{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "tags": [ "remove-cell" ] }, "outputs": [], "source": [ "# Reference: https://jupyterbook.org/interactive/hiding.html\n", "# Use {hide, remove}-{input, output, cell} tags to hiding content\n", "\n", "import sys\n", "import os\n", "if not any(path.endswith('textbook') for path in sys.path):\n", " sys.path.append(os.path.abspath('../../..'))\n", "from textbook_utils import *" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Wrangling and Transforming" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We begin by taking a peek at the contents of our datafile.\n", "To do this, we open the file and examine the first few rows\n", "({numref}`Chapter %s `):" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "BCS,Age,Sex,Length,Girth,Height,Weight,WeightAlt\n", "3,<2,stallion,78,90,90,77,NA\n", "2.5,<2,stallion,91,97,94,100,NA\n", "1.5,<2,stallion,74,93,95,74,NA\n", "3,<2,female,87,109,96,116,NA\n" ] } ], "source": [ "from pathlib import Path\n", "\n", "# Create a Path pointing to our data file\n", "insp_path = Path('data/donkeys.csv')\n", "\n", "with insp_path.open() as f:\n", " # Display first five lines of file\n", " for _ in range(5):\n", " print(f.readline(), end='')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Since the file is CSV formatted, we can easily read it into a dataframe:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
BCSAgeSexLengthGirthHeightWeightWeightAlt
03.0<2stallion78909077NaN
12.5<2stallion919794100NaN
21.5<2stallion74939574NaN
...........................
5412.510-15stallion103118103174NaN
5423.02-5stallion91112100139NaN
5433.05-10stallion104124110189NaN
\n", "

544 rows × 8 columns

\n", "
" ], "text/plain": [ " BCS Age Sex Length Girth Height Weight WeightAlt\n", "0 3.0 <2 stallion 78 90 90 77 NaN\n", "1 2.5 <2 stallion 91 97 94 100 NaN\n", "2 1.5 <2 stallion 74 93 95 74 NaN\n", ".. ... ... ... ... ... ... ... ...\n", "541 2.5 10-15 stallion 103 118 103 174 NaN\n", "542 3.0 2-5 stallion 91 112 100 139 NaN\n", "543 3.0 5-10 stallion 104 124 110 189 NaN\n", "\n", "[544 rows x 8 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "donkeys = pd.read_csv(\"data/donkeys.csv\")\n", "donkeys" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Over 500 donkeys participated in the survey, and eight measurements were made on each donkey. According to the documentation, the granularity is a single donkey ({numref}`Chapter %s `).\n", "{numref}`Table %s ` provides descriptions of the eight features.\n", "\n", ":::{table} Donkey study codebook\n", ":name: tbl:donkey-codebook\n", "\n", "| Feature | Data type | Feature type | Description |\n", "|----------------|-----------|------------|--------------------------------------------------------|\n", "|BCS | float64 | Ordinal | Body condition score: from 1 (emaciated) to 3 (healthy) to 5 (obese) in increments of 0.5. |\n", "| Age | string | Ordinal | Age in years, under 2, 2–5, 5–10, 10–15, 15–20, and over 20 years |\n", "| Sex | string | Nominal | Sex categories: stallion, gelding, female |\n", "| Length | int64 | Numeric | Body length (cm) from front leg elbow to back of pelvis |\n", "| Girth | int64 | Numeric | Body circumference (cm), measured just behind front legs |\n", "| Height | int64 | Numeric | Body height (cm) up to point where neck connects to back |\n", "| Weight |int64 | Numeric | Weight (kilogram) |\n", "| WeightAlt |float64 | Numeric | Second weight measurement taken on a subset of donkeys |\n", "\n", ":::\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "{numref}`Figure %s ` is a stylized representation of a donkey as a cylinder with neck and legs appended. Height is measured from the ground to the base of the neck above the shoulders; girth is around the body, just behind the legs; and length is from the front elbow to the back of the pelvis.