Merge pull request #433 from NannyML/chore/update-dependencies

Chore: the big bump

.github/workflows/dev.yml

@@ -20,7 +20,7 @@ jobs:
     # The type of runner that the job will run on
     strategy:
       matrix:
-        python-versions: ['3.8', '3.9', '3.10', '3.11']
+        python-versions: ['3.9', '3.10', '3.11', '3.12']
         os: [ubuntu-20.04]
 #        os: [ubuntu-18.04, macos-latest, windows-latest]
     runs-on: ${{ matrix.os }}

.github/workflows/preview.yml

@@ -22,7 +22,7 @@ jobs:
 
     strategy:
       matrix:
-        python-versions: [ 3.8 ]
+        python-versions: [ 3.11 ]
 
     steps:
       - uses: actions/checkout@v2

.github/workflows/release.yml

@@ -24,7 +24,7 @@ jobs:
 
     strategy:
       matrix:
-        python-versions: [3.8]
+        python-versions: [3.11]
 
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:

nannyml/config.py

@@ -9,7 +9,7 @@
 
 import jinja2
 import yaml
-from pydantic import BaseModel, validator, Field
+from pydantic import BaseModel, Field, field_validator
 
 from nannyml._typing import Self
 from nannyml.exceptions import IOException
@@ -71,7 +71,7 @@ class CalculatorConfig(BaseModel):
     store: Optional[StoreConfig] = Field(default=None)
     params: Dict[str, Any]
 
-    @validator('params')
+    @field_validator('params')
     def _parse_thresholds(cls, value: Dict[str, Any]):
         """Parse thresholds in params and convert them to :class:`Threshold`'s"""
         # Some calculators expect `thresholds` parameter as dict

nannyml/drift/ranker.py

@@ -372,7 +372,11 @@ def rank(
             filtered_values = values[~(feature_nan | perf_nan)]
             filtered_perf_change = abs_perf_change[~(feature_nan | perf_nan)]
 
-            tmp1 = pearsonr(filtered_values.ravel(), filtered_perf_change)
+            tmp1 = (
+                pearsonr(filtered_values.ravel(), filtered_perf_change)
+                if len(filtered_values) > 1
+                else (np.nan, np.nan)
+            )
             spearmanr1.append(tmp1[0])
             spearmanr2.append(tmp1[1])
 

nannyml/drift/univariate/calculator.py

@@ -441,10 +441,10 @@ def _calculate_for_column(
             logger.error(
                 f"an unexpected exception occurred during calculation of method '{method.display_name}': " f"{exc}"
             )
-        result['value'] = np.NaN
+        result['value'] = np.nan
         result['upper_threshold'] = method.upper_threshold_value
         result['lower_threshold'] = method.lower_threshold_value
-        result['alert'] = np.NaN
+        result['alert'] = np.nan
     finally:
         return result
 

nannyml/drift/univariate/methods.py

@@ -278,7 +278,9 @@ def _fit(self, reference_data: pd.Series, timestamps: Optional[pd.Series] = None
         reference_data = _remove_nans(reference_data)
         len_reference = len(reference_data)
 
-        bins = np.histogram_bin_edges(reference_data, bins='doane')
+        # Explicit conversion to float because of
+        # https://github.com/numpy/numpy/commit/c63969c6e1d58e791632aacfb88ecae465d6dcfc
+        bins = np.histogram_bin_edges(reference_data.astype("float64"), bins='doane')
         reference_proba_in_bins = np.histogram(reference_data, bins=bins)[0] / len_reference
         self._bins = bins
         self._reference_proba_in_bins = reference_proba_in_bins
@@ -731,7 +733,7 @@ def _fit(self, reference_data: pd.Series, timestamps: Optional[pd.Series] = None
         reference_data = _remove_nans(reference_data)
         len_reference = len(reference_data)
 
-        bins = np.histogram_bin_edges(reference_data, bins='doane')
+        bins = np.histogram_bin_edges(reference_data.astype("float64"), bins='doane')
         reference_proba_in_bins = np.histogram(reference_data, bins=bins)[0] / len_reference
         self._bins = bins
         self._reference_proba_in_bins = reference_proba_in_bins

nannyml/performance_calculation/metrics/base.py

@@ -197,11 +197,11 @@ def get_chunk_record(self, chunk_data: pd.DataFrame) -> Dict:
                 self._logger.error(
                     f"an unexpected exception occurred during calculation of method '{self.display_name}': " f"{exc}"
                 )
-            chunk_record[f'{column_name}_sampling_error'] = np.NaN
-            chunk_record[f'{column_name}'] = np.NaN
+            chunk_record[f'{column_name}_sampling_error'] = np.nan
+            chunk_record[f'{column_name}'] = np.nan
             chunk_record[f'{column_name}_upper_threshold'] = self.upper_threshold_value
             chunk_record[f'{column_name}_lower_threshold'] = self.lower_threshold_value
-            chunk_record[f'{column_name}_alert'] = np.NaN
+            chunk_record[f'{column_name}_alert'] = np.nan
         finally:
             return chunk_record