prediction horizon units changed

deployment/nbeats/predict.py

@@ -86,17 +86,17 @@ def main():
     influxdb_conn = InfluxdbPredictionsSender(METHOD, APP_NAME)
 
     logging.debug(
-        f"waiting {(msg['epoch_start'] - int(time.time()) * 1000 - prediction_cycle) // 1000} seconds"
+        f"waiting {(msg['epoch_start'] - int(time.time()) * 1000 - prediction_cycle * 1000) // 1000} seconds"
     )
 
     time.sleep(
-        max(0, (msg["epoch_start"] - int(time.time()) * 1000 - prediction_cycle))
+        max(0, (msg["epoch_start"] - int(time.time()) * 1000 - prediction_cycle * 1000))
         // 1000
     )
 
     tl = Timeloop()
 
-    @tl.job(interval=timedelta(seconds=prediction_cycle // 1000))
+    @tl.job(interval=timedelta(seconds=prediction_cycle))
     def metric_predict():
         logging.debug("prediction")
         dataset_preprocessor.prepare_csv()
@@ -139,7 +139,7 @@ if __name__ == "__main__":
         }
         for m in msg["all_metrics"]
     }
-    prediction_horizon = msg["prediction_horizon"]
+    prediction_horizon = msg["prediction_horizon"] * 1000
     predicted_metrics = set(msg["metrics"])
     prediction_cycle = msg["prediction_horizon"]
 

deployment/nbeats/retrain.py

@@ -49,7 +49,7 @@ if __name__ == "__main__":
         }
         for m in msg["all_metrics"]
     }
-    prediction_horizon = msg["prediction_horizon"] // msg["publish_rate"]
+    prediction_horizon = (msg["prediction_horizon"] * 1000) // msg["publish_rate"]
     predicted_metrics = set(metrics_info.keys())
     logging.debug(f"Predicted metrics: {predicted_metrics}")
     main(predicted_metrics, prediction_horizon)

deployment/tft/predict.py

@@ -86,17 +86,17 @@ def main():
     influxdb_conn = InfluxdbPredictionsSender(METHOD, APP_NAME)
 
     logging.debug(
-        f"waiting {(msg['epoch_start'] - int(time.time()) * 1000 - prediction_cycle) // 1000} seconds"
+        f"waiting {(msg['epoch_start'] - int(time.time()) * 1000 - prediction_cycle * 1000) // 1000} seconds"
     )
 
     time.sleep(
-        max(0, (msg["epoch_start"] - int(time.time()) * 1000 - prediction_cycle))
+        max(0, (msg["epoch_start"] - int(time.time()) * 1000 - prediction_cycle * 1000))
         // 1000
     )
 
     tl = Timeloop()
 
-    @tl.job(interval=timedelta(seconds=prediction_cycle // 1000))
+    @tl.job(interval=timedelta(seconds=prediction_cycle))
     def metric_predict():
         logging.debug("prediction")
         dataset_preprocessor.prepare_csv()
@@ -139,7 +139,7 @@ if __name__ == "__main__":
         }
         for m in msg["all_metrics"]
     }
-    prediction_horizon = msg["prediction_horizon"]
+    prediction_horizon = msg["prediction_horizon"] * 1000
     predicted_metrics = set(msg["metrics"])
     prediction_cycle = msg["prediction_horizon"]
 

deployment/tft/retrain.py

@@ -49,7 +49,7 @@ if __name__ == "__main__":
         }
         for m in msg["all_metrics"]
     }
-    prediction_horizon = msg["prediction_horizon"] // msg["publish_rate"]
+    prediction_horizon = (msg["prediction_horizon"] * 1000) // msg["publish_rate"]
     predicted_metrics = set(metrics_info.keys())
     logging.debug(f"Predicted metrics: {predicted_metrics}")
     main(predicted_metrics, prediction_horizon)