Update app.py

app.py

@@ -4,11 +4,12 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 import torch.nn.functional as F
 from datetime import datetime
+import gradio as gr
 
 # ==========================
-# 1️⃣ FINBERT LOAD
+# 1️⃣ MODEL LOAD (DistilFinBERT)
 # ==========================
-MODEL_NAME = "ProsusAI/finbert"
+MODEL_NAME = "yiyanghkust/finbert-tone-distil"  # DistilFinBERT, CPU-friendly
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
@@ -17,26 +18,12 @@ model.eval()
 # ==========================
 # 2️⃣ REUTERS SCRAPER
 # ==========================
-def fetch_reuters_articles(section="/business/", size=20):
-    """
-    Reuters unofficial JSON endpoint
-    """
+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"
     
-    query = {
-        "query": {
-            "section_id": section,
-            "size": size
-        }
-    }
-
-    params = {
-        "query": str(query).replace("'", '"')
-    }
-
-    headers = {
-        "User-Agent": "Mozilla/5.0"
-    }
+    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()
@@ -58,35 +45,23 @@ def fetch_reuters_articles(section="/business/", size=20):
 
     return pd.DataFrame(articles)
 
-
 # ==========================
-# 3️⃣ FINBERT SENTIMENT
+# 3️⃣ SENTIMENT SCORING
 # ==========================
 def finbert_score(text):
-    inputs = tokenizer(
-        text,
-        return_tensors="pt",
-        truncation=True,
-        padding=True,
-        max_length=512
-    )
-
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
     with torch.no_grad():
         outputs = model(**inputs)
         probs = F.softmax(outputs.logits, dim=1)
-
     labels = ["negative", "neutral", "positive"]
     scores = probs[0].tolist()
-
     return dict(zip(labels, scores))
 
-
 # ==========================
 # 4️⃣ PIPELINE
 # ==========================
 def run_pipeline():
-    df = fetch_reuters_articles(section="/business/", size=25)
-
+    df = fetch_reuters_articles(size=10)
     sentiments = []
     for _, row in df.iterrows():
         text = row["headline"] + ". " + row["summary"]
@@ -95,17 +70,26 @@ def run_pipeline():
 
     sentiment_df = pd.DataFrame(sentiments)
     final_df = pd.concat([df, sentiment_df], axis=1)
-
-    # Hawkish score (neg - pos)
     final_df["hawkish_score"] = final_df["negative"] - final_df["positive"]
 
     filename = f"reuters_finbert_{datetime.today().date()}.csv"
     final_df.to_csv(filename, index=False)
+    return final_df.head(), filename
 
-    print("Saved:", filename)
-    print(final_df.head())
-
-
 # ==========================
+# 5️⃣ GRADIO WEB APP
+# ==========================
+def gradio_interface(dummy_input):
+    table, fname = run_pipeline()
+    return table.to_string(), f"Saved CSV: {fname}"
+
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=gr.Textbox(label="Run Scraper (any text)"),
+    outputs=[gr.Textbox(label="Top Articles"), gr.Textbox(label="CSV Status")],
+    title="Reuters DistilFinBERT Scraper",
+    description="Fetch latest Reuters Business news + sentiment via DistilFinBERT"
+)
+
 if __name__ == "__main__":
-    run_pipeline()
+    iface.launch()