This repository has been archived by the owner on Feb 20, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 10
/
featureVector.html
530 lines (463 loc) · 30.3 KB
/
featureVector.html
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
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
<meta name="generator" content="pdoc 0.10.0" />
<title>mcat.featureVector API documentation</title>
<meta name="description" content="" />
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/styles/github.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/highlight.min.js" integrity="sha256-Uv3H6lx7dJmRfRvH8TH6kJD1TSK1aFcwgx+mdg3epi8=" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>mcat.featureVector</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python"># Copyright 2021 VMware, Inc.
# SPDX-License-Identifier: Apache-2.0
import argparse
import os
from pathlib import Path
import pandas as pd
import utils
from commentAnalysis import CommentAnalyzer
FILE_NAME_SUFFIX = "annotated"
class Featurizer:
def __init__(self, retain_features, analysis_features):
"""
Constructor sets instance variables
Inputs: Retained Features (list) -> pull data features, Analysis Features (list) - > comment analysis features
"""
self.analysis_features = analysis_features
self.retain_pull_features = retain_features
self.raw_filename = ""
self.raw_data = None
self.featurized_data = None
self.commentAnalyzer = None
def readRawData(self, filename):
"""
Function to read raw data stored as csv
Inputs: File location (string) -> input raw data file location
"""
self.raw_filename = filename
self.raw_data = pd.read_csv(filename)
# Convert Comments and Review Comments to dictionary
self.raw_data['Comments'] = self.raw_data['Comments'].apply(lambda comment: utils.string_to_dict(comment))
self.raw_data['Review_Comments'] = self.raw_data['Review_Comments'].apply(
lambda comment: utils.string_to_dict(comment))
def setupCommentAnalyzer(self, filename):
"""
Function to obtain Comment Analyzer with parameters
Inputs: File location (string) -> .txt containing keywords to count
"""
word_list = []
# Open file to obtain list of words in Comment Analzyer
if filename:
with open(filename, 'r') as wordFile:
word_list = wordFile.read().replace(" ", "").strip().split(',')
self.commentAnalyzer = CommentAnalyzer(word_list)
self.analysis_features = self.analysis_features + word_list
print("Comment Analyzer Setup")
def formFeatures(self):
"""
Function to create/export dataset with desired features
Inputs: Name of file to export (string), export flag (boolean)
"""
features = [] # List of rows to convert to dataframe
# Iterate over each pull
for index, row in self.raw_data.iterrows():
row_features = {} # Dictionary to store row features
# Pull Request Features
for feature in self.retain_pull_features:
row_features[feature] = row[feature]
pull_analyzed = self.commentAnalyzer.analyzeComment(row["Body"])
for analysis in pull_analyzed:
row_features["Pull_" + analysis] = pull_analyzed[analysis]
# Comment Features
if len(row['Comments']) > 0:
temp_df_comments = pd.DataFrame(row['Comments'])
all_comment_analysis = []
for comment_index, comment_row in temp_df_comments.iterrows():
all_comment_analysis.append(self.commentAnalyzer.analyzeComment(comment_row["Body"]))
all_comment_analysis = pd.DataFrame(
data=all_comment_analysis) # Form dataset of all individual comment features
# Aggregate comment features
for column in self.analysis_features:
row_features["Comment_Mean_" + column] = all_comment_analysis[column].mean()
row_features["Comment_Median_" + column] = all_comment_analysis[column].median()
row_features["Comment_Mode_" + column] = all_comment_analysis[column].mode()
row_features["Comment_Max_" + column] = all_comment_analysis[column].max()
row_features["Comment_Presence_Count_" + column] = len(
all_comment_analysis[all_comment_analysis[column] > 0.5])
row_features["Comment_Unique_Users"] = len(temp_df_comments["User"].unique())
