2018-11-30课程03

数据科学之3-3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':['Brussles','New Delhi', 'Brasilia'],
       'Population':[111190846, 1303171035, 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)

DataFrame

df1 = pd.DataFrame(data)
df1

	Country	Capital	Population
0	Belgium	Brussles	111190846
1	India	New Delhi	1303171035
2	Brazil	Brasilia	207847528

df1.iterrows()

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

(0, Country         Belgium
Capital        Brussles
Population    111190846
Name: 0, dtype: object)

(1, Country            India
Capital        New Delhi
Population    1303171035
Name: 1, dtype: object)

(2, Country          Brazil
Capital        Brasilia
Population    207847528
Name: 2, dtype: object)

DataFrame的IO操作

import webbrowser

link = "http://pandas.pydata.org/pandas-docs/version/0.20/io.html"
webbrowser.open(link)

True

df1 = pd.read_clipboard()

df1

	Format Type	Data Description	Reader	Writer
0	text	CSV	read_csv	to_csv
1	text	JSON	read_json	to_json
2	text	HTML	read_html	to_html
3	text	Local clipboard	read_clipboard	to_clipboard
4	binary	MS Excel	read_excel	to_excel
5	binary	HDF5 Format	read_hdf	to_hdf
6	binary	Feather Format	read_feather	to_feather
7	binary	Msgpack	read_msgpack	to_msgpack
8	binary	Stata	read_stata	to_stata
9	binary	SAS	read_sas
10	binary	Python Pickle Format	read_pickle	to_pickle
11	SQL	SQL	read_sql	to_sql
12	SQL	Google Big Query	read_gbq	to_gbq

# 复制一个12这个数字然后执行这个语句 会把df1中的数据写到粘贴板里
df1.to_clipboard()

df1.to_csv('df1.csv', index=False) # 去掉行索引

!ls

!more df1.csv

# 读取 csv
df2 = pd.read_csv('df1.csv')
df2

	Format Type	Data Description	Reader	Writer
0	text	CSV	read_csv	to_csv
1	text	JSON	read_json	to_json
2	text	HTML	read_html	to_html
3	text	Local clipboard	read_clipboard	to_clipboard
4	binary	MS Excel	read_excel	to_excel
5	binary	HDF5 Format	read_hdf	to_hdf
6	binary	Feather Format	read_feather	to_feather
7	binary	Msgpack	read_msgpack	to_msgpack
8	binary	Stata	read_stata	to_stata
9	binary	SAS	read_sas
10	binary	Python Pickle Format	read_pickle	to_pickle
11	SQL	SQL	read_sql	to_sql
12	SQL	Google Big Query	read_gbq	to_gbq

df1.to_json()

'{"Format Type":{"0":"text","1":"text","2":"text","3":"text","4":"binary","5":"binary","6":"binary","7":"binary","8":"binary","9":"binary","10":"binary","11":"SQL","12":"SQL"},"Data Description":{"0":"CSV","1":"JSON","2":"HTML","3":"Local clipboard","4":"MS Excel","5":"HDF5 Format","6":"Feather Format","7":"Msgpack","8":"Stata","9":"SAS","10":"Python Pickle Format","11":"SQL","12":"Google Big Query"},"Reader":{"0":"read_csv","1":"read_json","2":"read_html","3":"read_clipboard","4":"read_excel","5":"read_hdf","6":"read_feather","7":"read_msgpack","8":"read_stata","9":"read_sas","10":"read_pickle","11":"read_sql","12":"read_gbq"},"Writer":{"0":"to_csv","1":"to_json","2":"to_html","3":"to_clipboard","4":"to_excel","5":"to_hdf","6":"to_feather","7":"to_msgpack","8":"to_stata","9":" ","10":"to_pickle","11":"to_sql","12":"to_gbq"}}'

pd.read_json(df1.to_json())

	Format Type	Data Description	Reader	Writer
0	text	CSV	read_csv	to_csv
1	text	JSON	read_json	to_json
10	binary	Python Pickle Format	read_pickle	to_pickle
11	SQL	SQL	read_sql	to_sql
12	SQL	Google Big Query	read_gbq	to_gbq
2	text	HTML	read_html	to_html
3	text	Local clipboard	read_clipboard	to_clipboard
4	binary	MS Excel	read_excel	to_excel
5	binary	HDF5 Format	read_hdf	to_hdf
6	binary	Feather Format	read_feather	to_feather
7	binary	Msgpack	read_msgpack	to_msgpack
8	binary	Stata	read_stata	to_stata
9	binary	SAS	read_sas

df1.to_html('df.html')

df1.to_excel('df1.xlsx')