SIENTIAPDE-1579: Added date format and convert methods

model_manager/utils/models/train_model_params.py

@@ -34,6 +34,8 @@ class TrainModelParams:
         file_name (str): Name of the file in the MinIO bucket.
         line_separator (str): Line separator used in the CSV file.
         decimal_separator (str): Decimal separator used in the CSV file.
+        date_column (str | None): Name of the date/time column. If set with date_format, the column is parsed as datetime.
+        date_format (str | None): Format of the date column (e.g. dd/MM/yyyy HH:mm:ss). Used when date_column is set.
         train_size (int): Percentage of data to use for training (0-100).
         shuffle (bool): Whether to shuffle the data during train/test split.
         experiment_run_id (int): Unique identifier for the experiment run.
@@ -64,6 +66,8 @@ class TrainModelParams:
     file_name: str
     line_separator: str
     decimal_separator: str
+    date_column: str | None
+    date_format: str | None
     train_size: int
     shuffle: bool
     experiment_run_id: int
@@ -120,6 +124,8 @@ class TrainModelParams:
             decimal_separator=cls._check_none(
                 data.get('decimal_separator'), str, 'decimal_separator'
             ),
+            date_column=data.get('date_column'),
+            date_format=data.get('date_format'),
             train_size=cls._check_none(data.get('train_size'), int, 'train_size'),
             shuffle=cls._check_none(data.get('shuffle'), bool, 'shuffle'),
             experiment_run_id=cls._check_none(

model_manager/utils/repository/training_repository.py

@@ -21,6 +21,32 @@ from model_manager.utils.models.train_model_params import TrainModelParams
 from model_manager.utils.models.train_model_result import TrainModelResult
 
 
+def _frontend_format_to_strftime(fmt: str) -> str:
+    """Convert front-end date format (dd/MM/yyyy HH:mm:ss) to Python strftime (%d/%m/%Y %H:%M:%S)."""
+    if not fmt:
+        return fmt
+    out = fmt.replace('yyyy', '%Y').replace('MM', '%m').replace('dd', '%d')
+    out = out.replace('HH', '%H').replace('mm', '%M').replace('ss', '%S')
+    return out
+
+
+def _ensure_date_column_parsed(data: pd.DataFrame, params: TrainModelParams) -> pd.DataFrame:
+    """If date_column and date_format are set, parse the column as datetime to avoid comparison errors downstream."""
+    if not params.date_column or not params.date_format or params.date_column not in data.columns:
+        return data
+    try:
+        python_fmt = _frontend_format_to_strftime(params.date_format)
+        data = data.copy()
+        data[params.date_column] = pd.to_datetime(
+            data[params.date_column], format=python_fmt, errors='coerce'
+        )
+    except Exception as e:
+        raise ValueError(
+            f'Failed to parse date column "{params.date_column}" with format "{params.date_format}": {e}'
+        ) from e
+    return data
+
+
 class TrainingRepository:
     """
     Repository for machine learning model training operations.
@@ -67,10 +93,13 @@ class TrainingRepository:
             Exception: If data loading, preprocessing, or training fails
         """
         data = load_data(uploaded_file, params.line_separator, params.decimal_separator)
-
-        # Configure datetime index if timestamp column exists
-        # Required for TimeSeriesDiscontinuityAnalyzer (static window removal)
-        data = self._configure_datetime_index(data)
+        if data is None:
+            raise ValueError(
+                'Failed to load CSV data: load_data returned None. '
+                'Check file encoding, line separator and decimal separator.'
+            )
+        data = _ensure_date_column_parsed(data, params)
+        data = self._configure_datetime_index(data, params)
 
         process_data = self._init_data_preprocessor(params)
         process_data.fit(data)
@@ -350,40 +379,41 @@ class TrainingRepository:
             'original_features': params.variable_columns,
         }
 
-    def _configure_datetime_index(self, data: pd.DataFrame) -> pd.DataFrame:
+    def _configure_datetime_index(
+        self, data: pd.DataFrame | None, params: TrainModelParams
+    ) -> pd.DataFrame:
         """
         Configure datetime index for the DataFrame.
 
-        This method attempts to identify a timestamp column and set it as the
-        DataFrame index with DatetimeIndex type. This is required for
-        TimeSeriesDiscontinuityAnalyzer (used in static window removal).
-
-        The method looks for common timestamp column names and converts the
-        first matching column to datetime, then sets it as the index.
-
-        Args:
-            data: Input DataFrame
-
-        Returns:
-            pd.DataFrame: DataFrame with DatetimeIndex if timestamp column found,
-                         otherwise returns original DataFrame unchanged
+        Guards against None to avoid 'NoneType' object has no attribute 'index' downstream.
+        Prefers params.date_column when set; otherwise looks for common timestamp column names.
         """
-        # If index is already DatetimeIndex, just ensure it's sorted
+        if data is None:
+            raise ValueError(
+                'Data is None after load_data. '
+                'Check file format, line separator and decimal separator.'
+            )
+        if not isinstance(data, pd.DataFrame):
+            raise TypeError(f'Expected DataFrame, got {type(data).__name__}')
+
         if isinstance(data.index, pd.DatetimeIndex):
             self.logger.info('DataFrame already has DatetimeIndex')
             return data.sort_index()
 
-        # Common timestamp column names
-        timestamp_columns = [
+        common_timestamp_columns = [
             'timestamp',
             'Timestamp',
             'TIMESTAMP',
             'date',
             'Date',
             'DATE',
+            'DATA',
             'datetime',
             'DateTime',
         ]
+        timestamp_columns = (
+            [params.date_column] if params.date_column else []
+        ) + [c for c in common_timestamp_columns if c != params.date_column]
 
         for col in timestamp_columns:
             if col in data.columns: