import numpy as np
import pandas as pd
s = pd.Series([1,3,6,np.nan,44,1])
print(s)
datas = pd.date_range('20220719',periods=6)
print(datas)
#第一种创建DataFrame
df = pd.DataFrame(np.random.randn(6,4),index=datas,columns=['a','b','c','d'])
print(df)
#第二种创建DataFrame
df2 = pd.DataFrame({'A':1,
'B':pd.Series(1,index=list(range(4)),dtype='float32'),
'C':np.array([3]*4,dtype='int32'),
'D':pd.Timestamp('20220722'),
'E':pd.Categorical(['test','train','test','train']),
'F':'foo'
})
print(df2)
#类型，索引，值，列
print(df2.dtypes,df2.index,df2.values,df2.columns)
#详细信息
print(df2.describe)
#转置
print(df2.T)
#第排序
print(df2.sort_index(axis=1,ascending = False))
0 1.0
1 3.0
2 6.0
3 NaN
4 44.0
5 1.0
dtype: float64
DatetimeIndex(['2022-07-19', '2022-07-20', '2022-07-21', '2022-07-22',
'2022-07-23', '2022-07-24'],
dtype='datetime64[ns]', freq='D')
a b c d
2022-07-19 0.289809 0.632396 -0.770436 -2.898336
2022-07-20 -0.617356 -0.557689 -1.017138 0.796157
2022-07-21 -2.524918 2.134619 -0.013117 -0.206382
2022-07-22 0.095292 1.616551 0.401501 0.917743
2022-07-23 0.194531 -1.924176 -0.375617 -2.735487
2022-07-24 -0.847691 0.874190 0.694338 -0.577505
A B C D E F
0 1 1.0 3 2022-07-22 test foo
1 1 1.0 3 2022-07-22 train foo
2 1 1.0 3 2022-07-22 test foo
3 1 1.0 3 2022-07-22 train foo
A int64
B float32
C int32
D datetime64[ns]
E category
F object
dtype: object Int64Index([0, 1, 2, 3], dtype='int64') [[1 1.0 3 Timestamp('2022-07-22 00:00:00') 'test' 'foo']
[1 1.0 3 Timestamp('2022-07-22 00:00:00') 'train' 'foo']
[1 1.0 3 Timestamp('2022-07-22 00:00:00') 'test' 'foo']
[1 1.0 3 Timestamp('2022-07-22 00:00:00') 'train' 'foo']] Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')
0 1 2
A 1 1 1
B 1.0 1.0 1.0
C 3 3 3
D 2022-07-22 00:00:00 2022-07-22 00:00:00 2022-07-22 00:00:00
E test train test
F foo foo foo
3
A 1
B 1.0
C 3
D 2022-07-22 00:00:00
E train
F foo
F E D C B A
0 foo test 2022-07-22 3 1.0 1
1 foo train 2022-07-22 3 1.0 1
2 foo test 2022-07-22 3 1.0 1
3 foo train 2022-07-22 3 1.0 1
In [24]:
'''
pandas数据选择
'''
import numpy as np
import pandas as pd
datas = pd.date_range('20220719',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=datas,columns=['A','B','C','D'])
print(df)
print('________________________________________________')
print(df['A'],df.A)#两种方法获取指定列
print('________________________________________________')
print(df[0:3],df['20220719':'20220722'])
print('________________________________________________')
#select by lable:loc
print(df.loc['20220719'])#select by lable:loc(选取日期为20220719的一行)
print(df.loc['20220720',['A','B']])#select by lable:loc(选取日期为20220720，列为A，B的元素)
print('________________________________________________')
#select by possitions :iloc
print(df.iloc[3])#第3行
print(df.iloc[3,2])#第3行第2位
print(df.iloc[1:3,2:4])#1-3行，2-4列
print(df.iloc[[1,2,5],1:4])#第3行
print('________________________________________________')
print(df[df.A<8])
A B C D
2022-07-19 0 1 2 3
2022-07-20 4 5 6 7
2022-07-21 8 9 10 11
2022-07-22 12 13 14 15
2022-07-23 16 17 18 19
2022-07-24 20 21 22 23
________________________________________________
2022-07-19 0
2022-07-20 4
2022-07-21 8
2022-07-22 12
2022-07-23 16
2022-07-24 20
Freq: D, Name: A, dtype: int32 2022-07-19 0
2022-07-20 4
2022-07-21 8
2022-07-22 12
2022-07-23 16
2022-07-24 20
Freq: D, Name: A, dtype: int32
________________________________________________
A B C D
2022-07-19 0 1 2 3
2022-07-20 4 5 6 7
2022-07-21 8 9 10 11 A B C D
2022-07-19 0 1 2 3
2022-07-20 4 5 6 7
2022-07-21 8 9 10 11
2022-07-22 12 13 14 15
________________________________________________
A 0
B 1
C 2
D 3
Name: 2022-07-19 00:00:00, dtype: int32
A 4
B 5
Name: 2022-07-20 00:00:00, dtype: int32
________________________________________________
A 12
B 13
C 14
D 15
Name: 2022-07-22 00:00:00, dtype: int32
14
C D
2022-07-20 6 7
2022-07-21 10 11
B C D
2022-07-20 5 6 7
2022-07-21 9 10 11
2022-07-24 21 22 23
________________________________________________
A B C D
2022-07-19 0 1 2 3
2022-07-20 4 5 6 7
In [36]:
'''
pandas设置值
'''
import numpy as np
import pandas as pd
datas = pd.date_range('20220719',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=datas,columns=['A','B','C','D'])
df.iloc[2,2]=100
print(df)
print('________________________________________________')
df.loc['20220719','B']=200
print(df)
print('________________________________________________')
df[df.A>4]=0 #全部显示小于4的改变
print(df)
print('________________________________________________')
df.A[df.A>3]=0 #A中显示小于4的改变
print(df)
print('________________________________________________')
df['E']=np.nan #增加行
print(df)
print('________________________________________________')
df['F']=pd.Series([1,2,3,4,5,6],index=pd.date_range('20220719',periods=6))
print(df) #增加指定元素
print('________________________________________________')
A B C D
2022-07-19 0 1 2 3
2022-07-20 4 5 6 7
2022-07-21 8 9 100 11
2022-07-22 12 13 14 15
2022-07-23 16 17 18 19
2022-07-24 20 21 22 23
________________________________________________
A B C D
2022-07-19 0 200 2 3
2022-07-20 4 5 6 7
2022-07-21 8 9 100 11
2022-07-22 12 13 14 15
2022-07-23 16 17 18 19
2022-07-24 20 21 22 23
________________________________________________
A B C D
2022-07-19 0 200 2 3
2022-07-20 4 5 6 7
2022-07-21 0 0 0 0
2022-07-22 0 0 0 0
2022-07-23 0 0 0 0
2022-07-24 0 0 0 0
________________________________________________
A B C D
2022-07-19 0 200 2 3
2022-07-20 0 5 6 7
2022-07-21 0 0 0 0
2022-07-22 0 0 0 0
2022-07-23 0 0 0 0
2022-07-24 0 0 0 0
________________________________________________
A B C D E
2022-07-19 0 200 2 3 NaN
2022-07-20 0 5 6 7 NaN
2022-07-21 0 0 0 0 NaN
2022-07-22 0 0 0 0 NaN
2022-07-23 0 0 0 0 NaN
2022-07-24 0 0 0 0 NaN
________________________________________________
A B C D E F
2022-07-19 0 200 2 3 NaN 1
2022-07-20 0 5 6 7 NaN 2
2022-07-21 0 0 0 0 NaN 3
2022-07-22 0 0 0 0 NaN 4
2022-07-23 0 0 0 0 NaN 5
2022-07-24 0 0 0 0 NaN 6
________________________________________________
In [56]:
'''
pandas处理数据丢失
'''
import numpy as np
import pandas as pd
datas = pd.date_range('20220719',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=datas,columns=['A','B','C','D'])
df.iloc[0,1]=np.nan
df.iloc[1,2]=np.nan
print(df)
print('________________________________________________')
print(df.fillna(value=100))#填充数据中为nan的值，赋值为100
print(df)
print('________________________________________________')
print(df.dropna(axis=0,how='any'))#处理数据：axis=0对行处理,how='any'只要有一个没有数据就处理，how='all'所有没有数据就操作
print(df)
print('________________________________________________')
print(np.any(df.isnull())==True)
print('________________________________________________')
print(df.isnull())
A B C D
2022-07-19 0 NaN 2.0 3
2022-07-20 4 5.0 NaN 7
2022-07-21 8 9.0 10.0 11
2022-07-22 12 13.0 14.0 15
2022-07-23 16 17.0 18.0 19
2022-07-24 20 21.0 22.0 23
________________________________________________
A B C D
2022-07-19 0 100.0 2.0 3
2022-07-20 4 5.0 100.0 7
2022-07-21 8 9.0 10.0 11
2022-07-22 12 13.0 14.0 15
2022-07-23 16 17.0 18.0 19
2022-07-24 20 21.0 22.0 23
A B C D
2022-07-19 0 NaN 2.0 3
2022-07-20 4 5.0 NaN 7
2022-07-21 8 9.0 10.0 11
2022-07-22 12 13.0 14.0 15
2022-07-23 16 17.0 18.0 19
2022-07-24 20 21.0 22.0 23
________________________________________________
A B C D
2022-07-21 8 9.0 10.0 11
2022-07-22 12 13.0 14.0 15
2022-07-23 16 17.0 18.0 19
2022-07-24 20 21.0 22.0 23
A B C D
2022-07-19 0 NaN 2.0 3
2022-07-20 4 5.0 NaN 7
2022-07-21 8 9.0 10.0 11
2022-07-22 12 13.0 14.0 15
2022-07-23 16 17.0 18.0 19
2022-07-24 20 21.0 22.0 23
________________________________________________
True
________________________________________________
A B C D
2022-07-19 False True False False
2022-07-20 False False True False
2022-07-21 False False False False
2022-07-22 False False False False
2022-07-23 False False False False
2022-07-24 False False False False
In [ ]:
''' pandas导入导出数据 ''' import numpy as np import pandas as pd pd.read_csv(filename) # 导入csv格式文件中的数据 pd.read_table(filename) # 导入有分隔符的文本 (如TSV) 中的数据 pd.read_excel(filename) # 导入Excel格式文件中的数据 pd.read_sql(query, connection_object) # 导入SQL数据表/数据库中的数据 pd.read_json(json_string) # 导入JSON格式的字符，URL地址或者文件中的数据pd.read_html(url) # 导入经过解析的URL地址中包含的数据框 (DataFrame) 数据 pd.read_clipboard() # 导入系统粘贴板里面的数据 pd.DataFrame(dict) # 导入Python字典 (dict) 里面的数据，其中key是数据框的表头，value是数据框的内容。 df.to_csv(filename) # 将数据框 (DataFrame)中的数据导入csv格式的文件中 df.to_excel(filename) # 将数据框 (DataFrame)中的数据导入Excel格式的文件中 df.to_sql(table_name,connection_object) # 将数据框 (DataFrame)中的数据导入SQL数据表/数据库中 df.to_json(filename) # 将数据框 (DataFrame)中的数据导入JSON格式的文件中
In [61]:
'''
pandas DataFrame合并
'''
import numpy as np
import pandas as pd
df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])
df3 = pd.DataFrame(np.ones((3,4))*2,columns=['a','b','c','d'])
'''concatenating'''
print(pd.concat([df1,df2,df3],axis=0))#axis=0上下合并，而且index重复，不利于操作