row_features["First_Comment"] = min(temp_df_comments["Created_At"])
else: # If there are no comment set to none
for column in self.analysis_features:
row_features["Comment_Mean_" + column] = None
row_features["Comment_Median_" + column] = None
row_features["Comment_Mode_" + column] = None
row_features["Comment_Max_" + column] = None
row_features["Comment_Presence_Count_" + column] = None
row_features["Comment_Unique_Users"] = None
row_features["First_Comment"] = None
# Review Features
if len(row['Review_Comments']) > 0:
temp_df_review_comments = pd.DataFrame(row['Review_Comments'])
all_review_comment_analysis = []
for review_comment_index, review_comment_row in temp_df_review_comments.iterrows():
all_review_comment_analysis.append(self.commentAnalyzer.analyzeComment(review_comment_row["Body"]))
all_review_comment_analysis = pd.DataFrame(data=all_review_comment_analysis)
# Aggregate review features
for column in all_review_comment_analysis:
row_features["Review_Comment_Mean_" + column] = all_review_comment_analysis[column].mean()
row_features["Review_Comment_Median_" + column] = all_review_comment_analysis[column].median()
row_features["Review_Comment_Mode_" + column] = all_review_comment_analysis[column].mode()
row_features["Review_Comment_Max_" + column] = all_review_comment_analysis[column].max()
row_features["Review_Comment_Presence_Count_" + column] = len(
all_review_comment_analysis[all_review_comment_analysis[column] > 0.5])
row_features["Review_Comment_Unique_Users"] = len(temp_df_review_comments["User"].unique())
row_features["First_Review_Comment"] = min(temp_df_review_comments["Created_At"])
else: # If there are no reviews set to none
for column in self.analysis_features:
row_features["Review_Comment_Mean_" + column] = None
row_features["Review_Comment_Median_" + column] = None
row_features["Review_Comment_Mode_" + column] = None
row_features["Review_Comment_Max_" + column] = None
row_features["Review_Comment_Presence_Count_" + column] = None
row_features["Review_Comment_Unique_Users"] = None
row_features["First_Review_Comment"] = None
# Add pull features to list of row features
features.append(row_features)
export_df = pd.DataFrame(data=features)
return export_df
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Form features from raw data.')
parser.add_argument('rawdatafile', help='Raw Data Filename')
parser.add_argument('-w', '--words', required=False, help='File containing words to count')
parser.add_argument('-n', '--name', required=False, help='Output file name. If not specified, the name is '
'constructed like this: <rawdatafile>{'
'suffix}.csv'.format(suffix=FILE_NAME_SUFFIX))
args = parser.parse_args()
RETAINED_FEATURES = ["Number", "URL", "Title", "State", "Body", "Deletions", "Additions", "User", "Comments_Num",
"Commits_Num", "Created_At", "Closed_At", "Merged", "Merged_At", "Review_Comments_Num"]
COMMENT_ANALYSIS_FEATURES = ["Sentiment", "Code Blocks"]
featurizer = Featurizer(RETAINED_FEATURES, COMMENT_ANALYSIS_FEATURES)
featurizer.readRawData(args.rawdatafile)
featurizer.setupCommentAnalyzer(args.words)
df = featurizer.formFeatures()
file_name = utils.construct_file_name(args.name, args.rawdatafile, FILE_NAME_SUFFIX)
utils.export_to_cvs(df, file_name)</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-classes">Classes</h2>
<dl>
<dt id="mcat.featureVector.Featurizer"><code class="flex name class">
<span>class <span class="ident">Featurizer</span></span>
<span>(</span><span>retain_features, analysis_features)</span>
</code></dt>
<dd>
<div class="desc"><p>Constructor sets instance variables
Inputs: Retained Features (list) -> pull data features, Analysis Features (list) - > comment analysis features</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class Featurizer:
def __init__(self, retain_features, analysis_features):
"""
Constructor sets instance variables
Inputs: Retained Features (list) -> pull data features, Analysis Features (list) - > comment analysis features
"""
self.analysis_features = analysis_features
