{ "cells": [ { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# Fitting a line\n" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "## Setup" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "import pandas as pd\n", "\n", "from sklearn.linear_model import LinearRegression\n", "from sklearn.metrics import mean_squared_error" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "## Data" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "### Import data" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "df = pd.read_csv('https://raw.githubusercontent.com/kirenz/datasets/master/possum.csv')" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "### Data structure" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/html": [ "
\n", " | site | \n", "pop | \n", "sex | \n", "age | \n", "head_l | \n", "skull_w | \n", "total_l | \n", "tail_l | \n", "
---|---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "Vic | \n", "m | \n", "8.0 | \n", "94.1 | \n", "60.4 | \n", "89.0 | \n", "36.0 | \n", "
1 | \n", "1 | \n", "Vic | \n", "f | \n", "6.0 | \n", "92.5 | \n", "57.6 | \n", "91.5 | \n", "36.5 | \n", "
2 | \n", "1 | \n", "Vic | \n", "f | \n", "6.0 | \n", "94.0 | \n", "60.0 | \n", "95.5 | \n", "39.0 | \n", "
3 | \n", "1 | \n", "Vic | \n", "f | \n", "6.0 | \n", "93.2 | \n", "57.1 | \n", "92.0 | \n", "38.0 | \n", "
4 | \n", "1 | \n", "Vic | \n", "f | \n", "2.0 | \n", "91.5 | \n", "56.3 | \n", "85.5 | \n", "36.0 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
99 | \n", "7 | \n", "other | \n", "m | \n", "1.0 | \n", "89.5 | \n", "56.0 | \n", "81.5 | \n", "36.5 | \n", "
100 | \n", "7 | \n", "other | \n", "m | \n", "1.0 | \n", "88.6 | \n", "54.7 | \n", "82.5 | \n", "39.0 | \n", "
101 | \n", "7 | \n", "other | \n", "f | \n", "6.0 | \n", "92.4 | \n", "55.0 | \n", "89.0 | \n", "38.0 | \n", "
102 | \n", "7 | \n", "other | \n", "m | \n", "4.0 | \n", "91.5 | \n", "55.2 | \n", "82.5 | \n", "36.5 | \n", "
103 | \n", "7 | \n", "other | \n", "f | \n", "3.0 | \n", "93.6 | \n", "59.9 | \n", "89.0 | \n", "40.0 | \n", "
104 rows × 8 columns
\n", "LinearRegression()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
LinearRegression()