Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -2,14 +2,17 @@ import streamlit as st
|
|
| 2 |
import requests
|
| 3 |
import pandas as pd
|
| 4 |
from datetime import datetime, timedelta
|
|
|
|
|
|
|
| 5 |
import nltk
|
|
|
|
|
|
|
|
|
|
| 6 |
import numpy as np
|
| 7 |
from sklearn.linear_model import LinearRegression
|
| 8 |
import plotly.graph_objects as go
|
| 9 |
from plotly.subplots import make_subplots
|
| 10 |
import yfinance as yf
|
| 11 |
-
import torch
|
| 12 |
-
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
|
| 13 |
|
| 14 |
# --------------------------
|
| 15 |
# CONFIG
|
|
@@ -17,62 +20,22 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipe
|
|
| 17 |
st.set_page_config(page_title="📰 News Sentiment Analysis for Young Investor", layout="wide")
|
| 18 |
API_KEY = "88bc396d4eab4be494a4b86ec842db47"
|
| 19 |
|
| 20 |
-
# --------------------------
|
| 21 |
-
# โหลด FinBERT model
|
| 22 |
-
# --------------------------
|
| 23 |
-
@st.cache_resource
|
| 24 |
-
def load_finbert():
|
| 25 |
-
tokenizer = AutoTokenizer.from_pretrained("project-aps/finbert-finetune")
|
| 26 |
-
model = AutoModelForSequenceClassification.from_pretrained("project-aps/finbert-finetune")
|
| 27 |
-
return tokenizer, model
|
| 28 |
-
|
| 29 |
-
tokenizer, model = load_finbert()
|
| 30 |
-
|
| 31 |
-
# --------------------------
|
| 32 |
-
# โหลด Zero-shot classifier สำหรับธีมข่าว
|
| 33 |
-
# --------------------------
|
| 34 |
-
@st.cache_resource
|
| 35 |
-
def load_theme_classifier():
|
| 36 |
-
return pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
|
| 37 |
-
|
| 38 |
-
theme_classifier = load_theme_classifier()
|
| 39 |
-
candidate_labels = ["Stock Movement", "Earnings", "M&A", "Regulation", "Product Launch", "Market Analysis"]
|
| 40 |
-
|
| 41 |
# --------------------------
|
| 42 |
# UTILITIES
|
| 43 |
# --------------------------
|
| 44 |
-
def analyze_text(text):
|
| 45 |
-
|
| 46 |
-
if not text or not text.strip():
|
| 47 |
return 0
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
)
|
| 56 |
-
|
| 57 |
-
with torch.no_grad():
|
| 58 |
-
outputs = model(**inputs)
|
| 59 |
-
logits = outputs.logits
|
| 60 |
-
probs = torch.softmax(logits, dim=1).numpy()[0]
|
| 61 |
-
|
| 62 |
-
# FinBERT = [negative, neutral, positive]
|
| 63 |
-
score = (-1 * probs[0]) + (0 * probs[1]) + (1 * probs[2])
|
| 64 |
-
return float(score)
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
def summarize_themes(news_texts):
|
| 68 |
-
"""สรุปธีมข่าวด้วย Zero-shot classification"""
|
| 69 |
-
themes = []
|
| 70 |
-
for text in news_texts:
|
| 71 |
-
if not text.strip():
|
| 72 |
-
continue
|
| 73 |
-
result = theme_classifier(text, candidate_labels)
|
| 74 |
-
themes.append(result["labels"][0])
|
| 75 |
-
return themes
|
| 76 |
|
| 77 |
# --------------------------
|
| 78 |
# แปลงชื่อ/ตัวย่อ → (Company Name, Symbol)
|
|
@@ -81,7 +44,6 @@ def resolve_company_symbol(keyword: str):
|
|
| 81 |
keyword = keyword.strip()
|
| 82 |
ticker = None
|
| 83 |
name = None
|
| 84 |
-
|
| 85 |
try:
|
| 86 |
data = yf.Ticker(keyword)
|
| 87 |
info = data.info
|
|
