快捷導(dǎo)航

Python3.5 Pandas模塊之DataFrame用法實(shí)例分析

更新時(shí)間：2019年04月23日 11:41:45 作者：loveliuzz

這篇文章主要介紹了Python3.5 Pandas模塊之DataFrame用法,結(jié)合實(shí)例形式詳細(xì)分析了Python3.5中Pandas模塊的DataFrame結(jié)構(gòu)創(chuàng)建、讀取、過(guò)濾、獲取等相關(guān)操作技巧與注意事項(xiàng),需要的朋友可以參考下

本文實(shí)例講述了Python3.5 Pandas模塊之DataFrame用法。分享給大家供大家參考，具體如下：

1、DataFrame的創(chuàng)建

（1）通過(guò)二維數(shù)組方式創(chuàng)建

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author:ZhengzhengLiu

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

#1.DataFrame通過(guò)二維數(shù)組創(chuàng)建
print("======DataFrame直接通過(guò)二維數(shù)組創(chuàng)建======")
d1 = DataFrame([["a","b","c","d"],[1,2,3,4]])
print(d1)

print("======DataFrame借助array二維數(shù)組創(chuàng)建======")
arr = np.array([
  ["jack",78],
  ["lili",86],
  ["amy",97],
  ["tom",100]
])

d2 = DataFrame(arr,index=["01","02","03","04"],columns=["姓名","成績(jī)"])
print(d2)
print("========打印行索引========")
print(d2.index)
print("========打印列索引========")
print(d2.columns)
print("========打印值========")
print(d2.values)

運(yùn)行結(jié)果：

======DataFrame直接通過(guò)二維數(shù)組創(chuàng)建======
   0 1 2 3
0 a b c d
1 1 2 3 4
======DataFrame借助array二維數(shù)組創(chuàng)建======
      姓名   成績(jī)
01 jack   78
02 lili   86
03   amy   97
04   tom 100
========打印行索引========
Index(['01', '02', '03', '04'], dtype='object')
========打印列索引========
Index(['姓名', '成績(jī)'], dtype='object')
========打印值========
[['jack' '78']
['lili' '86']
['amy' '97']
['tom' '100']]

（2）通過(guò)字典方式創(chuàng)建

#2.DataFrame通過(guò)字典創(chuàng)建，鍵作為列索引，鍵值作為數(shù)據(jù)值，行索引值自動(dòng)生成

data = {
  "apart":['1101',"1102","1103","1104"],
  "profit":[2000,4000,5000,3500],
  "month":8
}

d3 = DataFrame(data)
print(d3)
print("========行索引========")
print(d3.index)
print("========列索引========")
print(d3.columns)
print("========數(shù)據(jù)值========")
print(d3.values)

運(yùn)行結(jié)果：

apart month profit
0 1101      8    2000
1 1102      8    4000
2 1103      8    5000
3 1104      8    3500
========行索引========
RangeIndex(start=0, stop=4, step=1)
========列索引========
Index(['apart', 'month', 'profit'], dtype='object')
========數(shù)據(jù)值========
[['1101' 8 2000]
['1102' 8 4000]
['1103' 8 5000]
['1104' 8 3500]]

2、DataFrame數(shù)據(jù)獲取

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

#3.DataFrame獲取數(shù)據(jù)
data = {
  "apart":['1101',"1102","1103","1104"],
  "profit":[2000,4000,5000,3500],
  "month":8
}

d3 = DataFrame(data)
print(d3)

print("======獲取一列數(shù)據(jù)======")
print(d3["apart"])
print("======獲取一行數(shù)據(jù)======")
print(d3.ix[1])

print("======修改數(shù)據(jù)值======")
d3["month"] = [7,8,9,10]        #修改值
d3["year"] = [2001,2001,2003,2004]   #新增列
d3.ix["4"] = np.NaN
print(d3)

運(yùn)行結(jié)果：

apart month profit
0 1101      8    2000
1 1102      8    4000
2 1103      8    5000
3 1104      8    3500
======獲取一列數(shù)據(jù)======
0    1101
1    1102
2    1103
3    1104
Name: apart, dtype: object
======獲取一行數(shù)據(jù)======
apart     1102
month        8
profit    4000
Name: 1, dtype: object
======修改數(shù)據(jù)值======
apart month profit    year
0 1101    7.0 2000.0 2001.0
1 1102    8.0 4000.0 2001.0
2 1103    9.0 5000.0 2003.0
3 1104   10.0 3500.0 2004.0
4   NaN    NaN     NaN     NaN

3、pandas基本功能

（1）pandas數(shù)據(jù)文件讀取

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

#pandas基本操作
#1.數(shù)據(jù)文件讀取

df = pd.read_csv("data.csv")
print(df)

運(yùn)行結(jié)果：

    name age source
0 gerry   18    98.5
1    tom   21    78.2
2   lili   24    98.5
3   john   20    89.2

（2）數(shù)據(jù)過(guò)濾獲取

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

#pandas基本操作
#1.數(shù)據(jù)文件讀取

df = pd.read_csv("data.csv")
print(df)

#2.數(shù)據(jù)過(guò)濾獲取

columns = ["姓名","年齡","成績(jī)"]
df.columns = columns    #更改列索引
print("=======更改列索引========")
print(df)

#獲取幾列的值
df1 = df[columns[1:]]
print("=======獲取幾列的值========")
print(df1)
print("=======獲取幾行的值========")
print(df.ix[1:3])

#刪除含有NaN值的行
df2 = df1.dropna()
print("=======刪除含有NaN值的行=======")
print(df2)

運(yùn)行結(jié)果：

name age source
0 gerry   18    98.5
1    tom   21     NaN
2   lili   24    98.5
3   john   20    89.2
=======更改列索引========
      姓名年齡    成績(jī)
0 gerry 18 98.5
1    tom 21   NaN
2   lili 24 98.5
3   john 20 89.2
=======獲取幾列的值========
   年齡    成績(jī)
0 18 98.5
1 21   NaN
2 24 98.5
3 20 89.2
=======獲取幾行的值========
     姓名年齡    成績(jī)
1   tom 21   NaN
2 lili 24 98.5
3 john 20 89.2
=======刪除含有NaN值的行=======
   年齡    成績(jī)
0 18 98.5
2 24 98.5
3 20 89.2