Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import requests | |
| import pandas as pd | |
| from datetime import datetime, timedelta | |
| from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer | |
| from textblob import TextBlob | |
| import nltk | |
| from wordcloud import WordCloud | |
| import base64 | |
| from io import BytesIO | |
| import numpy as np | |
| from sklearn.linear_model import LinearRegression | |
| import plotly.graph_objects as go | |
| from plotly.subplots import make_subplots | |
| import yfinance as yf | |
| # -------------------------- | |
| # CONFIG | |
| # -------------------------- | |
| st.set_page_config(page_title="📰 News Sentiment Analysis for Young Investor", layout="wide") | |
| API_KEY = "88bc396d4eab4be494a4b86ec842db47" | |
| # -------------------------- | |
| # UTILITIES | |
| # -------------------------- | |
| def analyze_text(text, vader): | |
| if not text.strip(): | |
| return 0 | |
| vader_score = vader.polarity_scores(text)["compound"] | |
| textblob_score = TextBlob(text).sentiment.polarity | |
| return np.mean([vader_score, textblob_score]) | |
| def generate_wordcloud(text): | |
| stopwords = nltk.corpus.stopwords.words('english') | |
| wordcloud = WordCloud(width=800, height=400, background_color="white", stopwords=stopwords).generate(text) | |
| buf = BytesIO() | |
| wordcloud.to_image().save(buf, format="PNG") | |
| return base64.b64encode(buf.getvalue()).decode() | |
| # -------------------------- | |
| # แปลงชื่อ/ตัวย่อ → (Company Name, Symbol) | |
| # -------------------------- | |
| def resolve_company_symbol(keyword: str): | |
| keyword = keyword.strip() | |
| ticker = None | |
| name = None | |
| try: | |
| data = yf.Ticker(keyword) | |
| info = data.info | |
| if "symbol" in info and info["symbol"]: | |
| ticker = info["symbol"] | |
| name = info.get("longName", info.get("shortName", keyword)) | |
| else: | |
| url = f"https://query2.finance.yahoo.com/v1/finance/search?q={keyword}" | |
| res = requests.get(url).json() | |
| if "quotes" in res and len(res["quotes"]) > 0: | |
| q = res["quotes"][0] | |
| ticker = q.get("symbol") | |
| name = q.get("longname", q.get("shortname", keyword)) | |
| except Exception as e: | |
| print("Lookup failed:", e) | |
| if not ticker: | |
| ticker = keyword.upper() | |
| if not name: | |
| name = keyword.capitalize() | |
| return name, ticker | |
| # -------------------------- | |
| # ดึงข่าว 7 วัน สำหรับ Company + Symbol | |
| # -------------------------- | |
| def fetch_financial_news(keyword): | |
| company, symbol = resolve_company_symbol(keyword) | |
| to_date = datetime.now().strftime('%Y-%m-%d') | |
| from_date = (datetime.now() - timedelta(days=7)).strftime('%Y-%m-%d') | |
| query_keyword = f"({company} OR {symbol}) finance stock" | |
| all_articles = [] | |
| page = 1 | |
| while True: | |
| url = ( | |
| f"https://newsapi.org/v2/everything?" | |
| f"q={query_keyword}&" | |
| f"from={from_date}&to={to_date}&" | |
| f"language=en&sortBy=publishedAt&" | |
| f"pageSize=100&page={page}&apiKey={API_KEY}" | |
| ) | |
| r = requests.get(url) | |
| data = r.json() | |
| if data.get("status") != "ok": | |
| st.error(f"API Error: {data}") | |
| break | |
| articles = data.get("articles", []) | |
| if not articles: | |
| break | |
| for a in articles: | |
| if a["description"]: | |
| all_articles.append({ | |
| "date": pd.to_datetime(a["publishedAt"]), | |
| "text": f"{a['title']} {a['description']}", | |
| "source": a["source"]["name"], | |
| "url": a["url"] | |
| }) | |
| if len(articles) < 100: | |
| break | |
| page += 1 | |
| return pd.DataFrame(all_articles) | |
| # -------------------------- | |
| # ดึงราคาหุ้นตามช่วงเวลาที่กำหนด (และ Flatten Header) | |
| # -------------------------- | |
| def fetch_stock_price(symbol, start_date, end_date): | |
| try: | |
| start_str = (start_date - timedelta(days=2)).strftime('%Y-%m-%d') | |
| end_str = (end_date + timedelta(days=1)).strftime('%Y-%m-%d') | |
| df = yf.download(symbol, start=start_str, end=end_str, interval="1d") | |
