AutoStatLib 0.2.5__py3-none-any.whl → 0.2.6__py3-none-any.whl

AutoStatLib/AutoStatLib.py

@@ -16,7 +16,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
                  paired=False,
                  tails=2,
                  popmean=None,
-                 posthoc=False,
+                 posthoc=True,
                  verbose=True):
         self.results = None
         self.error = False
@@ -92,6 +92,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         self.p_value = None
         self.posthoc_matrix_df = None
         self.posthoc_matrix = []
+        self.posthoc_name = None
 
         self.log('\n' + '-'*67)
         self.log('Statistical analysis __init__iated for data in {} groups\n'.format(
@@ -174,7 +175,6 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         else:
             self.run_test_auto()
 
-
         # print the results
         self.results = self.create_results_dict()
         self.print_results()
@@ -186,9 +186,8 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         if self.verbose == True:
             print(self.summary)
 
-
-
     # public methods:
+
     def RunAuto(self):
         self.run_test(test='auto')
 

AutoStatLib/_version.py

@@ -1,2 +1,2 @@
 # AutoStatLib package version:
-__version__ = "0.2.5"
+__version__ = "0.2.6"

AutoStatLib/helpers.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pandas as pd
 
+
 class Helpers():
 
     def matrix_to_dataframe(self, matrix):
@@ -61,9 +62,11 @@ class Helpers():
             'Groups_SE': [np.std(self.data[i]).item() / np.sqrt(len(self.data)).item() for i in range(len(self.data))],
             # actually returns list of lists of numpy dtypes of float64, next make it return regular floats:
             'Samples': self.data,
-            'Posthoc_Matrix': self.posthoc_matrix if self.posthoc_matrix else 'N/A',
-            'Posthoc_Matrix_printed': [[self.make_p_value_printed(element) for element in row] for row in self.posthoc_matrix] if self.posthoc_matrix else 'N/A',
-            'Posthoc_Matrix_stars': [[self.make_stars_printed(self.make_stars(element)) for element in row] for row in self.posthoc_matrix] if self.posthoc_matrix else 'N/A',
+            'Posthoc_Tests_Name': self.posthoc_name if self.posthoc_name is not None else '',
+            'Posthoc_Matrix': self.posthoc_matrix if self.posthoc_matrix else [],
+            'Posthoc_Matrix_bool': [[bool(element) for element in row] for row in self.posthoc_matrix] if self.posthoc_matrix else [],
+            'Posthoc_Matrix_printed': [[self.make_p_value_printed(element) for element in row] for row in self.posthoc_matrix] if self.posthoc_matrix else [],
+            'Posthoc_Matrix_stars': [[self.make_stars_printed(self.make_stars(element)) for element in row] for row in self.posthoc_matrix] if self.posthoc_matrix else [],
         }
 
     def log(self, *args, **kwargs):
@@ -74,4 +77,4 @@ class Helpers():
     def AddWarning(self, warning_id):
         message = self.warning_ids_all[warning_id]
         self.log(message)
-        self.warnings.append(message)
+        self.warnings.append(message)

AutoStatLib/normality_tests.py

@@ -20,7 +20,7 @@ class NormalityTests():
 
         # Shapiro-Wilk test
         sw_stat, sw_p_value = shapiro(data)
-        if sw_p_value > 0.05:
+        if sw_p_value and sw_p_value > 0.05:
             sw = True
         else:
             sw = False
@@ -28,7 +28,7 @@ class NormalityTests():
         # Lilliefors test
         lf_stat, lf_p_value = lilliefors(
             data, dist='norm')
-        if lf_p_value > 0.05:
+        if lf_p_value and lf_p_value > 0.05:
             lf = True
         else:
             lf = False
@@ -37,7 +37,7 @@ class NormalityTests():
         if n >= 20:
             ad_stat, ad_p_value = self.anderson_get_p(
                 data, dist='norm')
-            if ad_p_value > 0.05:
+            if ad_p_value and ad_p_value > 0.05:
                 ad = True
             else:
                 ad = False
@@ -46,13 +46,11 @@ class NormalityTests():
         # test result is skewed if n<20
         if n >= 20:
             ap_stat, ap_p_value = normaltest(data)
-            if ap_p_value > 0.05:
+            if ap_p_value and ap_p_value > 0.05:
                 ap = True
             else:
                 ap = False
 
