python-数据处理

import pandas  as pd

# 读取整个csv文件
path='C:/Users/18578/Desktop/testCF.csv'
orgin_data = pd.read_csv(path,header=None)

items=orgin_data.iloc[:,1].drop_duplicates().sort_values()
user=orgin_data.iloc[:,0].drop_duplicates().sort_values()
print(items)
print(user)

0     101
1     102
2     103
6     104
9     105
14    106
10    107
Name: 1, dtype: int64
0     A1
3     A2
7     B3
11    C4
15    D5
Name: 0, dtype: object

import numpy as np
item_list=[]
user_list=[]
for i in items:
    item_list.append(i)
for j in user:
    user_list.append(j) 

print(item_list)
print(user_list)

[101, 102, 103, 104, 105, 106, 107]
['A1', 'A2', 'B3', 'C4', 'D5']

import numpy as np
#创建一个Dataframe
new_data=pd.DataFrame(np.arange(35).reshape(len(user_list),len(item_list)),index=user_list,columns=item_list)
# data=np.array(new_data)
new_data.loc[:,:] = 0
print(new_data)

    101  102  103  104  105  106  107
A1    0    0    0    0    0    0    0
A2    0    0    0    0    0    0    0
B3    0    0    0    0    0    0    0
C4    0    0    0    0    0    0    0
D5    0    0    0    0    0    0    0

with open(path,encoding = 'utf-8') as f:
    list_data = np.loadtxt(f,str,delimiter = ",") 
print(list_data)

[['A1' '101' '5']
 ['A1' '102' '3']
 ['A1' '103' '2.5']
 ['A2' '101' '2']
 ['A2' '102' '2.5']
 ['A2' '103' '5']
 ['A2' '104' '2']
 ['B3' '101' '2.5']
 ['B3' '104' '4']
 ['B3' '105' '4.5']
 ['B3' '107' '5']
 ['C4' '101' '5']
 ['C4' '103' '3']
 ['C4' '104' '4.5']
 ['C4' '106' '4']
 ['D5' '101' '4']
 ['D5' '102' '3']
 ['D5' '103' '2']
 ['D5' '104' '4']
 ['D5' '105' '3.5']
 ['D5' '106' '4']]

# print(new_data.loc['A1',101])
for i in list_data:
    for j in new_data.columns.values:
        for k in new_data.index.values:
             if(i[1]==str(j) and i[0]==str(k)):
                print(i,j,k)
                new_data.loc[str(k),j]=i[2]

['A1' '101' '5'] 101 A1
['A1' '102' '3'] 102 A1
['A1' '103' '2.5'] 103 A1
['A2' '101' '2'] 101 A2
['A2' '102' '2.5'] 102 A2
['A2' '103' '5'] 103 A2
['A2' '104' '2'] 104 A2
['B3' '101' '2.5'] 101 B3
['B3' '104' '4'] 104 B3
['B3' '105' '4.5'] 105 B3
['B3' '107' '5'] 107 B3
['C4' '101' '5'] 101 C4
['C4' '103' '3'] 103 C4
['C4' '104' '4.5'] 104 C4
['C4' '106' '4'] 106 C4
['D5' '101' '4'] 101 D5
['D5' '102' '3'] 102 D5
['D5' '103' '2'] 103 D5
['D5' '104' '4'] 104 D5
['D5' '105' '3.5'] 105 D5
['D5' '106' '4'] 106 D5

print(new_data)

    101  102  103  104  105 106 107
A1    5    3  2.5    0    0   0   0
A2    2  2.5    5    2    0   0   0
B3  2.5    0    0    4  4.5   0   5
C4    5    0    3  4.5    0   4   0
D5    4    3    2    4  3.5   4   0