@@ -95,27 +57,23 @@ def resolve_company_symbol(keyword: str):
|
|
| 95 |
q = res["quotes"][0]
|
| 96 |
ticker = q.get("symbol")
|
| 97 |
name = q.get("longname", q.get("shortname", keyword))
|
| 98 |
-
except:
|
| 99 |
-
|
| 100 |
-
|
| 101 |
if not ticker:
|
| 102 |
ticker = keyword.upper()
|
| 103 |
if not name:
|
| 104 |
name = keyword.capitalize()
|
| 105 |
-
|
| 106 |
return name, ticker
|
| 107 |
|
| 108 |
# --------------------------
|
| 109 |
-
# ดึงข่าว 7 วัน
|
| 110 |
# --------------------------
|
| 111 |
@st.cache_data(ttl=3600)
|
| 112 |
def fetch_financial_news(keyword):
|
| 113 |
company, symbol = resolve_company_symbol(keyword)
|
| 114 |
to_date = datetime.now().strftime('%Y-%m-%d')
|
| 115 |
from_date = (datetime.now() - timedelta(days=7)).strftime('%Y-%m-%d')
|
| 116 |
-
|
| 117 |
query_keyword = f"({company} OR {symbol}) finance stock"
|
| 118 |
-
|
| 119 |
all_articles = []
|
| 120 |
page = 1
|
| 121 |
while True:
|
|
@@ -131,11 +89,9 @@ def fetch_financial_news(keyword):
|
|
| 131 |
if data.get("status") != "ok":
|
| 132 |
st.error(f"API Error: {data}")
|
| 133 |
break
|
| 134 |
-
|
| 135 |
articles = data.get("articles", [])
|
| 136 |
if not articles:
|
| 137 |
break
|
| 138 |
-
|
| 139 |
for a in articles:
|
| 140 |
if a["description"]:
|
| 141 |
all_articles.append({
|
|
@@ -144,15 +100,13 @@ def fetch_financial_news(keyword):
|
|
| 144 |
"source": a["source"]["name"],
|
| 145 |
"url": a["url"]
|
| 146 |
})
|
| 147 |
-
|
| 148 |
if len(articles) < 100:
|
| 149 |
break
|
| 150 |
page += 1
|
| 151 |
-
|
| 152 |
return pd.DataFrame(all_articles)
|
| 153 |
|
| 154 |
# --------------------------
|
| 155 |
-
#
|
| 156 |
# --------------------------
|
| 157 |
@st.cache_data(ttl=3600)
|
| 158 |
def fetch_stock_price(symbol, start_date, end_date):
|
|
@@ -160,20 +114,16 @@ def fetch_stock_price(symbol, start_date, end_date):
|
|
| 160 |
start_str = (start_date - timedelta(days=2)).strftime('%Y-%m-%d')
|
| 161 |
end_str = (end_date + timedelta(days=1)).strftime('%Y-%m-%d')
|
| 162 |
df = yf.download(symbol, start=start_str, end=end_str, interval="1d")
|
| 163 |
-
|
| 164 |
if df.empty:
|
| 165 |
-
st.warning("
|
| 166 |
return pd.DataFrame()
|
| 167 |
-
|
| 168 |
df = df.reset_index()
|
| 169 |
df_subset = df[['Date', 'Close']]
|
| 170 |
df_subset.columns = ['date', 'price']
|
| 171 |
df_subset["date"] = pd.to_datetime(df_subset["date"].dt.date)
|
| 172 |
-
|
| 173 |
return df_subset
|
| 174 |
-
|
| 175 |
except Exception as e:
|
| 176 |
-
st.warning(f"
|
| 177 |
return pd.DataFrame()
|
| 178 |
|
| 179 |
# --------------------------
|
|
@@ -189,44 +139,44 @@ def main():
|
|
| 189 |
analyze_btn = st.button("วิเคราะห์เลย")
|
| 190 |
|
| 191 |
if not analyze_btn:
|
| 192 |
-
st.info("กรอกคำค้นแล้วกด 'วิเคราะห์เลย'")
|
| 193 |
return
|
| 194 |
|
|
|
|
| 195 |
# ดึงข่าว
|
| 196 |
-
st.info(f"กำลังดึงข่าวย้อนหลัง 7 วันสำหรับ '{keyword}'...")
|
| 197 |
news_df = fetch_financial_news(keyword)
|
|
|
|
| 198 |
if news_df.empty:
|
| 199 |
-
st.warning("
|
| 200 |
return
|
| 201 |
|
| 202 |
-
# วิเคราะห์
|
| 203 |
st.info("กำลังวิเคราะห์อารมณ์ของข่าว...")
