import streamlit as st
import pickle
import spacy
import re


nlp = spacy.load("en_core_web_sm")

# Load saved model, vectorizer, and target names
with open("logreg_model.pkl", "rb") as f:
    model = pickle.load(f)

with open("tfidf_vectorizer.pkl", "rb") as f:
    vectorizer = pickle.load(f)

with open("target_names.pkl", "rb") as f:
    target_names = pickle.load(f)


friendly_labels = {
    'alt.atheism': "🌌 Atheism Discussions",
    'comp.graphics': "💻 Computer Graphics",
    'comp.os.ms-windows.misc': "🪟 Windows OS Topics",
    'comp.sys.ibm.pc.hardware': "🖥️ IBM PC Hardware",
    'comp.sys.mac.hardware': "🍏 Mac Hardware",
    'comp.windows.x': "🧱 X Window System",
    'misc.forsale': "🛒 Miscellaneous For Sale",
    'rec.autos': "🚗 Automobiles",
    'rec.motorcycles': "🏍️ Motorcycles",
    'rec.sport.baseball': "⚾ Baseball",
    'rec.sport.hockey': "🏒 Hockey",
    'sci.crypt': "🔐 Cryptography",
    'sci.electronics': "🔌 Electronics",
    'sci.med': "🧬 Medical Science",
    'sci.space': "🚀 Space",
    'soc.religion.christian': "✝️ Christianity",
    'talk.politics.guns': "🔫 Gun Politics",
    'talk.politics.mideast': "🌍 Middle East Politics",
    'talk.politics.misc': "💬 General Politics",
    'talk.religion.misc': "🙏 Other Religious Topics"
}


def preprocess_text(text):
    text = text.lower()
    text = re.sub(r"[^a-z\s]", " ", text)
    doc = nlp(text)
    tokens = [token.lemma_ for token in doc if token.is_alpha and not token.is_stop]
    return " ".join(tokens)

# Streamlit UI
st.set_page_config(page_title="Newsgroups Text Classifier", layout="centered")
st.title(" Newsgroups Text Classification")
st.markdown("Enter any piece of text and the model will predict its category.")

user_input = st.text_area("Enter your text here:", height=200)

if st.button("Classify"):
    if user_input.strip() == "":
        st.warning("Please enter some text.")
    else:
        preprocessed = preprocess_text(user_input)
        vect_text = vectorizer.transform([preprocessed])
        prediction = model.predict(vect_text)[0]
        predicted_label = target_names[prediction]
        friendly_name = friendly_labels.get(predicted_label, predicted_label)
        st.success(f"🔍 Predicted Category: **{friendly_name}**")