{
"cells": [
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"tags": [
"remove-cell"
]
},
"outputs": [],
"source": [
"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": "code",
"execution_count": 12,
"metadata": {
"tags": [
"remove-cell"
]
},
"outputs": [],
"source": [
"dogs = pd.read_csv('data/akc.csv')\n",
"\n",
"kids = {1:\"high\", 2:\"medium\", 3:\"low\"}\n",
"dogs[\"kids\"] = dogs['children'].map(kids)"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"(sec:eda_multi)=\n",
"# Comparisons in Multivariate Settings"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"When we examine a distribution or relationship, we often want to compare it\n",
"across subgroups of the data. This process of conditioning on additional\n",
"factors often leads to visualizations that involve three or more variables.\n",
"In this section, we explain how to read plots that are commonly used to\n",
"visualize multiple variables."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"As an example, let's compare the relationship between height and\n",
"longevity across repetition categories. First, we collapse repetition\n",
"(the typical number of times it takes for a dog to learn a new command) \n",
"from six categories into four: <15, 15–25, 25–40, and 40+:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"rep_replacements = {\n",
" '80-100': '40+', '40-80': '40+', \n",
" '<5': '<15', '5-15': '<15',\n",
"}\n",
"dogs = dogs.assign(\n",
" repetition=dogs['repetition'].replace(rep_replacements))"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Now each group has about 30 breeds in it, and having fewer categories makes it easier to decipher relationships. These categories are conveyed by differently shaped symbols in a scatter plot: "
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"application/vnd.plotly.v1+json": {
"config": {
"plotlyServerURL": "https://plot.ly"
},
"data": [
{
"hovertemplate": "Repetition=<15
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "<15",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "markers",
"name": "<15",
"orientation": "v",
"showlegend": true,
"type": "scatter",
"x": [
51,
48,
41,
37,
24,
47,
37,
33,
50,
41,
61,
58,
null,
58,
59,
66,
61,
28,
62,
61,
64,
61,
61,
29,
61,
57,
44,
29,
47,
57,
64
],
"xaxis": "x",
"y": [
12.52,
12.92,
11.66,
12.5,
13,
11.67,
12.53,
11.81,
12.54,
11.95,
11.46,
12.04,
9.67,
12.04,
9.02,
10.33,
10.6,
12.25,
9.11,
9.73,
7.56,
null,
null,
12.7,
null,
9.33,
12.17,
13,
null,
12.5,
null
],
"yaxis": "y"
},
{
"hovertemplate": "Repetition=15-25
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "15-25",
"marker": {
"color": "#1F77B4",
"symbol": "diamond"
},
"mode": "markers",
"name": "15-25",
"orientation": "v",
"showlegend": true,
"type": "scatter",
"x": [
null,
25,
46,
26,
27,
null,
66,
58,
54,
60,
64,
62,
62,
53,
65,
47,
65,
47,
69,
58,
46,
53,
44,
null,
29,
51,
25,
42,
24
],
"xaxis": "x",
"y": [
14,
13.84,
12.49,
11.42,
11.05,
12.6,
11.63,
11.83,
12.44,
9.48,
11.1,
11.57,
11.17,
11.27,
10.34,
10,
10,
9.4,
9.32,
11.45,
null,
12.77,
9.9,
9.32,
null,
null,
null,
null,
14.25
],
"yaxis": "y"
},
{
"hovertemplate": "Repetition=25-40
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "25-40",
"marker": {
"color": "#1F77B4",
"symbol": "square"
},
"mode": "markers",
"name": "25-40",
"orientation": "v",
"showlegend": true,
"type": "scatter",
"x": [
55,
null,
51,
27,
null,
27,
65,
25,
52,
null,
25,
32,
38,
58,
null,
66,
65,
59,
61,
81,
76,
58,
42,
64,
48,
64,
61,
45,
61,
64,
46,
71,
65,
null,
38,
46,
38,
38,
56
],
"xaxis": "x",
"y": [
12.58,
12.63,
12.87,
12.8,
13.51,
12.21,
12.42,
14.42,
12.28,
10.92,
10.1,
11.29,
12.05,
12,
9.36,
10.16,
9.1,
8.81,
10.67,
6.94,
6.96,
null,
null,
null,
null,
10.75,
null,
11.17,
10,
null,
null,
null,
10.8,
8.7,
13.17,
12.16,
null,
13.17,
8.8
],
"yaxis": "y"
},
{
"hovertemplate": "Repetition=40+
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "40+",
"marker": {
"color": "#1F77B4",
"symbol": "x"
},
"mode": "markers",
"name": "40+",
"orientation": "v",
"showlegend": true,
"type": "scatter",
"x": [
