Added file

.gitignore

@@ -0,0 +1,2 @@
+.venv
+.gradio

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import joblib
+import numpy as np
+
+from intent import predict_intent
+from topic_model import get_review_topic
+
+
+
+try:
+    sentiment_pipeline = joblib.load("sentiment_pipeline.pkl")
+except Exception as e:  # pragma: no cover - helpful when learning
+    raise RuntimeError("could not load sentiment pipeline: %s" % e)
+
+try:
+    vectorizer = joblib.load("tfidf_vectorizer.pkl")
+    nmf_model = joblib.load("nmf_model.pkl")
+except Exception as e:
+    raise RuntimeError("could not load vectorizer/nmf model: %s" % e)
+
+# the pipeline predicts integer labels (-1, 0, 1) corresponding to
+# default negative/neutral/positive sentiment.  map them to human-readable
+# strings for display.
+label_map = {
+    -1: "negative",
+    0: "neutral",
+    1: "positive",
+}
+
+
+def analyze_review(review_text: str):
+    """Return sentiment, intent, topic keywords, and confidence scores for a piece of text."""
+    if not review_text:
+        return "", "", ""
+
+    # Get sentiment prediction and confidence scores
+    pred = sentiment_pipeline.predict([review_text])[0]
+    sentiment = label_map.get(pred, str(pred))
+    
+    # Get probability scores for all classes
+    proba = sentiment_pipeline.predict_proba([review_text])[0]
+    
+    # Map probabilities to sentiment labels
+    confidence_map = {
+        -1: proba[0],  # negative
+        0: proba[1],   # neutral
+        1: proba[2],   # positive
+    }
+    
+    confidence_score = confidence_map.get(pred, 0.0)
+    confidence_text = f"Sentiment: {sentiment}\nConfidence: {confidence_score:.2%}"
+
+    intent = predict_intent(review_text)
+    topic = get_review_topic(review_text, vectorizer, nmf_model)
+
+    return confidence_text, intent, topic
+
+
+# build a simple Gradio interface with one text input and multiple outputs.
+iface = gr.Interface(
+    fn=analyze_review,
+    inputs=gr.Textbox(lines=4, placeholder="Enter a customer review...", label="Customer Review"),
+    outputs=[
+        gr.Textbox(label="Sentiment & Confidence Score"),
+        gr.Textbox(label="Predicted Intent"),
+        gr.Textbox(label="Topic / Keywords"),
+    ],
+    title="Interactive NLP Sentiment Analysis System",
+    description=(
+        "Enter a customer review to analyze its sentiment, predicted intent, "
+        "identified topics, and model confidence scores. This interactive demo "
+        "showcases how the NLP system works in a real-world setting."
+    ),
+    examples=[
+        ["I love this product! Amazing quality and fast delivery."],
+        ["The package arrived damaged and the refund process was slow."],
+        ["Average product, nothing special."],
+    ],
+)
+
+if __name__ == "__main__":
+    iface.launch()

intent.py

@@ -0,0 +1,18 @@
+def predict_intent(text):
+    text = text.lower()
+    
+    # Refund Request
+    if any(word in text for word in ["refund", "return", "money back", "replace"]):
+        return "Refund Request"
+    
+    # Delivery Issue
+    elif any(word in text for word in ["late", "delayed", "never arrived", "lost", "shipping"]):
+        return "Delivery Issue"
+    
+    # Complaint
+    elif any(word in text for word in ["wrong", "damaged", "broken", "poor", "bad", "defective"]):
+        return "Complaint"
+    
+    # Default
+    else:
+        return "General Query"

requirements.txt

@@ -0,0 +1,4 @@
+gradio==4.41.1
+scikit-learn==1.5.1
+joblib==1.4.2
+numpy==1.26.4

topic_model.py

@@ -0,0 +1,13 @@
+def get_review_topic(review_text, vectorizer, nmf_model, top_n_words=5):
+    # Transform the review into TF-IDF space
+    review_vect = vectorizer.transform([review_text])
+    
+    # Get topic distribution
+    topic_probs = nmf_model.transform(review_vect)  # shape (1, num_topics)
+    topic_index = topic_probs.argmax()              # pick topic with highest score
+    
+    # Get top words for that topic
+    words = vectorizer.get_feature_names_out()
+    topic_words = [words[j] for j in nmf_model.components_[topic_index].argsort()[-top_n_words:][::-1]]
+    
+    return ", ".join(topic_words)