|
| 204 |
-
news_df["sentiment"] = news_df["text"].apply(analyze_text)
|
| 205 |
news_df["date"] = pd.to_datetime(news_df["date"])
|
| 206 |
|
| 207 |
-
#
|
| 208 |
avg_sentiment = news_df["sentiment"].mean()
|
| 209 |
pos_pct = (news_df["sentiment"] > 0.1).mean() * 100
|
| 210 |
neg_pct = (news_df["sentiment"] < -0.1).mean() * 100
|
| 211 |
|
| 212 |
col1, col2, col3 = st.columns(3)
|
| 213 |
-
col1.metric("ค่าเฉลี่ยอารมณ์ข่าว", f"{avg_sentiment:.2f}")
|
| 214 |
col2.metric("ข่าวเชิงบวก", f"{pos_pct:.1f}%")
|
| 215 |
col3.metric("ข่าวเชิงลบ", f"{neg_pct:.1f}%")
|
| 216 |
|
| 217 |
-
#
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
theme_counts = news_df["theme"].value_counts()
|
| 223 |
-
st.bar_chart(theme_counts)
|
| 224 |
-
|
| 225 |
-
# ---------------------------------------------------------
|
| 226 |
-
# ส่วนกราฟ Sentiment & Price (เหมือนเดิม)
|
| 227 |
-
# ---------------------------------------------------------
|
| 228 |
-
st.subheader("📈 แนวโน้มอารมณ์ของข่าว & ราคาหุ้น")
|
| 229 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 230 |
news_df["date_day"] = pd.to_datetime(news_df["date"].dt.date)
|
| 231 |
|
| 232 |
def sentiment_type(score):
|
|
@@ -237,99 +187,140 @@ def main():
|
|
| 237 |
return "neutral"
|
| 238 |
|
| 239 |
news_df["sentiment_type"] = news_df["sentiment"].apply(sentiment_type)
|
| 240 |
-
|
| 241 |
-
|
|
|
|
| 242 |
daily_counts = news_df.groupby(["date_day", "sentiment_type"]).size().unstack(fill_value=0).reset_index()
|
|
|
|
| 243 |
|
| 244 |
-
|
|
|
|
|
|
|
|
|
|
| 245 |
|
| 246 |
if len(df_sorted) < 2:
|
| 247 |
-
st.warning("
|
| 248 |
-
st.
|
|
|
|
| 249 |
return
|
| 250 |
|
| 251 |
-
# ดึงราคาหุ้น
|
| 252 |
_, symbol = resolve_company_symbol(keyword)
|
| 253 |
-
min_date
|
| 254 |
-
|
|
|
|
| 255 |
stock_df = fetch_stock_price(symbol, min_date, max_date)
|
| 256 |
|
| 257 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
|
| 259 |
-
# Correlation
|
| 260 |
correlation = plot_data['price'].corr(plot_data['avg_sentiment'])
|
| 261 |
-
corr_text = "
|
| 262 |
-
|
| 263 |
-
|
| 264 |
-
|
| 265 |
-
|
| 266 |
-
|
| 267 |
-
|
| 268 |
-
|
|
|
|
|
|
|
|
|
|
| 269 |
plot_data["timestamp"] = (plot_data["date_day"] - plot_data["date_day"].min()).dt.days
|
| 270 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 271 |
|
| 272 |
-
|
| 273 |
-
|
| 274 |
-
|
|
|
|
|
|
|
|
|
|
| 275 |
|
| 276 |
-
|
| 277 |
-
|
| 278 |
-
|
| 279 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 280 |
)
|
| 281 |
-
future_dates = [plot_data["date_day"].max() + timedelta(days=i) for i in range(1, future_days + 1)]
|
| 282 |
-
future_preds = model_lr.predict(future_timestamps.reshape(-1, 1))
|
| 283 |
-
|
| 284 |
-
# Plot
|
| 285 |
-
fig = make_subplots(rows=2, cols=1, specs=[[{"secondary_y": True}], [{}]],
|
| 286 |
-
row_heights=[0.7, 0.3], vertical_spacing=0.1,
|
| 287 |
-
shared_xaxes=True)
|
| 288 |
-
|
| 289 |
-
# ราคาหุ้น
|
| 290 |
-
fig.add_trace(go.Scatter(x=plot_data["date_day"], y=plot_data["price"], name=f"{symbol} Price",
|
| 291 |
-
mode="lines+markers", line=dict(color="orange")), row=1, col=1, secondary_y=False)
|
| 292 |
-
# Sentiment จริง
|
| 293 |
-
fig.add_trace(go.Scatter(x=plot_data["date_day"], y=plot_data["avg_sentiment"], name="Actual Sentiment",
|
| 294 |
-
mode="lines+markers", line=dict(color="blue")), row=1, col=1, secondary_y=True)
|
| 295 |
-
# Sentiment พยากรณ์
|
| 296 |
-
