Python中分组值计数条形图的子图

• 正确的方法只有 pandas ,是用 .pivot ,然后正确使用 pandas.DataFrame.plot .

进口及;数据

import pandas as pd
import numpy as np  # for test data
import seaborn as sns  # only for seaborn option

# test data
np.random.seed(365)
rows = 100000
data = {'YEAR': np.random.choice(range(2014, 2021), size=rows),
        'RESPONSIBLE DISTRICT': np.random.choice(['05 - LUBBOCK', '15 - SAN ANTONIO', '18 - DALLAS', '04 - AMARILLO', '08 - ABILENE', '21 - PHARR', '25 - CHILDRESS', '20 - BEAUMONT', '22 - LAREDO', '24 - EL PASO'], size=rows)}
df = pd.DataFrame(data)

# get the value count of each district by year and pivot the shape
dfp = df.value_counts(subset=['YEAR', 'RESPONSIBLE DISTRICT']).reset_index(name='VC').pivot(index='YEAR', columns='RESPONSIBLE DISTRICT', values='VC')

# display(dfp)
RESPONSIBLE DISTRICT  04 - AMARILLO  05 - LUBBOCK  08 - ABILENE  15 - SAN ANTONIO  18 - DALLAS  20 - BEAUMONT  21 - PHARR  22 - LAREDO  24 - EL PASO  25 - CHILDRESS
YEAR                                                                                                                                                                
2014                           1407          1406          1485              1456         1392           1456        1499         1458          1394            1452
2015                           1436          1423          1428              1441         1395           1400        1423         1442          1375            1399
2016                           1480          1381          1393              1415         1446           1442        1414         1435          1452            1454
2017                           1422          1388          1485              1447         1404           1401        1413         1470          1424            1426
2018                           1479          1424          1384              1450         1390           1384        1445         1435          1478            1386
2019                           1387          1317          1379              1457         1457           1476        1447         1459          1451            1406
2020                           1462          1452          1454              1448         1441           1428        1411         1407          1402            1445

熊猫。数据帧。情节

• 使用 kind='line' 如果首选线图。

# plot the dataframe
fig = dfp.plot(kind='bar', subplots=True, layout=(5, 5), figsize=(20, 20), legend=False)

seaborn.catplot

• seaborn 是用于 matplotlib
• 这是最简单的方法,因为数据帧不需要重塑。

p = sns.catplot(kind='count', data=df, col='RESPONSIBLE DISTRICT', col_wrap=5, x='YEAR', height=3.5, )
p.set_titles(row_template='{row_name}', col_template='{col_name}')  # shortens the titles

这应该行得通。

import matplotlib.pyplot as plt
import pandas as pd


g = df.groupby('YEAR')['RESPONSIBLE DISTRICT'].value_counts()


fig, axs = plt.subplots(5, 5, constrained_layout=True)

for ax, (district, dfi) in zip(axs.ravel(), g.groupby('RESPONSIBLE DISTRICT')):
    x = dfi.index.get_level_values('YEAR').values
    y = dfi.values
    ax.bar(x, y)
    ax.set_title(district)

plt.show()

这是你所期待的吗?

import matplotlib.pyplot as plt

fig, axs = plt.subplots(5, 5, sharex=True, sharey=True, figsize=(15, 15))
for ax, (district, sr) in zip(axs.flat, g.groupby('RESPONSIBLE DISTRICT')):
    ax.set_title(district)
    ax.plot(sr.index.get_level_values('YEAR'), sr.values)
fig.tight_layout()

plt.show()