Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: SentimentAnalysis
+emoji: 📈
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 5.46.1
+app_file: app.py
+pinned: false
+license: cc-by-sa-4.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,225 @@
+import pandas as pd
+import plotly.express as px
+from datasets import load_dataset
+import gradio as gr
+import yfinance as yf
+
+df = pd.DataFrame(load_dataset("SelmaNajih001/NewsSentiment")["train"])
+df = df[df["Company"].isin(["Tesla", "Microsoft", "Apple", "Facebook", "Google"])]
+
+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]
+
+
+TICKERS = {
+    "Tesla": "TSLA",
+    "Microsoft": "MSFT",
+    "Apple": "AAPL",
+    "Facebook": "META",
+    "Google": "GOOGL",
+    "NASDAQ": "^IXIC"
+}
+
+prices = {}
+for company, ticker in TICKERS.items():
+    start_date = "2015-01-01"
+    end_date = pd.Timestamp.today()
+    df_prices = yf.download(ticker, start=start_date, end=end_date)
+    if isinstance(df_prices.columns, pd.MultiIndex):
+        df_prices.columns = ['_'.join([str(c) for c in col]).strip() for col in df_prices.columns]
+    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
+
+def get_prices_for_agg(agg_col):
+    df_prices_agg = {}
+    for company, df_price in prices.items():
+        df_temp = df_price.copy()
+        col = 'Close_NASDAQ' if company == 'NASDAQ' else f"Close_{TICKERS[company]}"
+        df_temp = df_temp.rename(columns={df_temp.columns[1]: 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
+
+df_merged = df.copy()
+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')
+
+df_merged = df_merged.merge(prices['NASDAQ'][['Date', 'Close_NASDAQ']], on='Date', how='left')
+
+
+# --- GRADIO FUNCTION ---
+def show_sentiment(selected_companies=None, aggregation="Day", selected_year="All"):
+    if not selected_companies:
+        selected_companies = ["NASDAQ"]
+        
+    
+    if isinstance(selected_companies, str):
+        selected_companies = [selected_companies]
+
+    df_filtered = df_merged.copy()
+    if selected_year != "All" and selected_year is not None:
+        df_filtered = df_filtered[df_filtered['Year'] == int(selected_year)]
+
+    # colonna aggregazione
+    group_col = aggregation
+    if aggregation == "Month":
+        df_filtered['Month'] = df_filtered['Month'].dt.to_timestamp()
+    elif aggregation == "Day":
+        df_filtered['Day'] = df_filtered['Date']
+
+    # prezzi interpolati
+    prices_agg = get_prices_for_agg(aggregation)
+
+    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:
+            if c not in TICKERS:
+                continue
+            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 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
+
+import gradio as gr
+
+
+description_text = """
+### Dynamic Sentiment Dashboard
+
+This dashboard allows you to explore the sentiment of news articles related to major tech companies (Apple, Tesla, Microsoft, Meta, Alphabet) and compare it with their stock prices.
+
+- **Dataset structure**: The dataset includes a company column; each row corresponds to a news item for a specific company.
+- **Sentiment aggregation**: Select a time aggregation level (Month or Year) to see how sentiment evolves over time.
+- **NASDAQ comparison**: Selecting "NASDAQ" shows the general market sentiment alongside the company-specific sentiment.
+- **Visual insights**: Top-left graph shows average sentiment score and closing price for the selected company.
+"""
+
+findings_text = """
+### Key Findings
+
+- Some news articles refer to multiple companies, e.g., the same article may mention Apple and Tesla.  
+- Merging news with stock prices allows analyzing correlations between sentiment and stock movements for each company.  
+- **Apple (2018, 2019, 2022):** Sentiment trends generally align with closing prices, showing similar monthly patterns.  
+- **Tesla (2018, 2019, 2022):** More volatility observed; sentiment aligns with stock movement but is more sensitive to news on Elon Musk’s actions.  
+- **Microsoft, Meta, Alphabet:** Across periods, sentiment trends follow stock prices with moderate correlation.  
+- The custom sentiment model is more aligned with actual stock movements compared to FinBERT, which is more influenced by word positivity/negativity.  
+- Aggregating sentiment by month or year helps identify broader trends while reducing noise from daily fluctuations.  
+- Including “NASDAQ” as a general market reference allows comparison of individual companies’ sentiment with overall market sentiment.
+"""
+
+
+companies = sorted(df['Company'].unique().tolist()) + ["NASDAQ"]
+years = sorted(df['Year'].dropna().unique().tolist())
+
+# --- Build Gradio Blocks ---
+with gr.Blocks() as demo:
+    # Markdown in alto
+    gr.Markdown("# Dynamic Sentiment Dashboard")
+    gr.Markdown(description_text)
+
+
+    with gr.Row():
+        dropdown_companies = gr.Dropdown(
+            choices=companies,
+            value=None,
+            multiselect=False,
+            label="Select Companies"
+        )
+
+        radio_aggregation = gr.Radio(
+            choices=["Month", "Year"],
+            value="Month",
+            label="Aggregation Level"
+        )
+
+        dropdown_year = gr.Dropdown(
+            choices=["All"] + years,
+            value="All",
+            label="Select Year"
+        )
+
+    # Bottone submit
+    submit_btn = gr.Button("Submit")
+
+    # Output
+    data_table = gr.Dataframe(label="Sentiment Table", type="pandas")
+    sentiment_plot = gr.Plot(label="Sentiment Trend")
+    
+    # Findings section
+    gr.Markdown(findings_text)
+
+
+    submit_btn.click(
+        fn=show_sentiment, 
+        inputs=[dropdown_companies, radio_aggregation, dropdown_year],
+        outputs=[data_table, sentiment_plot]
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,9 @@
+pandas
+datasets
+selenium
+transformers
+plotly
+gradio
+torch
+datetime
+yfinance