Update app.py

app.py

@@ -1,78 +1,31 @@
-import pandas as pd
-import numpy as np
+import joblib
 from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LogisticRegression
-from sklearn.metrics import accuracy_score
-import nltk
 import gradio as gr
-import joblib
-import os
-
-nltk.download('stopwords', quiet=True)
-
-MODEL_PATH = 'sentiment_model.joblib'
-VECTORIZER_PATH = 'vectorizer.joblib'
 
-def train_model():
-    df = pd.read_csv("TuniziDataset.csv")
-    clean_dataset = df.drop_duplicates()
-    
-    X = clean_dataset['InputText'].values
-    Y = clean_dataset['SentimentLabel'].values
-    
-    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, stratify=Y, random_state=2)
-    
-    vectorizer = TfidfVectorizer()
-    X_train = vectorizer.fit_transform(X_train)
-    X_test = vectorizer.transform(X_test)
-    
-    model = LogisticRegression(max_iter=1000)
-    model.fit(X_train, Y_train)
-    
-    # Save the model and vectorizer
-    joblib.dump(model, MODEL_PATH)
-    joblib.dump(vectorizer, VECTORIZER_PATH)
-    
-    # Calculate accuracies
-    train_accuracy = accuracy_score(Y_train, model.predict(X_train))
-    test_accuracy = accuracy_score(Y_test, model.predict(X_test))
-    
-    return model, vectorizer, train_accuracy, test_accuracy
+# Load the model
+model = joblib.load('tunisian_arabiz_sentiment_analysis_model.pkl')
+vectorizer = joblib.load('tfidf_vectorizer.pkl')
 
-def load_model():
-    if os.path.exists(MODEL_PATH) and os.path.exists(VECTORIZER_PATH):
-        model = joblib.load(MODEL_PATH)
-        vectorizer = joblib.load(VECTORIZER_PATH)
-        return model, vectorizer
-    return None, None
-
-def predict_sentiment(input_text):
-    model, vectorizer = load_model()
-    
-    if model is None or vectorizer is None:
-        model, vectorizer, train_accuracy, test_accuracy = train_model()
-        print(f"Model trained. Train accuracy: {train_accuracy:.4f}, Test accuracy: {test_accuracy:.4f}")
-    
-    # Transform input text
-    input_vector = vectorizer.transform([input_text])
-    
-    # Predict
+# Function to predict sentiment
+def predict_sentiment(text):
+    input_vector = vectorizer.transform([text])
     prediction = model.predict(input_vector)[0]
     probabilities = model.predict_proba(input_vector)[0]
-    
+
     sentiment = "Positive" if prediction == 1 else "Negative"
     confidence = probabilities[1] if prediction == 1 else probabilities[0]
-    
-    return f"Sentiment: {sentiment}\nConfidence: {confidence:.4f}"
 
-# Gradio Interface
+    return f"Sentiment: {sentiment}, Confidence: {confidence:.4f}"
+
+# Define Gradio interface
 iface = gr.Interface(
     fn=predict_sentiment,
-    inputs="text",
-    outputs="text",
-    title="Sentiment Analysis Predictor",
-    description="Enter a text to predict its sentiment."
+    inputs=gr.inputs.Textbox(lines=5, label="Enter text in Tunisian Arabizi:"),
+    outputs=gr.outputs.Textbox(label="Sentiment Prediction"),
+    title="Tunisian Arabizi Sentiment Analysis",
+    description="Predict sentiment (Positive/Negative) of Tunisian Arabizi text."
 )
 
-iface.launch()
+# Launch the Gradio interface
+iface.launch()