pr feedback

NannyML · Feb 16, 2024 · c239ea1 · c239ea1
1 parent 4871a01
commit c239ea1
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 9 deletions.
diff --git a/nannyml/sampling_error/summary_stats.py b/nannyml/sampling_error/summary_stats.py
@@ -7,7 +7,9 @@
 import numpy as np
 import pandas as pd
 from scipy.stats import gaussian_kde, moment
+from logging import getLogger
 
+logger = getLogger(__name__)
 
 def summary_stats_std_sampling_error_components(col: pd.Series) -> Tuple:
     """
@@ -28,7 +30,7 @@ def summary_stats_std_sampling_error_components(col: pd.Series) -> Tuple:
     return (std, moment_4th)
 
 
-def summary_stats_std_sampling_error(sampling_error_components, col, logger) -> float:
+def summary_stats_std_sampling_error(sampling_error_components, col) -> float:
     """
     Calculate sampling error for Summary Stats Standard Deviation
     using reference data.
@@ -42,8 +44,6 @@ def summary_stats_std_sampling_error(sampling_error_components, col, logger) ->
         a set of parameters that were derived from reference data.
     col:
         the (analysis) column you want to calculate sampling error for.
-    logger:
-        logger to log calculation issues
 
     Returns
     -------

diff --git a/nannyml/stats/base.py b/nannyml/stats/base.py
@@ -5,15 +5,12 @@
 
 """Module containing base classes for data quality calculations."""
 
-from numpy import isfinite, issubdtype, number
+from numpy import isnan
 
 
 def _add_alert_flag(row_result: dict) -> bool:
     flag = False
-    # issubdtype checks for numeric type
-    # # np.nan and np.inf pass
-    # isfinite makes check go false for them
-    if not ( issubdtype(type(row_result['value']), number) and isfinite(row_result['value'])):
+    if isnan(row_result['value']):
         flag = True
     if row_result['upper_threshold'] is not None:
         if row_result['value'] > row_result['upper_threshold']:

diff --git a/nannyml/stats/std/calculator.py b/nannyml/stats/std/calculator.py
@@ -201,7 +201,7 @@ def _calculate_for_column(self, data: pd.DataFrame, column_name: str) -> Dict[st
             value = _calculate_std_value_stats(data[column_name])
             result['value'] = value
             result['sampling_error'] = summary_stats_std_sampling_error(
-                self._sampling_error_components[column_name], data[column_name], self._logger
+                self._sampling_error_components[column_name], data[column_name]
             )
             result['upper_confidence_boundary'] = result['value'] + SAMPLING_ERROR_RANGE * result['sampling_error']
             result['lower_confidence_boundary'] = np.maximum(