Update app.py

app.py

@@ -1,94 +1,39 @@
-import requests
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
-import csv
-from datetime import datetime
 import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 
-# ==========================
-# 1️⃣ MODEL (CPU-Friendly)
-# ==========================
-MODEL_NAME = "cardiffnlp/twitter-roberta-base-financial-sentiment"
+# Model ve Tokenizer'ı yükleme
+MODEL_NAME = "yiyanghkust/finbert"  # Bu FinBERT modelini kullanacağız
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
 
-nlp = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
+# Sentiment analizi fonksiyonu
+def analyze_sentiment(text):
+    # Verilen metni tokenize et
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
 
-# ==========================
-# 2️⃣ REUTERS SCRAPER
-# ==========================
-def fetch_reuters_articles(section="/business/", size=10):
-    url = "https://www.reuters.com/pf/api/v3/content/fetch/articles-by-section-alias-or-id-v1"
+    # CPU'da çalışacak şekilde modelin inference yapmasını sağlıyoruz
+    with torch.no_grad():
+        outputs = model(**inputs)
     
-    query = {"query":{"section_id": section, "size": size}}
-    params = {"query": str(query).replace("'", '"')}
-    headers = {"User-Agent": "Mozilla/5.0"}
-
-    response = requests.get(url, params=params, headers=headers)
-    data = response.json()
-
-    articles = []
-    try:
-        contents = data["result"]["articles"]
-        for item in contents:
-            headline = item.get("title", "")
-            summary = item.get("description", "")
-            published = item.get("published_time", "")
-            articles.append({
-                "headline": headline,
-                "summary": summary,
-                "published": published
-            })
-    except Exception as e:
-        print("Parsing error:", e)
-
-    return articles
-
-# ==========================
-# 3️⃣ SENTIMENT SCORING
-# ==========================
-def score_articles(articles):
-    scored = []
-    for art in articles:
-        text = art["headline"] + ". " + art["summary"]
-        result = nlp(text)[0]  # cardiffnlp döndürür: {'label': 'positive', 'score': 0.95}
-        art.update(result)
-        scored.append(art)
-    return scored
-
-# ==========================
-# 4️⃣ CSV SAVE
-# ==========================
-def save_csv(scored_articles):
-    filename = f"reuters_sentiment_{datetime.today().date()}.csv"
-    keys = scored_articles[0].keys()
-    with open(filename, "w", newline="", encoding="utf-8") as f:
-        dict_writer = csv.DictWriter(f, fieldnames=keys)
-        dict_writer.writeheader()
-        dict_writer.writerows(scored_articles)
-    return filename
-
-# ==========================
-# 5️⃣ PIPELINE
-# ==========================
-def run_pipeline(dummy_input):
-    articles = fetch_reuters_articles(size=10)
-    scored = score_articles(articles)
-    csv_file = save_csv(scored)
-
-    # Terminal için tablo görünümü
-    display_text = "\n".join([f"{a['headline']} -> {a['label']} ({a['score']:.2f})" for a in scored])
-    return display_text, f"Saved CSV: {csv_file}"
-
-# ==========================
-# 6️⃣ GRADIO WEB APP
-# ==========================
-iface = gr.Interface(
-    fn=run_pipeline,
-    inputs=gr.Textbox(label="Run Scraper (any text)"),
-    outputs=[gr.Textbox(label="Top Articles"), gr.Textbox(label="CSV Status")],
-    title="Reuters Financial Sentiment (CardiffNLP)",
-    description="Fetch latest Reuters Business news + sentiment via CardiffNLP Roberta model (CPU-friendly, no pandas)"
-)
-
-if __name__ == "__main__":
-    iface.launch()
+    # Modelin çıktısını al (logits)
+    logits = outputs.logits
+    predicted_class = torch.argmax(logits, dim=-1).item()
+    
+    # Sentiment sınıfını belirle
+    if predicted_class == 0:
+        return "Negative"
+    elif predicted_class == 1:
+        return "Neutral"
+    else:
+        return "Positive"
+
+# Gradio arayüzü
+iface = gr.Interface(fn=analyze_sentiment, 
+                     inputs="text", 
+                     outputs="text", 
+                     title="Financial Sentiment Analysis",
+                     description="Enter a financial text, and the model will analyze its sentiment (Positive, Neutral, or Negative).")
+
+# Uygulamayı başlat
+iface.launch()