python - 使用 dataframe python 以矩阵格式显示列

Question

我有下表

我想使用 python 将 int 转换为矩阵，如下所示:

我能得到一些关于从哪里开始的指导吗？我使用 pandas 读取两个数据帧并将它们合并以创建我显示的初始表(一个有两列)。

我正在使用的代码如下:

import pandas as pd
from pyexcelerate import Workbook
import numpy as np
import time
start = time.process_time()
excel_file = 'Test.xlsx'
df = pd.read_excel(excel_file, sheet_name=0, index_col=0)
print(df.columns)
print(df.index)

newdf= (df.pivot(index='ColumnB',columns='ColumnA', values='ColumnB'))
myNewDF = newdf.transform(lambda x: np.where(x.isnull(), '', 'yes'))
aftercalc = time.process_time()
print(aftercalc - start)

myNewDF.to_excel("1.xlsx")
print(time.process_time() - aftercalc)

打印的输出是:

Index(['ColumnB'], dtype='object') Index(['TypeA', 'TypeA', 'TypeA', 'TypeA', 'TypeA', 'TypeB', 'TypeB', 'TypeC', 'TypeC', 'TypeC', 'TypeD'], dtype='object', name='ColumnA')

运行时遇到的错误是:

Traceback (most recent call last): File "C:_data\learn\Miniconda\lib\site-packages\pandas\core\indexes\base.py", line 2657, in get_loc return self._engine.get_loc(key) File "pandas/_libs/index.pyx", line 108, in pandas._libs.index.IndexEngine.get_loc File "pandas/_libs/index.pyx", line 132, in pandas._libs.index.IndexEngine.get_loc File "pandas/_libs/hashtable_class_helper.pxi", line 1601, in pandas._libs.hashtable.PyObjectHashTable.get_item File "pandas/_libs/hashtable_class_helper.pxi", line 1608, in pandas._libs.hashtable.PyObjectHashTable.get_item KeyError: 'ColumnA'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "test.py", line 10, in newdf= (df.pivot(index='ColumnB',columns='ColumnA', values='ColumnB')) File "C:_data\learn\Miniconda\lib\site-packages\pandas\core\frame.py", line 5628, in pivot return pivot(self, index=index, columns=columns, values=values) File "C:_data\learn\Miniconda\lib\site-packages\pandas\core\reshape\pivot.py", line 379, in pivot index = MultiIndex.from_arrays([index, data[columns]]) File "C:_data\learn\Miniconda\lib\site-packages\pandas\core\frame.py", line 2927, in getitem indexer = self.columns.get_loc(key) File "C:_data\learn\Miniconda\lib\site-packages\pandas\core\indexes\base.py", line 2659, in get_loc return self._engine.get_loc(self._maybe_cast_indexer(key)) File "pandas/_libs/index.pyx", line 108, in pandas._libs.index.IndexEngine.get_loc File "pandas/_libs/index.pyx", line 132, in pandas._libs.index.IndexEngine.get_loc File "pandas/_libs/hashtable_class_helper.pxi", line 1601, in pandas._libs.hashtable.PyObjectHashTable.get_item File "pandas/_libs/hashtable_class_helper.pxi", line 1608, in pandas._libs.hashtable.PyObjectHashTable.get_item

Answer 1

这样可以解决吗？

newdf= (df.pivot(index='ColumnB',columns='ColumnA', values='ColumnB'))

newdf
Out[28]: 
ColumnA TypeA TypeB TypeC TypeD
ColumnB                        
A           A     A   NaN     A
B           B   NaN     B   NaN
C           C   NaN     C   NaN
D           D   NaN   NaN   NaN
E           E   NaN   NaN   NaN
F         NaN     F   NaN   NaN
Z         NaN   NaN     Z   NaN

newdf.transform(lambda x: np.where(x.isnull(), '', 'yes'))
Out[29]: 
ColumnA TypeA TypeB TypeC TypeD
ColumnB                        
A         yes   yes         yes
B         yes         yes      
C         yes         yes      
D         yes                  
E         yes                  
F               yes            
Z                     yes      

修改后的代码

import pandas as pd
#from pyexcelerate import Workbook
import time
import numpy as np
start = time.process_time()
excel_file = 'C:\\Users\\ss\\Desktop\\check.xlsx'
df = pd.read_excel(excel_file, sheet_name=0, index_col=0)
print(df.columns)
print(df.index)

newdf= (df.pivot(index='ColumnB',columns='ColumnA', values='ColumnB'))
myNewDF = newdf.transform(lambda x: np.where(x.isnull(), '', 'yes'))
aftercalc = time.process_time()
print(aftercalc - start)

myNewDF.to_excel("C:\\Users\\ss\\Desktop\\output.xlsx")