if "future_preds" in locals():
|
| 297 |
-
fig.add_trace(go.Scatter(x=future_dates, y=future_preds, name="Predicted Sentiment",
|
| 298 |
-
mode="lines+markers", line=dict(color="#05a0fa", dash="dash")), row=1, col=1, secondary_y=True)
|
| 299 |
-
# เส้นเชื่อม Actual -> Predicted
|
| 300 |
-
last_actual_date = plot_data["date_day"].max()
|
| 301 |
-
last_actual_value = plot_data["avg_sentiment"].iloc[-1]
|
| 302 |
-
first_pred_date = future_dates[0]
|
| 303 |
-
first_pred_value = future_preds[0]
|
| 304 |
-
fig.add_trace(go.Scatter(x=[last_actual_date, first_pred_date],
|
| 305 |
-
y=[last_actual_value, first_pred_value],
|
| 306 |
-
mode="lines",
|
| 307 |
-
line=dict(color="#05a0fa", dash="dot"),
|
| 308 |
-
name="Connector Actual→Predicted"), row=1, col=1, secondary_y=True)
|
| 309 |
-
|
| 310 |
-
# จำนวนข่าว
|
| 311 |
-
for col in ["neutral", "negative", "positive"]:
|
| 312 |
-
if col not in plot_data.columns:
|
| 313 |
-
plot_data[col] = 0
|
| 314 |
-
fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["neutral"], name="Neutral",
|
| 315 |
-
marker_color='rgba(128, 128, 128, 0.7)'), row=2, col=1)
|
| 316 |
-
fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["negative"], name="Negative",
|
| 317 |
-
marker_color='rgba(255, 0, 0, 0.7)'), row=2, col=1)
|
| 318 |
-
fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["positive"], name="Positive",
|
| 319 |
-
marker_color='rgba(0, 128, 0, 0.7)'), row=2, col=1)
|
| 320 |
-
|
| 321 |
-
fig.update_layout(title=f"แนวโน้มอารมณ์ของข่าว + ราคาหุ้น ({symbol})",
|
| 322 |
-
barmode="stack", height=650, hovermode="x unified", template="plotly_white")
|
| 323 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 324 |
st.plotly_chart(fig, use_container_width=True)
|
| 325 |
|
| 326 |
-
#
|
| 327 |
-
st.subheader("📰
|
| 328 |
-
st.dataframe(news_df[["date", "source", "text", "sentiment", "
|
| 329 |
|
| 330 |
-
# ---------------------------------------------------------
|
| 331 |
-
# RUN APP
|
| 332 |
-
# ---------------------------------------------------------
|
| 333 |
if __name__ == "__main__":
|
| 334 |
nltk.download("stopwords", quiet=True)
|
| 335 |
-
main()
|
|
|
|
| 2 |
import requests
|
| 3 |
import pandas as pd
|
| 4 |
from datetime import datetime, timedelta
|
| 5 |
+
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
|
| 6 |
+
from textblob import TextBlob
|
| 7 |
import nltk
|
| 8 |
+
from wordcloud import WordCloud
|
| 9 |
+
import base64
|
| 10 |
+
from io import BytesIO
|
| 11 |
import numpy as np
|
| 12 |
from sklearn.linear_model import LinearRegression
|
| 13 |
import plotly.graph_objects as go
|
| 14 |
from plotly.subplots import make_subplots
|
| 15 |
import yfinance as yf
|
|
|
|
|
|
|
| 16 |
|
| 17 |
# --------------------------
|
| 18 |
# CONFIG
|
|
|
|
| 20 |
st.set_page_config(page_title="📰 News Sentiment Analysis for Young Investor", layout="wide")
|
| 21 |
API_KEY = "88bc396d4eab4be494a4b86ec842db47"
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
# --------------------------
|
| 24 |
# UTILITIES
|
| 25 |
# --------------------------
|
| 26 |
+
def analyze_text(text, vader):
|
| 27 |
+
if not text.strip():
|
|
|
|
| 28 |
return 0
|
| 29 |
+
vader_score = vader.polarity_scores(text)["compound"]
|
| 30 |
+
textblob_score = TextBlob(text).sentiment.polarity
|
| 31 |
+
return np.mean([vader_score, textblob_score])
|
| 32 |
|
| 33 |
+
def generate_wordcloud(text):
|
| 34 |
+
stopwords = nltk.corpus.stopwords.words('english')
|
| 35 |
+
wordcloud = WordCloud(width=800, height=400, background_color="white", stopwords=stopwords).generate(text)
|
| 36 |
+
buf = BytesIO()
|
| 37 |
+
wordcloud.to_image().save(buf, format="PNG")
|
| 38 |
+
return base64.b64encode(buf.getvalue()).decode()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
# --------------------------
|
| 41 |
# แปลงชื่อ/ตัวย่อ → (Company Name, Symbol)
|
|
|
|
| 44 |
keyword = keyword.strip()
|
| 45 |
ticker = None
|
| 46 |
name = None
|
|
|
|
| 47 |
try:
|
| 48 |
data = yf.Ticker(keyword)
|
| 49 |
info = data.info
|
|
|
|
| 57 |
q = res["quotes"][0]
|
| 58 |
ticker = q.get("symbol")
|
| 59 |
name = q.get("longname", q.get("shortname", keyword))
|
| 60 |
+
except Exception as e:
|
| 61 |
+
print("Lookup failed:", e)
|
|
|
|
| 62 |
if not ticker:
|
| 63 |
ticker = keyword.upper()
|
| 64 |
if not name:
|
| 65 |
name = keyword.capitalize()
|
|
|
|
| 66 |
return name, ticker
|
| 67 |
|
| 68 |
# --------------------------
|
| 69 |
+
# ดึงข่าว 7 วัน สำหรับ Company + Symbol
|
| 70 |
# --------------------------
|
| 71 |
@st.cache_data(ttl=3600)
|
| 72 |
def fetch_financial_news(keyword):
|
| 73 |
company, symbol = resolve_company_symbol(keyword)
|
| 74 |
to_date = datetime.now().strftime('%Y-%m-%d')
|
| 75 |
from_date = (datetime.now() - timedelta(days=7)).strftime('%Y-%m-%d')
|
|
|
|
| 76 |
query_keyword = f"({company} OR {symbol}) finance stock"
|
|
|
|
| 77 |
all_articles = []
|
| 78 |
page = 1
|
| 79 |
while True:
|
|
|
|
| 89 |
if data.get("status") != "ok":
|
| 90 |
st.error(f"API Error: {data}")
|
| 91 |
break
|
|
|
|
| 92 |
articles = data.get("articles", [])
|
| 93 |
if not articles:
|
| 94 |
break
|
|
|
|
| 95 |
for a in articles:
|
| 96 |
if a["description"]:
|
| 97 |
all_articles.append({
|
|
|
|
| 100 |
"source": a["source"]["name"],
|
| 101 |
"url": a["url"]
|
| 102 |
})
|
|
|
|
| 103 |
if len(articles) < 100:
|
| 104 |
break
|
| 105 |
page += 1
|
|
|
|
| 106 |
return pd.DataFrame(all_articles)
|
| 107 |
|
| 108 |
# --------------------------
|
| 109 |
+
# ดึงราคาหุ้นตามช่วงเวลาที่กำหนด (และ Flatten Header)
|
| 110 |
# --------------------------
|
| 111 |
@st.cache_data(ttl=3600)
|
| 112 |
def fetch_stock_price(symbol, start_date, end_date):
|
|
|
|
| 114 |
start_str = (start_date - timedelta(days=2)).strftime('%Y-%m-%d')
|
| 115 |
end_str = (end_date + timedelta(days=1)).strftime('%Y-%m-%d')
|
| 116 |
df = yf.download(symbol, start=start_str, end=end_str, interval="1d")
|
|
|
|
| 117 |
if df.empty:
|
| 118 |
+
st.warning("ไม่พบข้อมูลราคาหุ้นในช่วงเวลานี้")
|
| 119 |
return pd.DataFrame()
|
|
|
|
| 120 |
df = df.reset_index()
|
| 121 |
df_subset = df[['Date', 'Close']]
|
| 122 |
df_subset.columns = ['date', 'price']
|
| 123 |
df_subset["date"] = pd.to_datetime(df_subset["date"].dt.date)
|
|
|
|
| 124 |
return df_subset
|
|
|
|
| 125 |
except Exception as e:
|
| 126 |
+
st.warning(f"ไม่สามารถดึงราคาหุ้นได้: {e}")
|
| 127 |
return pd.DataFrame()
|
| 128 |
|
| 129 |
# --------------------------
|
|
|
|
| 139 |
analyze_btn = st.button("วิเคราะห์เลย")
|
| 140 |
|
| 141 |
if not analyze_btn:
|
| 142 |
+
st.info("กรอกคำค้นแล้วกด 'วิเคราะห์เลย' เพื่อเริ่มต้น")
|
| 143 |
return
|
| 144 |
|
| 145 |
+
vader = SentimentIntensityAnalyzer()
|
| 146 |
# ดึงข่าว
|
| 147 |
+
st.info(f"กำลังดึงข่าวย้อนหลัง 7 วันสำหรับ '{keyword}' ...")
