1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
| import re
import openpyxl
log = "3.txt"
filename = "tmp.txt"
def process_log():
with open(log, 'r', encoding='GBK') as file:
lines = file.readlines()
required_lines = [line for line in lines if 'sim' in line or 'return productcodes' in line or 'hit' in line or 'start' in line]
with open('tmp.txt', 'w', encoding='GBK') as file:
file.writelines(required_lines)
print("日志预处理完成")
def get_dict_from_line(line):
match = re.search(r'code:(\d+),.*sim:(\d+(\.\d+)?)', line)
return {match.group(1): match.group(2)} if match else None
def get_list_from_per_identify(lines,start_position):
processed_list = []
num = len(lines[start_position - 2].split(",")) - 2
processed_list.append(num)
code = lines[start_position - 1].split(" ")[6]
processed_list.append(code)
hit = lines[start_position + 1].split(",")[1][-2:].strip()
for i in range(start_position - 3, start_position - 9, -1):
if i >= 0:
new_dict = get_dict_from_line(lines[i])
if new_dict:
processed_list.append(new_dict)
return hit, processed_list
def recommend_product_2(data):
max_confidence = float(list(data[0].values())[0])
recommended_codes = [list(item.keys())[0] for item in data if
max_confidence - 0.03 <= float(list(item.values())[0]) <= max_confidence + 0.03]
recommended_codes = list(set(recommended_codes))
return recommended_codes
def recommend_product_3(data):
max_confidence = float(list(data[0].values())[0])
max_confidence_code = list(data[0].keys())[0]
if max_confidence >= 0.96:
result = [max_confidence_code]
elif max_confidence >= 0.88:
if float(list(data[1].values())[0]) >= 0.88:
result = [max_confidence_code, list(data[1].keys())[0]]
else:
result = [max_confidence_code]
elif max_confidence >= 0.8:
if float(list(data[2].values())[0]) >= 0.8:
result = [max_confidence_code, list(data[1].keys())[0], list(data[2].keys())[0]]
elif float(list(data[1].values())[0]) >= 0.8:
result =[max_confidence_code, list(data[1].keys())[0]]
else:
result = [max_confidence_code]
else:
print("未推荐出商品", data)
return []
return list(set(result))
def handle_file(filename):
with open(filename, 'r', encoding="GBK") as file:
lines = file.readlines()
workbook = openpyxl.load_workbook("aa.xlsx")
worksheet = workbook.worksheets[2]
count = 1
start_positions = [idx for idx, line in enumerate(lines) if 'start feed back' in line]
for start_position in start_positions:
hit, identify_list = get_list_from_per_identify(lines, start_position)
if len(identify_list) == 8:
count = count + 1
print(count)
num_0 = identify_list[0]
if hit != "-1":
result_0 = 1
else:
result_0 = 0
result_list = sorted(identify_list[2:], key=lambda x: list(x.values())[0], reverse=True)
code_list_2 = recommend_product_2(result_list)
num_2 = len(code_list_2)
if identify_list[1] in code_list_2:
result_2 = 1
else:
result_2 = 0
code_list_3 = recommend_product_3(result_list)
num_3 = len(code_list_3)
if identify_list[1] in code_list_3:
result_3 = 1
else:
result_3 = 0
worksheet["A{}".format(count)] = str(identify_list[0:2]+result_list)
worksheet["B{}".format(count)] = num_0
worksheet["C{}".format(count)] = result_0
worksheet["D{}".format(count)] = num_2
worksheet["E{}".format(count)] = result_2
worksheet["F{}".format(count)] = num_3
worksheet["G{}".format(count)] = result_3
for i in ['B', 'C', 'D', 'E', 'F', 'G']:
worksheet["{}{}".format(i, (count + 1),)] = "=AVERAGE({}2:{}{})".format(i, i, count)
workbook.save("aa.xlsx")
print("OK")
process_log()
handle_file(filename)
|