\n", "\n", "```{figure} donkeyDiagram.png\n", "---\n", "name: fig:donkeyDiagram\n", "width: 400px\n", "---\n", "Diagram of a donkey's girth, length, and height, characterized as measurements on a cylinder\n", "```" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Our next step is to perform some quality checks on the data. In the previous section, we listed a few potential quality concerns based on scope. Next, we check the quality of the measurements and their distributions." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's start by comparing the two weight measurements made on the subset of donkeys to check on the consistency of the scale. We make a histogram of the difference between these two measurements for the 31 donkeys that were weighed twice: " ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "tags": [] }, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "alignmentgroup": "True", "bingroup": "x", "hovertemplate": "Differences of two weighings (kg)
on the same donkey=%{x}
count=%{y}", "legendgroup": "", "marker": { "color": "#1F77B4", "pattern": { "shape": "" } }, "name": "", "nbinsx": 15, "offsetgroup": "", "orientation": "v", "showlegend": false, "type": "histogram", "x": [ null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 1, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, null, null, null, null, null, null, 0, null, null, null, 0, null, -1, null, null, 0, null, 0, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, -1, -1, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, 0, null, 0, null, null, null, null, null, null, null, null, null, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, null, null, null, null, null, 0, null, null, null, null, null, null, 0, null, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, null, null, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, -1, null, null, null, null, null, null, null, null, null, null, -1, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 1, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 1, null, null, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, -1, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 1, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, 0, 0, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null ], "xaxis": "x", "yaxis": "y" } ], "layout": { "barmode": "relative", "height": 250, "legend": { "tracegroupgap": 0 }, "template": { "data": { "bar": [ { "error_x": { "color": "rgb(36,36,36)" }, "error_y": { "color": "rgb(36,36,36)" }, "marker": { "line": { "color": "white", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "white", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(36,36,36)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(36,36,36)" }, "baxis": { "endlinecolor": "rgb(36,36,36)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(36,36,36)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "line": { "color": "white", "width": 0.6 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autosize": true, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "colorscale": { "diverging": [ [ 0, "rgb(103,0,31)" ], [ 0.1, "rgb(178,24,43)" ], [ 0.2, "rgb(214,96,77)" ], [ 0.3, "rgb(244,165,130)" ], [ 0.4, "rgb(253,219,199)" ], [ 0.5, "rgb(247,247,247)" ], [ 0.6, "rgb(209,229,240)" ], [ 0.7, "rgb(146,197,222)" ], [ 0.8, "rgb(67,147,195)" ], [ 0.9, "rgb(33,102,172)" ], [ 1, "rgb(5,48,97)" ] ], "sequential": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "sequentialminus": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ] }, "colorway": [ "#1F77B4", "#FF7F0E", "#2CA02C", "#D62728", "#9467BD", "#8C564B", "#E377C2", "#7F7F7F", "#BCBD22", "#17BECF" ], "font": { "color": "rgb(36,36,36)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "white", "showlakes": true, "showland": true, "subunitcolor": "white" }, "height": 250, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "margin": { "b": 