Update app.py

app.py

@@ -1,116 +1,174 @@
 import gradio as gr
 import requests
+from transformers import pipeline
+from langdetect import detect
 import pandas as pd
 import textstat
+import matplotlib.pyplot as plt
 import os
 
-# Récupération du token Hugging Face
 HF_TOKEN = os.getenv("HF_TOKEN")
 
-# Fonction pour appeler l'API Zephyr-7B
+
+# Fonction pour appeler l'API Zephyr
 def call_zephyr_api(prompt, hf_token=HF_TOKEN):
     API_URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta"
     headers = {"Authorization": f"Bearer {hf_token}"}
-    payload = {"inputs": prompt}
-
+    payload = {"inputs": prompt, "parameters": {"max_new_tokens": 300}}
+    
     try:
         response = requests.post(API_URL, headers=headers, json=payload, timeout=60)
         response.raise_for_status()
-        return response.json()[0]["generated_text"].strip()
+        return response.json()[0]["generated_text"]
     except Exception as e:
         raise gr.Error(f"❌ Erreur d'appel API Hugging Face : {str(e)}")
 
-# Fonction principale d'analyse
-def full_analysis(text, history):
-    if not text:
-        return "Entrez une phrase.", "", 0, history, 0
-
-    # 1. Demander à Zephyr de détecter le sentiment
-    prompt_sentiment = f"""
-You are a financial news sentiment detector.
-
-Given the following news text:
-\"{text}\"
 
-Respond only with one word: positive, neutral, or negative.
-
-Do not add any explanation or extra text.
-"""
-    detected_sentiment = call_zephyr_api(prompt_sentiment).lower()
+# Chargement du modèle de sentiment
+classifier = pipeline("sentiment-analysis", model="mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis")
+
+# Modèles de traduction
+translator_to_en = pipeline("translation", model="Helsinki-NLP/opus-mt-mul-en")
+translator_to_fr = pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr")
+
+# Fonction pour suggérer le meilleur modèle
+def suggest_model(text):
+    word_count = len(text.split())
+    if word_count < 50:
+        return "Rapide"
+    elif word_count <= 200:
+        return "Équilibré"
+    else:
+        return "Précis"
+
+# Fonction pour générer un graphique de clarté
+def plot_clarity(clarity_scores):
+    plt.figure(figsize=(8, 4))
+    plt.plot(range(1, len(clarity_scores) + 1), clarity_scores, marker='o')
+    plt.title("Évolution du Score de Clarté")
+    plt.xlabel("Numéro d'analyse")
+    plt.ylabel("Score de Clarté")
+    plt.ylim(0, 100)
+    plt.grid(True)
+    return plt.gcf()
+
+# Fonction pour reset le graphique
+def reset_clarity_graph():
+    return [], plot_clarity([])
+
+# Fonction d'analyse
+def full_analysis(text, mode, detail_mode, count, history, clarity_scores):
+    if not text:
+        return "Entrez une phrase.", "", "", 0, history, clarity_scores, None, None
 
-    if detected_sentiment not in ["positive", "neutral", "negative"]:
-        detected_sentiment = "neutral"
+    try:
+        lang = detect(text)
+    except:
+        lang = "unknown"
 
-    # 2. Demander à Zephyr d'expliquer
-    prompt_explanation = f"""
-You are a financial analyst AI.
+    if lang != "en":
+        text = translator_to_en(text, max_length=512)[0]['translation_text']
 
-Given the following financial news:
-\"{text}\"
+    result = classifier(text)[0]
+    sentiment_output = f"Sentiment : {result['label']} (Score: {result['score']:.2f})"
 
-The detected sentiment is: {detected_sentiment}.
+    prompt = f"""
+    You are a financial analyst AI.
+    Based on the following financial news: \"{text}\",
+    explain clearly why the sentiment is {result['label'].lower()}.
+    {"Write a concise paragraph." if detail_mode == "Normal" else "Write a detailed explanation over multiple paragraphs."}
+    """
 
-Now explain clearly why the sentiment is {detected_sentiment}.
-Write a concise paragraph.
-"""
-    explanation = call_zephyr_api(prompt_explanation)
+    explanation_en = call_zephyr_api(prompt)
+    explanation_fr = translator_to_fr(explanation_en, max_length=512)[0]['translation_text']
 
-    # 3. Calculer la clarté
-    clarity_score = textstat.flesch_reading_ease(explanation)
-    clarity_score = max(0, min(clarity_score, 100))  # Limité entre 0-100
+    clarity_score = textstat.flesch_reading_ease(explanation_en)
+    clarity_scores.append(clarity_score)
 