27,
13,
23,
25,
null,
36,
39,
41,
24,
36,
42,
36,
23,
25,
66,
null,
56,
null,
71,
55,
47,
64,
65,
76,
67,
null,
30,
72,
24,
37,
36,
27,
25
],
"xaxis": "x",
"y": [
13.92,
16.5,
12.25,
13.2,
12,
12.3,
12.31,
11,
13.07,
11.43,
13.58,
10.02,
12.17,
10.69,
11.92,
11.56,
11.19,
9,
9.08,
10.21,
9.01,
6.75,
7.57,
6.5,
7.78,
6.29,
10.08,
10,
9.25,
null,
12.7,
12.25,
11
],
"yaxis": "y"
}
],
"layout": {
"height": 250,
"legend": {
"title": {
"text": "Repetition"
},
"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": [
{
"fillpattern": {
"fillmode": "overlay",
"size": 10,
"solidity": 0.2
},
"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": 450,
"xaxis": {
"anchor": "y",
"autorange": true,
"domain": [
0,
1
],
"range": [
8.142857142857142,
85.85714285714286
],
"title": {
"text": "Height (cm)"
},
"type": "linear"
},
"yaxis": {
"anchor": "x",
"autorange": true,
"domain": [
0,
1
],
"range": [
5.4490218790218785,
17.34097812097812
],
"title": {
"text": "Typical lifespan (yr)"
},
"type": "linear"
}
}
},
"image/png": "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",
"image/svg+xml": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"px.scatter(dogs.dropna(subset=['repetition']), x='height', y='longevity', \n",
" symbol='repetition', width=450, height=250,\n",
" labels={'height':'Height (cm)', \n",
" 'longevity':'Typical lifespan (yr)',\n",
" 'repetition':'Repetition'},\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"This plot would be challenging to interpret if there were\n",
"more levels within the `repetition` feature."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Facet plots offer an alternative approach to display these three features:"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": [],
"user_expressions": []
},
"source": [
"```python\n",
"px.scatter(dogs.dropna(subset=['repetition']), \n",
" x='height', y='longevity', trendline='ols', \n",
" facet_col='repetition', facet_col_wrap=2,\n",
" labels={'height':'Height (cm)', \n",
" 'longevity':'Typical lifespan (yr)'})\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"tags": [
"remove-input"
]
},
"outputs": [
{
"data": {
"application/vnd.plotly.v1+json": {
"config": {
"plotlyServerURL": "https://plot.ly"
},
"data": [
{
"hovertemplate": "repetition=<15
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "markers",
"name": "",
"orientation": "v",
"showlegend": false,
"type": "scatter",
"x": [
51,
48,
41,
37,
24,
47,
37,
33,
50,
41,
61,
58,
null,
58,
59,
66,
61,
28,
62,
61,
64,
61,
61,
29,
61,
57,
44,
29,
47,
57,
64
],
"xaxis": "x3",
"y": [
12.52,
12.92,
11.66,
12.5,
13,
11.67,
12.53,
11.81,
12.54,
11.95,
11.46,
12.04,
9.67,
12.04,
9.02,
10.33,
10.6,
12.25,
9.11,
9.73,
7.56,
null,
null,
12.7,
null,
9.33,
12.17,
13,
null,
12.5,
null
],
"yaxis": "y3"
},
{
"hovertemplate": "OLS trendline
longevity = -0.0766249 * height + 15.1648
R2=0.454049
repetition=<15
Height (cm)=%{x}
Typical lifespan (yr)=%{y} (trend)",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "lines",
"name": "",
"showlegend": false,
"type": "scatter",
"x": [
24,
28,
29,
29,
33,
37,
37,
41,
41,
44,
47,
48,
50,
51,
57,
57,
58,
58,
59,
61,
61,
61,
62,
64,
66
],
"xaxis": "x3",
"y": [
13.32579208799006,
13.019292570910448,
12.942667691640544,
12.942667691640544,
12.636168174560932,
12.32966865748132,
12.32966865748132,
12.023169140401707,
12.023169140401707,
11.793294502591998,
11.563419864782288,
11.486794985512386,
11.333545226972578,
11.256920347702676,
10.797171072083259,
10.797171072083259,
10.720546192813355,
10.720546192813355,
10.643921313543451,
10.490671555003646,
10.490671555003646,
10.490671555003646,
10.414046675733742,
10.260796917193936,
10.10754715865413
],
"yaxis": "y3"
},
{
"hovertemplate": "repetition=15-25
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "markers",
"name": "",
"orientation": "v",
"showlegend": false,
"type": "scatter",
"x": [
null,
25,
46,
26,
27,
null,
66,
58,
54,
60,
64,
62,
62,
53,
65,
47,
65,
47,
69,
58,
46,
53,
44,
null,
29,
51,
25,
42,
24
],
"xaxis": "x4",
"y": [
14,
13.84,
12.49,
11.42,
11.05,
12.6,
11.63,
11.83,
12.44,
9.48,
11.1,
11.57,
11.17,
11.27,
10.34,
10,
10,
9.4,
9.32,
11.45,
null,
12.77,
9.9,
9.32,
null,
null,
null,
null,
14.25
],
"yaxis": "y4"
},
{
"hovertemplate": "OLS trendline
longevity = -0.0456982 * height + 13.6117
R2=0.235689
repetition=15-25
Height (cm)=%{x}
Typical lifespan (yr)=%{y} (trend)",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "lines",
"name": "",
"showlegend": false,
"type": "scatter",
"x": [
24,
25,
26,
27,
44,
46,
47,
47,
53,
53,
54,
58,
58,
60,
62,
62,
64,
65,
65,
66,
69
],
"xaxis": "x4",
"y": [
12.514936831984254,
12.469238629757164,
12.423540427530071,
12.377842225302981,
11.600972787442421,
11.509576382988238,
11.463878180761146,
11.463878180761146,
11.189688967398595,
11.189688967398595,
11.143990765171504,
10.961197956263137,
10.961197956263137,
10.869801551808953,
10.77840514735477,
10.77840514735477,
10.687008742900586,
10.641310540673494,
10.641310540673494,
10.595612338446402,
10.458517731765127
],
"yaxis": "y4"
},
{
"hovertemplate": "repetition=25-40
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "markers",
"name": "",
"orientation": "v",
"showlegend": false,
"type": "scatter",
"x": [
55,
null,
51,
27,
null,
27,
65,
25,
52,
null,
25,
32,
38,
58,
null,
66,
65,
59,
61,
81,
76,
58,
42,
64,
48,
64,
61,
45,
61,
64,
46,
71,
65,
null,
38,
46,
38,
38,
56
],
"xaxis": "x",
"y": [
12.58,
12.63,
12.87,
12.8,
13.51,
12.21,
12.42,
14.42,
12.28,
10.92,
10.1,
11.29,
12.05,
12,
9.36,
10.16,
9.1,
8.81,
10.67,
6.94,
6.96,
null,
null,
null,
null,
10.75,
null,
11.17,
10,
null,
null,
null,
10.8,
8.7,
13.17,
12.16,
null,
13.17,
8.8
],
"yaxis": "y"
},
{
"hovertemplate": "OLS trendline
longevity = -0.0787387 * height + 15.126
R2=0.445933
repetition=25-40
Height (cm)=%{x}
Typical lifespan (yr)=%{y} (trend)",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "lines",
"name": "",
"showlegend": false,
"type": "scatter",
"x": [
25,
25,
27,
27,
32,
38,
38,
38,
45,
46,
51,
52,
55,
56,
58,
59,
61,
61,
64,
65,
65,
65,
66,
76,
81
],
"xaxis": "x",
"y": [
13.15755671203629,
13.15755671203629,
13.000079237993564,
13.000079237993564,
12.60638555288675,
12.13395313075857,
12.13395313075857,
12.13395313075857,
11.582781971609029,
11.504043234587666,
11.110349549480851,
11.031610812459487,
10.795394601395397,
10.716655864374035,
10.559178390331308,
10.480439653309945,
10.322962179267218,
10.322962179267218,
10.086745968203129,
10.008007231181766,
10.008007231181766,
10.008007231181766,
9.929268494160404,
9.141881123946773,
8.748187438839956
],
"yaxis": "y"
},
{
"hovertemplate": "repetition=40+
Height (cm)=%{x}
Typical lifespan (yr)=%{y}",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "markers",
"name": "",
"orientation": "v",
"showlegend": false,
"type": "scatter",
"x": [
27,
13,
23,
25,
null,
36,
39,
41,
24,
36,
42,
36,
23,
25,
66,
null,
56,
null,
71,
55,
47,
64,
65,
76,
67,
null,
30,
72,
24,
37,
36,
27,
25
],
"xaxis": "x2",
"y": [
13.92,
16.5,
12.25,
13.2,
12,
12.3,
12.31,
11,
13.07,
11.43,
13.58,
10.02,
12.17,
10.69,
11.92,
11.56,
11.19,
9,
9.08,
10.21,
9.01,
6.75,
7.57,
6.5,
7.78,
6.29,
10.08,
10,
9.25,
null,
12.7,
12.25,
11
],
"yaxis": "y2"
},
{
"hovertemplate": "OLS trendline
longevity = -0.0858459 * height + 14.5806
R2=0.487114
repetition=40+
Height (cm)=%{x}
Typical lifespan (yr)=%{y} (trend)",
"legendgroup": "",
"marker": {
"color": "#1F77B4",
"symbol": "circle"
},
"mode": "lines",
"name": "",
"showlegend": false,
"type": "scatter",
"x": [
13,
23,
23,
24,
24,
25,
25,
25,
27,
27,
30,
36,
36,
36,
36,
39,
41,
42,
47,
55,
56,
64,
65,
66,
67,
71,
72,
76
],
"xaxis": "x2",
"y": [
13.464559091030946,
12.606099926856642,
12.606099926856642,
12.520254010439212,
12.520254010439212,
12.434408094021782,
12.434408094021782,
12.434408094021782,
12.26271626118692,
12.26271626118692,
12.00517851193463,
11.490103013430048,
11.490103013430048,
11.490103013430048,
11.490103013430048,
11.232565264177756,
11.060873431342896,
10.975027514925465,
10.545797932838314,
9.859030601498871,
9.773184685081441,
9.086417353741998,
9.000571437324568,
8.914725520907137,
8.828879604489707,
8.485495938819986,
8.399650022402556,
8.056266356732834
],
"yaxis": "y2"
}
],
"layout": {
"annotations": [
{
"font": {},
"showarrow": false,
"text": "repetition=25-40",
"x": 0.245,
"xanchor": "center",
"xref": "paper",
"y": 0.45,
"yanchor": "bottom",
"yref": "paper"
},
{
"font": {},
"showarrow": false,
"text": "repetition=40+",
"x": 0.755,
"xanchor": "center",
"xref": "paper",
"y": 0.45,
"yanchor": "bottom",
"yref": "paper"
},
{
"font": {},
"showarrow": false,
"text": "repetition=<15",
"x": 0.245,
"xanchor": "center",
"xref": "paper",
"y": 1,
"yanchor": "bottom",
"yref": "paper"
},
{
"font": {},
"showarrow": false,
"text": "repetition=15-25",
"x": 0.755,
"xanchor": "center",
"xref": "paper",
"y": 1,
"yanchor": "bottom",
"yref": "paper"
}
],
"height": 400,
"legend": {
"tracegroupgap": 0
},
"margin": {
"t": 30
},
"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": [
{
"fillpattern": {
"fillmode": "overlay",
"size": 10,
"solidity": 0.2
},
"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": 450,
"xaxis": {
"anchor": "y",
"autorange": true,
"domain": [
0,
0.49
],
"range": [
7.466781906160356,
86.53321809383965
],
"title": {
"text": "Height (cm)"
},
"type": "linear"
},
"xaxis2": {
"anchor": "y2",
"autorange": true,
"domain": [
0.51,
1
],
"matches": "x",
"range": [
7.466781906160356,
86.53321809383965
],
"title": {
"text": "Height (cm)"
},
"type": "linear"
},
"xaxis3": {
"anchor": "y3",
"autorange": true,
"domain": [
0,
0.49
],
"matches": "x",
"range": [
7.466781906160356,
86.53321809383965
],
"showticklabels": false,
"type": "linear"
},
"xaxis4": {
"anchor": "y4",
"autorange": true,
"domain": [
0.51,
1
],
"matches": "x",
"range": [
7.466781906160356,
86.53321809383965
],
"showticklabels": false,
"type": "linear"
},
"yaxis": {
"anchor": "x",
"autorange": true,
"domain": [
0,
0.45
],
"range": [
5.36363998986957,
17.42636001013043
],
"title": {
"text": "Typical lifespan (yr)"
},
"type": "linear"
},
"yaxis2": {
"anchor": "x2",
"autorange": true,
"domain": [
0,
0.45
],
"matches": "y",
"range": [
5.36363998986957,
17.42636001013043
],
"showticklabels": false,
"type": "linear"
},
"yaxis3": {
"anchor": "x3",
"autorange": true,
"domain": [
0.55,
1
],
"matches": "y",
"range": [
5.36363998986957,
17.42636001013043
],
"title": {
"text": "Typical lifespan (yr)"
},
"type": "linear"
},
"yaxis4": {
"anchor": "x4",
"autorange": true,
"domain": [
0.55,
1
],
"matches": "y",
"range": [
5.36363998986957,
17.42636001013043
],
"showticklabels": false,
"type": "linear"
}
}
},
"image/png": "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",
"image/svg+xml": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = px.scatter(dogs.dropna(subset=['repetition']), x='height', y='longevity', \n",
" facet_col='repetition', facet_col_wrap=2, trendline='ols',\n",
" facet_row_spacing=0.1,\n",
" width=450, height=400, \n",
" labels={'height':'Height (cm)',\n",
" 'longevity':'Typical lifespan (yr)'})\n",
"margin(fig, t=30)"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Each of the four scatter plots shows the relationship between longevity and height for a different range of repetitions.\n",
"By separating the scatter plots, we can better assess how the relationship between two\n",
"quantitative features changes across the subgroups. And we can more easily see the range of\n",
"height and longevity for each repetition range.\n",
"We can see that the larger breeds tend to have shorter lifespans.\n",
"Another interesting feature is that the lines are similar in slope, but the line for the 40+ repetitions sits about 1.5 years below the others.\n",
"Those breeds tend to live about 1.5 years less on average than the other repetition categories no matter the height."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Here we summarize the various plotting techniques for making comparisons when we have three (or more) features:"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Two quantitative and one qualitative\n",
": We demonstrated this case already with a scatter plot that varies the markers according to the qualitative feature's categories, or by the panels of scatter plots, with one for each category. "
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": [],
"user_expressions": []
},
"source": [
"Two qualitative and one quantitative feature\n",
": We have seen in the collections of box plots of height according to breed size that we can compare the basic shape of a distribution across\n",
"subgroups with side-by-side box plots. When we have two or more qualitative\n",
"features, we can organize the box plots into groups according to one of the\n",
"qualitative features."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Three quantitative features\n",
": We can use a similar technique when we plot two quantitative features and one qualitative. This time, we convert one of the quantitative features into an ordinal feature, where each category typically has roughly the same number of records. Then we make faceted scatter plots of the other two features. We again look for similarities in relationships across the facets."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Three qualitative features\n",
": When we examine relationships between\n",
"qualitative features, we examine proportions of one feature within subgroups\n",
"defined by another. \n",
"In the previous section, the three line plots in one figure and the side-by-side bar plots both display such comparisons. With three (or more) qualitative features, we can\n",
"continue to subdivide the data according to the combinations of levels of the features\n",
"and compare these proportions using line plots, dot plots, side-by-side bar charts, and so forth. \n",
"But these plots tend to get increasingly difficult to understand with further subdivisions."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
":::{note}\n",
"\n",
"It's a good practice to break down a visualization to see whether a relationship changes for subgroups of the data determined by a qualitative feature. This technique is called *controlling for* a feature. You might get a surprise when, for example, a linear relationship in a scatter plot that has an upward trend reverses to downward trends in some or all facets of the scatter plot. This phenomenon is known as *Simpson's paradox*. The paradox can happen with qualitative features as well. A [famous case](https://pubmed.ncbi.nlm.nih.gov/29484824/) occurred at Berkeley when the admissions to graduate school for men were higher than for women, but when examined within each program the rates favored women. The issue was that women were applying in greater numbers to programs that had lower admission rates. \n",
"\n",
":::"
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Comparisons that involve more than one categorical\n",
"variable can quickly become cumbersome as the number of possible combinations\n",
"of categories grows. For example, there are 3 × 4 = 12 size–repetition\n",
"combinations (if we had kept the original categories for repetitions, we would\n",
"have 18 combinations). Examining a distribution across 12 subgroups can be\n",
"difficult. Further, we come up against the problem of having too few\n",
"observations in subgroups. Although there are nearly 200 rows in the dogs\n",
"data frame, half of the size–repetition combinations have 10 or fewer\n",
"observations. (This is compounded by losing an observation when one feature has\n",
"a missing value.) This *curse of dimensionality* also arises when we compare\n",
"relationships with quantitative data. With just three quantitative variables,\n",
"some of the scatter plots in a facet plot can easily have too few observations\n",
"to confirm the shape of the relationship between two variables for the\n",
"subgroups."
]
},
{
"cell_type": "markdown",
"metadata": {
"user_expressions": []
},
"source": [
"Now that we've seen practical examples of visualizations that are commonly\n",
"used in exploratory data analysis, we proceed to discuss some high-level guidelines for EDA."
]
}
],
"metadata": {
"celltoolbar": "Tags",
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}