10, "l": 10, "r": 10, "t": 10 }, "paper_bgcolor": "white", "plot_bgcolor": "white", "polar": { "angularaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "bgcolor": "white", "radialaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "yaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "zaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "baxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "bgcolor": "white", "caxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" } }, "title": { "x": 0.5, "xanchor": "center" }, "width": 350, "xaxis": { "automargin": true, "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": true, "showline": true, "ticks": "outside", "title": { "standoff": 15 }, "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "yaxis": { "automargin": true, "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": true, "showline": true, "ticks": "outside", "title": { "standoff": 15 }, "zeroline": false, "zerolinecolor": "rgb(36,36,36)" } } }, "width": 350, "xaxis": { "anchor": "y", "autorange": true, "domain": [ 0, 1 ], "range": [ -1.1, 1.1 ], "title": { "text": "Differences of two weighings (kg)
on the same donkey" }, "type": "linear" }, "yaxis": { "anchor": "x", "autorange": true, "domain": [ 0, 1 ], "range": [ 0, 22.105263157894736 ], "title": { "text": "count" } } } }, "image/png": "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", "image/svg+xml": [ "−1−0.500.5105101520Differences of two weighings (kg)on the same donkeycount" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "donkeys = donkeys.assign(difference=donkeys[\"WeightAlt\"] - donkeys[\"Weight\"])\n", "\n", "px.histogram(donkeys, x=\"difference\", nbins=15,\n", " labels=dict(\n", " difference=\"Differences of two weighings (kg)
on the same donkey\"\n", " ),\n", " width=350, height=250,\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The measurements are all within 1 kg of each other, and the majority are exactly the same (to the nearest kilogram). This gives us confidence in the accuracy of the measurements. \n", "\n", "Next, we look for unusual values in the body condition score: " ] }, { "cell_type": "code", "execution_count": 86, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "BCS\n", "3.0 307\n", "2.5 135\n", "3.5 55\n", " ... \n", "1.5 5\n", "4.5 1\n", "1.0 1\n", "Name: count, Length: 8, dtype: int64" ] }, "execution_count": 86, "metadata": {}, "output_type": "execute_result" } ], "source": [ "donkeys['BCS'].value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "From this output, we see that there's only one emaciated (BCS = 1) and one obese (BCS = 4.5) donkey.\n", "Let's look at the complete records for these two donkeys:" ] }, { "cell_type": "code", "execution_count": 87, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
BCSAgeSexLengthGirthHeightWeightWeightAlt
2914.510-15female107130106227NaN
4451.0>20female97109102115NaN
\n", "
" ], "text/plain": [ " BCS Age Sex Length Girth Height Weight WeightAlt\n", "291 4.5 10-15 female 107 130 106 227 NaN\n", "445 1.0 >20 female 97 109 102 115 NaN" ] }, "execution_count": 87, "metadata": {}, "output_type": "execute_result" } ], "source": [ "donkeys[(donkeys['BCS'] == 1.0) | (donkeys['BCS'] == 4.5)]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Since these BCS values are extreme, we want to be cautious about including these two donkeys in our analysis. Since we have only one donkey in each of these extreme categories, our model might well not extend to donkeys with a BCS of 1 or 4.5. So we remove these two records from the dataframe and note that our analysis may not extend to emaciated or obese donkeys. In general, we exercise caution in dropping records from a dataframe. Later, we may also decide to remove the five donkeys with a score of 1.5 if they appear anomalous in our analysis, but for now, we keep them in our