Python与数据科学实战课程——第三章Pandas：深入理解series和dataframe

import numpy as np
import pandas as pd
from pandas import Series, DataFrame
data = {"Country":["Belgium","India","Brazil"],
        "Capital":["Brussels","New Delhi","Brasilia"],
        "Population":[11190846,130317135,207847528]}

Series

s1 = pd.Series(data["Country"])
s1

0 Belgium
1 India
2 Brazil
dtype: object

s1.values

array([‘Belgium’, ‘India’, ‘Brazil’], dtype=object)

s1.index

RangeIndex(start=0, stop=3, step=1)

s1 = pd.Series(data["Country"],index=["A","B","C"])
s1

A Belgium
B India
C Brazil
dtype: object

s1.index

Index([‘A’, ‘B’, ‘C’], dtype=‘object’)

dataframe

df1 = pd.DataFrame(data)
df1

	Capital	Country	Population
0	Brussels	Belgium	11190846
1	New Delhi	India	130317135
2	Brasilia	Brazil	207847528

cou = df1["Country"]
cou

0 Belgium
1 India
2 Brazil
Name: Country, dtype: object

type(cou)

pandas.core.series.Series

df1.iterrows()

for row in df1.iterrows():
    print(row)

(0, Capital Brussels
Country Belgium
Population 11190846
Name: 0, dtype: object)
(1, Capital New Delhi
Country India
Population 130317135
Name: 1, dtype: object)
(2, Capital Brasilia
Country Brazil
Population 207847528
Name: 2, dtype: object)

for row in df1.iterrows():
    print(type(row)),print(len(row))
    print("------row[0]------------------------------------------"),print(row[0])  
    print("-------------------------------------type(row[0])----------"),print(type(row[0]))
    print("------row[1]------------------------------------------"),print(row[1])
    print("-------------------------------------type(row[1]))---------"),print(type(row[1]))
    break

2
------row[0]------------------------------------------
0
-------------------------------------type(row[0])----------

------row[1]------------------------------------------
Capital Brussels
Country Belgium
Population 11190846
Name: 0, dtype: object
-------------------------------------type(row[1]))---------

通过series创建dataframe

data

{'Country': ['Belgium', 'India', 'Brazil'],
 'Capital': ['Brussels', 'New Delhi', 'Brasilia'],
 'Population': [11190846, 130317135, 207847528]}

s1 = pd.Series(data["Capital"])
s2 = pd.Series(data["Country"])
s3 = pd.Series(data["Population"])

df_new = pd.DataFrame([s1,s2,s3])
df_new

	0	1	2
0	Brussels	New Delhi	Brasilia
1	Belgium	India	Brazil
2	11190846	130317135	207847528

df1

	Capital	Country	Population
0	Brussels	Belgium	11190846
1	New Delhi	India	130317135
2	Brasilia	Brazil	207847528

df_new = df_new.T  #转置
df_new

	0	1	2
0	Brussels	Belgium	11190846
1	New Delhi	India	130317135
2	Brasilia	Brazil	207847528

df_new = pd.DataFrame([s1,s2,s3],index=["Capital","Country","Population"]).T
df_new       #这样就跟df1完全一致了

	Capital	Country	Population
0	Brussels	Belgium	11190846
1	New Delhi	India	130317135
2	Brasilia	Brazil	207847528

Series与DataFrame关系