Update app.py

app.py

@@ -8,11 +8,12 @@ import yfinance as yf
 df = pd.DataFrame(load_dataset("SelmaNajih001/NewsSentiment")["train"])
 df = df[df["Company"].isin(["Tesla", "Microsoft", "Apple", "Facebook", "Google"])]
 
-# --- CONVERT DATE TO DATETIME SAFELY ---
+# --- CONVERT DATE TO DATETIME ---
 df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
 df['Year'] = df['Date'].dt.year
 df['Month'] = df['Date'].dt.to_period('M')
 df['Day'] = df['Date'].dt.date
+df = df[df['Year'] >= 2015]  # filtro anno
 
 # --- TICKERS ---
 TICKERS = {
@@ -24,49 +25,61 @@ TICKERS = {
     "NASDAQ": "^IXIC"
 }
 
-# --- FETCH STOCK PRICES ROBUSTLY ---
+# --- FETCH STOCK PRICES ---
 prices = {}
 for company, ticker in TICKERS.items():
-    start_date = df['Date'].min()
+    start_date = "2015-01-01"
     end_date = pd.Timestamp.today()
     df_prices = yf.download(ticker, start=start_date, end=end_date)
-
-    # Flatten MultiIndex columns if present
     if isinstance(df_prices.columns, pd.MultiIndex):
         df_prices.columns = ['_'.join([str(c) for c in col]).strip() for col in df_prices.columns]
-
-    # Ensure 'Close' column exists
-    if 'Close' not in df_prices.columns:
-        if 'Adj Close' in df_prices.columns:
-            df_prices['Close'] = df_prices['Adj Close']
-        else:
-            df_prices['Close'] = None
-
-    df_prices = df_prices.reset_index()[['Date', 'Close']]
+    df_prices = df_prices.reset_index()[['Date', f'Close_{ticker}']]
+    if company == "NASDAQ":
+        df_prices = df_prices.rename(columns={f'Close_{ticker}': 'Close_NASDAQ'})
     prices[company] = df_prices
 
-# --- MERGE PRICES INTO DATASET ---
+# --- FUNZIONE PER PREZZI INTERPOLATI ---
+def get_prices_for_agg(agg_col):
+    df_prices_agg = {}
+    for company, df_price in prices.items():
+        df_temp = df_price.copy()
+        if company == "NASDAQ":
+            col = "Close_NASDAQ"
+        else:
+            col = f"Close_{TICKERS[company]}"
+            df_temp = df_temp.rename(columns={f"Close_{TICKERS[company]}": col})
+
+        if agg_col == "Day":
+            df_temp = df_temp.set_index('Date').resample('D').mean().interpolate('linear').reset_index()
+        elif agg_col == "Month":
+            df_temp['Month'] = df_temp['Date'].dt.to_period('M').dt.to_timestamp()
+            df_temp = df_temp.groupby('Month')[col].last().reset_index()
+        elif agg_col == "Year":
+            df_temp['Year'] = df_temp['Date'].dt.year
+            df_temp = df_temp.groupby('Year')[col].last().reset_index()
+        df_prices_agg[company] = df_temp
+    return df_prices_agg
+
+# --- MERGE NEWS CON PREZZI ---
 df_merged = df.copy()
-for company, df_price in prices.items():
-    if company == "NASDAQ":
-        continue  # NASDAQ only for comparison
-    mask = df_merged['Company'] == company
-    temp = df_merged[mask].merge(df_price, on='Date', how='left', suffixes=('', '_tmp'))
-    df_merged.loc[mask, 'Close'] = temp['Close'].values
+for company in df['Company'].unique():
+    ticker_col = f"Close_{TICKERS[company]}"
+    df_temp = prices[company][['Date', ticker_col]]
+    df_merged = df_merged.merge(df_temp, on='Date', how='left')
+# NASDAQ per tutte le righe
+df_merged = df_merged.merge(prices['NASDAQ'][['Date', 'Close_NASDAQ']], on='Date', how='left')
 
 # --- GRADIO FUNCTION ---
-def show_sentiment(selected_companies, aggregation="Day"):
-    # Filter selected companies
-    if selected_companies:
-        df_filtered = df_merged[df_merged['Company'].isin(selected_companies)].copy()
-    else:
-        df_filtered = df_merged.copy()
-        # Add NASDAQ data for general sentiment
-        df_nasdaq = prices['NASDAQ'].copy()
-        df_nasdaq['Company'] = "NASDAQ"
-        df_filtered = pd.concat([df_filtered, df_nasdaq], ignore_index=True, sort=False)
+def show_sentiment(selected_companies=None, aggregation="Day", selected_year=None):
+    if not selected_companies:
+        selected_companies = ["NASDAQ"]
 