dataframe. We need good reasons for their exclusion, document our action, and keep the number of excluded observations low so that we avoid overfitting a model because we dropped any record that disagreed with the model. \n", "\n", "We remove these two outliers next:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "def remove_bcs_outliers(donkeys):\n", " return donkeys[(donkeys['BCS'] >= 1.5) & (donkeys['BCS'] <= 4)] \n", "\n", "donkeys = (pd.read_csv('data/donkeys.csv')\n", " .pipe(remove_bcs_outliers))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now, we examine the distribution of values for weight to see if there are any issues with quality:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "tags": [] }, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "alignmentgroup": "True", "bingroup": "x", "hovertemplate": "Weight (kg)=%{x}
count=%{y}", "legendgroup": "", "marker": { "color": "#1F77B4", "pattern": { "shape": "" } }, "name": "", "nbinsx": 40, "offsetgroup": "", "orientation": "v", "showlegend": false, "type": "histogram", "x": [ 77, 100, 74, 116, 91, 105, 108, 86, 27, 141, 100, 95, 115, 106, 112, 117, 94, 107, 102, 127, 90, 108, 72, 102, 86, 118, 65, 90, 118, 113, 117, 124, 89, 130, 150, 87, 96, 117, 94, 105, 94, 107, 117, 106, 75, 105, 114, 115, 107, 98, 71, 142, 146, 106, 162, 164, 133, 152, 129, 110, 181, 160, 172, 164, 192, 163, 169, 144, 165, 160, 145, 110, 154, 133, 152, 145, 130, 183, 173, 161, 172, 151, 170, 159, 142, 136, 185, 143, 107, 173, 161, 176, 169, 184, 166, 152, 98, 131, 136, 109, 165, 138, 137, 177, 142, 160, 125, 158, 178, 157, 164, 162, 155, 166, 170, 141, 142, 165, 146, 163, 170, 159, 154, 165, 167, 157, 114, 181, 170, 168, 146, 163, 190, 138, 162, 171, 167, 139, 188, 152, 174, 125, 179, 167, 149, 144, 158, 144, 145, 140, 168, 152, 161, 155, 179, 143, 150, 170, 136, 167, 169, 141, 154, 131, 155, 157, 165, 92, 171, 156, 182, 157, 194, 174, 160, 178, 152, 157, 170, 142, 156, 167, 151, 158, 149, 146, 139, 133, 144, 178, 159, 114, 142, 175, 145, 150, 155, 140, 140, 158, 160, 160, 188, 172, 145, 154, 158, 158, 165, 149, 128, 167, 126, 158, 168, 134, 186, 148, 162, 134, 136, 168, 174, 123, 196, 146, 149, 148, 170, 155, 165, 166, 165, 164, 178, 170, 142, 173, 127, 204, 155, 162, 137, 171, 212, 165, 157, 148, 178, 151, 150, 190, 178, 188, 158, 195, 163, 149, 202, 116, 165, 145, 147, 144, 121, 200, 179, 138, 136, 143, 140, 149, 166, 173, 146, 143, 114, 145, 179, 174, 162, 158, 199, 210, 171, 130, 125, 156, 177, 175, 144, 227, 154, 166, 180, 130, 155, 162, 171, 145, 176, 138, 149, 135, 156, 157, 166, 160, 126, 177, 156, 145, 136, 152, 154, 126, 139, 160, 134, 120, 177, 130, 163, 159, 153, 130, 162, 168, 164, 167, 150, 134, 154, 169, 143, 167, 166, 122, 178, 170, 138, 165, 160, 155, 120, 149, 125, 126, 122, 137, 139, 178, 145, 146, 173, 172, 144, 158, 135, 130, 174, 126, 129, 127, 161, 168, 183, 122, 184, 160, 148, 146, 160, 137, 184, 141, 142, 147, 146, 132, 142, 114, 158, 148, 143, 152, 113, 133, 159, 183, 171, 136, 180, 167, 132, 184, 150, 147, 135, 180, 166, 160, 175, 114, 166, 181, 129, 154, 174, 165, 141, 156, 142, 96, 156, 178, 141, 175, 183, 151, 161, 183, 163, 161, 162, 173, 132, 143, 122, 174, 115, 144, 177, 175, 164, 204, 133, 163, 133, 160, 140, 151, 132, 143, 158, 115, 147, 146, 158, 152, 165, 152, 161, 144, 139, 174, 164, 153, 153, 142, 150, 180, 173, 126, 154, 130, 171, 172, 168, 196, 132, 192, 159, 173, 185, 181, 140, 185, 119, 153, 142, 173, 170, 177, 194, 143, 145, 142, 159, 184, 156, 179, 157, 179, 163, 177, 143, 177, 174, 143, 193, 183, 183, 181, 170, 189, 193, 191, 195, 163, 153, 183, 156, 185, 170, 170, 214, 179, 173, 147, 171, 189, 214, 230, 145, 162, 169, 178, 177, 151, 172, 180, 187, 132, 167, 152, 165, 213, 189, 145, 183, 174, 139, 189 ], "xaxis": "x", "yaxis": "y" } ], "layout": { "barmode": "relative", "height": 250, "legend": { "tracegroupgap": 0 }, "template": { "data": { "bar": [ { "error_x": { "color": "rgb(36,36,36)" }, "error_y": { "color": "rgb(36,36,36)" }, "marker": { "line": { "color": "white", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "white", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(36,36,36)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(36,36,36)" }, "baxis": { "endlinecolor": "rgb(36,36,36)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(36,36,36)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "line": { "color": "white", "width": 0.6 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autosize": true, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "colorscale": { "diverging": [ [ 0, "rgb(103,0,31)" ], [ 0.1, "rgb(178,24,43)" ], [ 0.2, "rgb(214,96,77)" ], [ 0.3, "rgb(244,165,130)" ], [ 0.4, "rgb(253,219,199)" ], [ 0.5, "rgb(247,247,247)" ], [ 0.6, "rgb(209,229,240)" ], [ 0.7, "rgb(146,197,222)" ], [ 0.8, "rgb(67,147,195)" ], [ 0.9, "rgb(33,102,172)" ], [ 1, "rgb(5,48,97)" ] ], "sequential": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "sequentialminus": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ] }, "colorway": [ "#1F77B4", "#FF7F0E", "#2CA02C", "#D62728", "#9467BD", "#8C564B", "#E377C2", "#7F7F7F", "#BCBD22", "#17BECF" ], "font": { "color": "rgb(36,36,36)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "white", "showlakes": true, "showland": true, "subunitcolor": "white" }, "height": 250, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "margin": { "b": 10, "l": 10, "r": 10, "t": 10 }, "paper_bgcolor": "white", "plot_bgcolor": "white", "polar": { "angularaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "bgcolor": "white", "radialaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "yaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "zaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "baxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "bgcolor": "white", "caxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" } }, "title": { "x": 0.5, "xanchor": "center" }, "width": 350, "xaxis": { "automargin": true, "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": true, "showline": true, "ticks": "outside", "title": { "standoff": 15 }, "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "yaxis": { "automargin": true, "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": true, "showline": true, "ticks": "outside", "title": { "standoff": 15 }, "zeroline": false, "zerolinecolor": "rgb(36,36,36)" } } }, "width": 350, "xaxis": { "anchor": "y", "autorange": true, "domain": [ 0, 1 ], "range": [ 19.5, 239.5 ], "title": { "text": "Weight (kg)" }, "type": "linear" }, "yaxis": { "anchor": "x", "autorange": true, "domain": [ 0, 1 ], "range": [ 0, 95.78947368421052 ], "title": { "text": "count" } } } }, "image/png": "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", "image/svg+xml": [ "50100150200020406080Weight (kg)count" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "px.histogram(donkeys, x='Weight', nbins=40, width=350, height=250,\n", " labels={'Weight':'Weight (kg)'})" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It appears there is one very light donkey weighing less than 30 kg. Next, we check the relationship between weight and height to assess the quality of the data for analysis:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "tags": [] }, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "hovertemplate": "Height (cm)=%{x}
