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.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder


df = pd.read_csv("IMDB Dataset.csv")
st.title(":red[IMDB Sentiment Prediction]")
st.subheader(":blue[Original DataFrame]")
df = df[:5001]  
st.dataframe(df) 

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

df["review"] = df["review"].apply(clean_text)
st.subheader(":blue[Cleaned DataFrame]")
st.dataframe(df) 

st.header(":blue[Accuracy of model]") 

vectorizer = CountVectorizer(stop_words="english")
X = vectorizer.fit_transform(df["review"]).toarray()

df1 = pd.DataFrame(data=X,columns=vectorizer.get_feature_names_out())

label_encoder = LabelEncoder()
y = label_encoder.fit_transform(df["sentiment"])
X_train, X_test, y_train, y_test = train_test_split(df1, y, test_size=0.2, random_state=42)



model_2 = RandomForestClassifier()
model_2.fit(X_train,y_train)
y_pred = model_2.predict(X_test)
accuracy_2 = accuracy_score(y_test,y_pred)
st.write(accuracy_2)



text_input = st.text_area("Write the movie review:")

if st.button("Predict"):  
    if text_input is not None:  
        transformed_text = vectorizer.transform([text_input]).toarray()
        af1 = pd.DataFrame(data=transformed_text,columns=vectorizer.get_feature_names_out())
        prediction = model_2.predict(af1)
        

        st.write("Prediction:",prediction[0])

        if prediction[0] == 1:
            st.write("Positive Review!")
            st.balloons()  
        else:
            st.write("Negative Review!")
            st.snow()