|
| 148 |
news_df = fetch_financial_news(keyword)
|
| 149 |
+
|
| 150 |
if news_df.empty:
|
| 151 |
+
st.warning("ไม่พบบทความข่าวในช่วง 7 วันที่ผ่านมา")
|
| 152 |
return
|
| 153 |
|
| 154 |
+
# วิเคราะห์ sentiment
|
| 155 |
st.info("กำลังวิเคราะห์อารมณ์ของข่าว...")
|
| 156 |
+
news_df["sentiment"] = news_df["text"].apply(lambda x: analyze_text(x, vader))
|
| 157 |
news_df["date"] = pd.to_datetime(news_df["date"])
|
| 158 |
|
| 159 |
+
# แสดง Metric
|
| 160 |
avg_sentiment = news_df["sentiment"].mean()
|
| 161 |
pos_pct = (news_df["sentiment"] > 0.1).mean() * 100
|
| 162 |
neg_pct = (news_df["sentiment"] < -0.1).mean() * 100
|
| 163 |
|
| 164 |
col1, col2, col3 = st.columns(3)
|
| 165 |
+
col1.metric("ค่าเฉลี่ยอารมณ์ข่าว", f"{avg_sentiment:.2f}", "Positive" if avg_sentiment > 0 else "Negative" if avg_sentiment < 0 else "Neutral")
|
| 166 |
col2.metric("ข่าวเชิงบวก", f"{pos_pct:.1f}%")
|
| 167 |
col3.metric("ข่าวเชิงลบ", f"{neg_pct:.1f}%")
|
| 168 |
|
| 169 |
+
# Wordcloud
|
| 170 |
+
st.subheader("☁️ Word Cloud ของข่าว")
|
| 171 |
+
all_text = " ".join(news_df["text"].tolist())
|
| 172 |
+
img = generate_wordcloud(all_text)
|
| 173 |
+
st.image(f"data:image/png;base64,{img}", use_column_width=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
|
| 175 |
+
# -----------------------------------------------------------------
|
| 176 |
+
# กราฟไฮบริด (Ref1 + Prediction)
|
| 177 |
+
# -----------------------------------------------------------------
|
| 178 |
+
st.subheader("📈 แนวโน้มอารมณ์ของข่าว & ราคาหุ้น")
|
| 179 |
+
# 1. รวบรวมข้อมูลข่าวเป็นรายวัน (Daily Aggregation)
|
| 180 |
news_df["date_day"] = pd.to_datetime(news_df["date"].dt.date)
|
| 181 |
|
| 182 |
def sentiment_type(score):
|
|
|
|
| 187 |
return "neutral"
|
| 188 |
|
| 189 |
news_df["sentiment_type"] = news_df["sentiment"].apply(sentiment_type)
|
| 190 |
+
daily_avg_sentiment = news_df.groupby("date_day").agg(
|
| 191 |
+
avg_sentiment=('sentiment', 'mean')
|
| 192 |
+
).reset_index()
|
| 193 |
daily_counts = news_df.groupby(["date_day", "sentiment_type"]).size().unstack(fill_value=0).reset_index()
|
| 194 |
+
daily_data = pd.merge(daily_avg_sentiment, daily_counts, on="date_day", how="left").fillna(0)
|
| 195 |
|
| 196 |
+
for col in ['positive', 'negative', 'neutral']:
|
| 197 |
+
if col not in daily_data.columns:
|
| 198 |
+
daily_data[col] = 0
|
| 199 |
+
df_sorted = daily_data.sort_values("date_day").copy()
|
| 200 |
|
| 201 |
if len(df_sorted) < 2:
|
| 202 |
+
st.warning("มีข้อมูลข่าวไม่เพียงพอที่จะสร้างแนวโน้ม (น้อยกว่า 2 วัน)")
|
| 203 |
+
st.subheader("📰 รายการข่าว")
|
| 204 |
+
st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True)
|
| 205 |
return
|
| 206 |
|
| 207 |
+
# 2. ดึงราคาหุ้น
|
| 208 |
_, symbol = resolve_company_symbol(keyword)
|
| 209 |
+
min_date = df_sorted["date_day"].min()
|
| 210 |
+
max_date = df_sorted["date_day"].max()
|
| 211 |
+
st.info(f"กำลังดึงราคาหุ้น {symbol} ระหว่างวันที่ {min_date.strftime('%Y-%m-%d')} ถึง {max_date.strftime('%Y-%m-%d')}...")