Weight (kg)=%{y}", "legendgroup": "", "marker": { "color": "#1F77B4", "symbol": "circle" }, "mode": "markers", "name": "", "orientation": "v", "showlegend": false, "type": "scatter", "x": [ 90, 94, 95, 96, 91, 98, 96, 89, 71, 99, 92, 92, 96, 96, 97, 98, 90, 96, 94, 98, 93, 96, 86, 96, 92, 106, 91, 96, 97, 98, 98, 99, 94, 101, 106, 97, 98, 100, 93, 93, 92, 100, 97, 96, 89, 96, 98, 91, 99, 96, 89, 101, 104, 97, 100, 101, 99, 97, 98, 93, 101, 104, 101, 97, 106, 99, 102, 100, 97, 100, 98, 95, 98, 104, 102, 105, 98, 108, 107, 106, 101, 101, 102, 99, 98, 104, 107, 99, 94, 97, 107, 103, 100, 98, 101, 101, 97, 96, 97, 100, 100, 98, 99, 102, 99, 99, 102, 101, 104, 103, 103, 104, 107, 102, 103, 103, 102, 102, 98, 102, 97, 103, 103, 103, 107, 101, 97, 98, 102, 104, 100, 102, 102, 104, 106, 102, 98, 97, 105, 106, 106, 99, 105, 102, 101, 95, 104, 97, 101, 102, 105, 102, 103, 100, 97, 98, 100, 102, 105, 105, 104, 102, 100, 97, 106, 102, 103, 98, 101, 104, 104, 101, 101, 107, 99, 99, 101, 99, 98, 99, 104, 104, 102, 105, 99, 102, 102, 101, 99, 98, 101, 95, 96, 102, 98, 98, 100, 98, 98, 106, 105, 100, 103, 101, 102, 105, 99, 103, 101, 99, 97, 103, 105, 101, 104, 100, 106, 99, 103, 94, 101, 103, 108, 96, 101, 103, 100, 98, 103, 101, 100, 102, 102, 101, 105, 102, 99, 100, 94, 111, 102, 103, 105, 103, 113, 103, 98, 101, 103, 102, 99, 103, 105, 103, 100, 107, 99, 99, 105, 101, 100, 105, 99, 99, 96, 103, 102, 100, 98, 104, 97, 98, 99, 99, 106, 100, 97, 101, 104, 102, 100, 101, 110, 110, 101, 102, 89, 102, 104, 104, 99, 106, 103, 99, 108, 97, 103, 99, 103, 101, 104, 101, 100, 97, 106, 102, 106, 105, 97, 101, 101, 102, 101, 99, 103, 98, 103, 100, 100, 100, 102, 103, 101, 103, 108, 102, 105, 112, 105, 103, 99, 101, 105, 107, 105, 107, 102, 94, 102, 108, 102, 107, 106, 107, 102, 107, 103, 102, 99, 103, 100, 98, 101, 101, 105, 107, 104, 102, 100, 99, 109, 101, 96, 100, 99, 104, 107, 100, 105, 104, 99, 102, 106, 103, 110, 104, 100, 99, 104, 102, 96, 89, 103, 100, 103, 99, 102, 98, 105, 101, 106, 101, 101, 100, 101, 106, 100, 100, 104, 103, 105, 97, 106, 98, 107, 103, 99, 102, 100, 106, 99, 103, 105, 90, 101, 104, 98, 106, 110, 102, 101, 104, 102, 98, 103, 106, 102, 100, 100, 105, 99, 102, 102, 100, 102, 107, 98, 101, 94, 112, 100, 100, 98, 98, 105, 102, 98, 103, 103, 101, 103, 104, 108, 100, 101, 103, 107, 103, 104, 100, 99, 103, 105, 97, 103, 99, 104, 101, 102, 109, 101, 105, 108, 106, 105, 103, 97, 104, 97, 103, 101, 106, 105, 102, 106, 103, 99, 102, 99, 106, 103, 102, 103, 104, 104, 104, 101, 105, 104, 100, 108, 102, 105, 100, 103, 105, 108, 102, 105, 101, 108, 102, 102, 106, 103, 106, 110, 107, 103, 101, 106, 109, 108, 116, 103, 104, 107, 103, 105, 106, 109, 105, 105, 103, 107, 100, 103, 108, 102, 101, 110, 103, 100, 110 ], "xaxis": "x", "y": [ 77, 100, 74, 116, 91, 105, 108, 86, 27, 141, 100, 95, 115, 106, 112, 117, 94, 107, 102, 127, 90, 108, 72, 102, 86, 118, 65, 90, 118, 113, 117, 124, 89, 130, 150, 87, 96, 117, 94, 105, 94, 107, 117, 106, 75, 105, 114, 115, 107, 98, 71, 142, 146, 106, 162, 164, 133, 152, 129, 110, 181, 160, 172, 164, 192, 163, 169, 144, 165, 160, 145, 110, 154, 133, 152, 145, 130, 183, 173, 161, 172, 151, 170, 159, 142, 136, 185, 143, 107, 173, 161, 176, 169, 184, 166, 152, 98, 131, 136, 109, 165, 138, 137, 177, 142, 160, 125, 158, 178, 157, 164, 162, 155, 166, 170, 141, 142, 165, 146, 163, 170, 159, 154, 165, 167, 157, 114, 181, 170, 168, 146, 163, 190, 138, 162, 171, 167, 139, 188, 152, 174, 125, 179, 167, 149, 144, 158, 144, 145, 140, 168, 152, 161, 155, 179, 143, 150, 170, 136, 167, 169, 141, 154, 131, 155, 157, 165, 92, 171, 156, 182, 157, 194, 174, 160, 178, 152, 157, 170, 142, 156, 167, 151, 158, 149, 146, 139, 133, 144, 178, 159, 114, 142, 175, 145, 150, 155, 140, 140, 158, 160, 160, 188, 172, 145, 154, 158, 158, 165, 149, 128, 167, 126, 158, 168, 134, 186, 148, 162, 134, 136, 168, 174, 123, 196, 146, 149, 148, 170, 155, 165, 166, 165, 164, 178, 170, 142, 173, 127, 204, 155, 162, 137, 171, 212, 165, 157, 148, 178, 151, 150, 190, 178, 188, 158, 195, 163, 149, 202, 116, 165, 145, 147, 144, 121, 200, 179, 138, 136, 143, 140, 149, 166, 173, 146, 143, 114, 145, 179, 174, 162, 158, 199, 210, 171, 130, 125, 156, 177, 175, 144, 227, 154, 166, 180, 130, 155, 162, 171, 145, 176, 138, 149, 135, 156, 157, 166, 160, 126, 177, 