基础知识汇总-series

https://baijiahao.baidu.com/s?id=1606423705612438940&wfr=spider&for=pc
import numpy as np
import pandas as pd
import numpy as np
series = pd.Series([1,2,3,44],index=list(‘abcd’))
print(series)
a 1
b 2
c 3
d 44
dtype: int64
bo = series[series<2]
print(bo)
a 1
dtype: int64
bo1 = series[(series>1) & (series ❤️)]
print(bo1)
b 2
dtype: int64
‘’‘当series的标签索引是整型时,那么使用series[1]方法里面的数值为值，使用series[1：3]里面的数值为行，使用series[[1,2,3]]方法里面的数值为值。
当series的标签（索引）是字符串时，那么使用series[1]方法里面的数值为行，使用series[‘a’]里面的数值为值，使用series[[1,2,3]]方法里面的数值为行，使用series[1：3]里面的数值为行，使用series[[‘a’,‘b’,‘c’]]方法里面的数值为行
‘’’

series = pd.Series([1,2,3,44],index=list(‘abcd’))

print(series)

‘’‘判断是否为空’’’

if series.empty:

print(‘yes’)

if not series.any():

print(‘yes’)

if series.all():

print(‘yes’)

‘’‘查询大于小于等于’’’

bo = series[series<2]

bo1 = series[(series>1) | (series == 44)]

‘’‘or | and &’’’

bo11 = series[~(series<0)]

‘’’ ~ 波浪线是not’’’

print(bo11)

series = pd.Series([None,1,None,None,12,3,46,])
print(series)
‘’‘判断是否有空值，缺值’’’

series = series.isnull()

print(series)

‘’‘判断空值，不是空是true’’’

series = series.notnull()

print(series)

‘’‘判断空值，返回不是空的值 反之isnull’’’

a = series[series.notnull()]

print(a)

‘’‘删除空值’’’

series = series.dropna()

print(series)

‘’‘给空值赋值’’’

series.fillna(0,inplace=True)

series = series.fillna(0)

print(series)

‘’‘向下填充’’’

series = series.fillna(method=‘ffill’) # front fill

‘’‘向上填充’’’
series = series.fillna(method=‘bfill’) # back fill
print(series)

series = pd.Series([1,2,5,7,1,6],index=[list(‘sasssd’)])

print(series)

‘’‘排序’’’

‘’‘ascending=False降序，默认升序’’’

series = series.sort_index()

series =series.sort_index(ascending=False)

print(series)

‘’‘根据值来排序’’’
‘’‘ascending=False降序，默认升序’’’

series = series.sort_values()

series = series.sort_values(ascending=False)

print(series)

‘’‘中国式排名，如果有相同的值，则会出现并列的情况’’’

series = series.rank(method=‘dense’)

‘’‘默认排名。如果有相同的值则按照他们数量的均值进行排序’’’

series = series.rank(method=‘average’)

‘’‘去平均值的最小值max最大值 四舍五入’’’
rank
rank函数返回从小到大排序的下标，对于平级的数，rank是通过“为各组分配一个平均排名”的方式破坏评级关系

obj = pd.Series([7,-5,7,4,2,0,4])
print (obj.rank())

0 6.5
1 1.0
2 6.5
3 4.5
4 3.0
5 2.0
6 4.5
dtype: float64
1
2
3
4
5
6
7
8
9
10
11
12
最小的为1
根据值在源数据中出现的顺序给出排名

obj.rank(method=‘first’)
0 6.0
1 1.0
2 7.0
3 4.0
4 3.0
5 2.0
6 5.0
dtype: float64
1
2
3
4
5
6
7
8
9

也可以按照降序进行排名

obj.rank(ascending=False, method=‘max’)
0 2.0
1 7.0
2 2.0
3 4.0
4 5.0
5 6.0
6 4.0
dtype: float64
1
2
3
4
5
6
7
8
9
最小的是7

series = series.rank(method=‘min’)

series = series.rank(method=‘max’)

‘’‘计算所有元素出现的次数，会改变原有数据下标记’’’

series = series.value_counts()

‘’‘返回最大的数据 反之min’’’

series = series.max()

‘’‘返回中值’’’

series = series.median()

‘’‘平均值’’’

series = series.mean()

‘’‘求和’’’

series = series.sum()

‘’‘标准差 越小 价值越高,真实性越高’’’

series = series.std()

‘’‘所有信息的输出 .round一位小数’’’

series = series.describe().round()

print(series)

‘’‘标准差’’’

import math

from functools import reduce

def std(s):

result = 0

for i in s:

result +=i

mean = result/len(s)

std_2 = reduce(lambda x,y:x+y,list(map(lambda x:math.pow((x-mean),2),s)))/len(s)

return math.sqrt(std_2)

print(std([1,2,3,5,5,6]))