UMAR798 commited on
Commit
bb6f20d
·
verified ·
1 Parent(s): fd87b65

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +53 -37
app.py CHANGED
@@ -1,112 +1,128 @@
1
  import re
2
  import nltk
3
  import gradio as gr
 
4
  from nltk.corpus import stopwords
5
- from nltk.tokenize import word_tokenize
6
  from sklearn.feature_extraction.text import TfidfVectorizer
7
  from sklearn.metrics.pairwise import cosine_similarity
8
 
9
- # Download NLTK data
10
- nltk.download("punkt")
11
  nltk.download("stopwords")
12
 
13
- # -------------------------------
14
  # FAQ Dataset
15
- # -------------------------------
16
 
17
  faq_data = {
18
- "What is AI?":
19
- "Artificial Intelligence is the simulation of human intelligence by machines.",
20
 
21
  "What is Machine Learning?":
22
- "Machine Learning is a subset of AI that allows systems to learn from data.",
23
 
24
  "What is Deep Learning?":
25
- "Deep Learning is a branch of Machine Learning that uses neural networks.",
 
 
 
 
 
 
26
 
27
  "Who developed Python?":
28
  "Python was created by Guido van Rossum.",
29
 
30
- "What is Hugging Face?":
31
- "Hugging Face is a platform for Machine Learning models and datasets.",
32
-
33
  "What is Google Colab?":
34
- "Google Colab is a free cloud-based Jupyter Notebook service.",
35
-
36
- "What is NLP?":
37
- "Natural Language Processing enables computers to understand human language.",
38
 
39
- "What is Streamlit?":
40
- "Streamlit is a Python framework used to build data apps.",
41
 
42
  "What is Gradio?":
43
- "Gradio is a Python library for creating web interfaces for ML models.",
44
 
45
  "What is cosine similarity?":
46
- "Cosine similarity measures how similar two text vectors are."
 
 
 
 
 
 
47
  }
48
 
49
- # -------------------------------
50
  # Text Preprocessing
51
- # -------------------------------
52
 
53
  stop_words = set(stopwords.words("english"))
54
 
55
  def preprocess(text):
56
  text = text.lower()
57
- text = re.sub(r'[^a-zA-Z ]', '', text)
58
 
59
- tokens = word_tokenize(text)
 
 
 
 
60
 
 
61
  tokens = [word for word in tokens if word not in stop_words]
62
 
63
  return " ".join(tokens)
64
 
65
- # Preprocess Questions
66
  questions = list(faq_data.keys())
67
  answers = list(faq_data.values())
68
 
69
  processed_questions = [preprocess(q) for q in questions]
70
 
71
- # TF-IDF Vectorizer
 
 
 
72
  vectorizer = TfidfVectorizer()
73
 
74
  question_vectors = vectorizer.fit_transform(processed_questions)
75
 
76
- # -------------------------------
77
  # Chatbot Function
78
- # -------------------------------
79
 
80
  def chatbot(user_input):
81
 
 
 
 
82
  processed_input = preprocess(user_input)
83
 
84
  input_vector = vectorizer.transform([processed_input])
85
 
86
- similarities = cosine_similarity(input_vector, question_vectors)
87
 
88
- best_match = similarities.argmax()
89
 
90
- score = similarities[0][best_match]
91
 
92
  if score < 0.25:
93
  return "Sorry, I couldn't find a relevant answer."
94
 
95
  return answers[best_match]
96
 
97
- # -------------------------------
98
  # Gradio UI
99
- # -------------------------------
100
 
101
  demo = gr.Interface(
102
  fn=chatbot,
103
  inputs=gr.Textbox(
104
  lines=2,
105
- placeholder="Ask a question..."
106
  ),
107
- outputs="text",
108
  title="🤖 FAQ Chatbot",
109
- description="FAQ Chatbot using NLP, TF-IDF and Cosine Similarity"
 
110
  )
111
 
112
- demo.launch()
 
 
1
  import re
2
  import nltk
3
  import gradio as gr
4
+
5
  from nltk.corpus import stopwords
 