-    # Determine aggregation column
+    df_filtered = df_merged.copy()
+    if selected_year != "All":
+        df_filtered = df_filtered[df_filtered['Year'] == int(selected_year)]
+
+
+    # colonna aggregazione
     if aggregation == "Day":
         group_col = "Day"
     elif aggregation == "Month":
@@ -76,39 +89,67 @@ def show_sentiment(selected_companies, aggregation="Day"):
         group_col = "Year"
     else:
         group_col = "Day"
-
-    # Aggregate sentiment
-    if selected_companies:
-        df_grouped = df_filtered.groupby([group_col, 'Company'])['Score'].sum().reset_index()
-    else:
-        df_grouped = df_filtered.groupby([group_col, 'Company']).agg({
-            'Score':'sum',
-            'Close':'last'
-        }).reset_index()
-
-    # --- PLOT ---
+    
+
+    # prezzi interpolati per il livello di aggregazione
+    prices_agg = get_prices_for_agg(group_col)
+
+    include_nasdaq = "NASDAQ" in selected_companies
+    companies_to_plot = [c for c in selected_companies if c != "NASDAQ"]
+
+    df_grouped_list = []
+
+    # aziende selezionate
+    if companies_to_plot:
+        df_sent = df_filtered[df_filtered['Company'].isin(companies_to_plot)]
+        df_tmp = df_sent.groupby([group_col, 'Company']).agg({'Score':'sum'}).reset_index()
+        for c in companies_to_plot:
+            ticker_col = f"Close_{TICKERS[c]}"
+            df_price_col = prices_agg[c][[group_col, ticker_col]]
+            df_tmp = df_tmp.merge(df_price_col, on=group_col, how='left')
+        df_grouped_list.append(df_tmp)
+
+    # NASDAQ con sentiment generale
+    if include_nasdaq:
+        df_general = df_filtered.groupby(group_col).agg({'Score':'sum'}).reset_index()
+        df_general['Company'] = 'General'
+        df_general = df_general.merge(prices_agg['NASDAQ'].rename(columns={'Date':group_col}), on=group_col, how='left')
+        df_grouped_list.append(df_general)
+
+    # unisci tutto
+    df_grouped = pd.concat(df_grouped_list, ignore_index=True, sort=False)
+    df_grouped = df_grouped.sort_values([group_col, 'Company'])
+
+    # --- Plot ---
     fig = px.line(df_grouped, x=group_col, y='Score', color='Company',
-                  title=f"Sentiment Score by {aggregation} per Company")
-
-    # Add stock price as secondary y-axis if available
-    if 'Close' in df_grouped.columns:
-        for c in df_grouped['Company'].unique():
-            df_c = df_grouped[df_grouped['Company'] == c]
-            if df_c['Close'].notnull().any():
-                fig.add_scatter(x=df_c[group_col], y=df_c['Close'], mode='lines',
-                                name=f"{c} Price", yaxis="y2", line=dict(dash='dot'))
-        fig.update_layout(
-            yaxis2=dict(
-                title="Stock Price",
-                overlaying="y",
-                side="right"
-            )
+                  title=f"Sentiment Trend ({aggregation} Aggregation)")
+
+    for c in companies_to_plot:
+        ticker_col = f"Close_{TICKERS[c]}"
+        df_c = df_grouped[df_grouped['Company'] == c]
+        if ticker_col in df_c.columns and df_c[ticker_col].notnull().any():
+            fig.add_scatter(x=df_c[group_col], y=df_c[ticker_col],
+                            mode='lines', name=f"{c} Price", yaxis="y2", line=dict(dash='dot'))
+
+    if include_nasdaq:
+        df_c = df_grouped[df_grouped['Company'] == 'General']
+        if 'Close_NASDAQ' in df_c.columns and df_c['Close_NASDAQ'].notnull().any():
+            fig.add_scatter(x=df_c[group_col], y=df_c['Close_NASDAQ'],
+                            mode='lines', name="NASDAQ Price", yaxis="y2", line=dict(dash='dot'))
+
+    fig.update_layout(
+        yaxis2=dict(
+            title="Stock Price",
+            overlaying="y",
+            side="right"
         )
+    )
 
     return df_grouped.tail(30), fig
 
 # --- GRADIO INTERFACE ---
-companies = sorted(df['Company'].unique().tolist())
+companies = sorted(df['Company'].unique().tolist()) + ["NASDAQ"]
+years = sorted(df['Year'].dropna().unique().tolist())
 
 demo = gr.Interface(
     fn=show_sentiment,
@@ -116,13 +157,18 @@ demo = gr.Interface(
         gr.Dropdown(
             choices=companies,
             value=None,
-            label="Select Companies (leave empty for general sentiment with NASDAQ)",
-            multiselect=True
+            label="Select Companies (NASDAQ compares with general sentiment)",
+            multiselect=False
         ),
         gr.Radio(
-            choices=["Day", "Month", "Year"],
-            value="Day",
+            choices=["Month", "Year"],
+            value="Year",
             label="Aggregation Level"
+        ),
+        gr.Dropdown(
+            choices=["All"] + years,
+            value="All",
+            label="Select Year"
         )
     ],
     outputs=[
@@ -130,7 +176,7 @@ demo = gr.Interface(
         gr.Plot(label="Sentiment Trend"),
     ],
     title="Dynamic Sentiment Dashboard",
-    description="Shows sentiment scores aggregated by day, month, or year. Positive = +score, Negative = -score, Neutral = 0."
+    description="Shows sentiment scores aggregated by day, month, or year. NASDAQ compares with general sentiment if selected."
 )
 
-demo.launch()
+demo.launch()