{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "e063ca9c",
"metadata": {},
"source": [
"# 分组"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "93ce55e2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
"from matplotlib import patches\n",
"from scipy.spatial import ConvexHull"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "fd541dbc",
"metadata": {},
"source": [
"## Bar\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "782afb32",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" manufacturer | \n",
" model | \n",
" displ | \n",
" year | \n",
" cyl | \n",
" trans | \n",
" drv | \n",
" cty | \n",
" hwy | \n",
" fl | \n",
" class | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" audi | \n",
" a4 | \n",
" 1.8 | \n",
" 1999 | \n",
" 4 | \n",
" auto(l5) | \n",
" f | \n",
" 18 | \n",
" 29 | \n",
" p | \n",
" compact | \n",
"
\n",
" \n",
" | 1 | \n",
" audi | \n",
" a4 | \n",
" 1.8 | \n",
" 1999 | \n",
" 4 | \n",
" manual(m5) | \n",
" f | \n",
" 21 | \n",
" 29 | \n",
" p | \n",
" compact | \n",
"
\n",
" \n",
" | 2 | \n",
" audi | \n",
" a4 | \n",
" 2.0 | \n",
" 2008 | \n",
" 4 | \n",
" manual(m6) | \n",
" f | \n",
" 20 | \n",
" 31 | \n",
" p | \n",
" compact | \n",
"
\n",
" \n",
" | 3 | \n",
" audi | \n",
" a4 | \n",
" 2.0 | \n",
" 2008 | \n",
" 4 | \n",
" auto(av) | \n",
" f | \n",
" 21 | \n",
" 30 | \n",
" p | \n",
" compact | \n",
"
\n",
" \n",
" | 4 | \n",
" audi | \n",
" a4 | \n",
" 2.8 | \n",
" 1999 | \n",
" 6 | \n",
" auto(l5) | \n",
" f | \n",
" 16 | \n",
" 26 | \n",
" p | \n",
" compact | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" manufacturer | \n",
" cty | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" lincoln | \n",
" 11.333333 | \n",
"
\n",
" \n",
" | 1 | \n",
" land rover | \n",
" 11.500000 | \n",
"
\n",
" \n",
" | 2 | \n",
" dodge | \n",
" 13.135135 | \n",
"
\n",
" \n",
" | 3 | \n",
" mercury | \n",
" 13.250000 | \n",
"
\n",
" \n",
" | 4 | \n",
" jeep | \n",
" 13.500000 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig, ax = plt.subplots(figsize=(10, 6), facecolor=\"white\")\n",
"\n",
"x = mpg_group[\"manufacturer\"].str.upper()\n",
"y = mpg_group[\"cty\"]\n",
"\n",
"ax.bar(x=x, height=y)\n",
"\n",
"for i, cty in enumerate(y):\n",
" ax.text(i, cty + 0.5, round(cty, 1), horizontalalignment=\"center\")\n",
"\n",
"p1 = patches.Rectangle(\n",
" (0.57, -0.005),\n",
" width=0.33,\n",
" height=0.13,\n",
" alpha=0.1,\n",
" facecolor=\"green\",\n",
" transform=fig.transFigure,\n",
")\n",
"p2 = patches.Rectangle(\n",
" (0.124, -0.005),\n",
" width=0.446,\n",
" height=0.13,\n",
" alpha=0.1,\n",
" facecolor=\"red\",\n",
" transform=fig.transFigure,\n",
")\n",
"fig.add_artist(p1)\n",
"fig.add_artist(p2)\n",
"\n",
"ax.set(ylim=(0, 30), ylabel=\"Miles Per Gallon\", title=\"Bar Chart for Highway Mileage\")\n",
"plt.setp(ax.get_xticklabels(), rotation=60, horizontalalignment=\"right\")\n",
"\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "cd3b41f3",
"metadata": {},
"source": [
"## Dendrogram\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "821f0dc7",
"metadata": {},
"outputs": [],
"source": [
"from scipy.cluster import hierarchy"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4bb98c03",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Murder | \n",
" Assault | \n",
" UrbanPop | \n",
