Create app.py

app.py

@@ -0,0 +1,81 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.linear_model import LogisticRegression
+import joblib
+import gradio as gr
+
+# Load the dataset
+data_df = pd.read_csv('homework01_text_data_group13.csv')
+
+# Separate features and labels
+X = data_df['reviews']
+y = data_df['class']
+
+# Split the data into train and test sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
+
+# Create bag-of-words representations
+vectorizer = CountVectorizer()
+X_train_counts = vectorizer.fit_transform(X_train)
+X_test_counts = vectorizer.transform(X_test)
+
+# Train the KNN model
+knn_model = KNeighborsClassifier(n_neighbors=2, metric='euclidean')
+knn_model.fit(X_train_counts, y_train)
+
+# Train the Logistic Regression model
+logistic_model = LogisticRegression(penalty='l2', C=1, random_state=0)
+logistic_model.fit(X_train_counts, y_train)
+
+# Save the trained models
+joblib.dump(knn_model, 'best_knn_model.pkl')
+joblib.dump(logistic_model, 'best_logistic_regression_model.pkl')
+
+def predict_knn(review_text, model=knn_model):
+    X_test = vectorizer.transform([review_text])
+    y_pred = model.predict(X_test)
+    y_pred_proba = model.predict_proba(X_test)[0]
+    return {'Positive': y_pred_proba[1], 'Negative': y_pred_proba[0]}
+
+def predict_logistic(review_text, model=logistic_model):
+    X_test = vectorizer.transform([review_text])
+    y_pred = model.predict(X_test)
+    y_pred_proba = model.predict_proba(X_test)[0]
+    return {'Positive': y_pred_proba[1], 'Negative': y_pred_proba[0]}
+
+models = ["KNN", "Logistic Regression"]
+
+def predict(review_text, model):
+    if model == "KNN":
+        output = predict_knn(review_text)
+    else:
+        output = predict_logistic(review_text)
+    
+    if output['Positive'] > output['Negative']:
+        sentiment = "Positive Feedback"
+    else:
+        sentiment = "Negative Feedback"
+    
+    return sentiment, output
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Enter your review comment...", label="Review Comment"),
+        gr.Dropdown(choices=models, label="Select Model")
+    ],
+    outputs=[
+        gr.Textbox(label="Predicted Sentiment Class"),
+        gr.Label(num_top_classes=2, label="Predicted Probability")
+    ],
+    examples=[
+        ["This Food is interesting, I need a second Plate", "KNN"],
+        ["This Food is interesting, I need a second Plate", "Logistic Regression"],
+        ["The food was terrible, and the service was worse.", "KNN"],
+        ["The food was terrible, and the service was worse.", "Logistic Regression"]
+    ]
+)
+
+demo.launch()