|
| 212 |
stock_df = fetch_stock_price(symbol, min_date, max_date)
|
| 213 |
|
| 214 |
+
# 3. Merge ข้อมูล 2 ชุด (Sentiment & Stock)
|
| 215 |
+
plot_data = pd.merge(
|
| 216 |
+
df_sorted,
|
| 217 |
+
stock_df,
|
| 218 |
+
left_on="date_day",
|
| 219 |
+
right_on="date",
|
| 220 |
+
how="left"
|
| 221 |
+
)
|
| 222 |
|
| 223 |
+
# 4. (*** ใหม่ ***) คำนวณและตีความ Correlation
|
| 224 |
correlation = plot_data['price'].corr(plot_data['avg_sentiment'])
|
| 225 |
+
corr_text = "ไม่มีความสัมพันธ์กัน"
|
| 226 |
+
corr_delta = f"Correlation = {correlation:.2f}"
|
| 227 |
+
if pd.isna(correlation):
|
| 228 |
+
corr_text = "ไม่สามารถคำนวณได้"
|
| 229 |
+
corr_delta = "N/A"
|
| 230 |
+
elif correlation > 0.3:
|
| 231 |
+
corr_text = "มีความสัมพันธ์กันในทิศทางเดียวกัน"
|
| 232 |
+
elif correlation < -0.3:
|
| 233 |
+
corr_text = "มีความสัมพันธ์กันในทิศทางตรงข้าม"
|
| 234 |
+
|
| 235 |
+
# 5. เทรนโมเดล Prediction (ใช้ข้อมูลที่ Merge แล้ว)
|
| 236 |
plot_data["timestamp"] = (plot_data["date_day"] - plot_data["date_day"].min()).dt.days
|
| 237 |
+
# แก้ปัญหา .fit() ถ้ามี NaN ใน sentiment
|
| 238 |
+
train_data = plot_data.dropna(subset=['avg_sentiment', 'timestamp'])
|
| 239 |
+
|
| 240 |
+
if len(train_data) < 2:
|
| 241 |
+
st.warning("มีข้อมูลไม่พอสำหรับเทรนโมเดล")
|
| 242 |
+
else:
|
| 243 |
+
model = LinearRegression()
|
| 244 |
+
model.fit(train_data[["timestamp"]], train_data["avg_sentiment"])
|
| 245 |
+
future_days = 7
|
| 246 |
+
future_timestamps = np.arange(plot_data["timestamp"].max() + 1, plot_data["timestamp"].max() + future_days + 1)
|
| 247 |
+
future_dates = [plot_data["date_day"].max() + timedelta(days=i) for i in range(1, future_days + 1)]
|
| 248 |
+
future_preds = model.predict(future_timestamps.reshape(-1, 1))
|
| 249 |
|
| 250 |
+
# 6. (*** ใหม่ ***) แสดงผล Correlation Metric
|
| 251 |
+
st.metric(
|
| 252 |
+
label="วิเคราะห์ความสัมพันธ์ (Sentiment vs Price)",
|
| 253 |
+
value=corr_text,
|
| 254 |
+
delta=corr_delta
|
| 255 |
+
)
|
| 256 |
|
| 257 |
+
# 7. ส���้างกราฟ (Plot) ด้วย Subplots (ใช้ 'plot_data' เป็นหลัก)
|
| 258 |
+
fig = make_subplots(rows=2, cols=1, specs=[[{"secondary_y": True}], [{}]], row_heights=[0.7, 0.3], vertical_spacing=0.1, shared_xaxes=True)
|
| 259 |
+
|
| 260 |
+
# --- กราฟส่วนบน (ราคา, Sentiment, Prediction) ---
|
| 261 |
+
fig.add_trace(
|
| 262 |
+
go.Scatter(
|
| 263 |
+
x=plot_data["date_day"],
|
| 264 |
+
y=plot_data["price"],
|
| 265 |
+