" Rape | \n",
" State | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 13.2 | \n",
" 236 | \n",
" 58 | \n",
" 21.2 | \n",
" Alabama | \n",
"
\n",
" \n",
" | 1 | \n",
" 10.0 | \n",
" 263 | \n",
" 48 | \n",
" 44.5 | \n",
" Alaska | \n",
"
\n",
" \n",
" | 2 | \n",
" 8.1 | \n",
" 294 | \n",
" 80 | \n",
" 31.0 | \n",
" Arizona | \n",
"
\n",
" \n",
" | 3 | \n",
" 8.8 | \n",
" 190 | \n",
" 50 | \n",
" 19.5 | \n",
" Arkansas | \n",
"
\n",
" \n",
" | 4 | \n",
" 9.0 | \n",
" 276 | \n",
" 91 | \n",
" 40.6 | \n",
" California | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"_, ax = plt.subplots(figsize=(10, 6))\n",
"\n",
"dend = hierarchy.dendrogram(\n",
" hierarchy.linkage(\n",
" arrests[[\"Murder\", \"Assault\", \"UrbanPop\", \"Rape\"]], method=\"ward\"\n",
" ),\n",
" labels=arrests.State.array,\n",
" color_threshold=100,\n",
")\n",
"\n",
"ax.set(title=\"USArrests Dendograms\")\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "9efdf631",
"metadata": {},
"source": [
"## Encircling\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e457732",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" PID | \n",
" county | \n",
" state | \n",
" area | \n",
" poptotal | \n",
" popdensity | \n",
" popwhite | \n",
" popblack | \n",
" popamerindian | \n",
" popasian | \n",
" ... | \n",
" percprof | \n",
" poppovertyknown | \n",
" percpovertyknown | \n",
" percbelowpoverty | \n",
" percchildbelowpovert | \n",
" percadultpoverty | \n",
" percelderlypoverty | \n",
" inmetro | \n",
" category | \n",
" dot_size | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 561 | \n",
" ADAMS | \n",
" IL | \n",
" 0.052 | \n",
" 66090 | \n",
" 12.709615 | \n",
" 63917 | \n",
" 1702 | \n",
" 98 | \n",
" 249 | \n",
" ... | \n",
" 4.355859 | \n",
" 63628 | \n",
" 96.274777 | \n",
" 13.151443 | \n",
" 18.011717 | \n",
" 11.009776 | \n",
" 12.443812 | \n",
" 0 | \n",
" AAR | \n",
" 250.944411 | \n",
"
\n",
" \n",
" | 1 | \n",
" 562 | \n",
" ALEXANDER | \n",
" IL | \n",
" 0.014 | \n",
" 10626 | \n",
" 7.590000 | \n",
" 7054 | \n",
" 3496 | \n",
" 19 | \n",
" 48 | \n",
" ... | \n",
" 2.870315 | \n",
" 10529 | \n",
" 99.087145 | \n",
" 32.244278 | \n",
" 45.826514 | \n",
" 27.385647 | \n",
" 25.228976 | \n",
" 0 | \n",
" LHR | \n",
" 185.781260 | \n",
"
\n",
" \n",
" | 2 | \n",
" 563 | \n",
" BOND | \n",
" IL | \n",
" 0.022 | \n",
" 14991 | \n",
" 6.814091 | \n",
" 14477 | \n",
" 429 | \n",
" 35 | \n",
" 16 | \n",
" ... | \n",
" 4.488572 | \n",
" 14235 | \n",
" 94.956974 | \n",
" 12.068844 | \n",
" 14.036061 | \n",
" 10.852090 | \n",
" 12.697410 | \n",
" 0 | \n",
" AAR | \n",
" 175.905385 | \n",
"
\n",
" \n",
" | 3 | \n",
" 564 | \n",
" BOONE | \n",
" IL | \n",
" 0.017 | \n",
" 30806 | \n",
" 18.121177 | \n",
" 29344 | \n",
" 127 | \n",
" 46 | \n",
" 150 | \n",
" ... | \n",
" 4.197800 | \n",
" 30337 | \n",
" 98.477569 | \n",
" 7.209019 | \n",
" 11.179536 | \n",
" 5.536013 | \n",
" 6.217047 | \n",
" 1 | \n",
" ALU | \n",
" 319.823487 | \n",
"
\n",
" \n",
" | 4 | \n",
" 565 | \n",
" BROWN | \n",
" IL | \n",
" 0.018 | \n",
" 5836 | \n",
" 3.242222 | \n",
" 5264 | \n",
" 547 | \n",
" 14 | \n",
" 5 | \n",
" ... | \n",
" 3.367680 | \n",
" 4815 | \n",
" 82.505140 | \n",
" 13.520249 | \n",
" 13.022889 | \n",
" 11.143211 | \n",
" 19.200000 | \n",
" 0 | \n",
" AAR | \n",