156, 145, 136, 152, 154, 126, 139, 160, 134, 120, 177, 130, 163, 159, 153, 130, 162, 168, 164, 167, 150, 134, 154, 169, 143, 167, 166, 122, 178, 170, 138, 165, 160, 155, 120, 149, 125, 126, 122, 137, 139, 178, 145, 146, 173, 172, 144, 158, 135, 130, 174, 126, 129, 127, 161, 168, 183, 122, 184, 160, 148, 146, 160, 137, 184, 141, 142, 147, 146, 132, 142, 114, 158, 148, 143, 152, 113, 133, 159, 183, 171, 136, 180, 167, 132, 184, 150, 147, 135, 180, 166, 160, 175, 114, 166, 181, 129, 154, 174, 165, 141, 156, 142, 96, 156, 178, 141, 175, 183, 151, 161, 183, 163, 161, 162, 173, 132, 143, 122, 174, 115, 144, 177, 175, 164, 204, 133, 163, 133, 160, 140, 151, 132, 143, 158, 115, 147, 146, 158, 152, 165, 152, 161, 144, 139, 174, 164, 153, 153, 142, 150, 180, 173, 126, 154, 130, 171, 172, 168, 196, 132, 192, 159, 173, 185, 181, 140, 185, 119, 153, 142, 173, 170, 177, 194, 143, 145, 142, 159, 184, 156, 179, 157, 179, 163, 177, 143, 177, 174, 143, 193, 183, 183, 181, 170, 189, 193, 191, 195, 163, 153, 183, 156, 185, 170, 170, 214, 179, 173, 147, 171, 189, 214, 230, 145, 162, 169, 178, 177, 151, 172, 180, 187, 132, 167, 152, 165, 213, 189, 145, 183, 174, 139, 189 ], "yaxis": "y" } ], "layout": { "height": 250, "legend": { "tracegroupgap": 0 }, "template": { "data": { "bar": [ { "error_x": { "color": "rgb(36,36,36)" }, "error_y": { "color": "rgb(36,36,36)" }, "marker": { "line": { "color": "white", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "white", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(36,36,36)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(36,36,36)" }, "baxis": { "endlinecolor": "rgb(36,36,36)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(36,36,36)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "line": { "color": "white", "width": 0.6 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" }, "colorscale": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autosize": true, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 1, "tickcolor": "rgb(36,36,36)", "ticks": "outside" } }, "colorscale": { "diverging": [ [ 0, "rgb(103,0,31)" ], [ 0.1, "rgb(178,24,43)" ], [ 0.2, "rgb(214,96,77)" ], [ 0.3, "rgb(244,165,130)" ], [ 0.4, "rgb(253,219,199)" ], [ 0.5, "rgb(247,247,247)" ], [ 0.6, "rgb(209,229,240)" ], [ 0.7, "rgb(146,197,222)" ], [ 0.8, "rgb(67,147,195)" ], [ 0.9, "rgb(33,102,172)" ], [ 1, "rgb(5,48,97)" ] ], "sequential": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ], "sequentialminus": [ [ 0, "#440154" ], [ 0.1111111111111111, "#482878" ], [ 0.2222222222222222, "#3e4989" ], [ 0.3333333333333333, "#31688e" ], [ 0.4444444444444444, "#26828e" ], [ 0.5555555555555556, "#1f9e89" ], [ 0.6666666666666666, "#35b779" ], [ 0.7777777777777778, "#6ece58" ], [ 0.8888888888888888, "#b5de2b" ], [ 1, "#fde725" ] ] }, "colorway": [ "#1F77B4", "#FF7F0E", "#2CA02C", "#D62728", "#9467BD", "#8C564B", "#E377C2", "#7F7F7F", "#BCBD22", "#17BECF" ], "font": { "color": "rgb(36,36,36)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "white", "showlakes": true, "showland": true, "subunitcolor": "white" }, "height": 250, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "margin": { "b": 10, "l": 10, "r": 10, "t": 10 }, "paper_bgcolor": "white", "plot_bgcolor": "white", "polar": { "angularaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "bgcolor": "white", "radialaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "yaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "zaxis": { "backgroundcolor": "white", "gridcolor": "rgb(232,232,232)", "gridwidth": 2, "linecolor": "rgb(36,36,36)", "showbackground": true, "showgrid": false, "showline": true, "ticks": "outside", "zeroline": false, "zerolinecolor": "rgb(36,36,36)" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "baxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" }, "bgcolor": "white", "caxis": { "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": false, "showline": true, "ticks": "outside" } }, "title": { "x": 