-
Notifications
You must be signed in to change notification settings - Fork 0
/
Vendor_Check.py
53 lines (36 loc) · 1.87 KB
/
Vendor_Check.py
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
from __future__ import unicode_literals, print_function
import spacy
from PySide6 import QtCore
from PySide6.QtWidgets import QApplication
import time
class Vendor_Check(QtCore.QThread):
#This is the signal that will be emitted during the processing.
#By including int as an argument, it lets the signal know to expect
#an integer argument when emitting.
updateProgress = QtCore.Signal(int)
# Train the spacy program
# Getting the pipeline component
def create_model(self):
try:
nlp = spacy.load("ner") # load folder ner trong thư mục chương trình (model)
return nlp
except:
nlp = spacy.load("en_core_web_lg") # Load thư viện gốc
return nlp
# initial_data = pd.read_excel(r"C:\Users\ADMIN\Documents\Aufinia\Data_Test.xlsx",sheet_name='Euro', converters={'LFA1_LIFNR':str,'LFA1_STCD1':str},usecols={'LFA1_LIFNR','LFA1_NAME1','COUNTRY','LFA1_STCD1','LFA1_LAND1'})
def classify_execution(self, df_company):
df_require_col = df_company[['Supplier_number','Supplier_name','Country','Tax_code','Country_code']]
nlp = self.create_model() # tạo ra một nlp object từ hàm create model
for idx in range(len(df_require_col)):
label_EN = ''
Supplier_name = df_require_col.loc[idx, "Supplier_name"]
doc = nlp(Supplier_name)
for ent in doc.ents:
label_EN = label_EN + ent.label_ + '/'
df_require_col.loc[idx, "Supplier label"] = label_EN
df_require_col["Supplier label"] = df_require_col["Supplier label"].fillna('Not determined')
# emit signal to main_GUI
QApplication.processEvents()
self.updateProgress.emit(((idx+1) * 100)/len(df_require_col))
time.sleep(0.1)
return df_require_col