tanish78 commited on
Commit
34d2248
·
verified ·
1 Parent(s): 1927724

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +31 -46
app.py CHANGED
@@ -10,58 +10,41 @@ import matplotlib.pyplot as plt
10
  import plotly.express as px
11
  from PIL import Image
12
 
13
- # Define categories
14
  categories_keywords = {
15
- "Application Status": ["application status", "application", "status", "submitted", "processing", "pending", "approval", "rejected", "accepted"],
16
- "Volunteering": ["volunteer", "volunteering", "help out", "assist", "volunteer work", "volunteer opportunities"],
17
- "Certificates": ["certificate", "certificates", "completion", "certification", "accreditation", "proof", "document", "certified"],
18
- "Job Opportunities": ["job", "opportunity", "career", "vacancy", "position", "employment", "hiring", "recruitment", "internship"],
19
- "Surveys and Forms": ["survey", "form", "forms", "questionnaire", "feedback form", "response", "fill out", "submission"],
20
- "General Queries": ["hello", "hi", "help", "general", "query", "question", "info", "information", "inquiry", "ask"],
21
- "Spam": ["spam", "unsubscribe", "remove", "stop", "junk", "block", "opt-out"],
22
- "Rescheduling and Postponing": ["reschedule", "postpone", "delay", "change date", "new time", "rearrange", "shift", "adjust timing"],
23
- "Contact and Communication Issues": ["contact", "communicate", "communication", "reach out", "phone", "email", "address", "details"],
24
- "Email and Credentials Issues": ["email", "credentials", "login", "password", "access", "username", "account", "verification", "reset"],
25
- "Timing and Scheduling": ["timing", "schedule", "scheduling", "time", "appointment", "availability", "calendar", "book", "slot"],
26
- "Salary and Benefits": ["salary", "benefits", "pay", "compensation", "wages", "earnings", "package", "remuneration", "incentives"],
27
- "Technical Issues": ["technical", "issue", "problem", "error", "bug", "glitch", "fix", "troubleshoot", "support"],
28
- "End of Conversation": ["bye", "thank you", "thanks", "goodbye", "see you", "later", "end", "close", "sign off"],
29
- "Start of Conversation": ["start", "begin", "hello", "hi", "initiate", "greet", "greeting", "open", "commence"],
30
- "Feedback": ["feedback", "comments", "review", "opinion", "suggestion", "critique", "rating"],
31
- "Event Inquiries": ["event", "webinar", "meeting", "conference", "session", "seminar", "workshop", "invitation"],
32
- "Payment Issues": ["payment", "billing", "transaction", "charge", "fee", "invoice", "refund", "receipt"],
33
- "Registration Issues": ["registration", "register", "sign up", "enroll", "join", "signup", "enrollment"],
34
- "Service Requests": ["service", "support", "request", "assistance", "help", "aid", "maintenance"],
35
- "Account Issues": ["account", "profile", "update", "activation", "deactivation", "credentials", "reset"],
36
- "Product Information": ["product", "service", "details", "info", "information", "specifications", "features"],
37
- "Account Management": ["login", "account", "new account", "create account", "log out", "google", "access"],
38
- "Order Status": ["order", "status", "tracking", "shipment", "delivery", "purchase", "dispatch"],
39
- "Miscellaneous": ["miscellaneous", "other", "various", "random", "general", "unknown", "unsorted"]
40
-
41
  }
42
 
43
- # Initialize
44
 
45
  def categorize_question(question):
46
- # Split the question into words
47
- words = question.split()
48
-
49
- # Check if the question has only one word
50
- if len(words) == 1:
51
- single_word = words[0].lower()
52
- # Check if the single word is in the Start of Conversation category
53
- if any(single_word in keyword for keyword in categories_keywords["Start of Conversation"]):
54
- return "Start of Conversation"
55
- else:
56
- return "End of Conversation"
57
-
58
- # General categorization based on multiple words
59
  for category, keywords in categories_keywords.items():
60
- if any(keyword.lower() in question.lower() for keyword in keywords):
61
- return category
62
- return "Miscellaneous"
 
 
 
 
 
 
 
 
63
 
64
- def preprocess_data(df, categories_keywords):
65
  df.rename(columns={'Question Asked': 'texts'}, inplace=True)
66
  df['texts'] = df['texts'].astype(str).str.lower()
67
  df['texts'] = df['texts'].apply(lambda text: re.sub(r'https?://\S+|www\.\S+', '', text))
@@ -112,7 +95,8 @@ def preprocess_data(df, categories_keywords):
112
  df['texts'] = df['texts'].str.strip()
113
  df = df[df['texts'] != '']
114
 
115
- df['Category'] = df['texts'].apply(lambda x: categorize_question(x, categories_keywords))
 
116
 
117
  return df
118
 
@@ -154,6 +138,7 @@ def generate_wordcloud(df):
154
  return img
155
 
156
  def generate_bar_chart(df, num_clusters_to_display):
 
157
  common_words = {'i', 'you', 'thanks', 'thank', 'ok', 'okay', 'sure', 'done'}
158
 
159
  top_categories = df['Category'].value_counts().index[:num_clusters_to_display]
 
10
  import plotly.express as px
11
  from PIL import Image
12
 
 
13
  categories_keywords = {
14
+ 'Application Status': ['application', 'applied', 'update on my application', 'result of my application', 'selected', 'selection process', 'apply', 'fellow', 'lesson plan', 'status of my application', 'application update', 'application status', 'applied for'],
15
+ 'Volunteering': ['volunteering', 'volunteer', 'volunteering certificate', 'resume my volunteering', 'volunteering journey', 'volunteering with TFI', 'volunteering opportunities', 'volunteer work', 'volunteer program'],
16
+ 'Certificates': ['certificate', 'certificates', 'certificate of completion', 'volunteer certificate', 'issue certificate'],
17
+ 'Job Opportunities': ['job', 'vacancy', 'Talent Acquisition Executive job', 'opportunity', 'job opening', 'job position', 'career opportunities'],
18
+ 'Surveys and Forms': ['survey', 'form', 'fill out the survey', 'application form', 'survey link', 'survey form', 'form submission'],
19
+ 'General Queries': ['query', 'queries', 'questions', 'feedback', 'loved', 'overwhelming', 'general question', 'inquiry', 'query about'],
20
+ 'Spam': ['free recharge', 'offer', 'click the link', 'https'],
21
+ 'Rescheduling and Postponing': ['reschedule', 'postpone', 'cancellation', 'date', 'time slot', 'change date', 'change time', 'reschedule appointment'],
22
+ 'Contact and Communication Issues': ['call', 'phone', 'contact', 'not received', 'contact support', 'phone call', 'call back', 'internet'],
23
+ 'Email and Credentials Issues': ['email', 'credentials', 'received', 'email issue', 'email problem', 'credential issue', 'login problem'],
24
+ 'Timing and Scheduling': ['session', 'time', 'interview', 'baje', 'schedule time', 'meeting time', 'appointment time'],
25
+ 'Salary and Benefits': ['salary', 'increment', 'accommodation', 'training period', 'reside', 'stipend', 'pay', 'wage', 'salary details', 'benefits information'],
26
+ 'Technical Issues': ['network issues', 'zoom meeting', 'passcode', 'technical', 'issue','technical problem', 'system issue', 'technical support'],
27
+ 'Complaint Handling': ['help', 'i need help', 'Help me', 'complaint', 'issue is unresolved', 'unsatisfied', 'bad experience'],
28
+ 'End of Conversation': ['thanks', 'thankss', 'thank u', 'thank you', 'ok', 'okay', 'done', 'joining', 'sounds good', 'goodbye', 'end chat', 'end'],
29
+ 'Miscellaneous': []
 
 
 
 
 
 
 
 
 
 
30
  }
31
 
 
32
 
33
  def categorize_question(question):
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  for category, keywords in categories_keywords.items():
35
+ for keyword in keywords:
36
+ if keyword.lower() in question.lower():
37
+ # Check if the question is one word and belongs to 'End of Conversation'
38
+ if category == 'End of Conversation':
39
+ return category
40
+ # If not 'End of Conversation', return the matched category
41
+ if category != 'End of Conversation':
42
+ return category
43
+ return 'Miscellaneous'
44
+
45
+
46
 
47
+ def preprocess_data(df):
48
  df.rename(columns={'Question Asked': 'texts'}, inplace=True)
49
  df['texts'] = df['texts'].astype(str).str.lower()
50
  df['texts'] = df['texts'].apply(lambda text: re.sub(r'https?://\S+|www\.\S+', '', text))
 
95
  df['texts'] = df['texts'].str.strip()
96
  df = df[df['texts'] != '']
97
 
98
+ # Categorize the texts
99
+ df['Category'] = df['texts'].apply(categorize_question)
100
 
101
  return df
102
 
 
138
  return img
139
 
140
  def generate_bar_chart(df, num_clusters_to_display):
141
+ # Exclude common words from the top words
142
  common_words = {'i', 'you', 'thanks', 'thank', 'ok', 'okay', 'sure', 'done'}
143
 
144
  top_categories = df['Category'].value_counts().index[:num_clusters_to_display]