Update app.py

app.py

@@ -2,7 +2,6 @@ import pandas as pd
 import yfinance as yf
 from datasets import load_dataset
 from transformers import pipeline
-import plotly.express as px
 import plotly.graph_objects as go
 import gradio as gr
 
@@ -16,7 +15,7 @@ MODEL_FINBERT = "ProsusAI/finbert"
 TICKERS = {
     "Tesla": "TSLA",
     "Microsoft": "MSFT",
-    #"Nvidia": "NVDA"
+    "Nvidia": "NVDA"
 }
 companies = list(TICKERS.keys())
 
@@ -42,7 +41,7 @@ df_multi['FinBERT_Confidence'] = 0.0
 for i, row in df_multi.iterrows():
     company = row['Company']
 
-    # --- Sentiment con modello custom ---
+    # Custom sentiment
     try:
         res = sentiment_pipeline(row['Summary'])[0]
         df_multi.at[i,'Sentiment'] = res['label'].upper().strip()
@@ -51,7 +50,7 @@ for i, row in df_multi.iterrows():
         df_multi.at[i,'Sentiment'] = 'ERROR'
         df_multi.at[i,'Confidence'] = 0.0
 
-    # --- FinBERT ---
+    # FinBERT
     try:
         res_f = finbert_pipeline(row['Summary'])[0]
         df_multi.at[i,'FinBERT_Sentiment'] = res_f['label'].upper().strip()
@@ -60,7 +59,7 @@ for i, row in df_multi.iterrows():
         df_multi.at[i,'FinBERT_Sentiment'] = 'ERROR'
         df_multi.at[i,'FinBERT_Confidence'] = 0.0
 
-    # --- Regression solo per Tesla & Microsoft ---
+    # Regression (Tesla & MSFT)
     try:
         if company == "Tesla":
             val = price_pipeline_tesla(row['Summary'])[0]['score']
@@ -94,7 +93,7 @@ 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: Sentiment custom ---
+    # Strategy A: Custom Sentiment
     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
@@ -105,10 +104,10 @@ for company in companies:
         else:
             df_c.loc[i,'StrategyA_Cumulative'] = df_c.loc[i-1,'StrategyA_Cumulative']
 
-    # --- Strategy B: Regression ---
+    # Strategy B: Regression
     df_c['StrategyB_Cumulative'] = (df_c['Predicted'] * df_c['PctChangeDaily']).cumsum()
 
-    # --- Strategy C: FinBERT ---
+    # Strategy C: FinBERT
     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
@@ -121,27 +120,63 @@ for company in companies:
 
     dfs_final[company] = df_c.drop(columns=["date", "date_merge"], errors="ignore")
 
-# --- PLOT: CONFRONTO STRATEGIE ---
-df_plot = pd.concat([
-    df[['Date','StrategyA_Cumulative','StrategyB_Cumulative','StrategyC_Cumulative']].assign(Company=company)
-    for company, df in dfs_final.items()
-], ignore_index=True)
-
-fig_strategies = px.line(
-    df_plot, x='Date', y=['StrategyA_Cumulative','StrategyB_Cumulative','StrategyC_Cumulative'], 
-    color='Company',
-    title="Confronto Strategie (Custom Sentiment vs Regression vs FinBERT)"
-)
-
-# --- PLOT: PREZZI ---
-df_prices_plot = pd.concat([
-    df[[f'Close_{TICKERS[company]}','Date']].assign(Company=company) for company, df in dfs_final.items()
-], ignore_index=True)
-
-fig_prices = px.line(
-    df_prices_plot, x='Date', y=df_prices_plot.columns[0], color='Company',
-    title="Andamento Prezzi"
+# --- FUNZIONE PER GRADIO ---
+def show_company_data(selected_companies, aggregation="Day"):
+    if not selected_companies:
+        return "Seleziona almeno un'azienda", None
+
+    fig = go.Figure()
+    agg_col = {"Day": "Day", "Month": "Month", "Year": "Year"}.get(aggregation, "Day")
+
+    for c in selected_companies:
+        if c not in dfs_final:
+            continue
+        df_c = dfs_final[c]
+
+        df_grouped = df_c.groupby(agg_col).agg({
+            'StrategyA_Cumulative':'last',
+            'StrategyB_Cumulative':'last',
+            'StrategyC_Cumulative':'last',
+            f'Close_{TICKERS[c]}':'last'
+        }).reset_index()
+
+        # Strategie
+        for strat in ['StrategyA_Cumulative','StrategyB_Cumulative','StrategyC_Cumulative']:
+            fig.add_trace(go.Scatter(
+                x=df_grouped[agg_col], y=df_grouped[strat],
+                mode="lines", name=f"{c} {strat}"
+            ))
+
+        # Prezzo (asse Y2)
+        fig.add_trace(go.Scatter(
+            x=df_grouped[agg_col], y=df_grouped[f'Close_{TICKERS[c]}'],
+            mode="lines", name=f"{c} Price", yaxis="y2", line=dict(dash="dot")
+        ))
+
+    fig.update_layout(
+        title="Confronto Strategie (Sentiment, Regression, FinBERT) + Prezzi",
+        xaxis_title=aggregation,
+        yaxis_title="Cumulative",
+        yaxis2=dict(title="Stock Price", overlaying="y", side="right"),
+        legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1),
+        template="plotly_dark",
+        hovermode="x unified"
+    )
+    return None, fig
+
+# --- INTERFACCIA GRADIO ---
+demo = gr.Interface(
+    fn=show_company_data,
+    inputs=[
+        gr.Dropdown(choices=companies, value=["Microsoft","Tesla"], multiselect=True, label="Seleziona Aziende"),
+        gr.Radio(choices=["Day","Month","Year"], value="Day", label="Aggregazione")
+    ],
+    outputs=[
+        gr.Dataframe(label="Preview", type="pandas"),
+        gr.Plot(label="Strategie & Prezzi")
+    ],
+    title="Portfolio Evolution",
+    description="Confronto tra Sentiment Custom, Regressione e FinBERT con andamento prezzi"
 )
 
-fig_strategies.show()
-fig_prices.show()
+demo.launch()