self.retain_pull_features = retain_features
self.raw_filename = ""
self.raw_data = None
self.featurized_data = None
self.commentAnalyzer = None
def readRawData(self, filename):
"""
Function to read raw data stored as csv
Inputs: File location (string) -> input raw data file location
"""
self.raw_filename = filename
self.raw_data = pd.read_csv(filename)
# Convert Comments and Review Comments to dictionary
self.raw_data['Comments'] = self.raw_data['Comments'].apply(lambda comment: utils.string_to_dict(comment))
self.raw_data['Review_Comments'] = self.raw_data['Review_Comments'].apply(
lambda comment: utils.string_to_dict(comment))
def setupCommentAnalyzer(self, filename):
"""
Function to obtain Comment Analyzer with parameters
Inputs: File location (string) -> .txt containing keywords to count
"""
word_list = []
# Open file to obtain list of words in Comment Analzyer
if filename:
with open(filename, 'r') as wordFile:
word_list = wordFile.read().replace(" ", "").strip().split(',')
self.commentAnalyzer = CommentAnalyzer(word_list)
self.analysis_features = self.analysis_features + word_list
print("Comment Analyzer Setup")
def formFeatures(self):
"""
Function to create/export dataset with desired features
Inputs: Name of file to export (string), export flag (boolean)
"""
features = [] # List of rows to convert to dataframe
# Iterate over each pull
for index, row in self.raw_data.iterrows():
row_features = {} # Dictionary to store row features
# Pull Request Features
for feature in self.retain_pull_features:
row_features[feature] = row[feature]
pull_analyzed = self.commentAnalyzer.analyzeComment(row["Body"])
for analysis in pull_analyzed:
row_features["Pull_" + analysis] = pull_analyzed[analysis]
# Comment Features
if len(row['Comments']) > 0:
temp_df_comments = pd.DataFrame(row['Comments'])
all_comment_analysis = []
for comment_index, comment_row in temp_df_comments.iterrows():
all_comment_analysis.append(self.commentAnalyzer.analyzeComment(comment_row["Body"]))
all_comment_analysis = pd.DataFrame(
data=all_comment_analysis) # Form dataset of all individual comment features
# Aggregate comment features
for column in self.analysis_features:
row_features["Comment_Mean_" + column] = all_comment_analysis[column].mean()
row_features["Comment_Median_" + column] = all_comment_analysis[column].median()
row_features["Comment_Mode_" + column] = all_comment_analysis[column].mode()
row_features["Comment_Max_" + column] = all_comment_analysis[column].max()
row_features["Comment_Presence_Count_" + column] = len(
all_comment_analysis[all_comment_analysis[column] > 0.5])
row_features["Comment_Unique_Users"] = len(temp_df_comments["User"].unique())
row_features["First_Comment"] = min(temp_df_comments["Created_At"])
else: # If there are no comment set to none
for column in self.analysis_features:
row_features["Comment_Mean_" + column] = None
row_features["Comment_Median_" + column] = None
row_features["Comment_Mode_" + column] = None
row_features["Comment_Max_" + column] = None
row_features["Comment_Presence_Count_" + column] = None
row_features["Comment_Unique_Users"] = None
row_features["First_Comment"] = None
# Review Features
if len(row['Review_Comments']) > 0:
temp_df_review_comments = pd.DataFrame(row['Review_Comments'])
all_review_comment_analysis = []
for review_comment_index, review_comment_row in temp_df_review_comments.iterrows():
all_review_comment_analysis.append(self.commentAnalyzer.analyzeComment(review_comment_row["Body"]))
all_review_comment_analysis = pd.DataFrame(data=all_review_comment_analysis)
# Aggregate review features
for column in all_review_comment_analysis:
row_features["Review_Comment_Mean_" + column] = all_review_comment_analysis[column].mean()
row_features["Review_Comment_Median_" + column] = all_review_comment_analysis[column].median()
row_features["Review_Comment_Mode_" + column] = all_review_comment_analysis[column].mode()
row_features["Review_Comment_Max_" + column] = all_review_comment_analysis[column].max()
