app.py

import streamlit as st
import pandas as pd
import numpy as np
import neattext.functions as nfx
from tensorflow.keras.models import load_model
import pickle
from textblob import TextBlob
import os
import nltk
import plotly.graph_objects as go

# --- NLTK / TEXTBLOB HATA ÇÖZÜCÜ ---
@st.cache_resource
def download_nltk_data():
    try:
        nltk.download('punkt')
        nltk.download('wordnet')
        nltk.download('omw-1.4')
        nltk.download('punkt_tab')
        from textblob import download_corpora
        download_corpora.download_all()
    except Exception as e:
        st.error(f"Paket yükleme hatası: {e}")

download_nltk_data()

# --- PICKLE İÇİN GEREKLİ FONKSİYON ---
def ekkok(title):
    try:
        return [word.lemmatize() for word in TextBlob(title).words]
    except:
        return title.split()

# --- SAYFA AYARLARI ---
st.set_page_config(page_title="News Classifier", layout="wide")

# --- MODEL VE DOSYALARI YÜKLEME ---
@st.cache_resource
def load_assets():
    model_path = "news_classification_model.h5"
    vect_path = "tfidf_vectorizer.pkl"
    le_path = "label_encoder.pkl"
    
    if not all(os.path.exists(p) for p in [model_path, vect_path, le_path]):
        st.error("⚠️ Model dosyaları bulunamadı!")
        st.stop()
        
    model = load_model(model_path)
    with open(vect_path, "rb") as f:
        vect = pickle.load(f)
    with open(le_path, "rb") as f:
        le = pickle.load(f)
    return model, vect, le

model, vect, le = load_assets()

# --- TAHMİN FONKSİYONU ---
def predict_news(text):
    clean_text = nfx.clean_text(text.lower())
    matrix = vect.transform([clean_text]).toarray()
    prediction = model.predict(matrix, verbose=0)
    class_index = np.argmax(prediction)
    prob = np.max(prediction)
    category = le.inverse_transform([class_index])[0]
    return category, prob, prediction[0]

# --- SIDEBAR (SOL PANEL) ---
st.sidebar.title("📌 Samples / Örnekler")

all_examples = {
    "Science / Bilim": [
        "NASA's Perseverance rover successfully collects high-priority rock samples from the Martian surface.",
        "The James Webb Space Telescope captures stunning new images of a distant star-forming nebula.",
        "Astronomers discover a new solar system with three potentially habitable planets."
    ],
    "Tech / Teknoloji": [
        "Apple announces new AI-powered features for the upcoming iPhone 18 Pro series.",
        "OpenAI releases a new language model that can reason like a human expert.",
        "Scientists develop a new quantum computer that performs calculations in seconds."
    ],
    "Sports / Spor": [
        "Manchester City secures a narrow victory against Arsenal in a thrilling Premier League match.",
        "The Olympic Committee announces the final list of cities bidding for the 2032 Games.",
        "Formula 1 introduces new sustainable fuel regulations to be implemented by 2026."
    ],
    "Business / Ekonomi": [
        "Global stock markets rally as central banks signal potential interest rate cuts.",
        "The tech industry faces new regulations regarding data privacy and user security.",
        "Gold prices hit an all-time high amidst global economic uncertainty and inflation."
    ],
    "Health / Sağlık": [
        "New clinical trials show a 90% success rate in a breakthrough cancer treatment.",
        "Doctors recommend daily exercise and a balanced diet to prevent heart disease.",
        "A new study reveals the long-term impact of sleep deprivation on mental health."
    ]
}

selected_cat = st.sidebar.selectbox("Select Category / Kategori Seçin:", [""] + list(all_examples.keys()))

if selected_cat != "":
    st.sidebar.markdown(f"### {selected_cat} Samples / Örnekleri:")
    # İSTEDİĞİN DÜZELTME BURADA:
    st.sidebar.write("Click to copy / Kopyalamak üzere tıklayın:")
    for i, ex in enumerate(all_examples[selected_cat], 1):
        st.sidebar.info(f"Example / Örnek {i}:")
        st.sidebar.code(ex, language=None)

# --- ANA SAYFA ---
st.title("📰 Multidisciplinary News Classifier / Çok Disiplinli Haber Sınıflandırıcı")
st.markdown("---")

user_input = st.text_area("News Headline / Haber Başlığı:", height=150, placeholder="Copy an example from the left and paste it here... / Sol taraftan bir örnek kopyalayıp buraya yapıştırın...")

if st.button("Predict / Tahmin Et"):
    if user_input.strip() != "":
        with st.spinner('Analiz ediliyor / Processing...'):
            category, confidence, all_probs = predict_news(user_input)
            
            try:
                translated = str(TextBlob(user_input).translate(from_lang='en', to='tr'))
            except:
                translated = "Çeviri şu an yapılamıyor / Translation failed."

            st.balloons()
            
            st.info(f"**Original / Orijinal:** {user_input}\n\n**Turkish Translation / Türkçe Çeviri:** *{translated}*")
            st.markdown("---")
            
            res_col1, res_col2 = st.columns(2)
            res_col1.success(f"**Predicted Category / Tahmin Edilen Kategori:**\n### {category}")
            res_col2.warning(f"**Confidence Score / Güven Oranı:**\n### %{confidence*100:.2f}")

            labels = le.classes_
            fig = go.Figure(go.Bar(
                x=all_probs, y=labels, orientation='h',
                marker_color='#1F77B4',
                text=[f"%{p*100:.1f}" for p in all_probs], textposition='auto'
            ))
            fig.update_layout(title="Probability Graph / Olasılık Grafiği", height=350)
            st.plotly_chart(fig, use_container_width=True)
    else:
        st.warning("⚠️ Please enter a headline! / Lütfen bir haber başlığı girin!")