{
"nbformat": 4,
"nbformat_minor": 0,
"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": "3.7.3"
},
"colab": {
"name": "02_Chapter02.ipynb",
"provenance": [],
"toc_visible": true,
"include_colab_link": true
}
},
"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": "qi2Spo5cLszc",
"colab_type": "text"
},
"source": [
"## Chapter 2 - Linear Models: Least Squares Theory"
]
},
{
"cell_type": "code",
"metadata": {
"id": "eFCoT0ieLszf",
"colab_type": "code",
"colab": {},
"outputId": "877ad949-5e6f-4662-a556-e890acb45d1c"
},
"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": {
"id": "wLgeOy9XLszu",
"colab_type": "code",
"colab": {},
"outputId": "fe8c3813-0692-4a9a-fe2a-5a1867a3ad7a"
},
"source": [
"scots_races_df = pd.read_csv(\"../data/ScotsRaces.tsv.gz\", sep=\"\\t\")\n",
"scots_races_df.head()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" race | \n",
" distance | \n",
" climb | \n",
" time | \n",
"
\n",
" \n",
" \n",
" \n",
" | 1 | \n",
" GreenmantleNewYearDash | \n",
" 2.5 | \n",
" 0.65 | \n",
" 16.08 | \n",
"
\n",
" \n",
" | 2 | \n",
" Carnethy5HillRace | \n",
" 6.0 | \n",
" 2.50 | \n",
" 48.35 | \n",
"
\n",
" \n",
" | 3 | \n",
" CraigDunainHillRace | \n",
" 6.0 | \n",
" 0.90 | \n",
" 33.65 | \n",
"
\n",
" \n",
" | 4 | \n",
" BenRhaHillRace | \n",
" 7.5 | \n",
" 0.80 | \n",
" 45.60 | \n",
"
\n",
" \n",
" | 5 | \n",
" BenLomondHillRace | \n",
" 8.0 | \n",
" 3.07 | \n",
" 62.27 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"tags": [],
"image/png": {
"height": 750,
"width": 750
}
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "L_FCkdklLs0M",
"colab_type": "code",
"colab": {},
"outputId": "e327d8f8-a2a2-48df-8fd4-708d729d65e4"
},
"source": [
"scots_races_df[[\"climb\", \"distance\", \"time\"]].corr()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" climb | \n",
" distance | \n",
" time | \n",
"
\n",
" \n",
" \n",
" \n",
" | climb | \n",
" 1.000000 | \n",
" 0.652346 | \n",
" 0.832654 | \n",
"
\n",
" \n",
" | distance | \n",
" 0.652346 | \n",
" 1.000000 | \n",
" 0.943094 | \n",
"
\n",
" \n",
" | time | \n",
" 0.832654 | \n",
" 0.943094 | \n",
" 1.000000 | \n",
"
\n",
" \n",
"
\n",
"