0.5, "xanchor": "center" }, "width": 350, "xaxis": { "automargin": true, "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": true, "showline": true, "ticks": "outside", "title": { "standoff": 15 }, "zeroline": false, "zerolinecolor": "rgb(36,36,36)" }, "yaxis": { "automargin": true, "gridcolor": "rgb(232,232,232)", "linecolor": "rgb(36,36,36)", "showgrid": true, "showline": true, "ticks": "outside", "title": { "standoff": 15 }, "zeroline": false, "zerolinecolor": "rgb(36,36,36)" } } }, "width": 350, "xaxis": { "anchor": "y", "autorange": true, "domain": [ 0, 1 ], "range": [ 67.72166874221669, 119.27833125778331 ], "title": { "text": "Height (cm)" }, "type": "linear" }, "yaxis": { "anchor": "x", "autorange": true, "domain": [ 0, 1 ], "range": [ 10.279279279279276, 246.72072072072072 ], "title": { "text": "Weight (kg)" }, "type": "linear" } } }, "image/png": "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", "image/svg+xml": [ "8010050100150200Height (cm)Weight (kg)" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "px.scatter(donkeys, x='Height', y='Weight', width=350, height=250,\n", " labels={'Weight':'Weight (kg)', 'Height':'Height (cm)'})" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The small donkey is far from the main concentration of donkeys and would overly influence our models. For this reason, we exclude it. Again, we keep in mind that we may also want to exclude the one or two heavy donkeys if they appear to overly influence our future model fitting: " ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(541, 8)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def remove_weight_outliers(donkeys):\n", " return donkeys[(donkeys['Weight'] >= 40)]\n", "\n", "donkeys = (pd.read_csv('data/donkeys.csv')\n", " .pipe(remove_bcs_outliers)\n", " .pipe(remove_weight_outliers))\n", "\n", "donkeys.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In summary, based on our cleaning and quality checks, we removed three anomalous observations from the dataframe. Now we're nearly ready to begin our exploratory analysis.\n", "Before we proceed, we set aside some of our data as a test set." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We talked about why it's important to separate out a test set from the train set in {numref}`Chapter %s `.\n", "A best practice is to separate out a test set early in the analysis, before we explore the data in detail, because in EDA, we begin to make decisions about what kinds of models to fit and what variables to use in the model. It's important that our test set isn't involved in these decisions so that it imitates how our model would perform with entirely new data.\n", "\n", "We divide our data into an 80/20 split, where we use 80\\% of the data to\n", "explore and build a model. Then we evaluate the model with the 20\\% that has\n", "been set aside. We use a simple random sample to split the dataframe into the\n", "test and train sets. To begin, we randomly shuffle the indices of the dataframe:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "np.random.seed(42)\n", "n = len(donkeys)\n", "indices = np.arange(n)\n", "np.random.shuffle(indices)\n", "n_train = int(np.round((0.8 * n)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we assign the first 80\\% of the dataframe to the train set and the remaining 20% to the test set: " ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "train_set = donkeys.iloc[indices[:n_train]]\n", "test_set = donkeys.iloc[indices[n_train:]]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we're ready to explore the training data and look for useful relationships and distributions that inform our modeling. " ] }, { "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": "3.9.4" } }, "nbformat": 4, "nbformat_minor": 4 }