Upload app.py with huggingface_hub

app.py

@@ -1,7 +1,9 @@
 
 import streamlit as st
-import joblib
+import pandas as pd
 from huggingface_hub import snapshot_download
+import joblib
+import numpy as np
 
 # Load the model and vectorizer from the repository
 repo_id = "Makima57/sentiment-model-svc"
@@ -13,11 +15,12 @@ svc_model = joblib.load(f"{model_path}/svc_model.pkl")
 # Load saved TfidfVectorizer
 vectorizer = joblib.load(f"{model_path}/vectorizer.pkl")
 
-# Create a function to make predictions
-def make_prediction(text):
+# Function to analyze sentiment
+def analyze_sentiment(text):
     text_vectorized = vectorizer.transform([text])
-    prediction = svc_model.predict(text_vectorized)
-    return prediction[0]
+    text_dense = text_vectorized.toarray()
+    sentiment = svc_model.predict(text_dense)
+    return sentiment[0]
 
 # Streamlit app
 st.title('Sentiment Analysis App')
@@ -27,7 +30,13 @@ st.write('This app analyzes the sentiment of a given text using the SVC model.')
 text = st.text_input('Enter a text to analyze sentiment')
 
 if st.button('Analyze Sentiment'):
-    sentiment = make_prediction(text)
+    sentiment = analyze_sentiment(text)
     st.write('The sentiment of the text is:', sentiment)
 
+# Analyze sentiment of dataset
+if st.button('Analyze Sentiment of Dataset'):
+    df = pd.read_csv('https://raw.githubusercontent.com/Sp1786/multiclass-sentiment-analysis-dataset/master/data/train.csv')
+    df['sentiment'] = df['text'].apply(analyze_sentiment)
+    st.write(df)
+