nkululeko 0.65.4__tar.gz → 0.65.5__tar.gz

{nkululeko-0.65.4 → nkululeko-0.65.5}/CHANGELOG.md

@@ -1,6 +1,10 @@
 Changelog
 =========
 
+Version 0.65.5
+--------------
+* added fill_na in plot effect size
+
 Version 0.65.4
 --------------
 * added datasets to distribution

{nkululeko-0.65.4/nkululeko.egg-info → nkululeko-0.65.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.65.4
+Version: 0.65.5
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -255,6 +255,10 @@ Nkululeko can be used under the [MIT license](https://choosealicense.com/license
 Changelog
 =========
 
+Version 0.65.5
+--------------
+* added fill_na in plot effect size
+
 Version 0.65.4
 --------------
 * added datasets to distribution

nkululeko-0.65.5/nkululeko/constants.py

@@ -0,0 +1,2 @@
+VERSION="0.65.5"
+SAMPLING_RATE=16000

{nkululeko-0.65.4 → nkululeko-0.65.5}/nkululeko/plots.py

@@ -57,6 +57,8 @@ class Plots():
         bin_reals = eval(self.util.config_val('EXPL', 'bin_reals', 'True'))
         for att in attributes:
             if len(att) == 1:
+                if att[0] not in df:
+                    self.util.error(f'unknown feature: {att[0]}')
                 self.util.debug(f'plotting {att[0]}')
                 filename = f'{self.target}-{att[0]}'
                 if self.util.is_categorical(df[att[0]]):
@@ -90,6 +92,10 @@ class Plots():
                 plt.close(fig)
                 # fig.clear()           # avoid error
             elif len(att) == 2:
+                if att[0] not in df:
+                    self.util.error(f'unknown feature: {att[0]}')
+                if att[1] not in df:
+                    self.util.error(f'unknown feature: {att[1]}')
                 self.util.debug(f'plotting {att}')
                 att1 = att[0]
                 att2 = att[1]

{nkululeko-0.65.4 → nkululeko-0.65.5}/nkululeko/utils/stats.py

@@ -3,6 +3,14 @@ import math
 import numpy as np
 import pandas as pd
 
+def check_na(a):
+    if np.isnan(a).any():
+        count = np.count_nonzero(np.isnan(a))
+        print(f'WARNING: got {count} Nans (of {len(a)}), setting to 0')
+        a[np.isnan(a)] = 0
+        return a 
+    else:
+        return a
 
 def cohen_d(d1, d2):
     """
@@ -13,6 +21,9 @@ def cohen_d(d1, d2):
     Returns:
         Cohen's d with precision 3
     """
+    # Checks:
+    d1 = check_na(d1)
+    d2 = check_na(d2)
     # calculate the size of samples
     n1, n2 = len(d1), len(d2)
     # calculate the variance of the samples
@@ -23,7 +34,7 @@ def cohen_d(d1, d2):
     u1, u2 = np.mean(d1), np.mean(d2)
     # calculate the effect size
     if math.isnan(s) or s == 0:
-        return 0
+        return -1
     return (int(1000 * np.abs((u1 - u2)) / s)) / 1000
 
 

{nkululeko-0.65.4 → nkululeko-0.65.5/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.65.4
+Version: 0.65.5
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -255,6 +255,10 @@ Nkululeko can be used under the [MIT license](https://choosealicense.com/license
 Changelog
 =========
 
+Version 0.65.5
+--------------
+* added fill_na in plot effect size
+
 Version 0.65.4
 --------------
 * added datasets to distribution

nkululeko-0.65.4/nkululeko/constants.py

@@ -1,2 +0,0 @@
-VERSION="0.65.4"
-SAMPLING_RATE=16000