Update app.py

app.py

@@ -1,181 +1,147 @@
-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 PAKETLERİ ---
-try:
-    nltk.data.find('corpora/wordnet')
-except LookupError:
-    nltk.download('wordnet')
-    nltk.download('punkt')
-    nltk.download('omw-1.4')
-
-# --- PICKLE İÇİN GEREKLİ FONKSİYON ---
-# Model eğitilirken kullanılan 'ekkok' fonksiyonu burada tanımlı olmalı
-def ekkok(title):
-    return [word.lemmatize() for word in TextBlob(title).words]
-
-# --- 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"
-    
-    # Dosyaların varlığını kontrol et
-    if not all(os.path.exists(p) for p in [model_path, vect_path, le_path]):
-        st.error("⚠️ Model dosyaları bulunamadı! Lütfen .h5 ve .pkl dosyalarını app.py ile aynı klasöre koyun.")
-        st.stop()
-        
-    # Modeli yükle
-    model = load_model(model_path)
-    
-    # Pickle dosyalarını yükle
-    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
-
-# Dosyaları belleğe alalım
-model, vect, le = load_assets()
-
-# --- TAHMİN FONKSİYONU ---
-def predict_news(text):
-    # Metin temizleme
-    clean_text = nfx.clean_text(text.lower())
-    # TF-IDF Dönüşümü
-    matrix = vect.transform([clean_text]).toarray()
-    # Model Tahmini
-    prediction = model.predict(matrix, verbose=0)
-    class_index = np.argmax(prediction)
-    prob = np.max(prediction)
-    # Kategori ismini bulma
-    category = le.inverse_transform([class_index])[0]
-    # Sınıf olasılıkları
-    probabilities = prediction[0]
-    return category, prob, probabilities
-
-# --- SIDEBAR (SOL PANEL) - ÇOKLU ÖRNEKLER ---
-st.sidebar.title("📌 Samples / Örnekler")
-
-# Her kategori için 3'er adet örnek cümle (Science/Uzay ağırlıklı)
-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."
-    ]
-}
-
-# Kategori seçimi
-selected_cat = st.sidebar.selectbox("Select Category / Kategori Seçin:", [""] + list(all_examples.keys()))
-
-if selected_cat != "":
-    st.sidebar.markdown(f"### {selected_cat} Örnekleri:")
-    st.sidebar.write("Kopyalamak için üzerine tıklayın:")
-    
-    # Seçilen kategorideki 3 örneği de kopyalanabilir code bloğu içinde gösteriyoruz
-    for i, ex in enumerate(all_examples[selected_cat], 1):
-        st.sidebar.info(f"Örnek {i}:")
-        st.sidebar.code(ex, language=None)
-
-# --- ANA SAYFA TASARIMI ---
-st.title("📰 News Topic Categorizer / Haber Sınıflandırıcı")
-st.markdown("---")
-
-# Metin Giriş Alanı (Her zaman boş başlar)
-user_input = st.text_area("News Headline / Haber Başlığı:", height=150, placeholder="Sol taraftan bir örnek kopyalayıp buraya yapıştırın...")
-
-# Tahmin Butonu ve İşlemi
-if st.button("Predict / Tahmin Et"):
-    if user_input.strip() != "":
-        with st.spinner('Analyzing... / Analiz ediliyor...'):
-            # 1. Tahmin Yap
-            category, confidence, all_probs = predict_news(user_input)
-            
-            # 2. Çeviri Yap (TextBlob kullanarak hatasız çeviri, cgi hatası vermez)
-            try:
-                # TextBlob bazen internet bağlantısına göre yavaşlayabilir
-                translated = str(TextBlob(user_input).translate(from_lang='en', to='tr'))
-            except:
-                translated = "Çeviri şu an yapılamıyor. / Translation failed."
-
-            # 3. Efektler
-            st.balloons()
-            
-            # 4. Haber ve Alt Satırda Çeviri (Şık Bilgi Kutusu)
-            st.info(f"**English:** {user_input}\n\n**Türkçe Çeviri:** *{translated}*")
-            
-            st.markdown("---")
-            
-            # 5. Sonuç Kartları (Metric formatında)
-            res_col1, res_col2 = st.columns(2)
-            with res_col1:
-                st.success(f"**Predicted Category / Tahmin Edilen Kategori:**\n\n## {category}")
-            with res_col2:
-                st.warning(f"**Confidence Score / Güven Oranı:**\n\n## %{confidence*100:.2f}")
-
-            # 6. Grafik Ekleme (Plotly ile Şık ve Renkli Görünüm)
-            st.markdown("#### Probability Distribution / Olasılık Dağılımı")
-            
-            # Etiketler ve olasılıklar
-            labels = le.classes_
-            
-            # --- GRAFİK RENGİ MAVİ OLSUN ---
-            fig = go.Figure(go.Bar(
-                x=all_probs, 
-                y=labels, 
-                orientation='h',
-                marker_color='#1F77B4', # Mazarine Blue / Mavi Renk Kodu
-                text=[f"%{p*100:.1f}" for p in all_probs], 
-                textposition='auto'
-            ))
-            
-            fig.update_layout(
-                title="Category Probabilities / Kategori Olasılıkları",
-                xaxis_title="Confidence / Güven",
-                yaxis_title="Categories / Kategoriler",
-                height=400,
-                margin=dict(l=20, r=20, t=40, b=20)
-            )
-            
-            st.plotly_chart(fig, use_container_width=True)
-            
-    else:
-        st.warning("⚠️ Lütfen bir haber başlığı girin! / Please enter a headline!")
-
-# Footer / Alt Bilgi
-st.markdown("---")
-st.caption("Deep Learning News Classification Project - Powered by Mergen")
+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 (KRİTİK KISIM) ---
+@st.cache_resource
+def download_nltk_data():
+    try:
+        nltk.download('punkt')
+        nltk.download('wordnet')
+        nltk.download('omw-1.4')
+        nltk.download('punkt_tab')
+        # TextBlob'un içsel corpora'sını zorla yükle
+        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} Örnekleri:")
+    st.sidebar.write("Kopyalamak için üzerine tıklayın:")
+    for i, ex in enumerate(all_examples[selected_cat], 1):
+        st.sidebar.info(f"Örnek {i}:")
+        st.sidebar.code(ex, language=None)
+
+# --- ANA SAYFA ---
+st.title("📰 Multidisciplinary News Classifier")
+st.markdown("---")
+
+user_input = st.text_area("News Headline / Haber Başlığı:", height=150, placeholder="Sol taraftan bir örnek kopyalayıp buraya yapıştırın...")
+
+if st.button("Predict / Tahmin Et"):
+    if user_input.strip() != "":
+        with st.spinner('Analiz ediliyor...'):
+            # 1. Tahmin
+            category, confidence, all_probs = predict_news(user_input)
+            
+            # 2. Çeviri (Hatasız Yöntem)
+            try:
+                translated = str(TextBlob(user_input).translate(from_lang='en', to='tr'))
+            except:
+                translated = "Çeviri şu an yapılamıyor (Bağlantı hatası)."
+
+            st.balloons()
+            
+            # 3. Haber ve Çeviri Gösterimi
+            st.info(f"**Original:** {user_input}\n\n**Türkçe Çeviri:** *{translated}*")
+            st.markdown("---")
+            
+            # 4. Sonuçlar
+            res_col1, res_col2 = st.columns(2)
+            res_col1.success(f"**Category / Kategori:**\n### {category}")
+            res_col2.warning(f"**Confidence / Güven:**\n### %{confidence*100:.2f}")
+
+            # 5. Mavi Grafik
+            labels = le.classes_
+            fig = go.Figure(go.Bar(
+                x=all_probs, y=labels, orientation='h',
+                marker_color='#1F77B4', # Mavi Renk
+                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("⚠️ Lütfen bir haber başlığı girin!")