| if df.empty: | |
| st.warning("ไม่พบข้อมูลราคาหุ้นในช่วงเวลานี้") | |
| return pd.DataFrame() | |
| df = df.reset_index() | |
| df_subset = df[['Date', 'Close']] | |
| df_subset.columns = ['date', 'price'] | |
| df_subset["date"] = pd.to_datetime(df_subset["date"].dt.date) | |
| return df_subset | |
| except Exception as e: | |
| st.warning(f"ไม่สามารถดึงราคาหุ้นได้: {e}") | |
| return pd.DataFrame() | |
| # -------------------------- | |
| # MAIN APP | |
| # -------------------------- | |
| def main(): | |
| st.title("📰 News Sentiment Analysis for Young Investor") | |
| st.markdown("วิเคราะห์แนวโน้มอารมณ์ของข่าวย้อนหลัง 7 วัน พร้อมราคาหุ้น") | |
| # Sidebar | |
| with st.sidebar: | |
| keyword = st.text_input("ค้นหา Stock Symbol (เช่น AAPL, TSLA):", "") | |
| analyze_btn = st.button("วิเคราะห์เลย") | |
| if not analyze_btn: | |
| st.info("กรอกคำค้นแล้วกด 'วิเคราะห์เลย' เพื่อเริ่มต้น") | |
| return | |
| vader = SentimentIntensityAnalyzer() | |
| # ดึงข่าว | |
| st.info(f"กำลังดึงข่าวย้อนหลัง 7 วันสำหรับ '{keyword}' ...") | |
| news_df = fetch_financial_news(keyword) | |
| if news_df.empty: | |
| st.warning("ไม่พบบทความข่าวในช่วง 7 วันที่ผ่านมา") | |
| return | |
| # วิเคราะห์ sentiment | |
| st.info("กำลังวิเคราะห์อารมณ์ของข่าว...") | |
| news_df["sentiment"] = news_df["text"].apply(lambda x: analyze_text(x, vader)) | |
| news_df["date"] = pd.to_datetime(news_df["date"]) | |
| # แสดง Metric | |
| avg_sentiment = news_df["sentiment"].mean() | |
| pos_pct = (news_df["sentiment"] > 0.1).mean() * 100 | |
| neg_pct = (news_df["sentiment"] < -0.1).mean() * 100 | |
| col1, col2, col3 = st.columns(3) | |
| col1.metric("ค่าเฉลี่ยอารมณ์ข่าว", f"{avg_sentiment:.2f}", "Positive" if avg_sentiment > 0 else "Negative" if avg_sentiment < 0 else "Neutral") | |
| col2.metric("ข่าวเชิงบวก", f"{pos_pct:.1f}%") | |
| col3.metric("ข่าวเชิงลบ", f"{neg_pct:.1f}%") | |
| # Wordcloud | |
| st.subheader("☁️ Word Cloud ของข่าว") | |
| all_text = " ".join(news_df["text"].tolist()) | |
| img = generate_wordcloud(all_text) | |
| st.image(f"data:image/png;base64,{img}", use_column_width=True) | |
| # ----------------------------------------------------------------- | |
| # กราฟไฮบริด (Ref1 + Prediction) | |
| # ----------------------------------------------------------------- | |
| st.subheader("📈 แนวโน้มอารมณ์ของข่าว & ราคาหุ้น") | |
| # 1. รวบรวมข้อมูลข่าวเป็นรายวัน (Daily Aggregation) | |
| news_df["date_day"] = pd.to_datetime(news_df["date"].dt.date) | |
| def sentiment_type(score): | |
| if score > 0.1: | |
| return "positive" | |
| if score < -0.1: | |
| return "negative" | |
| return "neutral" | |
| news_df["sentiment_type"] = news_df["sentiment"].apply(sentiment_type) | |
| daily_avg_sentiment = news_df.groupby("date_day").agg( | |
| avg_sentiment=('sentiment', 'mean') | |
| ).reset_index() | |
| daily_counts = news_df.groupby(["date_day", "sentiment_type"]).size().unstack(fill_value=0).reset_index() | |
| daily_data = pd.merge(daily_avg_sentiment, daily_counts, on="date_day", how="left").fillna(0) | |
| for col in ['positive', 'negative', 'neutral']: | |
| if col not in daily_data.columns: | |
| daily_data[col] = 0 | |
| df_sorted = daily_data.sort_values("date_day").copy() | |
| if len(df_sorted) < 2: | |
| st.warning("มีข้อมูลข่าวไม่เพียงพอที่จะสร้างแนวโน้ม (น้อยกว่า 2 วัน)") | |
| st.subheader("📰 รายการข่าว") | |
| st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True) | |
| return | |
| # 2. ดึงราคาหุ้น | |
| _, symbol = resolve_company_symbol(keyword) | |
| min_date = df_sorted["date_day"].min() | |
| max_date = df_sorted["date_day"].max() | |
| st.info(f"กำลังดึงราคาหุ้น {symbol} ระหว่างวันที่ {min_date.strftime('%Y-%m-%d')} ถึง {max_date.strftime('%Y-%m-%d')}...") | |
| stock_df = fetch_stock_price(symbol, min_date, max_date) | |
| # 3. Merge ข้อมูล 2 ชุด (Sentiment & Stock) | |
| plot_data = pd.merge( | |
| df_sorted, | |
| stock_df, | |
| left_on="date_day", | |
| right_on="date", | |
| how="left" | |
| ) | |
