pandas中的数值计算及统计基础

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'key1': [4, 5, 3, np.nan, 2],
    'key2': [1, 2, np.nan, 4, 5],
    'key3': [1, 2, 3, 'j', 'k']
}, index=['a', 'b', 'c', 'd', 'e'])
print(df)
print(df['key1'].dtype,df['key2'].dtype,df['key3'].dtype)
print('-------')
'''
   key1  key2 key3
a   4.0   1.0    1
b   5.0   2.0    2
c   3.0   NaN    3
d   NaN   4.0    j
e   2.0   5.0    k
float64 float64 object
-------
'''
# 计算每一列的均值 df.mean()
# 只统计数字列，默认忽略nan。
print(df.mean())
'''
key1    3.5
key2    3.0
dtype: float64
'''
# 不忽略nan值计算均值
# skipna默认为True，如果为False，有NaN的列统计结果仍为NaN
m3 = df.mean(skipna=False)
print(m3)
'''
key1   NaN
key2   NaN
dtype: float64
'''
# 计算单一列的均值
print('计算单一列的均值',df['key2'].mean())
'''
计算单一列的均值 3.0
'''

df2 = pd.DataFrame({
    'key1': [1, 3, 5],
    'key2': [2, 4, 6],
    'key3': [3, 5, 7]
}, index=['a', 'b', 'c'])
# print(df2)
# print('--------df2')
# 计算df2每一行的均值并将其结果添加到新的列
df2['mean'] = df2.mean(axis=1)
print(df2)
'''
   key1  key2  key3  mean
a     1     2     3   2.0
b     3     4     5   4.0
c     5     6     7   6.0
'''

# 统计非NaN值的数量  count()
print(df)
print('-'*6)
print(df.count())
'''
   key1  key2 key3
a   4.0   1.0    1
b   5.0   2.0    2
c   3.0   NaN    3
d   NaN   4.0    j
e   2.0   5.0    k
------
key1    4
key2    4
key3    5
dtype: int64
'''

# 统计
print(df)
print('-' * 6)
print('df的最小值',df.min())
print('df的最大值',df.max())
print('df的key2列的最大值',df['key2'].max())
print('统计df的分位数，参数q确定位置',df.quantile(q=0.75))
print('对df求和',df.sum())
print('求df的中位数，median(),50%分位数',df.median())
print('求df的标准差，std()',df.std())
print('求df的方差，var()',df.var())
print('求skew样本的偏度,skew()',df.skew())
print('求kurt样本的峰度，kurt()',df.kurt())
print('df累计求和，cumsum()',df['key2'].cumsum())
print('df累计求积，cumprod()',df['key2'].cumprod())
print('求df的累计最大值，cummax()', df['key2'].cummax())
print('求df的累计最小值，cummin()', df['key2'].cummin())
'''
   key1  key2 key3
a   4.0   1.0    1
b   5.0   2.0    2
c   3.0   NaN    3
d   NaN   4.0    j
e   2.0   5.0    k
------
df的最小值 key1    2.0
key2    1.0
dtype: float64
df的最大值 key1    5.0
key2    5.0
dtype: float64
df的key2列的最大值 5.0
统计df的分位数，参数q确定位置 key1    4.25
key2    4.25
Name: 0.75, dtype: float64
对df求和 key1    14.0
key2    12.0
dtype: float64
求df的中位数，median(),50%分位数 key1    3.5
key2    3.0
dtype: float64
求df的标准差，std() key1    1.290994
key2    1.825742
dtype: float64
求df的方差，var() key1    1.666667
key2    3.333333
dtype: float64
求skew样本的偏度,skew() key1    0.0
key2    0.0
dtype: float64
求kurt样本的峰度，kurt() key1   -1.2
key2   -3.3
dtype: float64
df累计求和，cumsum() a     1.0
b     3.0
c     NaN
d     7.0
e    12.0
Name: key2, dtype: float64
df累计求积，cumprod() a     1.0
b     2.0
c     NaN
d     8.0
e    40.0
Name: key2, dtype: float64
求df的累计最大值，cummax() a    1.0
b    2.0
c    NaN
d    4.0
e    5.0
Name: key2, dtype: float64
求df的累计最小值，cummin() a    1.0
b    1.0
c    NaN
d    1.0
e    1.0
Name: key2, dtype: float64
'''

# 唯一值 ：unique()
s = pd.Series(list('kjdhsakjdhjfh'))
sq = s.unique()
print(s)
print(sq)
print('sq的类型：',type(sq))
print('对sq进行重新排序：',pd.Series(sq).sort_values())
'''
0     k
1     j
2     d
3     h
4     s
5     a
6     k
7     j
8     d
9     h
10    j
11    f
12    h
dtype: object
['k' 'j' 'd' 'h' 's' 'a' 'f']
sq的类型： <class 'numpy.ndarray'>
对sq进行重新排序： 5    a
2    d
6    f
3    h
1    j
0    k
4    s
dtype: object
'''
# 对某一列进行值的计数，只能对一列，不能对Dataframe
print(df['key2'].value_counts())

# 判断Dataframe中的每个元素是否都是在某个列表中
print(df)
df_isin = df.isin([1,3])
print(df_isin)
'''
   key1  key2 key3
a   4.0   1.0    1
b   5.0   2.0    2
c   3.0   NaN    3
d   NaN   4.0    j
e   2.0   5.0    k


    key1   key2   key3
a  False   True   True
b  False  False  False
c   True  False   True
d  False  False  False
e  False  False  False
'''