『数据可视化』一文掌握Pandas可视化图表

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# 设置 可视化风格
plt.style.use('tableau-colorblind10') 

# 以下代码从全局设置字体为SimHei（黑体），解决显示中文问题【Windows】
plt.rcParams['font.sans-serif'] = ['SimHei']

# 解决中文字体下坐标轴负数的负号显示问题
plt.rcParams['axes.unicode_minus'] = False 

# 随机种子
np.random.seed(1)
ts = pd.Series(np.random.randn(100), index=pd.date_range("1/1/2020", periods=100))
ts = ts.cumsum()
ts.plot()

# 随机种子
np.random.seed(1)
df = pd.DataFrame(np.random.randn(100, 4), index=ts.index, columns=list("ABCD"))
df = df.cumsum()
df.head()

df.plot()

df.plot(y='A')

df["X"] = list(range(len(df)))
df.head()

# 指定多个Y
df.plot(x='X',y=['B','C'])

np.random.seed(1)
df = pd.DataFrame(np.random.rand(10, 3), columns=["a", "b", "c"])
df.head()

# 图像大小
df.plot.bar(figsize=(10,5))

plt.rcParams['figure.figsize'] = (10,5)

# 标题
df.plot.bar(title='标题',)

# 图例不显示
df.plot.bar(legend=False)

# 图例倒序
df.plot.bar(legend='reverse')

# x轴标签旋转角度
df.plot.bar(rot=0)

# 网格线
df.plot.bar(grid=True)

# 指定颜色
df.plot.bar(color=['red','orange','yellow'], edgecolor='grey')

# 字体大小
df.plot.bar(fontsize=20)

df.plot(style = ['.-','--','*-'] # 圆点、虚线、星星
       )

# 指定色系
x = df.plot.bar(colormap='rainbow')

# 多子图
x = df.plot.line(title ='多子图',
             fontsize =16,
             subplots =True, # 分列
             style = ['.-','--','*-','^-'] # 圆点、虚线、星星
            )

df.a.plot.bar()
df.b.plot(color='r')

# 绘图引擎
import pandas_bokeh

pandas_bokeh.output_notebook()
df.plot.bar(backend='pandas_bokeh')

# 绘图引擎 plotly
df.plot.bar(backend='plotly',
            barmode='group',
            height=500, # 图表高度
            width=800, # 图表宽度
           )

# 柱状图bar
df.plot.bar()

# 堆叠柱状图
df.plot.bar(stacked=True)

# 柱状图多子图
df.plot.bar(subplots=True, rot=0)

# 条形图barh
df.plot.barh(figsize=(6,8))

# 堆叠条形图
df.plot.barh(stacked=True)

# 直方图
np.random.seed(1)
df = pd.DataFrame(
    {
        "a": np.random.randn(1000) + 1,
        "b": np.random.randn(1000),
        "c": np.random.randn(1000) - 1,
    },
     columns=["a", "b", "c"],
)
df.head()

df.plot.hist(alpha=0.5) # alpha设置透明度

# 单直方图
df.a.plot.hist()

# 堆叠并指定分箱数（默认为 10）
df.plot.hist(stacked=True, bins=20)

# 可以通过orientation='horizontal'和 cumulative=True 绘制横向和累积直方图
df["a"].plot.hist(orientation="horizontal", cumulative=True)

# 绘制多子图
df.hist(color="k", alpha=0.5, bins=50)

# 以下2种方式效果一致
df.hist('a', bins = 20, alpha=0.5)
# df.a.hist(bins = 20, alpha=0.5)

# by 分组
np.random.seed(1)
data = pd.Series(np.random.randn(1000))
data.hist(by=np.random.randint(0, 4, 1000), figsize=(6, 4))

np.random.seed(1)
df = pd.DataFrame(np.random.rand(10, 5), columns=["A", "B", "C", "D", "E"])
df.head()

df.boxplot()

# 指定元素颜色
color = {
  "boxes": "Green", # 箱体颜色
  "whiskers": "Orange", # 连线颜色
  "medians": "Blue", # 中位数颜色
  "caps": "Gray", # 极值颜色
}

df.boxplot(color=color, sym="r+")

df.boxplot(vert=False, positions=[1, 4, 5, 6, 8])

np.random.seed(1)
df = pd.DataFrame(np.random.rand(10, 4), columns=["a", "b", "c", "d"])
df.head()

# 默认是堆叠
df.plot.area()

df.a.plot.area()

# 取消堆叠
df.plot.area(stacked=False)

np.random.seed(1)
df = pd.DataFrame(np.random.rand(50, 4), columns=["a", "b", "c", "d"])

df["species"] = pd.Categorical(
  ["setosa"] * 20 + ["versicolor"] * 20 + ["virginica"] * 10
)

df.head()

df.plot.scatter(x="a", y="b")

ax = df.plot.scatter(x="a", y="b", color="Blue", label="Group 1")
df.plot.scatter(x="c", y="d", color="red", label="Group 2", ax=ax)

df.plot.scatter(x="a", y="b", c="c", s=50) # 参数s代表散点大小

df.plot.scatter(x="a", y="b", c="species", cmap="viridis", s=50)

df.plot.scatter(x="a", y="b", color="red", s=df["c"] * 200)

np.random.seed(8)
series = pd.Series(3 * np.random.rand(4), index=["a", "b", "c", "d"], name="series")
series

series.plot.pie(figsize=(6, 6), fontsize=20)

np.random.seed(8)
df = pd.DataFrame(
     3 * np.random.rand(4, 2), index=["a", "b", "c", "d"], columns=["x", "y"]
 )
df

df.plot.pie(subplots=True, figsize=(8, 4), fontsize=16)

series.plot.pie(
     labels=["AA", "BB", "CC", "DD"], # 标签
     colors=["r", "g", "b", "c"], # 指定颜色
     autopct="%.2f", # 数字格式（百分比）
     fontsize=20,
     figsize=(6, 6),
 )

series = pd.Series([0.1] * 4, index=["a", "b", "c", "d"], name="series2")
series.plot.pie(figsize=(6, 6), normalize=False)

from pandas.plotting import scatter_matrix

df = pd.DataFrame(np.random.randn(1000, 4), columns=["a", "b", "c", "d"])
scatter_matrix(df, alpha=0.2, figsize=(6, 6), diagonal="kde")

from pandas.plotting import andrews_curves

data = pd.read_csv("iris.csv")
andrews_curves(data, "Name")