| # 4. (*** ใหม่ ***) คำนวณและตีความ Correlation | |
| correlation = plot_data['price'].corr(plot_data['avg_sentiment']) | |
| corr_text = "ไม่มีความสัมพันธ์กัน" | |
| corr_delta = f"Correlation = {correlation:.2f}" | |
| if pd.isna(correlation): | |
| corr_text = "ไม่สามารถคำนวณได้" | |
| corr_delta = "N/A" | |
| elif correlation > 0.3: | |
| corr_text = "มีความสัมพันธ์กันในทิศทางเดียวกัน" | |
| elif correlation < -0.3: | |
| corr_text = "มีความสัมพันธ์กันในทิศทางตรงข้าม" | |
| # 5. เทรนโมเดล Prediction (ใช้ข้อมูลที่ Merge แล้ว) | |
| plot_data["timestamp"] = (plot_data["date_day"] - plot_data["date_day"].min()).dt.days | |
| # แก้ปัญหา .fit() ถ้ามี NaN ใน sentiment | |
| train_data = plot_data.dropna(subset=['avg_sentiment', 'timestamp']) | |
| if len(train_data) < 2: | |
| st.warning("มีข้อมูลไม่พอสำหรับเทรนโมเดล") | |
| else: | |
| model = LinearRegression() | |
| model.fit(train_data[["timestamp"]], train_data["avg_sentiment"]) | |
| future_days = 7 | |
| future_timestamps = np.arange(plot_data["timestamp"].max() + 1, plot_data["timestamp"].max() + future_days + 1) | |
| future_dates = [plot_data["date_day"].max() + timedelta(days=i) for i in range(1, future_days + 1)] | |
| future_preds = model.predict(future_timestamps.reshape(-1, 1)) | |
| # 6. (*** ใหม่ ***) แสดงผล Correlation Metric | |
| st.metric( | |
| label="วิเคราะห์ความสัมพันธ์ (Sentiment vs Price)", | |
| value=corr_text, | |
| delta=corr_delta | |
| ) | |
| # 7. สร้างกราฟ (Plot) ด้วย Subplots (ใช้ 'plot_data' เป็นหลัก) | |
| fig = make_subplots(rows=2, cols=1, specs=[[{"secondary_y": True}], [{}]], row_heights=[0.7, 0.3], vertical_spacing=0.1, shared_xaxes=True) | |
| # --- กราฟส่วนบน (ราคา, Sentiment, Prediction) --- | |
| fig.add_trace( | |
| go.Scatter( | |
| x=plot_data["date_day"], | |
| y=plot_data["price"], | |
| name=f"{symbol} Stock Price", | |
| mode="lines+markers", | |
| connectgaps=True, | |
| line=dict(color="orange", width=2) | |
| ), | |
| row=1, col=1, | |
| secondary_y=False | |
| ) | |
| fig.add_trace( | |
| go.Scatter( | |
| x=plot_data["date_day"], | |
| y=plot_data["avg_sentiment"], | |
| name="Actual Sentiment (Daily Avg)", | |
| mode="lines+markers", | |
| line=dict(color="blue", width=2) | |
| ), | |
| row=1, col=1, | |
| secondary_y=True | |
| ) | |
| # เพิ่มการตรวจสอบว่า future_preds ถูกสร้างหรือยัง | |
| if 'future_preds' in locals(): | |
| fig.add_trace(go.Scatter( | |
| x=future_dates, | |
| y=future_preds, | |
| mode="lines+markers", | |
| name="Predicted Sentiment (7-day Forecast)", | |
| line=dict(color="#02caf7", dash="dash") | |
| ), | |
| row=1, col=1, | |
| secondary_y=True | |
| ) | |
| # --- กราFส่วนล่าง (จำนวนข่าว) --- | |
| fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["neutral"], name="Neutral", marker_color='rgba(128, 128, 128, 0.7)'), row=2, col=1) | |
| fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["negative"], name="Negative", marker_color='rgba(255, 0, 0, 0.7)'), row=2, col=1) | |
| fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["positive"], name="Positive", marker_color='rgba(0, 128, 0, 0.7)'), row=2, col=1) | |
| # 8. ตกแต่ง Layout | |
| fig.update_layout( | |
| title=f"แนวโน้มอารมณ์ข่าว & ราคาหุ้น '{keyword}'", | |
| template="plotly_white", | |
| hovermode="x unified", | |
| barmode='stack', | |
| legend=dict(orientation='h', yanchor='bottom', y=1.02, xanchor='right', x=1), | |
| height=600, | |
| margin=dict(l=20, r=20, t=80, b=20) | |
| ) | |
| fig.update_yaxes(title_text="Stock Price", row=1, col=1, secondary_y=False) | |
| fig.update_yaxes(title_text="Sentiment Score", range=[-1, 1], row=1, col=1, secondary_y=True) | |
| fig.update_yaxes(title_text="Article Count", row=2, col=1) | |
| fig.update_xaxes(title_text="วันที่", row=2, col=1) | |
| st.plotly_chart(fig, use_container_width=True) | |
| # แสดงข่าว (ยังใช้ news_df ตัวเต็ม) | |
| st.subheader("📰 รายการข่าว") | |
| st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True) | |
| if __name__ == "__main__": | |
| nltk.download("stopwords", quiet=True) | |
| main() |