Pandas工具包实战（4）数值运算操作：dataframe、二元统计

1 数值运算操作

import pandas as pd

df = pd.DataFrame([[1,2,3],[4,5,6]],index = ['a','b'],columns = ['A','B','C'])
df
#		A	B	C
#	a	1	2	3
#	b	4	5	6


df.sum()   # 默认按行求和，每行对应元素纵向相加
# A    5
# B    7
# C    9
# dtype: int64
df.sum(axis = 0)  # 默认按行求和 
# A    5
# B    7
# C    9
# dtype: int64

df.sum(axis = 1)  # 按列求和，每列对应元素横向相加 
# a     6
# b    15
# dtype: int64
df.sum(axis = 'columns') # 按列求和
# a     6
# b    15
# dtype: int64

df.mean()
df.min()
df.max()
df.median()

df.mean(axis = 1)

2 二元统计

df = pd.read_csv('./data/titanic.csv')
df.head()

df.cov()
df.corr()  # 相关性越高的列属性，越应该被剔除

df['Age'].value_counts()  # 对某一列的元素，按值进行计数统计， 默认是降序排列，大数在上

df['Age'].value_counts(ascending = True)  # 升序排列，从小到大
df['Pclass'].value_counts(ascending = True)

df['Age'].value_counts(ascending = True,bins = 5)  # bin的意思是分成5个同等宽度的区间
#(64.084, 80.0]       11
#(48.168, 64.084]     69
#(0.339, 16.336]     100
#(32.252, 48.168]    188
#(16.336, 32.252]    346
#Name: Age, dtype: int64