【数据分析可视化】DataFrame的简单数学计算

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

s1 = Series([1,2,3],index=['A','B','C'])
s1

A    1
B    2
C    3
dtype: int64

s2 = Series([4,5,6,7],index=['B','C','D','E'])
s2

B    4
C    5
D    6
E    7
dtype: int64

# Series相加（对应index的value相加）
# nan和任何数相加都为nan
s1 + s2

A    NaN
B    6.0
C    8.0
D    NaN
E    NaN
dtype: float64

df1 = DataFrame(np.arange(4).reshape(2,2), index=['A','B'], columns=['BJ','SH'])
df1

df2 = DataFrame(np.arange(9).reshape(3,3), index=['A','B','C'], columns=['BJ','GZ','SH'])
df2

# 加法，对应索引的值相加（nan加什么都是nan）
df1 + df2

df3 = DataFrame([[1,2,3],[4,5,np.nan],[7,8,9]], index=['A','B','C'], columns=['c1','c2','c3'])
df3

# 求和 默认列(此时求和会忽略nan)
df3.sum()

c1    12.0
c2    15.0
c3    12.0
dtype: float64

type(df3.sum())

pandas.core.series.Series

# 求和 行
df3.sum(axis=1)

A     6.0
B     9.0
C    24.0
dtype: float64

# 最小值 默认列
df3.min()

c1    1.0
c2    2.0
c3    3.0
dtype: float64

# 最小值 行
df3.min(axis=1)

A    1.0
B    4.0
C    7.0
dtype: float64

# 返回统计数据 平均值mean
df3.describe()

df3