Update app.py

app.py

@@ -1,3 +1,36 @@
+
+Hugging Face's logo Hugging Face
+
+Models
+Datasets
+Spaces
+Posts
+Docs
+Enterprise
+Pricing
+
+Spaces:
+DinoFrog
+/
+sentiment-analysis
+App
+Files
+Community
+Settings
+sentiment-analysis
+/ app.py
+DinoFrog's picture
+DinoFrog
+Update app.py
+9501ad8
+verified
+8 minutes ago
+raw
+history
+blame
+edit
+delete
+3.37 kB
 import gradio as gr
 import requests
 import pandas as pd
@@ -34,46 +67,25 @@ def full_analysis(text, history):
     if not text:
         return "Entrez une phrase.", "", 0, history
 
-    # 1. Détecter le sentiment via pipeline (ou Zephyr selon ton architecture)
-    prompt_sentiment = f"""
-You are a financial analyst AI specialized in analyzing news sentiment.
-
-Given the following financial news:
-\"{text}\"
-
-Classify the overall sentiment into exactly one of the following categories:
-- positive
-- neutral
-- negative
-
-Only answer with the exact category name, and nothing else.
-Be strict and do not be afraid to classify clearly.
-"""
-    detected_sentiment = call_zephyr_api(prompt_sentiment).lower()
-
-    if detected_sentiment not in ["positive", "neutral", "negative"]:
-        detected_sentiment = "neutral"
+    # 1. Détection sentiment par pipeline
+    result = classifier(text)[0]
+    detected_sentiment = result['label'].lower()
 
-    # 2. Générer l'explication avec un prompt explicite
+    # 2. Appel Zephyr pour explication basée sur ce sentiment
     prompt_explanation = f"""
 You are a financial analyst AI.
-
-Given the following financial news:
+Based on the following financial news:
 \"{text}\"
-
-Detected sentiment: {detected_sentiment}.
-
-Now, write only your explanation why the sentiment is {detected_sentiment}.
-Do not repeat the instructions or the prompt.
-Respond only with your explanation in a clear and concise paragraph.
+Explain clearly why the sentiment is {detected_sentiment}.
+Write a concise paragraph.
 """
     explanation = call_zephyr_api(prompt_explanation)
 
-    # 3. Calcul du score de clarté
+    # 3. Calcul score de clarté
     clarity_score = textstat.flesch_reading_ease(explanation)
-    clarity_score = max(0, min(clarity_score, 100))  # Borné 0-100
+    clarity_score = max(0, min(clarity_score, 100))  # Limité 0-100
 
-    # 4. Stockage historique
+    # 4. Stocker historique
     history.append({
         "Texte": text,
         "Sentiment": detected_sentiment.capitalize(),
@@ -83,7 +95,6 @@ Respond only with your explanation in a clear and concise paragraph.
 
     return detected_sentiment.capitalize(), explanation, int(clarity_score), history
 
-
 # Fonction pour télécharger historique
 def download_history(history):
     if not history:
@@ -128,3 +139,4 @@ def launch_app():
 
 if __name__ == "__main__":
     launch_app()
+