SIENTIAPDE-1084

Remove deprecated files and configurations, including .env, Dockerfile, docker-compose.yml, and client-schedule.py. Update README.md to reflect new architecture and features, enhancing clarity on system capabilities and workflows. Adjust values.yaml for image tag and replica count, and improve code documentation across various modules for better maintainability.

scouter/utils/quality/filters.py

@@ -5,14 +5,21 @@ from typing import Any
 
 def check_data_range(value: float | int | None, val_range: list) -> bool:
     """
-    Check if a value is out of a given range.
+    Check if a value falls outside the specified range.
+
+    This function validates if a numeric value is within the acceptable range
+    defined by the minimum and maximum bounds. It handles edge cases including
+    None values and NaN values.
 
     Args:
-        value (float | int | None): The value to check.
-        val_range (list): The range to check against.
+        value (float | int | None): The numeric value to validate
+        val_range (list): List containing [min_value, max_value] bounds
 
     Returns:
-        bool: True if the value is out of the range, False otherwise.
+        bool: True if value is outside the range, False if within range
+
+    Note:
+        None and NaN values are considered out of range (return True)
     """
     if value is None or np.isnan(value):
         return True
@@ -23,32 +30,46 @@ def check_data_range(value: float | int | None, val_range: list) -> bool:
     return value < bottom or value > up
 
 
-def out_of_bounds_filter(df: DataFrame, model_tags: dict[str, Any]):
+def out_of_bounds_filter(df: DataFrame, model_tags: dict[str, Any]) -> DataFrame:
     """
-    Filter out rows where the value is out of the range.
+    Filter DataFrame rows where values are outside configured ranges.
+
+    This function applies range validation to each row in the DataFrame based
+    on tag-specific configuration. Rows with values outside the configured
+    ranges are filtered out.
 
     Args:
-        df (DataFrame): The DataFrame to filter.
-        model_tags (dict[str, Any]): The model tags. Contains
-        the data_range for each tag. If the tag does not have a data_range,
-        it will be considered as (-inf, inf).
+        df (DataFrame): DataFrame containing sensor data with 'name' and 'value' columns
+        model_tags (dict[str, Any]): Tag configuration containing data_range for each tag.
+            If a tag doesn't have data_range, it's considered to have infinite bounds.
 
     Returns:
-        DataFrame: The filtered DataFrame.
+        DataFrame: Filtered DataFrame with out-of-bounds values removed
+
+    Note:
+        Tags without data_range configuration are treated as having infinite bounds
     """
     return df[df.apply(lambda x: check_data_range(
         x['value'], model_tags[x['name']].get('data_range', (-np.inf, np.inf))),
         axis=1)]
 
 
-def null_values_filter(df: DataFrame, _model_tags: dict[str, Any]):
+def null_values_filter(df: DataFrame, _model_tags: dict[str, Any]) -> DataFrame:
     """
-    Filter out rows where the value is null.
+    Filter DataFrame rows containing null values.
+
+    This function removes rows where the 'value' column contains null values.
+    It's used for data quality filtering to ensure only complete data records
+    are processed.
 
     Args:
-        df (DataFrame): The DataFrame to filter.
+        df (DataFrame): DataFrame containing sensor data with 'value' column
+        _model_tags (dict[str, Any]): Tag configuration (unused in this filter)
 
     Returns:
-        DataFrame: The filtered DataFrame.
+        DataFrame: Filtered DataFrame with null values removed
+
+    Note:
+        The _model_tags parameter is included for interface consistency but not used
     """
     return df[df['value'].isnull()]