Method find_anomalies

detection_engine.py:189–272

Main function that does everything

(self)

		return total_sum_percentage_change, future_volatility

	def find_anomalies(self):
		"""
		Main function that does everything
		"""

		# Gather data for all stocks
		if self.IS_LOAD_FROM_DICTIONARY == 0:
			features, historical_price_info, future_prices, symbol_names = self.dataEngine.collect_data_for_all_tickers()
		else:
			# Load data from dictionary
			features, historical_price_info, future_prices, symbol_names = self.dataEngine.load_data_from_dictionary()
		
		# Find anomalous stocks using the Isolation Forest model. Read more about the model at -> https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.IsolationForest.html
		detector = IsolationForest(n_estimators = 100, random_state = 0)
		detector.fit(features)
		predictions = detector.decision_function(features)
		
		# Print top predictions with some statistics
		predictions_with_output_data = [[predictions[i], symbol_names[i], historical_price_info[i], future_prices[i]] for i in range(0, len(predictions))]
		predictions_with_output_data = list(sorted(predictions_with_output_data))

		#Results object for storing results in JSON format
		results = []

		for item in predictions_with_output_data[:self.TOP_PREDICTIONS_TO_PRINT]:
			# Get some stats to print
			prediction, symbol, historical_price, future_price = item

			# Check if future data is present or not
			if self.IS_TEST == 1 and len(future_price) < 5:
				print("No future data is present. Please make sure that you ran the prior command with is_test enabled or disable that command now. Exiting now...")
				exit()

			latest_date, today_volume, average_vol_last_five_days, average_vol_last_twenty_days = self.calculate_volume_changes(historical_price)
			volatility_vol_last_five_days, volatility_vol_last_twenty_days, _ = self.calculate_recent_volatility(historical_price)
			if average_vol_last_five_days == None or volatility_vol_last_five_days == None:
				continue

			if self.IS_TEST == 0:
				# Not testing so just add/print the predictions
				
				if self.OUTPUT_FORMAT == "CLI":
					print("Last Bar Time: %s\nSymbol: %s\nAnomaly Score: %.3f\nToday Volume: %s\nAverage Volume 5d: %s\nAverage Volume 20d: %s\nVolatility 5bars: %.3f\nVolatility 20bars: %.3f\n----------------------" % 
																	(latest_date, symbol, prediction,
																	today_volume, average_vol_last_five_days, average_vol_last_twenty_days,
																	volatility_vol_last_five_days, volatility_vol_last_twenty_days))
				results.append({
					'latest_date' : latest_date,
					'Symbol' : symbol,
					'Anomaly Score' : prediction,
					'Today Volume' : today_volume,
					'Average Volume 5d' : average_vol_last_five_days,
					'Average Volume 20d' : average_vol_last_twenty_days,
					'Volatility 5bars' : volatility_vol_last_five_days,
					'Volatility 20bars' : volatility_vol_last_twenty_days
				})

			else: