Spaces:
Sleeping
Sleeping
Update and rename sentiment.py to backend/sentiment.py
Browse files- sentiment.py → backend/sentiment.py +184 -14
sentiment.py → backend/sentiment.py
RENAMED
|
@@ -17,11 +17,34 @@ MODEL_NAME = "ProsusAI/finbert"
|
|
| 17 |
_tokenizer = BertTokenizer.from_pretrained(MODEL_NAME)
|
| 18 |
_finbert = BertForSequenceClassification.from_pretrained(MODEL_NAME)
|
| 19 |
_finbert.eval()
|
| 20 |
-
|
|
|
|
| 21 |
|
| 22 |
VADER_WEIGHT = 0.4
|
| 23 |
FINBERT_WEIGHT = 0.6
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
def _score_vader(text: str) -> dict:
|
| 27 |
scores = _vader.polarity_scores(text)
|
|
@@ -46,7 +69,10 @@ def _score_finbert(text: str) -> dict:
|
|
| 46 |
probs = torch.nn.functional.softmax(logits, dim=-1).squeeze().tolist()
|
| 47 |
idx = int(np.argmax(probs))
|
| 48 |
|
| 49 |
-
|
|
|
|
|
|
|
|
|
|
| 50 |
return {
|
| 51 |
"label": FINBERT_LABELS[idx],
|
| 52 |
"score": round(signed_score, 4),
|
|
@@ -91,9 +117,155 @@ def fetch_news_headlines(ticker: str, max_items: int = 10) -> list[str]:
|
|
| 91 |
return headlines
|
| 92 |
|
| 93 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
def analyze_sentiment(ticker: str) -> dict:
|
| 95 |
headlines = fetch_news_headlines(ticker)
|
| 96 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
return {
|
| 98 |
"ticker": ticker,
|
| 99 |
"articles_analyzed": 0,
|
|
@@ -101,15 +273,13 @@ def analyze_sentiment(ticker: str) -> dict:
|
|
| 101 |
"overall_sentiment": "neutral",
|
| 102 |
"overall_score": 0.0,
|
| 103 |
"contradictory_dampened": False,
|
| 104 |
-
"method": "
|
| 105 |
}
|
| 106 |
|
| 107 |
-
|
| 108 |
-
raw_scores = [d["combined_score"] for d in details]
|
| 109 |
avg = float(np.mean(raw_scores))
|
| 110 |
|
| 111 |
-
# Dampen one-off outliers
|
| 112 |
-
# shouldn't override macro. Use variance and median to detect contradiction.
|
| 113 |
contradictory_dampened = False
|
| 114 |
n = len(raw_scores)
|
| 115 |
if n >= 2:
|
|
@@ -119,22 +289,22 @@ def analyze_sentiment(ticker: str) -> dict:
|
|
| 119 |
contradictory = variance > 0.15 or abs(avg - median) > 0.35
|
| 120 |
if contradictory:
|
| 121 |
contradictory_dampened = True
|
| 122 |
-
# Pull toward median
|
| 123 |
avg = 0.4 * avg + 0.6 * median
|
| 124 |
|
| 125 |
-
if avg > 0.
|
| 126 |
overall = "positive"
|
| 127 |
-
elif avg < -0.
|
| 128 |
overall = "negative"
|
| 129 |
else:
|
| 130 |
overall = "neutral"
|
| 131 |
|
| 132 |
return {
|
| 133 |
"ticker": ticker,
|
| 134 |
-
"articles_analyzed": len(
|
| 135 |
-
"details":
|
| 136 |
"overall_sentiment": overall,
|
| 137 |
"overall_score": round(avg, 4),
|
| 138 |
"contradictory_dampened": contradictory_dampened,
|
| 139 |
-
"method": "
|
| 140 |
}
|
|
|
|
| 17 |
_tokenizer = BertTokenizer.from_pretrained(MODEL_NAME)
|
| 18 |
_finbert = BertForSequenceClassification.from_pretrained(MODEL_NAME)
|
| 19 |
_finbert.eval()
|
| 20 |
+
# Correct mapping from transformers config: 0=positive, 1=negative, 2=neutral
|
| 21 |
+
FINBERT_LABELS = ["positive", "negative", "neutral"]
|
| 22 |
|
| 23 |
VADER_WEIGHT = 0.4
|
| 24 |
FINBERT_WEIGHT = 0.6
|
| 25 |
|
| 26 |
+
# Extend VADER lexicon with financial context terms
|
| 27 |
+
_vader.lexicon.update({
|
| 28 |
+
'hike': 1.5,
|
| 29 |
+
'stake': 1.0,
|
| 30 |
+
'approve': 2.0,
|
| 31 |
+
'approved': 2.0,
|
| 32 |
+
'approval': 2.0,
|
| 33 |
+
'raise': 1.5,
|
| 34 |
+
'raised': 1.5,
|
| 35 |
+
'growth': 2.0,
|
| 36 |
+
'gain': 2.0,
|
| 37 |
+
'jump': 1.5,
|
| 38 |
+
'surge': 1.5,
|
| 39 |
+
'fall': -1.5,
|
| 40 |
+
'drop': -1.5,
|
| 41 |
+
'plunge': -2.0,
|
| 42 |
+
'cut': -1.5,
|
| 43 |
+
'slash': -2.0,
|
| 44 |
+
'warn': -1.5,
|
| 45 |
+
'alert': -1.0,
|
| 46 |
+
})
|
| 47 |
+
|
| 48 |
|
| 49 |
def _score_vader(text: str) -> dict:
|
| 50 |
scores = _vader.polarity_scores(text)
|
|
|
|
| 69 |
probs = torch.nn.functional.softmax(logits, dim=-1).squeeze().tolist()
|
| 70 |
idx = int(np.argmax(probs))
|
| 71 |
|
| 72 |
+
# Logits match FINBERT_LABELS = ["positive", "negative", "neutral"]
|
| 73 |
+
# Score = Positive_Prob - Negative_Prob
|
| 74 |
+
signed_score = probs[0] - probs[1]
|
| 75 |
+
|
| 76 |
return {
|
| 77 |
"label": FINBERT_LABELS[idx],
|
| 78 |
"score": round(signed_score, 4),
|
|
|
|
| 117 |
return headlines
|
| 118 |
|
| 119 |
|
| 120 |
+
|
| 121 |
+
def _is_relevant(headline: str, ticker: str) -> bool:
|
| 122 |
+
"""
|
| 123 |
+
Relevance check. yfinance already returns ticker-specific news,
|
| 124 |
+
so we default to True (trust yfinance). We only reject headlines
|
| 125 |
+
that mention a clearly different well-known company.
|
| 126 |
+
"""
|
| 127 |
+
headline_lower = headline.lower()
|
| 128 |
+
ticker_base = ticker.split(".")[0].lower() # "RELIANCE" from "RELIANCE.NS"
|
| 129 |
+
|
| 130 |
+
# Quick accept: headline mentions the ticker or company directly
|
| 131 |
+
if ticker_base in headline_lower:
|
| 132 |
+
return True
|
| 133 |
+
|
| 134 |
+
# Common variations map
|
| 135 |
+
aliases = {
|
| 136 |
+
"RELIANCE": ["reliance", "ril", "ambani"],
|
| 137 |
+
"TCS": ["tcs", "tata consultancy"],
|
| 138 |
+
"INFY": ["infy", "infosys"],
|
| 139 |
+
"HDFCBANK": ["hdfc", "housing development"],
|
| 140 |
+
"ICICIBANK": ["icici"],
|
| 141 |
+
"SBIN": ["sbi", "state bank"],
|
| 142 |
+
"LT": ["l&t", "larsen", "toubro"],
|
| 143 |
+
"ITC": ["itc"],
|
| 144 |
+
"BHARTIARTL": ["airtel", "bharti"],
|
| 145 |
+
"KOTAKBANK": ["kotak"],
|
| 146 |
+
"TATAMOTORS": ["tata motors", "jlr"],
|
| 147 |
+
"MARUTI": ["maruti", "suzuki"],
|
| 148 |
+
"WIPRO": ["wipro"],
|
| 149 |
+
"ADANIENT": ["adani ent", "adani group"],
|
| 150 |
+
"TATASTEEL": ["tata steel"],
|
| 151 |
+
"BAJFINANCE": ["bajaj finance"],
|
| 152 |
+
"BAJAJFINSV": ["bajaj finserv"],
|
| 153 |
+
"HINDUNILVR": ["hul", "hindustan unilever"],
|
| 154 |
+
"SUNPHARMA": ["sun pharma"],
|
| 155 |
+
"TITAN": ["titan"],
|
| 156 |
+
"ASIANPAINT": ["asian paints"],
|
| 157 |
+
"ULTRACEMCO": ["ultratech"],
|
| 158 |
+
"NESTLEIND": ["nestle"],
|
| 159 |
+
"POWERGRID": ["power grid", "pgcil"],
|
| 160 |
+
"NTPC": ["ntpc"],
|
| 161 |
+
"M&M": ["mahindra"],
|
| 162 |
+
"JSWSTEEL": ["jsw steel"],
|
| 163 |
+
"GRASIM": ["grasim"],
|
| 164 |
+
"COALINDIA": ["coal india"],
|
| 165 |
+
"ADANIPORTS": ["adani ports"],
|
| 166 |
+
"ADANIGREEN": ["adani green"],
|
| 167 |
+
"TECHM": ["tech mahindra"],
|
| 168 |
+
"BPCL": ["bpcl", "bharat petroleum"],
|
| 169 |
+
"EICHERMOT": ["eicher"],
|
| 170 |
+
"DIVISLAB": ["divi's", "divis"],
|
| 171 |
+
"CIPLA": ["cipla"],
|
| 172 |
+
"HCLTECH": ["hcl tech"],
|
| 173 |
+
"ONGC": ["ongc", "oil and natural gas"],
|
| 174 |
+
"HINDALCO": ["hindalco"],
|
| 175 |
+
"DRREDDY": ["dr reddy"],
|
| 176 |
+
"INDUSINDBK": ["indusind"],
|
| 177 |
+
"BEL": ["bharat electronics"],
|
| 178 |
+
"HAL": ["hindustan aeronautics"],
|
| 179 |
+
"IOC": ["indian oil"],
|
| 180 |
+
"VEDL": ["vedanta"],
|
| 181 |
+
"DLF": ["dlf"],
|
| 182 |
+
"SBILIFE": ["sbi life"],
|
| 183 |
+
"HDFCLIFE": ["hdfc life"],
|
| 184 |
+
"ZOMATO": ["zomato"],
|
| 185 |
+
"PAYTM": ["paytm", "one97"],
|
| 186 |
+
"NYKAA": ["nykaa", "fsn"],
|
| 187 |
+
"IRCTC": ["irctc", "railway"],
|
| 188 |
+
}
|
| 189 |
+
|
| 190 |
+
# Check known aliases
|
| 191 |
+
if ticker_base.upper() in aliases:
|
| 192 |
+
for alias in aliases[ticker_base.upper()]:
|
| 193 |
+
if alias in headline_lower:
|
| 194 |
+
return True
|
| 195 |
+
|
| 196 |
+
# Default: trust yfinance — it already curates news for this ticker
|
| 197 |
+
return True
|
| 198 |
+
|
| 199 |
+
|
| 200 |
+
def _check_overrides(headline: str) -> float | None:
|
| 201 |
+
"""
|
| 202 |
+
Force scores for clear financial signals that NLP models often miss.
|
| 203 |
+
Returns: Score (-1 to 1) or None.
|
| 204 |
+
"""
|
| 205 |
+
hl = headline.lower()
|
| 206 |
+
|
| 207 |
+
# Strong Negative Signals
|
| 208 |
+
if any(x in hl for x in ["cuts", "lowers", "slashes", "misses", "below"]) and \
|
| 209 |
+
any(x in hl for x in ["guidance", "forecast", "outlook", "estimate", "target"]):
|
| 210 |
+
return -0.8
|
| 211 |
+
|
| 212 |
+
if "bankruptcy" in hl or "fraud" in hl or "scam" in hl or "default" in hl:
|
| 213 |
+
return -0.9
|
| 214 |
+
|
| 215 |
+
# Strong Positive Signals
|
| 216 |
+
if any(x in hl for x in ["raises", "hikes", "beats", "above", "record"]) and \
|
| 217 |
+
any(x in hl for x in ["guidance", "forecast", "outlook", "estimate", "profit", "revenue"]):
|
| 218 |
+
return 0.8
|
| 219 |
+
|
| 220 |
+
if "wins order" in hl or "wins contract" in hl or "bagged order" in hl:
|
| 221 |
+
return 0.7
|
| 222 |
+
|
| 223 |
+
return None
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
def _is_noise(headline: str) -> bool:
|
| 227 |
+
"""Discard junk headlines."""
|
| 228 |
+
# Too short or just a company name
|
| 229 |
+
if len(headline) < 20:
|
| 230 |
+
return True
|
| 231 |
+
if "share price" in headline.lower() and "live" in headline.lower():
|
| 232 |
+
# "Reliance share price live" -> Noise, no sentiment
|
| 233 |
+
return True
|
| 234 |
+
return False
|
| 235 |
+
|
| 236 |
+
|
| 237 |
def analyze_sentiment(ticker: str) -> dict:
|
| 238 |
headlines = fetch_news_headlines(ticker)
|
| 239 |
+
|
| 240 |
+
valid_details = []
|
| 241 |
+
|
| 242 |
+
for h in headlines:
|
| 243 |
+
# 1. Filter Noise
|
| 244 |
+
if _is_noise(h):
|
| 245 |
+
continue
|
| 246 |
+
|
| 247 |
+
# 2. Filter Relevance
|
| 248 |
+
if not _is_relevant(h, ticker):
|
| 249 |
+
continue
|
| 250 |
+
|
| 251 |
+
# 3. Check Overrides (Priority 1)
|
| 252 |
+
override_score = _check_overrides(h)
|
| 253 |
+
if override_score is not None:
|
| 254 |
+
label = "positive" if override_score > 0 else "negative"
|
| 255 |
+
valid_details.append({
|
| 256 |
+
"text": h,
|
| 257 |
+
"label": label,
|
| 258 |
+
"confidence": 1.0,
|
| 259 |
+
"combined_score": override_score,
|
| 260 |
+
"method": "Keyword Override"
|
| 261 |
+
})
|
| 262 |
+
continue
|
| 263 |
+
|
| 264 |
+
# 4. Use Model (Priority 2)
|
| 265 |
+
score_data = _score_text(h)
|
| 266 |
+
valid_details.append(score_data)
|
| 267 |
+
|
| 268 |
+
if not valid_details:
|
| 269 |
return {
|
| 270 |
"ticker": ticker,
|
| 271 |
"articles_analyzed": 0,
|
|
|
|
| 273 |
"overall_sentiment": "neutral",
|
| 274 |
"overall_score": 0.0,
|
| 275 |
"contradictory_dampened": False,
|
| 276 |
+
"method": "Hybrid (Keywords + VADER/FinBERT)",
|
| 277 |
}
|
| 278 |
|
| 279 |
+
raw_scores = [d["combined_score"] for d in valid_details]
|
|
|
|
| 280 |
avg = float(np.mean(raw_scores))
|
| 281 |
|
| 282 |
+
# Dampen one-off outliers
|
|
|
|
| 283 |
contradictory_dampened = False
|
| 284 |
n = len(raw_scores)
|
| 285 |
if n >= 2:
|
|
|
|
| 289 |
contradictory = variance > 0.15 or abs(avg - median) > 0.35
|
| 290 |
if contradictory:
|
| 291 |
contradictory_dampened = True
|
| 292 |
+
# Pull toward median
|
| 293 |
avg = 0.4 * avg + 0.6 * median
|
| 294 |
|
| 295 |
+
if avg > 0.1:
|
| 296 |
overall = "positive"
|
| 297 |
+
elif avg < -0.1:
|
| 298 |
overall = "negative"
|
| 299 |
else:
|
| 300 |
overall = "neutral"
|
| 301 |
|
| 302 |
return {
|
| 303 |
"ticker": ticker,
|
| 304 |
+
"articles_analyzed": len(valid_details),
|
| 305 |
+
"details": valid_details,
|
| 306 |
"overall_sentiment": overall,
|
| 307 |
"overall_score": round(avg, 4),
|
| 308 |
"contradictory_dampened": contradictory_dampened,
|
| 309 |
+
"method": "Hybrid (Keywords + VADER/FinBERT)",
|
| 310 |
}
|