6
  from sklearn.feature_extraction.text import TfidfVectorizer
7
  from sklearn.metrics.pairwise import cosine_similarity
8
 
9
+ # Download only stopwords (no punkt needed)
 
10
  nltk.download("stopwords")
11
 
12
+ # ---------------------------------
13
  # FAQ Dataset
14
+ # ---------------------------------
15
 
16
  faq_data = {
17
+ "What is Artificial Intelligence?":
18
+ "Artificial Intelligence (AI) is the simulation of human intelligence by machines.",
19
 
20
  "What is Machine Learning?":
21
+ "Machine Learning is a subset of AI that enables computers to learn from data.",
22
 
23
  "What is Deep Learning?":
24
+ "Deep Learning is a branch of Machine Learning based on neural networks.",
25
+
26
+ "What is NLP?":
27
+ "Natural Language Processing enables computers to understand human language.",
28
+
29
+ "What is Python?":
30
+ "Python is a popular programming language used in AI, web development, and automation.",
31
 
32
  "Who developed Python?":
33
  "Python was created by Guido van Rossum.",
34
 
 
 
 
35
  "What is Google Colab?":
36
+ "Google Colab is a free cloud-based Jupyter Notebook for Python programming.",
 
 
 
37
 
38
+ "What is Hugging Face?":
39
+ "Hugging Face is a platform for Machine Learning models and datasets.",
40
 
41
  "What is Gradio?":
42
+ "Gradio is a Python library for building interactive web interfaces.",
43
 
44
  "What is cosine similarity?":
45
+ "Cosine similarity measures how similar two pieces of text are.",
46
+
47
+ "Who is Donald Trump?":
48
+ "Donald Trump is the 45th and 47th President of the United States.",
49
+
50
+ "Who is Elon Musk?":
51
+ "Elon Musk is the CEO of Tesla and SpaceX."
52
  }
53
 
54
+ # ---------------------------------
55
  # Text Preprocessing
56
+ # ---------------------------------
57
 
58
  stop_words = set(stopwords.words("english"))
59
 
60
  def preprocess(text):
61
  text = text.lower()
 
62
 
63
+ # Remove punctuation
64
+ text = re.sub(r'[^a-zA-Z0-9 ]', '', text)
65
+
66
+ # Simple tokenization
67
+ tokens = text.split()
68
 
69
+ # Remove stopwords
70
  tokens = [word for word in tokens if word not in stop_words]
71
 
72
  return " ".join(tokens)
73
 
 
74
  questions = list(faq_data.keys())
75
  answers = list(faq_data.values())
76
 
77
  processed_questions = [preprocess(q) for q in questions]
78
 
79
+ # ---------------------------------
80
+ # TF-IDF
81
+ # ---------------------------------
82
+
83
  vectorizer = TfidfVectorizer()
84
 
85
  question_vectors = vectorizer.fit_transform(processed_questions)
86
 
87
+ # ---------------------------------
88
  # Chatbot Function
89
+ # ---------------------------------
90
 
91
  def chatbot(user_input):
92
 
93
+ if not user_input.strip():
94
+ return "Please enter a question."
95
+
96
  processed_input = preprocess(user_input)
97
 
98
  input_vector = vectorizer.transform([processed_input])
99
 
100
+ similarity = cosine_similarity(input_vector, question_vectors)
101
 
102
+ best_match = similarity.argmax()
103
 
104
+ score = similarity[0][best_match]
105
 
106
  if score < 0.25:
107
  return "Sorry, I couldn't find a relevant answer."
108
 
109
  return answers[best_match]
110
 
111
+ # ---------------------------------
112
  # Gradio UI
113
+ # ---------------------------------
114
 
115
  demo = gr.Interface(
116
  fn=chatbot,
117
  inputs=gr.Textbox(
118
  lines=2,
119
+ placeholder="Ask your question here..."
120
  ),
121
+ outputs=gr.Textbox(),
122
  title="🤖 FAQ Chatbot",
123
+ description="FAQ Chatbot using NLP, TF-IDF, and Cosine Similarity",
124
+ theme=gr.themes.Soft()
125
  )
126
 
127
+ if __name__ == "__main__":
128
+ demo.launch()