-        # print(ap_p_value, ad_p_value, sw_p_value, lf_p_value)
-
         return (sw, lf, ad, ap)
 
     def anderson_get_p(self, data, dist='norm'):
@@ -82,4 +80,4 @@ class NormalityTests():
         else:
             p = None
 
-        return ad, p
+        return ad, p

AutoStatLib/statistical_tests.py

@@ -1,10 +1,10 @@
 import numpy as np
 import scikit_posthocs as sp
 from statsmodels.stats.anova import AnovaRM
+from statsmodels.stats.multicomp import pairwise_tukeyhsd
 from scipy.stats import ttest_rel, ttest_ind, ttest_1samp, wilcoxon, mannwhitneyu, f_oneway, kruskal, friedmanchisquare
 
 
-
 class StatisticalTests():
     '''
         Statistical tests mixin
@@ -50,7 +50,7 @@ class StatisticalTests():
         test_names_dict = {
             'anova_1w_ordinary': 'Ordinary One-Way ANOVA',
             'anova_1w_rm': 'Repeated Measures One-Way ANOVA',
-            'friedman': 'Friedman test', 
+            'friedman': 'Friedman test',
             'kruskal_wallis': 'Kruskal-Wallis test',
             'mann_whitney': 'Mann-Whitney U test',
             't_test_independent': 't-test for independent samples',
@@ -89,6 +89,15 @@ class StatisticalTests():
         #     p_value /= 2
         # if self.tails == 1:
         #     p_value /= 2
+
+        # if p_value < 0.05 and self.posthoc:
+        #     data_flat = np.concatenate(self.data)
+        #     self.posthoc_name = 'Tukey`s multiple comparisons'
+        #     group_labels = np.concatenate(
+        #         [[f"Group_{i+1}"] * len(group) for i, group in enumerate(self.data)])
+        #     # Tukey's multiple comparisons
+        #     tukey_result = pairwise_tukeyhsd(data_flat, group_labels)
+        #     print(tukey_result)
         return stat, p_value
 
     def anova_1w_rm(self):
@@ -117,7 +126,9 @@ class StatisticalTests():
 
         # Perform Dunn's multiple comparisons if Kruskal-Wallis is significant
         if p_value < 0.05 and self.posthoc:
-            self.posthoc_matrix = sp.posthoc_dunn(self.data, p_adjust='bonferroni').values.tolist()
+            self.posthoc_matrix = sp.posthoc_dunn(
+                self.data, p_adjust='bonferroni').values.tolist()
+            self.posthoc_name = 'Dunn`s multiple comparisons'
         return stat, p_value
 
     def mann_whitney(self):
@@ -161,7 +172,7 @@ class StatisticalTests():
         if self.tails == 1:
             p_value /= 2
         return stat, p_value
-        
+
     def wilcoxon_single_sample(self):
         if self.popmean == None:
             self.popmean = 0
@@ -170,4 +181,4 @@ class StatisticalTests():
         stat, p_value = wilcoxon(data)
         if self.tails == 1:
             p_value /= 2
-        return stat, p_value
+        return stat, p_value

AutoStatLib/text_formatting.py

@@ -51,22 +51,26 @@ class TextFormatting():
                 break
             self.log(self.autospace(row_values, space))
 
-    def make_stars(self, p) -> int:
-        if p is not None:
-            if p < 0.0001:
-                return 4
-            if p < 0.001:
-                return 3
-            elif p < 0.01:
-                return 2
-            elif p < 0.05:
-                return 1
+    def print_results(self):
+        self.log('\n\nResults: \n')
+        for i in self.results:
+            shift = 27 - len(i)
+            if i == 'Warnings':
+                self.log(i, ':', ' ' * shift, len(self.results[i]))
+            elif i == 'Posthoc_Tests_Name':
+                self.log(i, ':', ' ' * shift,
+                         self.results[i]) if self.results[i] != '' else 'N/A'
+            elif i == 'Posthoc_Matrix':
+                self.log(i, ':', ' ' * shift, '{0}x{0} matrix'.format(
+                    len(self.results[i])) if self.results[i] else 'N/A')
+            elif (i == 'Samples'
+                  or i == 'Posthoc_Matrix_bool'
+                  or i == 'Posthoc_Matrix_printed'
+                  or i == 'Posthoc_Matrix_stars'
+                  ):
+                pass
             else:
-                return 0
-        return 0
-
-    def make_stars_printed(self, n) -> str:
-        return '*' * n if n else 'ns'
+                self.log(i, ':', ' ' * shift, self.results[i])
 
     def make_p_value_printed(self, p) -> str:
         if p is not None:
@@ -84,15 +88,19 @@ class TextFormatting():
                 return 'N/A'
         return 'N/A'
 
