第1章

第1章 pandas基础

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

1、读取写入文件

#不同类型的文件读取
#https://pandas.pydata.org/pandas-docs/version/0.23.4/generated/pandas.read_csv.html
data = pd.read_csv("table.csv")  
data1 = pd.read_table("table.txt") 
data2 = pd.read_excel("table.xlsx") 

data.head()

	School	Class	ID	Gender	Address	Height	Weight	Math	Physics
0	S_1	C_1	1101	M	street_1	173	63	34.0	A+
1	S_1	C_1	1102	F	street_2	192	73	32.5	B+
2	S_1	C_1	1103	M	street_2	186	82	87.2	B+
3	S_1	C_1	1104	F	street_2	167	81	80.4	B-
4	S_1	C_1	1105	F	street_4	159	64	84.8	B+

data1.head()

	col1	col2	col3	col4
0	2	a	1.4	apple
1	3	b	3.4	banana
2	6	c	2.5	orange
3	5	d	3.2	lemon

data2.head()

	School	Class	ID	Gender	Address	Height	Weight	Math	Physics
0	S_1	C_1	1101	M	street_1	173	63	34.0	A+
1	S_1	C_1	1102	F	street_2	192	73	32.5	B+
2	S_1	C_1	1103	M	street_2	186	82	87.2	B+
3	S_1	C_1	1104	F	street_2	167	81	80.4	B-
4	S_1	C_1	1105	F	street_4	159	64	84.8	B+

data.to_csv("new_data.csv")

data2.to_excel("new_data2.xlsx") # 默认为sheet1

2、Series

s =  pd.Series(np.random.randn(5),index=["a","b","c","d","e"],name="Series",dtype="float")

s

a   -0.104532
b   -1.099814
c   -0.143590
d   -1.507353
e   -0.400417
Name: Series, dtype: float64

s.values

array([-0.10453234, -1.09981446, -0.14358968, -1.50735287, -0.40041748])

s.name

'Series'

s.index

Index(['a', 'b', 'c', 'd', 'e'], dtype='object')

s.dtype

dtype('float64')

s["b"]

-1.0998144639653273

s.mean()

-0.6511413659907033

[i for i in s]

[-0.1045323399024992,
 -1.0998144639653273,
 -0.1435896809218303,
 -1.507352865614497,
 -0.4004174795493625]

3、DataFrame

df = pd.DataFrame({
   "col1":list("abcde"),"col2":range(5,10),"col3":[1.3,2.5,3.6,4.4,5.8]},index=list("一二三四五"))

df

	col1	col2	col3
一	a	5	1.3
二	b	6	2.5
三	c	7	3.6
四	d	8	4.4
五	e	9	5.8

df["col1"]

一    a
二    b
三    c
四    d
五    e
Name: col1, dtype: object

type(df)

pandas.core.frame.DataFrame

type(df["col1"])

pandas.core.series.Series

df.rename(index={
   "一":"one"},columns={
   "col1":"New_col1"})

	New_col1	col2	col3
one	a	5	1.3
二	b	6	2.5
三	c	7	3.6
四	d	8	4.4
五	e	9	5.8

df.index,df.columns,df.values

(Index(['一', '二', '三', '四', '五'], dtype='object'),
 Index(['col1', 'col2', 'col3'], dtype='object'),
 array([['a', 5, 1.3],
        ['b', 6, 2.5],
        ['c', 7, 3.6],
        ['d', 8, 4.4],
        ['e', 9, 5.8]], dtype=object))

df.shape

(5, 3)

df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 5 entries, 一 to 五
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   col1    5 non-null      object 
 1   col2    5 non-null      int64  
 2   col3    5 non-null      float64
dtypes: float64(1), int64(1), object(1)
memory usage: 320.0+ bytes

df.describe().T

	count	mean	std	min	25%	50%	75%	max
col2	5.0	7.00	1.581139	5.0	6.0	7.0	8.0	9.0
col3	5.0	3.52	1.728294	1.3	2.5	3.6	4.4	5.8

df.mean()

col2    7.00
col3    3.52
dtype: float64

df1 = pd.DataFrame({
   "A":[1,2,3]},index=[1,2,3])
df2 = pd.DataFrame({
   "A":[1,2,3]},index=[3,1,2])

df1-df2

	A
1	-1
2	-1
3	2

df.drop(index="五",columns="col1")

	col2	col3
一	5	1.3
二	6	2.5
三	7	3.6
四	8	4.4

df["col1"] = [1,2,3,4,5]

df

	col1	col2	col3
一	1	5	1.3
二	2	6	2.5
三	3	7	3.6
四	4	8	4.4
五	5	9	5.8

del df["col1"]

df

	col2	col3
一	5	1.3
二	6	2.5
三	7	3.6
四	8	4.4
五	9	5.8

df["col1"] = [1,2,