Python | 可视化 // Visualization

记录一些常用的Python绘图代码，为工作提效

常用图表

堆叠柱状图

import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns

import warnings
warnings.filterwarnings('ignore')

## Load Data
df = sns.load_dataset('diamonds')
df.head()  ## 预览数据，见下图

df.cut.unique()
# ['Ideal', 'Premium', 'Good', 'Very Good', 'Fair']
# Categories (5, object): ['Ideal', 'Premium', 'Very Good', 'Good', 'Fair']

df.clarity.unique()
# ['SI2', 'SI1', 'VS1', 'VS2', 'VVS2', 'VVS1', 'I1', 'IF']
# Categories (8, object): ['IF', 'VVS1', 'VVS2', 'VS1', 'VS2', 'SI1', 'SI2', 'I1']

df.color.unique()
# ['E', 'I', 'J', 'H', 'F', 'G', 'D']
# Categories (7, object): ['D', 'E', 'F', 'G', 'H', 'I', 'J']

sns.set_theme(style='ticks')
f, ax = plt.subplots(figsize=(7, 5))
sns.despine(f)

sns.histplot(
    df,
    x='price',
    hue='cut',
    multiple='stack', ## 堆叠
    palette='light:m_r',
    edgecolor='.3',
    linewidth=.5,
    log_scale=True,
)
ax.xaxis.set_major_formatter(mpl.ticker.ScalarFormatter())
ax.set_xticks([500, 1000, 2000, 5000, 10000])

plt.savefig('histplot_stack.jpg', dpi=400)
plt.show()

词云图

双轴图

import matplotlib.pyplot as plt
import pandas as pd 

## Data
df = pd.DataFrame([
    [-2, 10, 0.8],
    [-1, 20, 0.7], 
    [0, 30, 0.6],
    [1, 40, 0.5],
    [2, 50, 0.4],
    [3, 60, 0.3]
], columns=['x', 'y1', 'y2'])

## Visualization
fig = plt.figure(figsize=(10, 6))

ax1 = fig.add_subplot(111)
ax1.bar(df.x, df.y1, color='g', label='y1')

ax2 = ax1.twinx()
ax2.plot(df.x, df.y2, color='r', label='y2')

## Legend
fig.legend(loc=1, bbox_to_anchor=(0.1, 1), bbox_transform=ax1.transAxes)

ax1.set_xlabel(r"X axis")
ax1.set_ylabel(r"Y1")
ax2.set_ylabel(r"Y2")

plt.savefig('Twin_Xaxes.jpg', dpi=400)
plt.show()

参考资料