New notebooks for factorial design

statistics/anova_block_design.ipynb

@@ -0,0 +1,230 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Randomized Complete Block Design\n",
+ "## Example 13-5: Fabric Strength"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import statsmodels.formula.api as smf\n",
+ "from statsmodels.stats.anova import anova_lm\n",
+ "import matplotlib.pyplot as plt\n",
+ "import scipy.stats as st\n",
+ "%matplotlib inline"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Chemical</th>\n",
+ " <th>Fabric</th>\n",
+ " <th>Strength</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>1.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>2</td>\n",
+ " <td>1.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>0.5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>1.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1</td>\n",
+ " <td>5</td>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Chemical Fabric Strength\n",
+ "0 1 1 1.3\n",
+ "1 1 2 1.6\n",
+ "2 1 3 0.5\n",
+ "3 1 4 1.2\n",
+ "4 1 5 1.1"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = pd.read_excel('table 13-12.xlsx')\n",
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\stats\\_distn_infrastructure.py:879: RuntimeWarning: invalid value encountered in greater\n",
+ " return (self.a < x) & (x < self.b)\n",
+ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\stats\\_distn_infrastructure.py:879: RuntimeWarning: invalid value encountered in less\n",
+ " return (self.a < x) & (x < self.b)\n",
+ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\stats\\_distn_infrastructure.py:1818: RuntimeWarning: invalid value encountered in less_equal\n",
+ " cond2 = cond0 & (x <= self.a)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>df</th>\n",
+ " <th>sum_sq</th>\n",
+ " <th>mean_sq</th>\n",
+ " <th>F</th>\n",
+ " <th>PR(&gt;F)</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>C(Chemical)</th>\n",
+ " <td>3.0</td>\n",
+ " <td>18.044</td>\n",
+ " <td>6.014667</td>\n",
+ " <td>75.894848</td>\n",
+ " <td>4.518310e-08</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>C(Fabric)</th>\n",
+ " <td>4.0</td>\n",
+ " <td>6.693</td>\n",
+ " <td>1.673250</td>\n",
+ " <td>21.113565</td>\n",
+ " <td>2.318913e-05</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Residual</th>\n",
+ " <td>12.0</td>\n",
+ " <td>0.951</td>\n",
+ " <td>0.079250</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " df sum_sq mean_sq F PR(>F)\n",
+ "C(Chemical) 3.0 18.044 6.014667 75.894848 4.518310e-08\n",
+ "C(Fabric) 4.0 6.693 1.673250 21.113565 2.318913e-05\n",
+ "Residual 12.0 0.951 0.079250 NaN NaN"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "res = smf.ols('Strength ~ C(Chemical) + C(Fabric)', data=df).fit()\n",
+ "anova_lm(res)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "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": "3.6.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}