Merge pull request #163 from jarq6c/test-metrics

Metrics: Default to numpy scalars for computation
NOAA-OWP · Dec 9, 2021 · 4eb6f87 · 4eb6f87
2 parents 4930ced + b054d23
commit 4eb6f87
Show file tree

Hide file tree

Showing 3 changed files with 227 additions and 7 deletions.
diff --git a/python/metrics/src/hydrotools/metrics/_version.py b/python/metrics/src/hydrotools/metrics/_version.py
@@ -1 +1 @@
-__version__ = "1.0.3"
+__version__ = "1.1.3"
diff --git a/python/metrics/src/hydrotools/metrics/metrics.py b/python/metrics/src/hydrotools/metrics/metrics.py
@@ -11,6 +11,7 @@
 Functions
 ---------
  - compute_contingency_table
+ - convert_mapping_values
  - probability_of_detection
  - probability_of_false_detection
  - probability_of_false_alarm
@@ -27,7 +28,7 @@
 import numpy as np
 import numpy.typing as npt
 import pandas as pd
-from typing import Union
+from typing import Union, Mapping, MutableMapping
 
 def mean_squared_error(
     y_true: npt.ArrayLike,
@@ -84,7 +85,7 @@ def nash_sutcliffe_efficiency(
     Returns
     -------
     score: float
-        Nash–Sutcliffe model efficiency coefficient
+        Nash-Sutcliffe model efficiency coefficient
         
     References
     ----------
@@ -153,6 +154,36 @@ def compute_contingency_table(
         true_negative_key : ctab.loc[False, False]
         })
 
+def convert_mapping_values(
+    mapping: Mapping[str, npt.DTypeLike],
+    converter: np.dtype = np.float64
+    ) -> MutableMapping:
+    """Convert mapping values to a consistent type. Primarily used to validate 
+    contingency tables.
+        
+    Parameters
+    ----------
+    mapping: dict-like, required
+        Input mapping with string keys and values that can be coerced into a 
+        numpy data type.
+    converter: numpy.dtype, optional, default numpy.float64
+        Converter data type or function used to convert mapping values to a 
+        consistent type.
+        
+    Returns
+    -------
+    converted_mapping: dict-like, same type as mapping
+        New mapping with converted values.
+        
+    """
+    # Populate new dictionary with converted values
+    d = {}
+    for key, value in dict(mapping).items():
+        d[key] = converter(value)
+
+    # Return new mapping with same type as original
+    return type(mapping)(d)
+
 def probability_of_detection(
     contingency_table: Union[dict, pd.DataFrame, pd.Series],
     true_positive_key: str = 'true_positive',
@@ -177,6 +208,10 @@ def probability_of_detection(
         Probability of detection.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     a = contingency_table[true_positive_key]
     c = contingency_table[false_negative_key]
     return a / (a+c)
@@ -205,6 +240,10 @@ def probability_of_false_detection(
         Probability of false detection.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     b = contingency_table[false_positive_key]
     d = contingency_table[true_negative_key]
     return b / (b+d)
@@ -233,6 +272,10 @@ def probability_of_false_alarm(
         Probability of false alarm.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     b = contingency_table[false_positive_key]
     a = contingency_table[true_positive_key]
     return b / (b+a)
@@ -264,6 +307,10 @@ def threat_score(
         Threat score.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     a = contingency_table[true_positive_key]
     b = contingency_table[false_positive_key]
     c = contingency_table[false_negative_key]
@@ -296,6 +343,10 @@ def frequency_bias(
         Frequency bias.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     a = contingency_table[true_positive_key]
     b = contingency_table[false_positive_key]
     c = contingency_table[false_negative_key]
@@ -331,6 +382,10 @@ def percent_correct(
         Percent correct.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     a = contingency_table[true_positive_key]
     b = contingency_table[false_positive_key]
     c = contingency_table[false_negative_key]
@@ -365,6 +420,10 @@ def base_chance(
         Base chance to hit by chance.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     a = contingency_table[true_positive_key]
     b = contingency_table[false_positive_key]
     c = contingency_table[false_negative_key]
@@ -401,6 +460,10 @@ def equitable_threat_score(
         Equitable threat score.
         
     """
+    # Convert values to numpy scalars
+    contingency_table = convert_mapping_values(contingency_table)
+
+    # Compute
     a_r = base_chance(contingency_table,
         true_positive_key=true_positive_key,
         false_positive_key=false_positive_key,