Spaces:
Sleeping
Sleeping
File size: 10,432 Bytes
92a3517 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 |
"""
Database and Logging System for NegaBot API
Handles prediction logging using SQLite database
"""
import sqlite3
import json
import logging
from datetime import datetime
from typing import List, Dict
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Database configuration
DB_PATH = "negabot_predictions.db"
class PredictionLogger:
def __init__(self, db_path: str = DB_PATH):
"""
Initialize the prediction logger with SQLite database
Args:
db_path (str): Path to SQLite database file
"""
self.db_path = db_path
self.init_database()
def init_database(self):
"""Initialize the database with required tables"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Create predictions table
cursor.execute("""
CREATE TABLE IF NOT EXISTS predictions (
id INTEGER PRIMARY KEY AUTOINCREMENT,
text TEXT NOT NULL,
sentiment TEXT NOT NULL,
confidence REAL NOT NULL,
predicted_class INTEGER NOT NULL,
timestamp TEXT NOT NULL,
metadata TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
)
""")
# Create index for faster queries
cursor.execute("""
CREATE INDEX IF NOT EXISTS idx_sentiment ON predictions(sentiment)
""")
cursor.execute("""
CREATE INDEX IF NOT EXISTS idx_timestamp ON predictions(timestamp)
""")
conn.commit()
logger.info("Database initialized successfully")
except Exception as e:
logger.error(f"Error initializing database: {str(e)}")
raise e
def log_prediction(self, text: str, sentiment: str, confidence: float,
predicted_class: int = None, metadata: Dict = None):
"""
Log a prediction to the database
Args:
text (str): Input text
sentiment (str): Predicted sentiment
confidence (float): Prediction confidence
predicted_class (int): Predicted class (0 or 1)
metadata (dict): Optional metadata
"""
try:
# Infer predicted_class if not provided
if predicted_class is None:
predicted_class = 1 if sentiment == "Negative" else 0
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute("""
INSERT INTO predictions (text, sentiment, confidence, predicted_class, timestamp, metadata)
VALUES (?, ?, ?, ?, ?, ?)
""", (
text,
sentiment,
confidence,
predicted_class,
datetime.now().isoformat(),
json.dumps(metadata) if metadata else None
))
conn.commit()
except Exception as e:
logger.error(f"Error logging prediction: {str(e)}")
raise e
def get_all_predictions(self, limit: int = None) -> List[Dict]:
"""
Get all predictions from the database
Args:
limit (int): Maximum number of records to return
Returns:
List of prediction dictionaries
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
query = """
SELECT id, text, sentiment, confidence, predicted_class, timestamp, metadata, created_at
FROM predictions
ORDER BY created_at DESC
"""
if limit:
query += f" LIMIT {limit}"
cursor.execute(query)
rows = cursor.fetchall()
predictions = []
for row in rows:
prediction = {
"id": row[0],
"text": row[1],
"sentiment": row[2],
"confidence": row[3],
"predicted_class": row[4],
"timestamp": row[5],
"metadata": json.loads(row[6]) if row[6] else None,
"created_at": row[7]
}
predictions.append(prediction)
return predictions
except Exception as e:
logger.error(f"Error getting predictions: {str(e)}")
return []
def get_predictions_by_sentiment(self, sentiment: str) -> List[Dict]:
"""
Get predictions filtered by sentiment
Args:
sentiment (str): Sentiment to filter by ("Positive" or "Negative")
Returns:
List of prediction dictionaries
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute("""
SELECT id, text, sentiment, confidence, predicted_class, timestamp, metadata, created_at
FROM predictions
WHERE sentiment = ?
ORDER BY created_at DESC
""", (sentiment,))
rows = cursor.fetchall()
predictions = []
for row in rows:
prediction = {
"id": row[0],
"text": row[1],
"sentiment": row[2],
"confidence": row[3],
"predicted_class": row[4],
"timestamp": row[5],
"metadata": json.loads(row[6]) if row[6] else None,
"created_at": row[7]
}
predictions.append(prediction)
return predictions
except Exception as e:
logger.error(f"Error getting predictions by sentiment: {str(e)}")
return []
def get_stats(self) -> Dict:
"""
Get prediction statistics
Returns:
Dictionary with statistics
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Total count
cursor.execute("SELECT COUNT(*) FROM predictions")
total_count = cursor.fetchone()[0]
if total_count == 0:
return {
"total_predictions": 0,
"positive_count": 0,
"negative_count": 0,
"average_confidence": 0
}
# Sentiment counts
cursor.execute("SELECT sentiment, COUNT(*) FROM predictions GROUP BY sentiment")
sentiment_counts = dict(cursor.fetchall())
# Average confidence
cursor.execute("SELECT AVG(confidence) FROM predictions")
avg_confidence = cursor.fetchone()[0]
return {
"total_predictions": total_count,
"positive_count": sentiment_counts.get("Positive", 0),
"negative_count": sentiment_counts.get("Negative", 0),
"average_confidence": round(avg_confidence, 4) if avg_confidence else 0
}
except Exception as e:
logger.error(f"Error getting stats: {str(e)}")
return {}
# Global logger instance
_logger_instance = None
def get_logger():
"""Get the global logger instance"""
global _logger_instance
if _logger_instance is None:
_logger_instance = PredictionLogger()
return _logger_instance
def log_prediction(text: str, sentiment: str, confidence: float, metadata: Dict = None):
"""Convenience function to log a prediction"""
logger_instance = get_logger()
logger_instance.log_prediction(text, sentiment, confidence, metadata=metadata)
def get_all_predictions(limit: int = None) -> List[Dict]:
"""Convenience function to get all predictions"""
logger_instance = get_logger()
return logger_instance.get_all_predictions(limit=limit)
def get_predictions_by_sentiment(sentiment: str) -> List[Dict]:
"""Convenience function to get predictions by sentiment"""
logger_instance = get_logger()
return logger_instance.get_predictions_by_sentiment(sentiment)
def get_prediction_stats() -> Dict:
"""Convenience function to get prediction statistics"""
logger_instance = get_logger()
return logger_instance.get_stats()
if __name__ == "__main__":
# Test the logging system
logger_instance = PredictionLogger()
# Test logging
test_predictions = [
("This product is amazing!", "Positive", 0.95),
("Terrible quality, waste of money", "Negative", 0.89),
("It's okay, nothing special", "Positive", 0.67),
("Awful customer service", "Negative", 0.92)
]
print("Testing prediction logging...")
for text, sentiment, confidence in test_predictions:
logger_instance.log_prediction(text, sentiment, confidence)
print(f"Logged: {sentiment} - {text}")
# Test retrieval
print("\nRetrieving all predictions:")
predictions = logger_instance.get_all_predictions()
for pred in predictions:
print(f"ID: {pred['id']}, Sentiment: {pred['sentiment']}, Text: {pred['text'][:50]}...")
# Test stats
print("\nPrediction statistics:")
stats = logger_instance.get_stats()
print(json.dumps(stats, indent=2))
|