Python3.5——Pandas模块使用（中）——DataFrame

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

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

#1.DataFrame通过二维数组创建
print("======DataFrame直接通过二维数组创建======")
d1 = DataFrame([["a","b","c","d"],[1,2,3,4]])
print(d1)

print("======DataFrame借助array二维数组创建======")
arr = np.array([
["jack",78],
["lili",86],
["amy",97],
["tom",100]
])

d2 = DataFrame(arr,index=["01","02","03","04"],columns=["姓名","成绩"])
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)

#运行结果：

======DataFrame直接通过二维数组创建======
0  1  2  3
0  a  b  c  d
1  1  2  3  4
======DataFrame借助array二维数组创建======
姓名   成绩
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', '成绩'], dtype='object')
========打印值========
[['jack' '78']
['lili' '86']
['amy' '97']
['tom' '100']]

#2.DataFrame通过字典创建，键作为列索引，键值作为数据值，行索引值自动生成

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("========数据值========")
print(d3.values)

#运行结果：
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')
========数据值========
[['1101' 8 2000]
['1102' 8 4000]
['1103' 8 5000]
['1104' 8 3500]]

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

#3.DataFrame获取数据
data = {
"apart":['1101',"1102","1103","1104"],
"profit":[2000,4000,5000,3500],
"month":8
}

d3 = DataFrame(data)
print(d3)

print("======获取一列数据======")
print(d3["apart"])
print("======获取一行数据======")
print(d3.ix[1])

print("======修改数据值======")
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)

#运行结果：
apart  month  profit
0  1101      8    2000
1  1102      8    4000
2  1103      8    5000
3  1104      8    3500
======获取一列数据======
0    1101
1    1102
2    1103
3    1104
Name: apart, dtype: object
======获取一行数据======
apart     1102
month        8
profit    4000
Name: 1, dtype: object
======修改数据值======
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

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

#pandas基本操作
#1.数据文件读取

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

#运行结果：
name  age  source
0  gerry   18    98.5
1    tom   21    78.2
2   lili   24    98.5
3   john   20    89.2

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

#pandas基本操作
#1.数据文件读取

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

#2.数据过滤获取

columns = ["姓名","年龄","成绩"]
df.columns = columns        #更改列索引
print("=======更改列索引========")
print(df)

#获取几列的值
df1 = df[columns[1:]]
print("=======获取几列的值========")
print(df1)
print("=======获取几行的值========")
print(df.ix[1:3])

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

#运行结果：
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  年龄    成绩
0  gerry  18  98.5
1    tom  21   NaN
2   lili  24  98.5
3   john  20  89.2
=======获取几列的值========
年龄    成绩
0  18  98.5
1  21   NaN
2  24  98.5
3  20  89.2
=======获取几行的值========
姓名  年龄    成绩
1   tom  21   NaN
2  lili  24  98.5
3  john  20  89.2
=======删除含有NaN值的行=======
年龄    成绩
0  18  98.5
2  24  98.5
3  20  89.2