SIENTIAPDE-1579: Fixed data preprocessor

model_manager/sientia/models.py

@@ -18,6 +18,15 @@ FEATURE_CREATION = 'Feature Creation'
 LAG_CREATION = 'Lag Creation'
 
 
+def _frontend_date_format_to_strftime(fmt: str | None) -> str | None:
+    """Convert front-end date format (e.g. dd/MM/yyyy HH:mm:ss) to Python strftime."""
+    if not fmt:
+        return None
+    out = fmt.replace('yyyy', '%Y').replace('MM', '%m').replace('dd', '%d')
+    out = out.replace('HH', '%H').replace('mm', '%M').replace('ss', '%S')
+    return out
+
+
 class LinearRegressionModel(BaseEstimator, TransformerMixin):
     """
     Linear Regression Model for Time Series Analysis.
@@ -244,6 +253,7 @@ class DataPreprocessor(BaseEstimator, TransformerMixin):
         lag_transform: dict[str, int] | None = None,
         start_date: str | None = None,
         end_date: str | None = None,
+        date_format: str | None = None,
         removed_intervals: list[tuple[str, str]] | None = None,
         static_threshold: int | None = None,
         low_lim: dict[str, float] | None = None,
@@ -270,8 +280,9 @@ class DataPreprocessor(BaseEstimator, TransformerMixin):
                 *Format: {'variable_name': lag}*
             lag_transform (dict): The lags for each variable to be applyed during transformation \\
                 *Format: {'variable_name': lag}*
-            start_date (str): The start date for filtering data (format: 'YYYY-MM-DD HH:MM:SS')
-            end_date (str): The end date for filtering data (format: 'YYYY-MM-DD HH:MM:SS')
+            start_date (str): The start date for filtering data
+            end_date (str): The end date for filtering data
+            date_format (str | None): Frontend date format for start/end (e.g. dd/MM/yyyy HH:mm:ss or MM/dd/yyyy HH:mm:ss). When set, parsing matches the CSV date column.
             removed_intervals (list): List of tuples with intervals to remove from data \\
                 *Format: [('start_date', 'end_date'), ...]*
             static_threshold (int): The number of repeated values to be considered as static
@@ -314,6 +325,7 @@ class DataPreprocessor(BaseEstimator, TransformerMixin):
         self.lag_transform = lag_transform if lag_transform else {}
         self.start_date = start_date
         self.end_date = end_date
+        self.date_format = date_format
         self.removed_intervals = removed_intervals if removed_intervals else []
         self.ar_var = ar_var
         self.self_operations = self_operations
@@ -443,10 +455,17 @@ class DataPreprocessor(BaseEstimator, TransformerMixin):
         return input_data
 
     def _parse_datetime(self, date_str: str | None) -> pd.Timestamp | None:
-        """Parse a date string to Timestamp, returning None on failure."""
+        """Parse a date string to Timestamp using date_format when set.
+
+        When date_format is set (e.g. dd/MM/yyyy HH:mm:ss or MM/dd/yyyy HH:mm:ss),
+        parsing matches the CSV date column so start_date/end_date filter correctly.
+        """
         if not date_str:
             return None
         try:
+            python_fmt = _frontend_date_format_to_strftime(self.date_format) if self.date_format else None
+            if python_fmt:
+                return pd.to_datetime(date_str, format=python_fmt)
             return pd.to_datetime(date_str)
         except (ValueError, TypeError):
             return None