" 130.442161 | \n",
"
\n",
" \n",
"
\n",
"
5 rows × 29 columns
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" PID | \n",
" county | \n",
" state | \n",
" area | \n",
" poptotal | \n",
" popdensity | \n",
" popwhite | \n",
" popblack | \n",
" popamerindian | \n",
" popasian | \n",
" ... | \n",
" percprof | \n",
" poppovertyknown | \n",
" percpovertyknown | \n",
" percbelowpoverty | \n",
" percchildbelowpovert | \n",
" percadultpoverty | \n",
" percelderlypoverty | \n",
" inmetro | \n",
" category | \n",
" dot_size | \n",
"
\n",
" \n",
" \n",
" \n",
" | 83 | \n",
" 663 | \n",
" ADAMS | \n",
" IN | \n",
" 0.021 | \n",
" 31095 | \n",
" 14.807143 | \n",
" 30530 | \n",
" 36 | \n",
" 42 | \n",
" 60 | \n",
" ... | \n",
" 4.862299 | \n",
" 30490 | \n",
" 98.054350 | \n",
" 11.636602 | \n",
" 17.194524 | \n",
" 9.101888 | \n",
" 8.714027 | \n",
" 1 | \n",
" AAU | \n",
" 277.642023 | \n",
"
\n",
" \n",
" | 84 | \n",
" 665 | \n",
" BARTHOLOMEW | \n",
" IN | \n",
" 0.022 | \n",
" 63657 | \n",
" 28.935000 | \n",
" 61774 | \n",
" 1005 | \n",
" 97 | \n",
" 610 | \n",
" ... | \n",
" 6.844097 | \n",
" 62784 | \n",
" 98.628588 | \n",
" 8.545171 | \n",
" 10.736855 | \n",
" 6.992420 | \n",
" 10.811943 | \n",
" 0 | \n",
" AAR | \n",
" 457.463283 | \n",
"
\n",
" \n",
" | 85 | \n",
" 666 | \n",
" BENTON | \n",
" IN | \n",
" 0.024 | \n",
" 9441 | \n",
" 3.933750 | \n",
" 9389 | \n",
" 6 | \n",
" 16 | \n",
" 1 | \n",
" ... | \n",
" 4.014538 | \n",
" 9300 | \n",
" 98.506514 | \n",
" 8.043011 | \n",
" 8.349218 | \n",
" 6.842329 | \n",
" 10.502283 | \n",
" 0 | \n",
" AAR | \n",
" 139.244020 | \n",
"
\n",
" \n",
" | 86 | \n",
" 667 | \n",
" BLACKFORD | \n",
" IN | \n",
" 0.010 | \n",
" 14067 | \n",
" 14.067000 | \n",
" 13978 | \n",
" 7 | \n",
" 44 | \n",
" 16 | \n",
" ... | \n",
" 4.428124 | \n",
" 13903 | \n",
" 98.834151 | \n",
" 9.853988 | \n",
" 12.323745 | \n",
" 8.332247 | \n",
" 10.937500 | \n",
" 0 | \n",
" AAR | \n",
" 268.221385 | \n",
"
\n",
" \n",
" | 87 | \n",
" 668 | \n",
" BOONE | \n",
" IN | \n",
" 0.024 | \n",
" 38147 | \n",
" 15.894583 | \n",
" 37814 | \n",
" 83 | \n",
" 90 | \n",
" 94 | \n",
" ... | \n",
" 8.813967 | \n",
" 37402 | \n",
" 98.047029 | \n",
" 6.296455 | \n",
" 8.021754 | \n",
" 5.239599 | \n",
" 7.089425 | \n",
" 1 | \n",
" HLU | \n",
" 291.483110 | \n",
"
\n",
" \n",
"
\n",
"
5 rows × 29 columns
\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"_, ax = plt.subplots(figsize=(10, 8))\n",
"\n",
"midwest.plot.scatter(\n",
" x=\"area\", y=\"poptotal\", c=\"state\", s=\"popdensity\", cmap=\"tab10\", ax=ax\n",
")\n",
"\n",
"\n",
"# Encircling\n",
"def encircle(x, y, ax=None, **kw) -> None:\n",
" ax = ax or plt.gca()\n",
" p = np.stack([x, y], axis=1)\n",
" hull = ConvexHull(p)\n",
" poly = patches.Polygon(xy=p[hull.vertices, :], closed=True, **kw)\n",
" ax.add_patch(poly)\n",
"\n",
"\n",
"ax.set(\n",
" xlim=(0.0, 0.1),\n",
" ylim=(0, 90000),\n",
" xlabel=\"Area\",\n",
" ylabel=\"Population\",\n",
" title=\"Bubble Plot with Encircling\",\n",
")\n",
"\n",
"x = midwest_select[\"area\"]\n",
"y = midwest_select[\"poptotal\"]\n",
"\n",
"# Draw polygon surrounding vertices\n",
"encircle(x, y, ec=\"k\", fc=\"gold\", alpha=0.1, ax=ax)\n",
"encircle(x, y, ec=\"firebrick\", fc=\"none\", lw=1.5, ax=ax)\n",
"\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "125ee707",
"metadata": {},
"source": [
"## Andrews Curve\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "7a970335",
"metadata": {},
"outputs": [],
"source": [
"from pandas.plotting import andrews_curves"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "98323f12",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" mpg | \n",
" cyl | \n",
" disp | \n",
" hp | \n",
" drat | \n",
" wt | \n",
" qsec | \n",
" vs | \n",
" am | \n",
" gear | \n",
" carb | \n",
" fast | \n",
" cars | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 4.582576 | \n",
" 6 | \n",
" 160.0 | \n",
" 110 | \n",
" 3.90 | \n",
" 2.620 | \n",
" 16.46 | \n",
" 0 | \n",
" 1 | \n",
" 4 | \n",
" 4 | \n",
" 1 | \n",
" Mazda RX4 | \n",
"
\n",
" \n",
" | 1 | \n",
" 4.582576 | \n",
" 6 | \n",
" 160.0 | \n",
" 110 | \n",
" 3.90 | \n",
" 2.875 | \n",
" 17.02 | \n",
" 0 | \n",
" 1 | \n",
" 4 | \n",
" 4 | \n",
" 1 | \n",
" Mazda RX4 Wag | \n",
"
\n",
" \n",
" | 2 | \n",
" 4.774935 | \n",
" 4 | \n",
" 108.0 | \n",
" 93 | \n",
" 3.85 | \n",
" 2.320 | \n",
" 18.61 | \n",
" 1 | \n",
" 1 | \n",
" 4 | \n",
" 1 | \n",
" 1 | \n",
" Datsun 710 | \n",
"
\n",
" \n",
" | 3 | \n",
" 4.626013 | \n",
" 6 | \n",
" 258.0 | \n",
" 110 | \n",
" 3.08 | \n",
" 3.215 | \n",
" 19.44 | \n",
" 1 | \n",
" 0 | \n",
" 3 | \n",
" 1 | \n",
" 1 | \n",
" Hornet 4 Drive | \n",
"
\n",
" \n",
" | 4 | \n",
" 4.324350 | \n",
" 8 | \n",
" 360.0 | \n",
" 175 | \n",
" 3.15 | \n",
" 3.440 | \n",
" 17.02 | \n",
" 0 | \n",
" 0 | \n",
" 3 | \n",
" 2 | \n",
" 1 | \n",
" Hornet Sportabout | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"mtcars = mtcars.drop([\"cars\"], axis=1)\n",
"\n",
"_, ax = plt.subplots(figsize=(10, 6))\n",
"\n",
"andrews_curves(mtcars, \"cyl\", colormap=\"Set1\")\n",
"\n",
"ax.spines[[\"top\", \"right\"]].set_visible(False)\n",
"\n",
"ax.set(title=\"Andrews Curves of mtcars\", xlim=(-3, 3))\n",
"ax.grid(alpha=0.3)\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "6a7cd58c",
"metadata": {},
"source": [
"## Parallel Coordinates\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "bb194bfe",
"metadata": {},
"outputs": [],
"source": [
"from pandas.plotting import parallel_coordinates"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b7e93c25",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" carat | \n",
" cut | \n",
" color | \n",
" clarity | \n",
" depth | \n",
" table | \n",
" price | \n",
" x | \n",
" y | \n",
" z | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0.23 | \n",
" Ideal | \n",
" E | \n",
" SI2 | \n",
" 61.5 | \n",
" 55.0 | \n",
" 326 | \n",
" 3.95 | \n",
" 3.98 | \n",
" 2.43 | \n",
"
\n",
" \n",
" | 1 | \n",
" 0.21 | \n",
" Premium | \n",
" E | \n",
" SI1 | \n",
" 59.8 | \n",
" 61.0 | \n",
" 326 | \n",
" 3.89 | \n",
" 3.84 | \n",
" 2.31 | \n",
"
\n",
" \n",
" | 2 | \n",
" 0.23 | \n",
" Good | \n",
" E | \n",
" VS1 | \n",
" 56.9 | \n",
" 65.0 | \n",
" 327 | \n",
" 4.05 | \n",
" 4.07 | \n",
" 2.31 | \n",
"
\n",
" \n",
" | 3 | \n",
" 0.29 | \n",
" Premium | \n",
" I | \n",
" VS2 | \n",
" 62.4 | \n",
" 58.0 | \n",
" 334 | \n",
" 4.20 | \n",
" 4.23 | \n",
" 2.63 | \n",
"
\n",
" \n",
" | 4 | \n",
" 0.31 | \n",
" Good | \n",
" J | \n",
" SI2 | \n",
" 63.3 | \n",
" 58.0 | \n",
" 335 | \n",
" 4.34 | \n",
" 4.35 | \n",
" 2.75 | \n",
"
\n",
" \n",
"
\n",
"