print('________________________________________________')
print(pd.concat([df1,df2,df3],axis=0,ignore_index=True))#axis=0上下合并,ignore_index忽略原来的index
a b c d
0 0.0 0.0 0.0 0.0
1 0.0 0.0 0.0 0.0
2 0.0 0.0 0.0 0.0
0 1.0 1.0 1.0 1.0
1 1.0 1.0 1.0 1.0
2 1.0 1.0 1.0 1.0
0 2.0 2.0 2.0 2.0
1 2.0 2.0 2.0 2.0
2 2.0 2.0 2.0 2.0
________________________________________________
a b c d
0 0.0 0.0 0.0 0.0
1 0.0 0.0 0.0 0.0
2 0.0 0.0 0.0 0.0
3 1.0 1.0 1.0 1.0
4 1.0 1.0 1.0 1.0
5 1.0 1.0 1.0 1.0
6 2.0 2.0 2.0 2.0
7 2.0 2.0 2.0 2.0
8 2.0 2.0 2.0 2.0
In [64]:
'''
pandas DataFrame合并
'''
import numpy as np
import pandas as pd
df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1,columns=['b','c','d','e'])
'''join,['inner','outer']'''
print(pd.concat([df1,df2],axis=0,join='outer'))#axis=0上下合并,ignore_index忽略原来的index
print('________________________________________________')
print(pd.concat([df1,df2],axis=0,join='inner',ignore_index='True'))#axis=0上下合并,ignore_index忽略原来的index
print('________________________________________________')
a b c d e
0 0.0 0.0 0.0 0.0 NaN
1 0.0 0.0 0.0 0.0 NaN
2 0.0 0.0 0.0 0.0 NaN
0 NaN 1.0 1.0 1.0 1.0
1 NaN 1.0 1.0 1.0 1.0
2 NaN 1.0 1.0 1.0 1.0
________________________________________________
b c d
0 0.0 0.0 0.0
1 0.0 0.0 0.0
2 0.0 0.0 0.0
3 1.0 1.0 1.0
4 1.0 1.0 1.0
5 1.0 1.0 1.0
In [68]:
'''
pandas DataFrame合并
'''
import numpy as np
import pandas as pd
df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])
df3 = pd.DataFrame(np.ones((3,4))*2,columns=['a','b','c','d'],index=[2,3,4])
'''append'''
print(df1.append(df2,ignore_index=True))
print('________________________________________________')
df4 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
s1 = pd.Series([1,2,3,4],index=['a','b','c','d'])
res= df4.append(s1,ignore_index=True)
print(res)
a b c d
0 0.0 0.0 0.0 0.0
1 0.0 0.0 0.0 0.0
2 0.0 0.0 0.0 0.0
3 1.0 1.0 1.0 1.0
4 1.0 1.0 1.0 1.0
5 1.0 1.0 1.0 1.0
________________________________________________
a b c d
0 0.0 0.0 0.0 0.0
1 0.0 0.0 0.0 0.0
2 0.0 0.0 0.0 0.0
3 1.0 2.0 3.0 4.0
C:UsersDoubleAppDataLocalTempipykernel_133567792660.py:10: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead. print(df1.append(df2,ignore_index=True)) C:UsersDoubleAppDataLocalTempipykernel_133567792660.py:14: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead. res= df4.append(s1,ignore_index=True)
In [74]:
'''
pandas DataFrame合并
'''
import numpy as np
import pandas as pd
left = pd.DataFrame({
'key':['k1','k2','k3','k4'],
'A':['a1','a2','a3','a4'],
'B':['b1','b2','b3','b4']
})
right = pd.DataFrame({
'key':['k1','k2','k3','k4'],
'C':['C1','C2','C3','C4'],
'D':['D1','D2','D3','D4']
})
print(left)
print('____________________')
print(right)
print('____________________')
print(pd.merge(left,right,on='key'))
key A B 0 k1 a1 b1 1 k2 a2 b2 2 k3 a3 b3 3 k4 a4 b4 ____________________ key C D 0 k1 C1 D1 1 k2 C2 D2 2 k3 C3 D3 3 k4 C4 D4 ____________________ key A B C D 0 k1 a1 b1 C1 D1 1 k2 a2 b2 C2 D2 2 k3 a3 b3 C3 D3 3 k4 a4 b4 C4 D4
