5:11

app.py

@@ -1,39 +1,26 @@
-import os
-import joblib
 import gradio as gr
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.linear_model import LogisticRegression
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-MODEL_PATH = 'tunisian_arabiz_sentiment_analysis_model.pkl'
-VECTORIZER_PATH = 'tfidf_vectorizer.pkl'
+# Load your model and tokenizer
+model_name = "your-model-name"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-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(input_text):
+    # Tokenize and make prediction
+    inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True)
+    outputs = model(**inputs)
+    prediction = outputs.logits.argmax(-1).item()
+    return prediction
 
-def predict_sentiment(input_text):
-    model, vectorizer = load_model()
-    if model and vectorizer:
-        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}"
-    else:
-        return "Model not found or could not be loaded."
-
-# Gradio Interface
+# 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."
+    fn=predict,
+    inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
+    outputs="label",
+    title="Your Model Name",
+    description="Enter some text to get a prediction."
 )
 
+# Launch the interface
 iface.launch()