-    # 4. Sauvegarder dans l'historique
+    count += 1
     history.append({
         "Texte": text,
-        "Sentiment": detected_sentiment.capitalize(),
-        "Clarté": f"{clarity_score:.1f}",
-        "Explication": explanation
+        "Sentiment": result['label'],
+        "Score": f"{result['score']:.2f}",
+        "Explication_EN": explanation_en,
+        "Explication_FR": explanation_fr,
+        "Clarté": f"{clarity_score:.1f}"
     })
 
-    return detected_sentiment.capitalize(), explanation, clarity_score, history, int(clarity_score)
+    return sentiment_output, explanation_en, explanation_fr, clarity_score, count, history, clarity_scores, plot_clarity(clarity_scores)
 
-# Fonction pour télécharger l'historique
+# Fonction pour télécharger historique CSV
 def download_history(history):
     if not history:
         return None
     df = pd.DataFrame(history)
-    file_path = "/tmp/history.csv"
+    file_path = "/tmp/analysis_history.csv"
     df.to_csv(file_path, index=False)
     return file_path
 
-# Gradio Interface
+# Interface Gradio
 def launch_app():
-    with gr.Blocks() as iface:
-        gr.Markdown("# 📈 Analyse Financière Premium - Zephyr7B")
+    with gr.Blocks(theme=gr.themes.Base(), css="body {background-color: #0D1117; color: white;} .gr-button {background-color: #161B22; border: 1px solid #30363D;}") as iface:
+
+        gr.Markdown("# 📈 Analyse Financière Premium + Explication IA", elem_id="title")
+        gr.Markdown("Entrez une actualité financière. L'IA analyse et explique en anglais/français. Choisissez votre mode d'explication.")
+
+        count = gr.State(0)
+        history = gr.State([])
+        clarity_scores = gr.State([])
 
         with gr.Row():
-            input_text = gr.Textbox(label="Entrez votre question financière", lines=3)
+            input_text = gr.Textbox(lines=4, placeholder="Entrez une actualité ici...", label="Texte à analyser")
 
         with gr.Row():
-            analyze_btn = gr.Button("Analyser")
-            download_btn = gr.Button("Télécharger l'historique")
+            mode_selector = gr.Dropdown(
+                choices=["Rapide", "Équilibré", "Précis"],
+                value="Équilibré",
+                label="Mode recommandé selon la taille"
+            )
+            detail_mode_selector = gr.Dropdown(
+                choices=["Normal", "Expert"],
+                value="Normal",
+                label="Niveau de détail"
+            )
+
+        analyze_btn = gr.Button("Analyser")
+        reset_graph_btn = gr.Button("Reset Graphique")
+        download_btn = gr.Button("Télécharger CSV")
 
-        sentiment_output = gr.Textbox(label="Sentiment Détecté")
-        explanation_output = gr.Textbox(label="Explication de l'IA", lines=5)
-        clarity_score_text = gr.Textbox(label="Score de Clarté (%)")
-        clarity_slider = gr.Slider(0, 100, label="Clarté (%)", interactive=False)
-        file_output = gr.File(label="Fichier CSV")
+        with gr.Row():
+            sentiment_output = gr.Textbox(label="Résultat du Sentiment")
 
-        history = gr.State([])
+        with gr.Row():
+            with gr.Column():
+                explanation_output_en = gr.Textbox(label="Explication en Anglais")
+            with gr.Column():
+                explanation_output_fr = gr.Textbox(label="Explication en Français")
+
+        clarity_score_output = gr.Textbox(label="Score de Clarté (Flesch Reading Ease)")
+        clarity_plot = gr.Plot(label="Graphique des Scores de Clarté")
+        download_file = gr.File(label="Fichier CSV")
+
+        input_text.change(lambda t: gr.update(value=suggest_model(t)), inputs=[input_text], outputs=[mode_selector])
 
         analyze_btn.click(
             full_analysis,
-            inputs=[input_text, history],
-            outputs=[sentiment_output, explanation_output, clarity_score_text, history, clarity_slider]
+            inputs=[input_text, mode_selector, detail_mode_selector, count, history, clarity_scores],
+            outputs=[sentiment_output, explanation_output_en, explanation_output_fr, clarity_score_output, count, history, clarity_scores, clarity_plot]
+        )
+
+        reset_graph_btn.click(
+            reset_clarity_graph,
+            outputs=[clarity_scores, clarity_plot]
         )
 
         download_btn.click(
             download_history,
             inputs=[history],
-            outputs=[file_output]
+            outputs=[download_file]
         )
 
     iface.launch()
 
 if __name__ == "__main__":
-    launch_app()
+    launch_app()