Python中Pandas模塊的基本操作

2019-04-14 21:31发布生成海报

站内文章 / 模拟电子

16812 0

1. Pandas數據構成 1）Series數據構成

>>>import pandas as pd
>>>series1 = pd.Series([1, 2, 3])
>>>series1
0    1
1    2
2    3

2）DataFrame數據構成

>>>import pandas as pd
>>>import numpy as np
>>>dataframe1 = pd.DataFrame(np.arange(12).reshape(3, 4))
   0    1    2    3
0  0    1    2    3
1  4    5    6    7
2  8    9    10   11
>>>dataframe1 = pd.DataFrame(np.arange(12).reshape(3, 4), index = ['row0', 'row1', 'row2'], columns = ['col0', 'col1', 'col2', 'col3'])
>>>datafram1
     col0    col1    col2    col3
row0  0       1       2       3  
row1  4       5       6       7   
row2  8       9       10      11    
>>>datafram1 = pd.DataFrame({'col0':0, 'col1':1, 'col2':[2, 2, 2]})
>>>datafram1
   col0    col1    col2
0    0       1      2  
1    0       1      2
2    0       1      2

2. Pandas數據的索引

>>>import pandas as pd
>>>import numpy as np
#Series的索引
>>>series1 = pd.Series([1, 2, 3, 4, 5, 6], index = ['A', 'B', 'C', 'D', 'E', 'F'])
>>>series1
A    1
B    2
C    3
D    4
E    5
F    6
>>>series1['A']
1
>>>series1[0]
1
#DataFrame的索引
>>>dataframe1 = pd.DataFrame(np.arange(12).reshape(3, 4), index = ['row0', 'row1', 'row2'], columns = ['col0', 'col1', 'col2', 'col3'])
>>>dataframe1
      col0  col1  col2  col3
row0     0     1     2     3
row1     4     5     6     7
row2     8     9    10    11

>>>dataframe1.col0
row0    0
row1    4
row2    8

>>>dataframe1['col0']
row0    0
row1    4
row2    8

#按標簽進行索引
>>>dataframe1.loc['row0']
col0    0
col1    1
col2    2
col3    3
>>>dataframe1.loc['row0', 'col0']
0

#按位置使用序號索引
>>>dataframe1.iloc[0]
col0    0
col1    1
col2    2
col3    3
>>>dataframe1.iloc[0, 1]
1
#混合索引，不建議使用
>>>dataframe1.ix['row0', 0]
0
>>>dataframe1.ix[0, 'col0']
0

3. Pandas數據的插入和修改

>>>import numpy as np
>>>import pandas as pd
>>>dataframe1 = pd.DataFrame(np.arange(12).reshape(3, 4), index = ['row0', 'row1', 'row2'], columns = ['col0', 'col1', 'col2', 'col3'])
>>>dataframe1
      col0  col1  col2  col3
row0     0     1     2     3
row1     4     5     6     7
row2     8     9    10    11

#使用loc進行修改
>>>dataframe1.loc['row0', 'col0'] = 111
>>>dataframe1
      col0  col1  col2  col3
row0   111     1     2     3
row1     4     5     6     7
row2     8     9    10    11

#使用iloc進行修改
>>>dataframe1.iloc[0, 0] = 222
>>>dataframe1
      col0  col1  col2  col3
row0   222     1     2     3
row1     4     5     6     7
row2     8     9    10    11

#使用布爾索引
#將dataframe1的col1列<5的數值對應的行再將這些行中的col0列賦值為0
>>>dataframe1.col0[dataframe1.col1 < 5] = 0
>>>dataframe1
      col0  col1  col2  col3
row0     0     1     2     3
row1     4     5     6     7
row2     8     9    10    11

#插入一行數據(不使用index的情況)
>>>dataframe1['col4'] = pd.Series([11, 22, 33])
>>>dataframe1
      col0  col1  col2  col3  col4
row0     0     1     2     3   NaN
row1     4     5     6     7   NaN
row2     8     9    10    11   NaN
#插入一行數據，使用index的情況
>>>dataframe1['col4'] = pd.Series([11, 22, 33], index = ['row0', 'row1', 'row2'])
>>>dataframe1
      col0  col1  col2  col3  col4
row0     0     1     2     3    11
row1     4     5     6     7    22
row2     8     9    10    11    33

4. Pandas中nan值的相關操作

>>>dataframe1
      col0  col1  col2  col3  col4
row0     0     1     2     3    11
row1     4     5     6     7    22
row2     8     9    10    11    33

>>>dataframe1.iloc[0, 0] = np.nan
>>>ataframe1.iloc[1, 1] = np.nan
>>>dataframe1
      col0  col1  col2  col3  col4
row0   NaN   1.0     2     3    11
row1   4.0   NaN     6     7    22
row2   8.0   9.0    10    11    33

#將axis = 0(橫)或者axis = 1(列)中含有'nan'(how = 'any')或者都是'nan'(how = 'all')的橫或者列丟棄
>>>dataframe1.dropna(axis = 0, how = 'any')
      col0  col1  col2  col3  col4
row2   8.0   9.0    10    11    33
>>>dataframe1.dropna(axis = 1, how = 'any')
      col2  col3  col4
row0     2     3    11
row1     6     7    22
row2    10    11    33

#判斷是否含有nan
#nan值那一項為True
>>>dataframe1.isnull()
       col0   col1   col2   col3   col4
row0   True  False  False  False  False
row1  False   True  False  False  False
row2  False  False  False  False  False
#判斷數組中是否含有nan值
>>>np.any(dataframe1.isnull())
True

#將nan值改爲自己想要的值
>>>dataframe1.fillna(value = 0)
      col0  col1  col2  col3  col4
row0   0.0   1.0     2     3    11
row1   4.0   0.0     6     7    22
row2   8.0   9.0    10    11    33

5. Pandas中Dataframe數據的合并操作（concat）

>>>dataframe1
      col0  col1  col2  col3
row0   1.0   1.0   1.0   1.0
row1   1.0   1.0   1.0   1.0
row2   1.0   1.0   1.0   1.0

>>>dataframe2
      col1  col2  col3  col4
row1   1.0   1.0   1.0   1.0
row2   1.0   1.0   1.0   1.0
row3   1.0   1.0   1.0   1.0


#默認join = 'outer', axis = 0(多餘的row和col的數值會使用nan來補充)
>>>pd.concat([dataframe1, dataframe2], join = 'outer')
      col0  col1  col2  col3  col4
row0   1.0   1.0   1.0   1.0   NaN
row1   1.0   1.0   1.0   1.0   NaN
row2   1.0   1.0   1.0   1.0   NaN
row1   NaN   1.0   1.0   1.0   1.0
row2   NaN   1.0   1.0   1.0   1.0
row3   NaN   1.0   1.0   1.0   1.0

#join = 'inner'(多餘的row和col會被刪除)
>>>pd.concat([dataframe1, dataframe2], join = 'inner')
      col1  col2  col3
row0   1.0   1.0   1.0
row1   1.0   1.0   1.0
row2   1.0   1.0   1.0
row1   1.0   1.0   1.0
row2   1.0   1.0   1.0
row3   1.0   1.0   1.0

#忽略index，系統重新分配
>>>pd.concat([dataframe1, dataframe2], ignore_index = True)
   col0  col1  col2  col3  col4
0   1.0   1.0   1.0   1.0   NaN
1   1.0   1.0   1.0   1.0   NaN
2   1.0   1.0   1.0   1.0   NaN
3   NaN   1.0   1.0   1.0   1.0
4   NaN   1.0   1.0   1.0   1.0
5   NaN   1.0   1.0   1.0   1.0

#axis = 1
>>>pd.concat([dataframe1, dataframe2], axis = 1)
      col0  col1  col2  col3  col1  col2  col3  col4
row0   1.0   1.0   1.0   1.0   NaN   NaN   NaN   NaN
row1   1.0   1.0   1.0   1.0   1.0   1.0   1.0   1.0
row2   1.0   1.0   1.0   1.0   1.0   1.0   1.0   1.0
row3   NaN   NaN   NaN   NaN   1.0   1.0   1.0   1.0

#按照dataframe1的row index來進行合并,沒有就填充nan
>>>pd.concat([dataframe1, dataframe2], axis = 1, join_axes = [dataframe1.index])
      col0  col1  col2  col3  col1  col2  col3  col4
row0   1.0   1.0   1.0   1.0   NaN   NaN   NaN   NaN
row1   1.0   1.0   1.0   1.0   1.0   1.0   1.0   1.0
row2   1.0   1.0   1.0   1.0   1.0   1.0   1.0   1.0

#按照dataframe1的col來進行合并，沒有填充nan
>>> pd.concat([dataframe1, dataframe2], join_axes = [dataframe1.columns], axis = 0)
      col0  col1  col2  col3
row0   1.0   1.0   1.0   1.0
row1   1.0   1.0   1.0   1.0
row2   1.0   1.0   1.0   1.0
row1   NaN   1.0   1.0   1.0
row2   NaN   1.0   1.0   1.0
row3   NaN   1.0   1.0   1.0

#使用append來進行合并,麽有axis，默認上下添加
>>>dataframe1.append(dataframe1, ignore_index=True)
   col0  col1  col2  col3
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
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
#有index,ignore_index = True(沒有後面會報錯)
>>>dataframe1.append(pd.Series(np.arange(4), index = ['col0', 'col1', 'col2', 'col3']), ignore_index=True)
   col0  col1  col2  col3
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
3   0.0   1.0   2.0   3.0

#沒有index
>>>dataframe1.append(pd.Series(np.arange(4)), ignore_index= True)
   col0  col1  col2  col3    0    1    2    3
0   1.0   1.0   1.0   1.0  NaN  NaN  NaN  NaN
1   1.0   1.0   1.0   1.0  NaN  NaN  NaN  NaN
2   1.0   1.0   1.0   1.0  NaN  NaN  NaN  NaN
3   NaN   NaN   NaN   NaN  0.0  1.0  2.0  3.0