name=f"{symbol} Stock Price",
|
| 266 |
+
mode="lines+markers",
|
| 267 |
+
connectgaps=True,
|
| 268 |
+
line=dict(color="orange", width=2)
|
| 269 |
+
),
|
| 270 |
+
row=1, col=1,
|
| 271 |
+
secondary_y=False
|
| 272 |
+
)
|
| 273 |
+
|
| 274 |
+
fig.add_trace(
|
| 275 |
+
go.Scatter(
|
| 276 |
+
x=plot_data["date_day"],
|
| 277 |
+
y=plot_data["avg_sentiment"],
|
| 278 |
+
name="Actual Sentiment (Daily Avg)",
|
| 279 |
+
mode="lines+markers",
|
| 280 |
+
line=dict(color="blue", width=2)
|
| 281 |
+
),
|
| 282 |
+
row=1, col=1,
|
| 283 |
+
secondary_y=True
|
| 284 |
+
)
|
| 285 |
+
|
| 286 |
+
# เพิ่มการตรวจสอบว่า future_preds ถูกสร้างหรือยัง
|
| 287 |
+
if 'future_preds' in locals():
|
| 288 |
+
fig.add_trace(go.Scatter(
|
| 289 |
+
x=future_dates,
|
| 290 |
+
y=future_preds,
|
| 291 |
+
mode="lines+markers",
|
| 292 |
+
name="Predicted Sentiment (7-day Forecast)",
|
| 293 |
+
line=dict(color="#02caf7", dash="dash")
|
| 294 |
+
),
|
| 295 |
+
row=1, col=1,
|
| 296 |
+
secondary_y=True
|
| 297 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 298 |
|
| 299 |
+
# --- กราFส่วนล่าง (จำนวนข่าว) ---
|
| 300 |
+
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)
|
| 301 |
+
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)
|
| 302 |
+
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)
|
| 303 |
+
|
| 304 |
+
# 8. ตกแต่ง Layout
|
| 305 |
+
fig.update_layout(
|
| 306 |
+
title=f"แนวโน้มอารมณ์ข่าว & ราคาหุ้น '{keyword}'",
|
| 307 |
+
template="plotly_white",
|
| 308 |
+
hovermode="x unified",
|
| 309 |
+
barmode='stack',
|
| 310 |
+
legend=dict(orientation='h', yanchor='bottom', y=1.02, xanchor='right', x=1),
|
| 311 |
+
height=600,
|
| 312 |
+
margin=dict(l=20, r=20, t=80, b=20)
|
| 313 |
+
)
|
| 314 |
+
fig.update_yaxes(title_text="Stock Price", row=1, col=1, secondary_y=False)
|
| 315 |
+
fig.update_yaxes(title_text="Sentiment Score", range=[-1, 1], row=1, col=1, secondary_y=True)
|
| 316 |
+
fig.update_yaxes(title_text="Article Count", row=2, col=1)
|
| 317 |
+
fig.update_xaxes(title_text="วันที่", row=2, col=1)
|
| 318 |
st.plotly_chart(fig, use_container_width=True)
|
| 319 |
|
| 320 |
+
# แสดงข่าว (ยังใช้ news_df ตัวเต็ม)
|
| 321 |
+
st.subheader("📰 รายการข่าว")
|
| 322 |
+
st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True)
|
| 323 |
|
|
|
|
|
|
|
|
|
|
| 324 |
if __name__ == "__main__":
|
| 325 |
nltk.download("stopwords", quiet=True)
|
| 326 |
+
main()
|