~ (size + new + baths + beds)**6\"\"\", data=house_df\n",
").fit()\n",
"\n",
"anova_results = anova_lm(fit1, fit2)\n",
"anova_results"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" df_resid | \n",
" ssr | \n",
" df_diff | \n",
" ss_diff | \n",
" F | \n",
" Pr(>F) | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 95.0 | \n",
" 279624.077203 | \n",
" 0.0 | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
"
\n",
" \n",
" | 1 | \n",
" 89.0 | \n",
" 217916.368647 | \n",
" 6.0 | \n",
" 61707.708555 | \n",
" 4.200377 | \n",
" 0.000913 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" df_resid | \n",
" ssr | \n",
" df_diff | \n",
" ss_diff | \n",
" F | \n",
" Pr(>F) | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 89.0 | \n",
" 217916.368647 | \n",
" 0.0 | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
"
\n",
" \n",
" | 1 | \n",
" 95.0 | \n",
" 279624.077203 | \n",
" -6.0 | \n",
" -61707.708555 | \n",
" 3.494115 | \n",
" NaN | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" df_resid | \n",
" ssr | \n",
" df_diff | \n",
" ss_diff | \n",
" F | \n",
" Pr(>F) | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 89.0 | \n",
" 217916.368647 | \n",
" 0.0 | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
"
\n",
" \n",
" | 1 | \n",
" 95.0 | \n",
" 279624.077203 | \n",
" -6.0 | \n",
" -61707.708555 | \n",
" 3.494115 | \n",
" NaN | \n",
"
\n",
" \n",
"
\n",
"