python数据长度_python数据分析-常规操作

import numpy as np

1.创建一个长度为10的空向量

a=np.zeros(10)

print(a)

[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

2.第五个值设置为1

a[4]=1

print(a)

[0. 0. 0. 0. 1. 0. 0. 0. 0. 0.]

3.创建一个值域范围从10到49的向量

b=np.arange(10,50)

print(b)

[10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33

34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49]

4.反转一个向量(第一个元素变为最后一个)

b=b[::-1]

print(b)

[49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32 31 30 29 28 27 26

25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10]

5.创建一个长度为30的随机向量并找到它的平均值

c=np.random.random(30)

d=c.mean()

print(d)

0.5527580659886581

6.创建一个10*10的随机数组并找出它的最大值和最小值

e=np.random.random((10,10))

print(e)

[[0.9170069 0.66568986 0.56742636 0.14696659 0.93767453 0.09402097

0.54618329 0.12625947 0.90182726 0.61660999]

[0.3486533 0.98538757 0.68982081 0.33552572 0.24356616 0.1594021

0.40305814 0.0639056 0.67879594 0.57891074]

[0.60909009 0.99302626 0.54645758 0.73081934 0.45984285 0.82253375

0.35515268 0.57644458 0.2955276 0.18391424]

[0.24158195 0.49485468 0.59128442 0.55743579 0.99961246 0.4508759

0.74789393 0.02750277 0.98453766 0.01303206]

[0.0033238 0.88869616 0.14164172 0.85822794 0.58211973 0.56087155

0.77262901 0.24472144 0.96130194 0.62989183]

[0.07068191 0.40728846 0.47576458 0.44355222 0.10916397 0.64966196

0.49579891 0.17922588 0.87968783 0.69344045]

[0.23523426 0.02701388 0.22272702 0.72441141 0.84543185 0.57887048

0.58257562 0.24566879 0.27529409 0.99546806]

[0.81835016 0.53123186 0.0743116 0.23961043 0.95036313 0.42512372

0.12252098 0.10007916 0.3101578 0.14821808]

[0.03880317 0.07812695 0.835528 0.68364065 0.34818947 0.13560458

0.60249626 0.25700171 0.70802306 0.73026684]

[0.27389633 0.17089138 0.12786965 0.78076045 0.99042567 0.98327677

0.87483383 0.55379135 0.56356262 0.14683745]]

min,max=e.min(),e.max()

print(min,max)

0.0033238021751439417 0.999612459219021

7.对一个5*5的随机矩阵做归一化

f=np.random.random((5,5))

max,min=f.max(),f.min()

f=(f-min)/(max-min)

print(f)

[[0.79651043 0.77650729 0.68965856 0.0518204 0.81799265]

[0.9568898 0.77565194 0.44387402 0.71809914 0.70544833]

[0. 0.63012163 0.28662836 0.7276584 0.91605213]

[0.65708275 0.86770802 0.53851921 1. 0.30971719]

[0.49909808 0.25904126 0.20944617 0.28601671 0.99925076]]

8.如何得到所有与2016年7月对应的日期

g=np.arange('2016-07','2016-08',dtype='datetime64[D]')

print(g)

['2016-07-01' '2016-07-02' '2016-07-03' '2016-07-04' '2016-07-05'

'2016-07-06' '2016-07-07' '2016-07-08' '2016-07-09' '2016-07-10'

'2016-07-11' '2016-07-12' '2016-07-13' '2016-07-14' '2016-07-15'

'2016-07-16' '2016-07-17' '2016-07-18' '2016-07-19' '2016-07-20'

'2016-07-21' '2016-07-22' '2016-07-23' '2016-07-24' '2016-07-25'

'2016-07-26' '2016-07-27' '2016-07-28' '2016-07-29' '2016-07-30'

'2016-07-31']

9.检查一个二维数组是否有空列

h=np.random.randint(0,10,(3,10))

print(h)

[[5 2 3 1 4 3 7 0 0 4]

[1 2 0 9 4 7 4 6 3 4]

[3 5 0 1 7 1 4 1 7 4]]

print(h.any())

