diff --git a/services/ml/app/__pycache__/annotation_ingestion.cpython-313.pyc b/services/ml/app/__pycache__/annotation_ingestion.cpython-313.pyc index 9007ce5..8af78d0 100644 Binary files a/services/ml/app/__pycache__/annotation_ingestion.cpython-313.pyc and b/services/ml/app/__pycache__/annotation_ingestion.cpython-313.pyc differ diff --git a/services/ml/app/__pycache__/db.cpython-313.pyc b/services/ml/app/__pycache__/db.cpython-313.pyc new file mode 100644 index 0000000..311253d Binary files /dev/null and b/services/ml/app/__pycache__/db.cpython-313.pyc differ diff --git a/services/ml/app/annotation_ingestion.py b/services/ml/app/annotation_ingestion.py index 8c2bd0e..6515a8e 100644 --- a/services/ml/app/annotation_ingestion.py +++ b/services/ml/app/annotation_ingestion.py @@ -188,8 +188,8 @@ class AnnotationIngestion: for ann in annotations: label = ann['label'] - start_time = pd.Timestamp(ann['start_time']) - end_time = pd.Timestamp(ann['end_time']) + start_time = pd.Timestamp(ann['start_time']).tz_localize(None) + end_time = pd.Timestamp(ann['end_time']).tz_localize(None) # Find candles in span span_mask = (df['time'] >= start_time) & (df['time'] <= end_time) @@ -504,7 +504,7 @@ def run_annotation_ingestion( logger.info("Running annotation ingestion stage") # Load enriched data - enriched_df = pd.read_csv(enriched_path) + enriched_df = pd.read_csv(enriched_path, parse_dates=['time']) logger.info(f"Loaded enriched data: {enriched_df.shape}") # Process annotations diff --git a/services/ml/config/pipeline.yaml b/services/ml/config/pipeline.yaml index 0f065b7..918d7b8 100644 --- a/services/ml/config/pipeline.yaml +++ b/services/ml/config/pipeline.yaml @@ -86,8 +86,8 @@ stages: - "CDLHARAMI" - "CDLPIERCING" - "CDLDARKCLOUDCOVER" - - "CDLTHREEWHITESOLDIERS" - - "CDLTHREEBLACKCROWS" + - "CDL3WHITESOLDIERS" + - "CDL3BLACKCROWS" # Label merge strategy: "human_priority", "programmatic_priority", "both" merge_strategy: "human_priority" diff --git a/services/ml/training/__pycache__/__init__.cpython-313.pyc b/services/ml/training/__pycache__/__init__.cpython-313.pyc new file mode 100644 index 0000000..24be242 Binary files /dev/null and b/services/ml/training/__pycache__/__init__.cpython-313.pyc differ diff --git a/services/ml/training/__pycache__/evaluation.cpython-313.pyc b/services/ml/training/__pycache__/evaluation.cpython-313.pyc new file mode 100644 index 0000000..d4f842e Binary files /dev/null and b/services/ml/training/__pycache__/evaluation.cpython-313.pyc differ diff --git a/services/ml/training/__pycache__/train.cpython-313.pyc b/services/ml/training/__pycache__/train.cpython-313.pyc new file mode 100644 index 0000000..86eece0 Binary files /dev/null and b/services/ml/training/__pycache__/train.cpython-313.pyc differ diff --git a/services/ml/training/models/__pycache__/__init__.cpython-313.pyc b/services/ml/training/models/__pycache__/__init__.cpython-313.pyc new file mode 100644 index 0000000..b03fe69 Binary files /dev/null and b/services/ml/training/models/__pycache__/__init__.cpython-313.pyc differ diff --git a/services/ml/training/models/__pycache__/random_forest.cpython-313.pyc b/services/ml/training/models/__pycache__/random_forest.cpython-313.pyc new file mode 100644 index 0000000..413ccbc Binary files /dev/null and b/services/ml/training/models/__pycache__/random_forest.cpython-313.pyc differ diff --git a/services/ml/training/models/__pycache__/xgboost_model.cpython-313.pyc b/services/ml/training/models/__pycache__/xgboost_model.cpython-313.pyc new file mode 100644 index 0000000..318d1e0 Binary files /dev/null and b/services/ml/training/models/__pycache__/xgboost_model.cpython-313.pyc differ