row_features["Review_Comment_Presence_Count_" + column] = len(
all_review_comment_analysis[all_review_comment_analysis[column] > 0.5])
row_features["Review_Comment_Unique_Users"] = len(temp_df_review_comments["User"].unique())
row_features["First_Review_Comment"] = min(temp_df_review_comments["Created_At"])
else: # If there are no reviews set to none
for column in self.analysis_features:
row_features["Review_Comment_Mean_" + column] = None
row_features["Review_Comment_Median_" + column] = None
row_features["Review_Comment_Mode_" + column] = None
row_features["Review_Comment_Max_" + column] = None
row_features["Review_Comment_Presence_Count_" + column] = None
row_features["Review_Comment_Unique_Users"] = None
row_features["First_Review_Comment"] = None
# Add pull features to list of row features
features.append(row_features)
export_df = pd.DataFrame(data=features)
return export_df</code></pre>
</details>
<h3>Methods</h3>
<dl>
<dt id="mcat.featureVector.Featurizer.formFeatures"><code class="name flex">
<span>def <span class="ident">formFeatures</span></span>(<span>self)</span>
</code></dt>
<dd>
<div class="desc"><p>Function to create/export dataset with desired features
Inputs: Name of file to export (string), export flag (boolean)</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def formFeatures(self):
"""
Function to create/export dataset with desired features
Inputs: Name of file to export (string), export flag (boolean)
"""
features = [] # List of rows to convert to dataframe
# Iterate over each pull
for index, row in self.raw_data.iterrows():
row_features = {} # Dictionary to store row features
# Pull Request Features
for feature in self.retain_pull_features:
row_features[feature] = row[feature]
pull_analyzed = self.commentAnalyzer.analyzeComment(row["Body"])
for analysis in pull_analyzed:
row_features["Pull_" + analysis] = pull_analyzed[analysis]
# Comment Features
if len(row['Comments']) > 0:
temp_df_comments = pd.DataFrame(row['Comments'])
all_comment_analysis = []
for comment_index, comment_row in temp_df_comments.iterrows():
all_comment_analysis.append(self.commentAnalyzer.analyzeComment(comment_row["Body"]))
all_comment_analysis = pd.DataFrame(
data=all_comment_analysis) # Form dataset of all individual comment features
# Aggregate comment features
for column in self.analysis_features:
row_features["Comment_Mean_" + column] = all_comment_analysis[column].mean()
row_features["Comment_Median_" + column] = all_comment_analysis[column].median()
row_features["Comment_Mode_" + column] = all_comment_analysis[column].mode()
row_features["Comment_Max_" + column] = all_comment_analysis[column].max()
row_features["Comment_Presence_Count_" + column] = len(
all_comment_analysis[all_comment_analysis[column] > 0.5])
row_features["Comment_Unique_Users"] = len(temp_df_comments["User"].unique())
row_features["First_Comment"] = min(temp_df_comments["Created_At"])
else: # If there are no comment set to none
for column in self.analysis_features:
row_features["Comment_Mean_" + column] = None
row_features["Comment_Median_" + column] = None
row_features["Comment_Mode_" + column] = None
row_features["Comment_Max_" + column] = None
row_features["Comment_Presence_Count_" + column] = None
row_features["Comment_Unique_Users"] = None
row_features["First_Comment"] = None
# Review Features
if len(row['Review_Comments']) > 0:
temp_df_review_comments = pd.DataFrame(row['Review_Comments'])
all_review_comment_analysis = []
for review_comment_index, review_comment_row in temp_df_review_comments.iterrows():
all_review_comment_analysis.append(self.commentAnalyzer.analyzeComment(review_comment_row["Body"]))
all_review_comment_analysis = pd.DataFrame(data=all_review_comment_analysis)
# Aggregate review features
for column in all_review_comment_analysis:
row_features["Review_Comment_Mean_" + column] = all_review_comment_analysis[column].mean()
