Update app.py

app.py

@@ -7,10 +7,11 @@ import gradio as gr
 from huggingface_hub import login
 import os
 
+# Login Hugging Face
 token = os.getenv("HF_TOKEN")
 login(token=token)
 
-
+# --- Costanti ---
 HF_DATASET = "SelmaNajih001/FT_MultiCompany"
 HF_PRIVATE_DATASET = "SelmaNajih001/portfolio_strategy_data"
 MODEL_SENTIMENT = "SelmaNajih001/SentimentBasedOnPriceVariation"
@@ -24,11 +25,13 @@ TICKERS = {
 }
 companies = list(TICKERS.keys())
 
+# --- Pipelines ---
 sentiment_pipeline = pipeline("sentiment-analysis", model=MODEL_SENTIMENT)
 price_pipeline_tesla = pipeline("text-classification", model=MODEL_PRICE_TESLA)
 price_pipeline_msft = pipeline("text-classification", model=MODEL_PRICE_MICROSOFT)
 finbert_pipeline = pipeline("sentiment-analysis", model=MODEL_FINBERT)
 
+# --- Caricamento dataset ---
 df_multi = pd.DataFrame(load_dataset(HF_DATASET)["train"])
 df_multi['date'] = pd.to_datetime(df_multi['Date'], errors='coerce')
 df_multi['date_merge'] = df_multi['date'].dt.normalize()
@@ -40,60 +43,64 @@ try:
 except:
     df_existing = pd.DataFrame()
 
+# --- Determina nuove righe ---
 if not df_existing.empty:
     df_to_add = df_multi[~df_multi['Date'].isin(df_existing['Date'])]
 else:
     df_to_add = df_multi.copy()
 
-if not df_existing.empty:
-    df_updated = pd.concat([df_existing, df_to_add], ignore_index=True)
-else:
-    df_updated = df_to_add.copy()
-
-hf_dataset_updated = Dataset.from_pandas(df_updated)
-hf_dataset_updated.push_to_hub(HF_PRIVATE_DATASET, private=True)
-print(f"Dataset aggiornato su Hugging Face: {HF_PRIVATE_DATASET}")
+# --- Calcolo solo sulle nuove righe ---
+df_to_add['Sentiment'] = ""
+df_to_add['Confidence'] = 0.0
+df_to_add['Predicted'] = 0.0
+df_to_add['FinBERT_Sentiment'] = ""
+df_to_add['FinBERT_Confidence'] = 0.0
 
-
-df_multi = df_updated.copy() 
-df_multi['Sentiment'] = ""
-df_multi['Confidence'] = 0.0
-df_multi['Predicted'] = 0.0
-df_multi['FinBERT_Sentiment'] = ""
-df_multi['FinBERT_Confidence'] = 0.0
-
-for i, row in df_multi.iterrows():
+for i, row in df_to_add.iterrows():
     company = row['Company']
 
     # Custom sentiment
     try:
         res = sentiment_pipeline(row['Summary'])[0]
-        df_multi.at[i,'Sentiment'] = res['label'].upper().strip()
-        df_multi.at[i,'Confidence'] = res['score']
+        df_to_add.at[i,'Sentiment'] = res['label'].upper().strip()
+        df_to_add.at[i,'Confidence'] = res['score']
     except:
-        df_multi.at[i,'Sentiment'] = 'ERROR'
-        df_multi.at[i,'Confidence'] = 0.0
+        df_to_add.at[i,'Sentiment'] = 'ERROR'
+        df_to_add.at[i,'Confidence'] = 0.0
 
     # FinBERT
     try:
         res_f = finbert_pipeline(row['Summary'])[0]
-        df_multi.at[i,'FinBERT_Sentiment'] = res_f['label'].upper().strip()
-        df_multi.at[i,'FinBERT_Confidence'] = res_f['score']
+        df_to_add.at[i,'FinBERT_Sentiment'] = res_f['label'].upper().strip()
+        df_to_add.at[i,'FinBERT_Confidence'] = res_f['score']
     except:
-        df_multi.at[i,'FinBERT_Sentiment'] = 'ERROR'
-        df_multi.at[i,'FinBERT_Confidence'] = 0.0
+        df_to_add.at[i,'FinBERT_Sentiment'] = 'ERROR'
+        df_to_add.at[i,'FinBERT_Confidence'] = 0.0
 
-    # Regression (Tesla & MSFT)
+    # Regression
     try:
         if company == "Tesla, Inc.":
             val = price_pipeline_tesla(row['Summary'])[0]['score']
-            df_multi.at[i,'Predicted'] = max(val, 1.0)
+            df_to_add.at[i,'Predicted'] = max(val, 1.0)
         elif company == "Microsoft":
             val = price_pipeline_msft(row['Summary'])[0]['score']
-            df_multi.at[i,'Predicted'] = max(val, 1.0)
+            df_to_add.at[i,'Predicted'] = max(val, 1.0)
     except:
-        df_multi.at[i,'Predicted'] = 0.0
+        df_to_add.at[i,'Predicted'] = 0.0
 
