-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathCompany categorization.py
More file actions
345 lines (172 loc) · 8.69 KB
/
Company categorization.py
File metadata and controls
345 lines (172 loc) · 8.69 KB
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
import openpyxl
import numpy as np
import datetime
import pandas as pd
import os
import glob
import re
## Import files from a folder:
# Ask the user for the location path of the files.
def Read_multipleFiles ():
file_path = input('Enter a file path: ')
file_type = input('Define a file type (Excel, csv): ')
# Use os to get all the files in the folder
if file_type.lower() == "excel":
if os.path.exists(file_path):
files_xlsx = glob.glob(os.path.join(file_path, "*.xlsx"))
df = []
# Loop over list of files to append to empty dataframe:
df = pd.concat((pd.read_excel(f) for f in files_xlsx), ignore_index=True)
df.fillna('EMPTY', inplace=True)
#Erase duplicates in the dataframe.
Datos = df.drop_duplicates(keep="first")
Dup = len(df) - len(Datos)
print(Dup,"duplicates removed")
Datos.to_excel(file_path + "\DD.xlsx", index= False)
if len(files_xlsx) == 1:
print("There is", len(files_xlsx),"file in the folder")
else:
print("There are", len(files_xlsx),"files in the folder")
else:
print('The specified file path does NOT exist')
print(files_xlsx)
elif file_type.lower == "csv":
if os.path.exists(file_path):
files_csv = glob.glob(os.path.join(file_path, "*.csv"))
df = []
# Loop over list of files to append to empty dataframe:
df = pd.concat((pd.read_csv(f,sheet_name= "Results") for f in files_csv), ignore_index=True)
df.fillna('EMPTY', inplace=True)
#Erase duplicates in the dataframe.
Datos = df.drop_duplicates(keep="first")
Dup = len(df) - len(Datos)
print(Dup,"duplicates removed")
Datos.to_csv(file_path + "\DD.xlsx", index= False)
if len(files_csv) == 1:
print("There is", len(files_csv),"file in the folder")
else:
print("There are", len(files_csv),"files in the folder")
else:
print('The specified file path does NOT exist')
print(files_csv)
## Exporting dataframe in an excel file:
# Export the dataframe in an excel file at the same location path where we got the files.
Read_multipleFiles ()
def Cortellis_ATCtagging():
file_path = input("Enter a file path with your files: ")
Datos = pd.read_excel(file_path + "\DD.xlsx")
# Iteration through each row on the dataframe and appending to each list the right tag for "Type of active substance" and "Category" for each drug.
Type = []
Size =[]
# For loop to iterate through the columns of interest in the data frame
for colums,rows in Datos.iterrows():
if "center" in str(rows["Company Name"]).lower() or "centre" in str(rows["Company Name"]).lower() or "zentrum" in str(rows["Company Name"]).lower() or re.search("institut", str(rows["Company Name"]).lower()) or "istituto" in str(rows["Company Name"]).lower():
Type.append("Other")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
elif re.search("universit", str(rows["Company Name"]).lower()) or "hospital" in str(rows["Company Name"]).lower() or "foundation" in str(rows["Company Name"]).lower() :
Type.append("Working")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
elif re.search("company", str(rows["Organization Type"]).lower()):
if "Academic/Research" in str(rows["Field of Activity"]) or "Not for Profit" in str(rows["Field of Activity"]) or "Government Agency" in str(rows["Field of Activity"]):
Type.append("Non-profit")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
else:
Type.append("Profit")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
elif "Other" in str(rows["Organization Type"]):
if "Academic/Research" in str(rows["Field of Activity"]) or "Not for Profit" in str(rows["Field of Activity"]) or "Government Agency" in str(rows["Field of Activity"]):
Type.append("Non-profit")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
else:
Type.append("Other")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
elif "Non-Profit" in str(rows["Organization Type"]) or "Academic" in str(rows["Organization Type"]):
Type.append("Non-profit")
if "Large" in str(rows["Organization Type"]):
Size.append("Large")
elif "Medium" in str(rows["Organization Type"]):
Size.append("Medium")
elif "Mega" in str(rows["Organization Type"]):
Size.append("Mega")
elif "Small" in str(rows["Organization Type"]):
Size.append("Small")
elif "Micro" in str(rows["Organization Type"]):
Size.append("Micro")
else:
Size.append("Other")
else:
Size.append("Other")
Type.append("Other")
Datos["Company Type"] = Type
Datos["Company Size"] = Size
Datos.replace('EMPTY',"", inplace=True)
## Exporting dataframe in an excel file:
# Export the dataframe in an excel file at the same location path where we got the files.
Datos.to_excel(file_path + "\CompanytagsTest.xlsx", index= False)
Cortellis_ATCtagging()