row_features["Review_Comment_Median_" + column] = all_review_comment_analysis[column].median()
row_features["Review_Comment_Mode_" + column] = all_review_comment_analysis[column].mode()
row_features["Review_Comment_Max_" + column] = all_review_comment_analysis[column].max()
row_features["Review_Comment_Presence_Count_" + column] = len(
all_review_comment_analysis[all_review_comment_analysis[column] > 0.5])
row_features["Review_Comment_Unique_Users"] = len(temp_df_review_comments["User"].unique())
row_features["First_Review_Comment"] = min(temp_df_review_comments["Created_At"])
else: # If there are no reviews set to none
for column in self.analysis_features:
row_features["Review_Comment_Mean_" + column] = None
row_features["Review_Comment_Median_" + column] = None
row_features["Review_Comment_Mode_" + column] = None
row_features["Review_Comment_Max_" + column] = None
row_features["Review_Comment_Presence_Count_" + column] = None
row_features["Review_Comment_Unique_Users"] = None
row_features["First_Review_Comment"] = None
# Add pull features to list of row features
features.append(row_features)
export_df = pd.DataFrame(data=features)
return export_df</code></pre>
</details>
</dd>
<dt id="mcat.featureVector.Featurizer.readRawData"><code class="name flex">
<span>def <span class="ident">readRawData</span></span>(<span>self, filename)</span>
</code></dt>
<dd>
<div class="desc"><p>Function to read raw data stored as csv
Inputs: File location (string) -> input raw data file location</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def readRawData(self, filename):
"""
Function to read raw data stored as csv
Inputs: File location (string) -> input raw data file location
"""
self.raw_filename = filename
self.raw_data = pd.read_csv(filename)
# Convert Comments and Review Comments to dictionary
self.raw_data['Comments'] = self.raw_data['Comments'].apply(lambda comment: utils.string_to_dict(comment))
self.raw_data['Review_Comments'] = self.raw_data['Review_Comments'].apply(
lambda comment: utils.string_to_dict(comment))</code></pre>
</details>
</dd>
<dt id="mcat.featureVector.Featurizer.setupCommentAnalyzer"><code class="name flex">
<span>def <span class="ident">setupCommentAnalyzer</span></span>(<span>self, filename)</span>
</code></dt>
<dd>
<div class="desc"><p>Function to obtain Comment Analyzer with parameters
Inputs: File location (string) -> .txt containing keywords to count</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def setupCommentAnalyzer(self, filename):
"""
Function to obtain Comment Analyzer with parameters
Inputs: File location (string) -> .txt containing keywords to count
"""
word_list = []
# Open file to obtain list of words in Comment Analzyer
if filename:
with open(filename, 'r') as wordFile:
word_list = wordFile.read().replace(" ", "").strip().split(',')
self.commentAnalyzer = CommentAnalyzer(word_list)
self.analysis_features = self.analysis_features + word_list
print("Comment Analyzer Setup")</code></pre>
</details>
</dd>
</dl>
</dd>
</dl>
</section>
</article>
<nav id="sidebar">
<h1>Index</h1>
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3>Super-module</h3>
<ul>
<li><code><a title="mcat" href="index.html">mcat</a></code></li>
</ul>
</li>
<li><h3><a href="#header-classes">Classes</a></h3>
<ul>
<li>
<h4><code><a title="mcat.featureVector.Featurizer" href="#mcat.featureVector.Featurizer">Featurizer</a></code></h4>
<ul class="">
<li><code><a title="mcat.featureVector.Featurizer.formFeatures" href="#mcat.featureVector.Featurizer.formFeatures">formFeatures</a></code></li>
<li><code><a title="mcat.featureVector.Featurizer.readRawData" href="#mcat.featureVector.Featurizer.readRawData">readRawData</a></code></li>
<li><code><a title="mcat.featureVector.Featurizer.setupCommentAnalyzer" href="#mcat.featureVector.Featurizer.setupCommentAnalyzer">setupCommentAnalyzer</a></code></li>
</ul>
</li>
</ul>
</li>
</ul>
</nav>
</main>
<footer id="footer">
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
</footer>
</body>
</html>