In [84]:
'''
pandas DataFrame合并
'''
import numpy as np
import pandas as pd
left = pd.DataFrame({
'key1':['k1','k4','k2','k2'],
'key2':['k2','k1','k2','k1'],
'A':['a1','a2','a3','a4'],
'B':['b1','b2','b3','b4']
})
right = pd.DataFrame({
'key1':['k2','k1','k2','k2'],
'key2':['k2','k2','k2','k1'],
'C':['C1','C2','C3','C4'],
'D':['D1','D2','D3','D4']
})
print(left)
print('____________________')
print(right)
print('____________________')
#how=['left','right','outer','inner']
print(pd.merge(left,right,on=['key1','key2'],how='right'))
print('____________________')
print(pd.merge(left,right,on=['key1','key2'],how='right',indicator=True))
print('____________________')
print(pd.merge(left,right,left_index=True,right_index=True,how='right',indicator=True))
print('____________________')
key1 key2 A B 0 k1 k2 a1 b1 1 k4 k1 a2 b2 2 k2 k2 a3 b3 3 k2 k1 a4 b4 ____________________ key1 key2 C D 0 k2 k2 C1 D1 1 k1 k2 C2 D2 2 k2 k2 C3 D3 3 k2 k1 C4 D4 ____________________ key1 key2 A B C D 0 k2 k2 a3 b3 C1 D1 1 k1 k2 a1 b1 C2 D2 2 k2 k2 a3 b3 C3 D3 3 k2 k1 a4 b4 C4 D4 ____________________ key1 key2 A B C D _merge 0 k2 k2 a3 b3 C1 D1 both 1 k1 k2 a1 b1 C2 D2 both 2 k2 k2 a3 b3 C3 D3 both 3 k2 k1 a4 b4 C4 D4 both ____________________ key1_x key2_x A B key1_y key2_y C D _merge 0 k1 k2 a1 b1 k2 k2 C1 D1 both 1 k4 k1 a2 b2 k1 k2 C2 D2 both 2 k2 k2 a3 b3 k2 k2 C3 D3 both 3 k2 k1 a4 b4 k2 k1 C4 D4 both ____________________
In [88]:
''' pandas 图像 ''' import numpy as np import pandas as pd import matplotlib.pyplot as plt data =pd.Series(np.random.randn(1000),index=np.arange(1000)) data =data.cumsum() data.plot() plt.show()
____________________
--------------------------------------------------------------------------- TypeError Traceback (most recent call last) Input In [88], in| () 12 plt.show() 13 print('____________________') ---> 14 data1 =pd.DataFrame(np.random.randn(1000,4),index=np.arange(1000),colmuns=list('ABCD')) 15 data1 =data.cumsum() 16 data1.plot() TypeError: __init__() got an unexpected keyword argument 'colmuns' |
In [98]:
'''
pandas 图像
'''
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data1 =pd.DataFrame(np.random.randn(1000,4),index=np.arange(1000),columns=list('ABCD'))
data1 =data1.cumsum()
#ploat methoads:
#'bar','hist','box','kde','area','scatter','hexbin','pie'
data1.plot()
plt.show()
In [100]:
'''
pandas 图像
'''
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
print('____________________')
data =pd.DataFrame(np.random.randn(1000,4),index=np.arange(1000),columns=list('ABCD'))
data =data.cumsum()
#ploat methoads:
#'bar','hist','box','kde','area','scatter','hexbin','pie'
ax = data.plot.scatter(x='A',y='B',color='DarkBlue',label='Class 1')
data.plot.scatter(x='A',y='C',color='DarkGreen',label='Class 2',ax=ax)
plt.show()
____________________
In [ ]:
