import streamlit as st
import pandas as pd
import re
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder

# Streamlit Config
st.set_page_config(page_title="IMDB Sentiment Analysis", layout="wide")
st.title("🎬 IMDB Sentiment Analysis")

# Load Dataset
def load_data():
    df = pd.read_csv(r"C:\Users\pavilion\Desktop\INNOMATICS_PROJECTS(SL)\IMDB_SENTIMENTAL_ANALYSIS\IMDB Dataset.csv")
    return df  

df = load_data()

# Display Dataset
st.write("### 📌 Dataset")
st.dataframe(df)

# Data Cleaning Function
def clean_text(text):
    text = re.sub(r'<.*?>', '', text)  # Remove HTML tags
    text = re.sub(r'[^a-zA-Z\s]', '', text)  # Keep only letters
    return text.lower().strip()  

df["review"] = df["review"].apply(clean_text)

st.write("### 🔍 Cleaned Dataset")
st.dataframe(df)

# Feature Extraction & Model Training
vectorizer = CountVectorizer(stop_words="english", max_features=10000)  # Limit features
X = vectorizer.fit_transform(df["review"])  # Keep it sparse

label_encoder = LabelEncoder()
y = label_encoder.fit_transform(df["sentiment"])

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train Model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# Model Accuracy
accuracy = accuracy_score(y_test, y_pred)
st.write(f"### 🎯 Model Accuracy: `{accuracy:.2f}`")

# User Input for Prediction
st.write("### ✍️ Enter Your Movie Review Below")
text_input = st.text_area("Write your review here...")

if st.button("🔮 Predict Sentiment"):  
    if text_input.strip():  
        transformed_text = vectorizer.transform([clean_text(text_input)])  # Keep sparse
        prediction = model.predict(transformed_text)

        if prediction[0] == 1:
            st.success("🎉 **Positive Review!**")
            st.balloons()  
        else:
            st.error("❄️ **Negative Review!**")
            st.snow()  
    else:
        st.warning("⚠️ Please enter a review before predicting.")