True

10.以给定的形状创建一个数组，数组元素来符合标准正态分布N(0,1)

i=np.random.randn(4,6)

print(i)

[[-0.06696173 -0.397078 -0.54527181 1.40846477 0.38308806 1.39167608]

[ 0.43594496 -0.90587903 0.95744047 0.97402486 -1.98892672 -0.32113629]

[-0.80864666 -1.42289961 0.11787861 -1.39319269 0.0828501 0.04520828]

[ 0.99880749 -1.97154802 -1.24288586 0.22087789 0.12689615 0.33137178]]

11.以给定的形状创建一个数组，并在数组中加入在[0，1]之间均匀分布的随机样本

j=np.random.rand(4,6)

print(j)

[[0.91697975 0.65660303 0.96028603 0.9025543 0.13344065 0.24094464]

[0.09234047 0.84434315 0.25852919 0.04614204 0.52459626 0.16026817]

[0.26738904 0.15655722 0.89825181 0.51723048 0.72831946 0.02677522]

[0.71228968 0.19691786 0.19664906 0.66680613 0.44638245 0.5629584 ]]

12.生成在半开半闭区间[low,high)上离散均匀分布的整数值

k=np.random.randint(0,5,(4,6))

print(k)

[[0 2 0 4 4 2]

[1 0 0 1 3 0]

[3 1 2 4 2 4]

[4 1 3 3 3 2]]

import pandas as pd

13.从列表创建Series

l=[0,1,2,3,4]

df=pd.Series(l)

df

0 0

1 1

2 2

3 3

4 4

dtype: int64

14.从字典创建Series

m={'a':1,'b':2,'c':3,'d':4,'e':5}

df=pd.Series(m)

df

a 1

b 2

c 3

d 4

e 5

dtype: int64

15.从Numpy数组创建DataFrame

dates=pd.date_range('today',periods=6)

num_arr=np.random.rand(6,4)

columns=['A','B','C','D']

df=pd.DataFrame(num_arr,index=dates,columns=columns)

df

16.从字典对象创建DataFrame，并设置索引

data={'animal': ['cat', 'cat', 'snake', 'dog', 'dog', 'cat', 'snake', 'cat', 'dog', 'dog'],

'age': [2.5, 3, 0.5, np.nan, 5, 2, 4.5, np.nan, 7, 3],

'visits': [1, 3, 2, 3, 2, 3, 1, 1, 2, 1],

'priority': ['yes', 'yes', 'no', 'yes', 'no', 'no', 'no', 'yes', 'no', 'no']}

labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j']

df = pd.DataFrame(data, index=labels)

df

17.显示df的基础信息

Index: 10 entries, a to j

Data columns (total 4 columns):

# Column Non-Null Count Dtype

--- ------ -------------- -----

0 animal 10 non-null object

1 age 8 non-null float64

2 visits 10 non-null int64

3 priority 10 non-null object

dtypes: float64(1), int64(1), object(2)

memory usage: 400.0+ bytes

(2)df.describe()

18.展示df的前3行

(1)df.head(3)

(2)df.iloc[:3]

19.取出df的animal和age列

(1)df[['animal','age']]

(2)df.loc[:,['animal','age']]

20.取出索引为[3,4,8]行的animal和age列

df.loc[df.index[[3,4,8]],['animal','age']]

21.取出age值大于3的行

df[df['age']>3]

22.取出age值缺失的行

df[df['age'].isnull()]

23.取出age在2，4间的行(不含)

df[df['age'].between(2,4)]

24.f行的age改为1.5

df.loc['f','age']=1.5

25.计算visits的总和

df['visits'].sum()

19

26.计算每个不同种类animal的age的平均数

df.groupby('animal')['age'].mean()

animal

cat 2.333333

dog 5.000000

snake 2.500000

Name: age, dtype: float64

27.计算df中每个种类animal的数量

df['animal'].value_counts()

dog 4

cat 4

snake 2

Name: animal, dtype: int64

28.先按age降序排列，后按visits升序排列

df.sort_values(by=['age','visits'],ascending=[False,True])