6. Pandas中DataFrame數據的合并操作

>>>left
  key   A   B
0  K0  A0  B0
1  K1  A1  B1
2  K2  A2  B2
3  K3  A3  B3

>>>right
  key   C   D
0  K0  C0  D0
1  K1  C1  D1
2  K2  C2  D2
3  K3  C3  D3

#使用Merge按照key(單個Key)進行合并
>>>pd.merge(left, right, on = 'key')
  key   A   B   C   D
0  K0  A0  B0  C0  D0
1  K1  A1  B1  C1  D1
2  K2  A2  B2  C2  D2
3  K3  A3  B3  C3  D3

#兩個key進行合并（空缺的填充相同的即可）
>>>left
  key1 key2   A   B
0   K0   K0  A0  B0
1   K0   K1  A1  B1
2   K1   K0  A2  B2
3   K2   K1  A3  B3

>>>right
  key1 key2   C   D
0   K0   K0  C0  D0
1   K1   K0  C1  D1
2   K1   K0  C2  D2
3   K2   K0  C3  D3

#how = 'inner, outer, left, right',默認how = 'inner' 
>>>res = pd.merge(right, left, on = ['key1', 'key2'])
  key1 key2   C   D   A   B
0   K0   K0  C0  D0  A0  B0
1   K1   K0  C1  D1  A2  B2
2   K1   K0  C2  D2  A2  B2

>>>res = pd.merge(right, left, on = ['key1', 'key2'], how = 'outer')
>>>res
 key1 key2    C    D    A    B
0   K0   K0   C0   D0   A0   B0
1   K1   K0   C1   D1   A2   B2
2   K1   K0   C2   D2   A2   B2
3   K2   K0   C3   D3  NaN  NaN
4   K0   K1  NaN  NaN   A1   B1
5   K2   K1  NaN  NaN   A3   B3

#以右邊的KEY爲準，左邊沒有該Key的值填NaN，有該Key則填相應的值，不計次數
>>>res = pd.merge(left, right, on = ['key1', 'key2'], how = 'right')
>>>res
  key1 key2    A    B   C   D
0   K0   K0   A0   B0  C0  D0
1   K1   K0   A2   B2  C1  D1
2   K1   K0   A2   B2  C2  D2
3   K2   K0  NaN  NaN  C3  D3

>>>dataframe1
   col1 col_left
0     0        a
1     1        b

>>>dataframe2
   col1  col_right
0     1          2
1     2          2
2     2          2

#indicator參數會告知你哪邊有值哪邊沒值，默認indicator
>>>res = pd.merge(df1, df2, on = 'col1', how = 'outer', indicator = 'indicator_label')
>>>res
   col1 col_left  col_right indicator_label
0     0        a        NaN       left_only
1     1        b        2.0            both
2     2      NaN        2.0      right_only
3     2      NaN        2.0      right_only

>>>left
     A   B
K0  A0  B0
K1  A1  B1
K2  A2  B2
>>>right
     C   D
K0  C0  D0
K2  C2  D2
K3  C3  D3

>>>pd.merge(left, right, left_index=True, right_index=True, how = 'outer')
      A    B    C    D
K0   A0   B0   C0   D0
K1   A1   B1  NaN  NaN
K2   A2   B2   C2   D2
K3  NaN  NaN   C3   D3

#合并重復值
>>>boys
    k  age
0  K0    1
1  K1    2
2  K2    3

>>>girls
    k  age
0  K0    4
1  K0    5
2  K3    6

#suffixes中的字符串和前面的矩陣要一一對應
>>>pd.merge(boys, girls, on = 'k', suffixes = ['_a', '_b'], how = 'inner')
    k  age_a  age_b
0  K0      1      4
1  K0      1      5

7. Pandas plot圖表

#Pandas中Series的plot
>>>data = pd.Series(np.random.randn(1000), index = np.arange(1000))
>>>data = data.cumsum()
>>>data.plot()

#Pandas中DataFrame數據的plot
#plotmethod（plt.scatter）
#'bar', 'hist', 'box', 'kde', 'area', 'scatter', 'hexbin', 'pie'
>>> data = pd.DataFrame(np.random.randn(1000, 4), index = np.arange(1000), columns = list("ABCD"))
>>>data = data.cumsum()
>>>data.plot()

#plt.scatter(x = , y = )
#figure1
>>>data = pd.DataFrame(np.random.randn(1000, 4), index = np.arange(1000), columns = list("ABCD"))
>>>data = data.cumsum()
>>>data.plot.scatter()
#屬性 color,label
>>>data.plot.scatter(x = 'A', y = 'B')

#添加屬性并且在一個圖上打印兩個圖形
#figure2
>>>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)

Ta的文章更多 >>

Python中Pandas模塊的基本操作
0 个评论

Python中Pandas模塊的基本操作

Ta的文章 更多 >>

热门文章

举报内容

检举类型

检举原因

检举说明(必填)

打开微信“扫一扫”，打开网页后点击屏幕右上角分享按钮

Ta的文章更多 >>