+# --- Aggiorna dataset esistente ---
+if not df_existing.empty:
+    df_updated = pd.concat([df_existing, df_to_add], ignore_index=True)
+else:
+    df_updated = df_to_add.copy()
+
+# --- Push su Hugging Face ---
+hf_dataset_updated = Dataset.from_pandas(df_updated)
+hf_dataset_updated.push_to_hub(HF_PRIVATE_DATASET, private=True)
+print(f"Dataset aggiornato su Hugging Face: {HF_PRIVATE_DATASET}")
+
+# --- Resto del codice (prezzi, strategie, Gradio) ---
+df_multi = df_updated.copy()
 
 prices = {}
 for company, ticker in TICKERS.items():
@@ -116,38 +123,34 @@ for company in companies:
     df_c['Month'] = df_c['date'].dt.to_period('M').dt.to_timestamp()
     df_c['Year'] = df_c['date'].dt.year
     
-    # Strategy A: Custom Sentiment
+    # Strategy A
     df_c['StrategyA_Cumulative'] = 0.0
     for i in range(1, len(df_c)):
         pct = df_c.loc[i, 'PctChangeDaily'] if pd.notnull(df_c.loc[i,'PctChangeDaily']) else 0
-        price = df_c.loc[i-1, f'Close_{TICKERS[company]}']  # prezzo di acquisto del giorno precedente
-        
+        price = df_c.loc[i-1, f'Close_{TICKERS[company]}']
         if df_c.loc[i, 'Sentiment'] == "UP" and df_c.loc[i,'Confidence'] > 0.8:
             df_c.loc[i,'StrategyA_Cumulative'] = df_c.loc[i-1,'StrategyA_Cumulative'] + price * pct
         elif df_c.loc[i, 'Sentiment'] == "DOWN" and df_c.loc[i,'Confidence'] > 0.8:
             df_c.loc[i,'StrategyA_Cumulative'] = df_c.loc[i-1,'StrategyA_Cumulative'] - price * pct
         else:
             df_c.loc[i,'StrategyA_Cumulative'] = df_c.loc[i-1,'StrategyA_Cumulative']
-    # Strategy B: Regression (buy if >1, sell if <1)
+    # Strategy B
     df_c['StrategyB_Cumulative'] = 0.0
     for i in range(1, len(df_c)):
         pct = df_c.loc[i, 'PctChangeDaily'] if pd.notnull(df_c.loc[i,'PctChangeDaily']) else 0
         price = df_c.loc[i-1, f'Close_{TICKERS[company]}']
         predicted = df_c.loc[i, 'Predicted']
-    
         if predicted > 1:
             df_c.loc[i,'StrategyB_Cumulative'] = df_c.loc[i-1,'StrategyB_Cumulative'] + price * pct
         elif predicted < -1:
             df_c.loc[i,'StrategyB_Cumulative'] = df_c.loc[i-1,'StrategyB_Cumulative'] - price * pct
         else:
             df_c.loc[i,'StrategyB_Cumulative'] = df_c.loc[i-1,'StrategyB_Cumulative']
-
-    # Strategy C: FinBERT
+    # Strategy C
     df_c['StrategyC_Cumulative'] = 0.0
     for i in range(1, len(df_c)):
         pct = df_c.loc[i, 'PctChangeDaily'] if pd.notnull(df_c.loc[i,'PctChangeDaily']) else 0
         price = df_c.loc[i-1, f'Close_{TICKERS[company]}']
-        
         if df_c.loc[i, 'FinBERT_Sentiment'] == "POSITIVE" and df_c.loc[i,'FinBERT_Confidence'] > 0.8:
             df_c.loc[i,'StrategyC_Cumulative'] = df_c.loc[i-1,'StrategyC_Cumulative'] + price * pct
         elif df_c.loc[i, 'FinBERT_Sentiment'] == "NEGATIVE" and df_c.loc[i,'FinBERT_Confidence'] > 0.8:
@@ -157,14 +160,13 @@ for company in companies:
 
     dfs_final[company] = df_c.drop(columns=["date", "date_merge"], errors="ignore")
 
-# --- FUNZIONE PER GRADIO ---
+# --- Funzione Gradio ---
 def show_company_data(selected_companies, aggregation="Day"):
     if not selected_companies:
         return pd.DataFrame(), None, None  
 
     agg_col = {"Day": "Day", "Month": "Month", "Year": "Year"}.get(aggregation, "Day")
 
-    # --- Figures ---
     fig_strat = go.Figure()
     fig_price = go.Figure()
     dfs_display = []
@@ -223,7 +225,7 @@ def show_company_data(selected_companies, aggregation="Day"):
     df_display = pd.concat(dfs_display, ignore_index=True) if dfs_display else pd.DataFrame()
     return df_display, fig_strat, fig_price
 
-# --- INTERFACCIA GRADIO ---
+# --- Gradio Interface ---
 description_text = """
 ### Portfolio Strategy Comparison Dashboard
 This dashboard allows you to compare the performance of three sentiment models in driving trading strategies for Microsoft and Tesla.