-    def print_results(self):
-        self.log('\n\nResults: \n')
-        for i in self.results:
-            shift = 27 - len(i)
-            if i == 'Warnings':
-                self.log(i, ':', ' ' * shift, len(self.results[i]))
-            if i == 'Posthoc_Matrix':
-                self.log(i, ':', ' ' * shift, '{0}x{0} matrix'.format(len(self.results[i])))
-            elif i == 'Samples' or i == 'Posthoc_Matrix_printed' or i == 'Posthoc_Matrix_stars':
-                pass
+    def make_stars(self, p) -> int:
+        if p is not None:
+            if p < 0.0001:
+                return 4
+            if p < 0.001:
+                return 3
+            elif p < 0.01:
+                return 2
+            elif p < 0.05:
+                return 1
             else:
-                self.log(i, ':', ' ' * shift, self.results[i])
+                return 0
+        return 0
+
+    def make_stars_printed(self, n) -> str:
+        return '*' * n if n else 'ns'

{AutoStatLib-0.2.5.dist-info → autostatlib-0.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: AutoStatLib
-Version: 0.2.5
+Version: 0.2.6
 Summary: AutoStatLib - a simple statistical analysis tool
 Author: Stemonitis, SciWare LLC
 Author-email: konung-yaropolk <yaropolk1995@gmail.com>
@@ -509,15 +509,16 @@ License:                   GNU LESSER GENERAL PUBLIC LICENSE
         
         That's all there is to it!
         
-Project-URL: Homepage, https://github.com/konung-yaropolk/NPL
-Project-URL: Issues, https://github.com/konung-yaropolk/NPL/issues
+Project-URL: Homepage, https://github.com/konung-yaropolk/AutoStatLib
+Project-URL: Repository, https://github.com/konung-yaropolk/AutoStatLib.git
+Project-URL: Issues, https://github.com/konung-yaropolk/AutoStatLib/issues
 Keywords: Science,Statistics
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
 Classifier: License :: OSI Approved :: GNU Lesser General Public License v2 or later (LGPLv2+)
 Classifier: Operating System :: OS Independent
-Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
@@ -620,26 +621,30 @@ results = analysis.GetResult()
 The results dictionary keys with representing value types:
 ```
 {
-    'p-value':                     String
-    'Significance(p<0.05)':        Boolean
-    'Stars_Printed':               String
-    'Test_Name':                   String
-    'Groups_Compared':             Integer
-    'Population_Mean':             Float   (taken from the input)
-    'Data_Normaly_Distributed':    Boolean
-    'Parametric_Test_Applied':     Boolean
-    'Paired_Test_Applied':         Boolean
-    'Tails':                       Integer (taken from the input)
-    'p-value_exact':               Float
-    'Stars':                       Integer
-    'Warnings':                    String
-    'Groups_N':                    List of integers
-    'Groups_Median':               List of floats
-    'Groups_Mean':                 List of floats
-    'Groups_SD':                   List of floats
-    'Groups_SE':                   List of floats
-    'Samples':                     List of input values by groups
+    'p-value' :                    String
+    'Significance(p<0.05)' :       Boolean
+    'Stars_Printed' :              String
+    'Test_Name' :                  String
+    'Groups_Compared' :            Integer
+    'Population_Mean' :            Float   (taken from the input)
+    'Data_Normaly_Distributed' :   Boolean
+    'Parametric_Test_Applied' :    Boolean
+    'Paired_Test_Applied' :        Boolean
+    'Tails' :                      Integer (taken from the input)
+    'p-value_exact' :              Float
+    'Stars' :                      Integer
+    'Warnings' :                   String
+    'Groups_N' :                   List of integers
+    'Groups_Median' :              List of floats
+    'Groups_Mean' :                List of floats
+    'Groups_SD' :                  List of floats
+    'Groups_SE' :                  List of floats
+    'Samples' :                    List of input values by groups
                                            (taken from the input)
+    'Posthoc_Matrix' :             2D List of floats
+    'Posthoc_Matrix_bool' :        2D List of Boolean
+    'Posthoc_Matrix_printed':      2D List of String
+    'Posthoc_Matrix_stars':        2D List of String
 }
 ```
 If errors occured, *GetResult()* returns an empty dictionary

