Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,36 @@
+
+import streamlit as st
+import joblib
+from huggingface_hub import snapshot_download
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+# Load the model and tokenizer from the repository
+repo_id = "Makima57/sentiment-model-svc"
+model_path = snapshot_download(repo_id=repo_id)
+
+# Load saved SVC model
+svc_model = joblib.load(f"{model_path}/svc_model.pkl")
+
+# Load the saved TfidfVectorizer
+vectorizer = TfidfVectorizer()
+
+# Define prediction function
+def predict_sentiment(text, model, vectorizer):
+    text_transformed = vectorizer.transform([text])
+    prediction = model.predict(text_transformed)
+    return "positive" if prediction == 1 else "negative"
+
+# Streamlit app interface
+st.title("IMDB Movie Review Sentiment Analyzer")
+
+# Text input from user
+user_input = st.text_area("Enter a movie review:", "")
+
+# Predict sentiment when the user submits the input
+if st.button("Analyze Sentiment"):
+    if user_input.strip() != "":
+        sentiment = predict_sentiment(user_input, svc_model, vectorizer)
+        st.write(f"The sentiment of the review is: **{sentiment}**")
+    else:
+        st.write("Please enter a valid review!")
+