-
Notifications
You must be signed in to change notification settings - Fork 13
/
Copy pathexample_procesing.py
208 lines (197 loc) · 8.8 KB
/
example_procesing.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
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
"""
This program first identifies valid MD&A sections and then computes the tone of these sections. The final output file will by
SampleData.txt and it is saved in the file that you designate as filepath3.
"""
import csv
import os
import re
#This is the filepath of the Financial Statement text documents. This must be changed to your respective filepath.
filepath="statements"
#This is the filepath of the word dictionary files. This must be changed to your respective filepath.
filepath2="Word Dictionaries"
#This is where you would like the cleaned / identied MD&A section text files to be written. This file must also include the
#downloadlog file from the previously run MASTERSCRAPE.py program.
filepath3="statements"
#NEGATIVE=os.path.join(filepath2,"NEGATIVE.txt")
#POSITIVE=os.path.join(filepath2,"POSITIVE.txt")
SD=os.path.join(filepath3,"SampleData.csv")
download=os.path.join(filepath3,"DOWNLOADLOG_all.txt")
with open(SD,'w') as f:
f.write("File,CompanyName,CIK,SIC,ReportDate,Section,TotalWords,NumOrg,NumAcq\n")
'''
This section will upload the dictionaries
'''
#NEGATIVE=open(NEGATIVE, 'r').readlines()
#NEGATIVE=map(str.strip, NEGATIVE)
#NEGATIVE=[x.lower() for x in NEGATIVE]
#POSITIVE=open(POSITIVE, 'r').readlines()
#POSITIVE=map(str.strip, POSITIVE)
#POSITIVE=[x.lower() for x in POSITIVE]
'''
DONE
'''
'''
The following are the phrases that must be identified for a particular section to be considered a MD&A section.
'''
sayings=["the following discussion","this discussion and analysis","should be read in conjunction", "should be read together with", "the following managements discussion and analysis"]
acq=["proprietary","intellectual","patent","trademark","intangible","technology"]
personnel = ["key personnel", "personnel","talented employee", "key talent"]
'''
DONE
'''
'''
Beginning of the program
'''
with open(download, 'r') as txtfile:
reader = csv.reader(txtfile, delimiter='\t')
next(reader, None)
for line in reader:
FileNUM=line[0].strip()
Sections=int(line[1].strip())
if Sections!=0:
Filer=os.path.join(filepath,str(FileNUM))
CLEAN=os.path.join(filepath3,str(FileNUM))
SIC=""
Info=[str(FileNUM)]
hand=open(Filer)
for line in hand:
line=line.strip()
if re.findall('^COMPANY NAME:',line):
COMNAM=line.replace("COMPANY NAME: ","")
COMNAM='"{}"'.format(COMNAM)
if re.findall('^CIK:',line):
CIK=line.replace("CIK: ","")
if re.findall('^SIC:',line):
SIC=line.replace("SIC: ","")
if re.findall('^REPORT PERIOD END DATE:',line):
REPDATE=line.replace("REPORT PERIOD END DATE: ","")
Info.append(COMNAM)
Info.append(CIK)
if SIC=="":
SIC='9999'
Info.append(SIC)
else:
Info.append(SIC)
Info.append(REPDATE)
Info.append(str(Sections))
str1=open(Filer).read()
locations=[]
for m in re.finditer("<SECTION>",str1):
a=m.end()
locations.append(a)
for m in re.finditer("</SECTION>",str1):
a=m.start()
locations.append(a)
if locations!=[]:
locations.sort()
if Sections==1:
substring1=str1[locations[0]:locations[1]]
substring1=substring1.lower()
substring1=re.sub('\d','',substring1)
substring1=substring1.replace(',','')
substring1=substring1.replace(':',' ')
substring1=substring1.replace('?','')
substring1=substring1.replace('.','')
substring1=substring1.replace('$','')
substring1=substring1.replace('(','')
substring1=substring1.replace(')','')
substring1=substring1.replace('%','')
substring1=substring1.replace('"','')
substring1=substring1.replace('-',' ')
substring1=substring1.replace('[','')
substring1=substring1.replace(';',' ')
substring1=substring1.replace(']','')
substring1=substring1.replace('_','')
substring1=substring1.replace('|','')
substring1=substring1.replace('/','')
substring1=substring1.replace('`','')
substring1=substring1.replace("'",'')
substring1=substring1.replace('&','')
substring1=substring1.split()
TWORD=0
TWORD=len(substring1)
Post=[]
Post.extend(Info)
Post.append(str(TWORD))
# PLUS=0
ORG=0
ACQ=0
for s in substring1:
if s in personnel:
ORG=ORG+1
if s in acq:
ACQ=ACQ+1
#Post.append(str(PLUS))
Post.append(str(ORG))
Post.append(str(ACQ))
with open(CLEAN,'a') as f:
f.write("<SECTION>\n")
f.write(' '.join(substring1)+"\n")
f.write("</SECTION>\n")
f.close()
with open(SD,'a') as f:
f.write(','.join(Post)+'\n')
f.close
print(Post)
Post=[]
else:
for k in range(0,len(locations),2):
filed=0
substring1=str1[locations[0+k]:locations[1+k]]
substring1=substring1.lower()
substring1=substring1.split(". ")
if len(substring1)>5:
for j in range(0,6):
if any(s in substring1[j] for s in sayings):
filed=1
break
if filed==1:
substring1=str1[locations[0+k]:locations[1+k]]
substring1=substring1.lower()
substring1=re.sub('\d','',substring1)
substring1=substring1.replace(',','')
substring1=substring1.replace(':',' ')
substring1=substring1.replace('?','')
substring1=substring1.replace('.','')
substring1=substring1.replace('$','')
substring1=substring1.replace('(','')
substring1=substring1.replace(')','')
substring1=substring1.replace('%','')
substring1=substring1.replace('"','')
substring1=substring1.replace('-',' ')
substring1=substring1.replace('[','')
substring1=substring1.replace(';',' ')
substring1=substring1.replace(']','')
substring1=substring1.replace('_','')
substring1=substring1.replace('|','')
substring1=substring1.replace('/','')
substring1=substring1.replace('`','')
substring1=substring1.replace("'",'')
substring1=substring1.replace('&','')
substring1=substring1.split()
TWORD=0
TWORD=len(substring1)
Post=[]
Post.extend(Info)
Post.append(str(TWORD))
#PLUS=0
ORG=0
ACQ=0
for s in substring1:
if s in personnel:
ORG=ORG+1
if s in acq:
ACQ=ACQ+1
#Post.append(str(PLUS))
Post.append(str(ORG))
Post.append(str(ACQ))
with open(CLEAN,'a') as f:
f.write("<SECTION>\n")
f.write(' '.join(substring1)+"\n")
f.write("</SECTION>\n")
f.close()
with open(SD,'a') as f:
f.write(','.join(Post)+'\n')
f.close
print(Post)
Post=[]