Python中pandas库的常用操作实例

import pandas as pd
data = pd.Series([i for i in range(4)],index=['a','b','c','d'])
data

import pandas as pd
dict1 = {"a":0,"b":1,"c":2,"d":3}
data = pd.Series(dict1)
data

import pandas as pd
import numpy as np
arr = np.array([i for i in range(12)]).reshape(3,4)
data = pd.DataFrame(arr)
data

import pandas as pd
import numpy as np
arr = np.array([i for i in range(12)]).reshape(3,4)
data = pd.DataFrame(arr,columns=['a','b','c','d'])
data

#series
import pandas as pd
data = pd.Series([i for i in range(3)],index=['a','b','c'])
data.index
#DataFrame
import pandas as pd
import numpy as np
arr = np.array([i for i in range(9)]).reshape(3,3)
data = pd.DataFrame(arr,columns=['a','b','c'])
data.columns

#series
import pandas as pd
data = pd.Series([i for i in range(3)],index=['a','b','c'])
data[2] #2
data['c'] #2
data[0:2] #0,1
data['a':'c'] #0,1
data[[0,2]] #0,2
data[['a','c']] #0,2
#dataframe
import pandas as pd
import numpy as np
arr = np.array([i for i in range(9)]).reshape(3,3)
data = pd.DataFrame(arr,columns=['a','b','c'])
data['a'] 
""""
0    0
1    3
2    6
""""
data[['a','c']]
""""
	a	c
0	0	2
1	3	5
2	6	8
""""
data[:2]
"""
a	b	c
0	0	1	2
1	3	4	5
"""
##loc是index，iloc是行号
data.loc[:,["a","c"]]
data.iloc[:,[0,2]]

#series
import pandas as pd
data = pd.Series([1,3,0],index=['a','b','c'])
data.sort_index(axis=0)
data.sort_index(axis=0,ascending=False)
#DataFrame
import pandas as pd
import numpy as np
data = pd.DataFrame(np.arange(9).reshape(3,3),columns=['a','b','c'])
data.sort_index()

#series
import pandas as pd
data = pd.Series([1,3,0],index=['a','b','c'])
data.sort_values(axis=0)
data.sort_values(axis=0,ascending=False)
#DataFrame
import pandas as pd
import numpy as np
data = pd.DataFrame(np.arange(9).reshape(3,3),columns=['a','b','c'])
data.sort_values()
data.sort_values(by='a')

import pandas as pd
data = pd.DataFrame(np.arange(9).reshape(3,3),columns=['a','b','c'])
data.to_csv(r'./data.csv',index=False)
data = pd.read_csv(r'./data.csv')
data
import pandas as pd
data = pd.DataFrame(np.arange(9).reshape(3,3),columns=['a','b','c'])
data.to_excel(r'./data.xlsx',index=False)
data = pd.read_excel(r'./data.xlsx')
data

import pandas as pd
import numpy as np
from numpy import NaN
data = pd.Series([1,NaN,3])
data.isnull()
#delete
data.dropna()
#fill
data.fillna(6)

#重复值处理
import pandas as pd
data = pd.DataFrame({'id': [1, 2, 3, 4, 4, 5],
                            'name': ['小铭', '小月月', '彭岩', '刘华', '刘华', '周华'],
                            'age': [18, 18, 29, 58, 58, 36],
                            'height': [180, 180, 185, 175, 175, 178],
                            'gender': ['女', '女', '男', '男', '男', '男']})
data.duplicated() 
data.duplicateds()

import pandas as pd
dict1 = {'A':['5', '6', '7'], 'B':['3', '2', '1']}
data = pd.DataFrame(dict1)
data.dtypes 
data = pd.DataFrame(dict1,dtype='int')
data.dtypes
data.astype(dtype='float')

import pandas as pd
data1 = pd.DataFrame({'A': ['A0', 'A0', 'A1'],
                    'B': ['B0', 'B0', 'B1']})
data2 = pd.DataFrame({'C': ['C0', 'C0', 'C1', 'C3'],
                    'D': ['D0', 'D2', 'D2', 'D3']})
# 横向堆叠合并df1和df2，采用外连接的方式
pd.concat([data1,data2], join='outer',axis=1)

import pandas as pd
import numpy as np
dict1 = {"Key":['C','B','C','A','B','B','A','C','A'],"Data":[2,4,6,8,10,1,14,16,18]}
data = pd.DataFrame(dict1)
data
for i in pd.groupby(by='Key'):
    print(i)