autostatlib-0.2.6.dist-info/RECORD

@@ -0,0 +1,13 @@
+AutoStatLib/AutoStatLib.py,sha256=KJM2x-fChnxVinnCFsAKpoacKeoIJcJw_r8FYqPCljk,9677
+AutoStatLib/__init__.py,sha256=0wHYnglzKRPqSHtZlfbMEA2Bj5rDR4LLaXbOrJi-sqM,101
+AutoStatLib/__main__.py,sha256=ROKWensrxDh3Gl-yhexJ-BYFohDSh9y-CuMkaLpmnnQ,247
+AutoStatLib/_version.py,sha256=dXJmKxrIARBAzN_ILPim1iDgRdZ6HKMR3FqtamGwNUk,53
+AutoStatLib/helpers.py,sha256=d8P6_q706rjuc6N4WBbdOqNQFuAIjCHfmrhgJABFxqE,3646
+AutoStatLib/normality_tests.py,sha256=TYeKpfpJRzOHvDZucObuZhPktjiZpSZwh381eJ8ENC4,2381
+AutoStatLib/statistical_tests.py,sha256=xfHdTtN5Es_qoVMUwX8VFsl-FLpF3zd56S9ya7dPXVo,6566
+AutoStatLib/text_formatting.py,sha256=rWDsrlZdquook7lUg8t2mb3az8nR12BDprxfy_NwE2o,3576
+autostatlib-0.2.6.dist-info/LICENSE,sha256=IMF9i4xIpgCADf0U-V1cuf9HBmqWQd3qtI3FSuyW4zE,26526
+autostatlib-0.2.6.dist-info/METADATA,sha256=BDNKvdfcHaPlSF2q3YuDpOPFK_K7_hKcDH2NgjdCYtQ,36872
+autostatlib-0.2.6.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
+autostatlib-0.2.6.dist-info/top_level.txt,sha256=BuHzVyE2andc7RwD_UPmDjLl9CUAyBH6WHZGjaIReUI,12
+autostatlib-0.2.6.dist-info/RECORD,,

{AutoStatLib-0.2.5.dist-info → autostatlib-0.2.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (76.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

AutoStatLib-0.2.5.dist-info/RECORD

@@ -1,13 +0,0 @@
-AutoStatLib/AutoStatLib.py,sha256=yPNnwCvHSSlEKQvtnoaLFDq6znPlXCz-CrzGInG-1Ys,9647
-AutoStatLib/__init__.py,sha256=0wHYnglzKRPqSHtZlfbMEA2Bj5rDR4LLaXbOrJi-sqM,101
-AutoStatLib/__main__.py,sha256=ROKWensrxDh3Gl-yhexJ-BYFohDSh9y-CuMkaLpmnnQ,247
-AutoStatLib/_version.py,sha256=-QrGYOb9bx4vC_twSInOBJoijtj78lvUzV19y4-tH38,53
-AutoStatLib/helpers.py,sha256=9Fj9pHlXSM3tGHF5L0-i6DilA9VZk6Re93ob_IRxsYg,3424
-AutoStatLib/normality_tests.py,sha256=wvOmo6F7drnhhikoGltyQJC4OBk3PLCszY6ItJk1e0M,2385
-AutoStatLib/statistical_tests.py,sha256=LDcBRkq56hepR23RZtbBnZOs9k9frVjmiB2EKiEkCYs,5990
-AutoStatLib/text_formatting.py,sha256=ShE4BRO69lsC1VT3SsYrmPkuvW7QnyfHVPZEbjNQ_hI,3250
-AutoStatLib-0.2.5.dist-info/LICENSE,sha256=IMF9i4xIpgCADf0U-V1cuf9HBmqWQd3qtI3FSuyW4zE,26526
-AutoStatLib-0.2.5.dist-info/METADATA,sha256=qJxSrqHlL0wsqaH-ah6MAJa15ikH4NCco1dyVxuNlWs,36572
-AutoStatLib-0.2.5.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-AutoStatLib-0.2.5.dist-info/top_level.txt,sha256=BuHzVyE2andc7RwD_UPmDjLl9CUAyBH6WHZGjaIReUI,12
-AutoStatLib-0.2.5.dist-info/RECORD,,