AutoStatLib 0.2.10__py3-none-any.whl → 0.2.13__py3-none-any.whl

AutoStatLib/AutoStatLib.py

@@ -2,6 +2,7 @@ from AutoStatLib.statistical_tests import StatisticalTests
 from AutoStatLib.normality_tests import NormalityTests
 from AutoStatLib.helpers import Helpers
 from AutoStatLib.text_formatting import TextFormatting
+from AutoStatLib._version import __version__
 
 
 class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Helpers):
@@ -16,7 +17,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
                  paired=False,
                  tails=2,
                  popmean=None,
-                 posthoc=True,
+                 posthoc=False,
                  verbose=True):
         self.results = None
         self.error = False
@@ -28,7 +29,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         self.verbose = verbose
         self.n_groups = len(self.groups_list)
         self.warning_flag_non_numeric_data = False
-        self.summary = ''
+        self.summary = 'AutoStatLib v{}'.format(__version__)
 
         # test IDs classification:
         self.test_ids_all = [  # in aplhabetical order
@@ -86,13 +87,13 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         self.error = False
         self.warnings = []
         self.normals = []
-        self.test_name = None
+        self.test_name = ''
         self.test_id = None
         self.test_stat = None
         self.p_value = None
         self.posthoc_matrix_df = None
         self.posthoc_matrix = []
-        self.posthoc_name = None
+        self.posthoc_name = ''
 
         self.log('\n' + '-'*67)
         self.log('Statistical analysis initiated for data in {} groups\n'.format(

AutoStatLib/StatPlots.py

@@ -74,28 +74,34 @@ class BaseStatPlot(Helpers):
 
     def __init__(self,
                  data_groups,
-                 p=None,
-                 testname='',
-                 dependent=False,
+                 p_value_exact=None,
+                 Test_Name='',
+                 Paired_Test_Applied=False,
                  plot_title='',
                  x_label='',
                  y_label='',
                  print_x_labels=True,
                  x_manual_tick_labels=None,
-                 posthoc_matrix=[],
+                 Posthoc_Matrix=[],
+                 Posthoc_Tests_Name='',
                  colormap=None,
+                 print_p_label=True,
+                 print_stars=True,
                  **kwargs):
         self.data_groups = [group if group else [0, 0, 0, 0]
                             for group in data_groups]
         self.n_groups = len(self.data_groups)
-        self.p = p
-        self.testname = testname
-        self.posthoc_matrix = posthoc_matrix
+        self.p = p_value_exact
+        self.testname = Test_Name
+        self.posthoc_name = Posthoc_Tests_Name
+        self.posthoc_matrix = Posthoc_Matrix
         self.n_significance_bars = 1
-        self.dependent = dependent
+        self.dependent = Paired_Test_Applied
         self.plot_title = plot_title
         self.x_label = x_label
         self.y_label = y_label
+        self.print_p_label = print_p_label
+        self.print_stars = print_stars
         self.print_x_labels = print_x_labels
 
         #  sd sem mean and median calculation if they are not provided
@@ -396,9 +402,7 @@ class BaseStatPlot(Helpers):
     def add_significance_bars(self, ax,
                               linewidth=2,
                               capsize=0.01,
-                              col='k',
-                              label=''):
-        '''label can be "p", "s", "both"'''
+                              col='k'):
 
         # # Estimate how many bars needed
         # self.n_significance_bars = comb(
@@ -409,25 +413,28 @@ class BaseStatPlot(Helpers):
         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 draw_bar(p, stars, order=0, x1=0, x2=self.n_groups-1, capsize=capsize, linewidth=linewidth, col=col, label=label):
-            if label == 'p':
-                vspace = capsize+0.03
-                label = '{}'.format(p)
-            elif label == 's':
-                vspace = capsize+0.03
-                label = '{}'.format(stars)
-            else:
-                vspace = capsize+0.06
-                label = '{}\n{}'.format(p, stars)
-
-            # Draw significance bar connecting x1 and x2 coords
-            y, h = ((1.05 + (order*vspace)) *
-                    self.y_max), capsize * self.y_max
-            ax.plot([x1, x1, x2, x2], [y, y + h, y + h, y],
-                    lw=linewidth, c=col)
-
-            ax.text((x1 + x2) * 0.5, y + h, label,
-                    ha='center', va='bottom', color=col, fontweight='bold', fontsize=8)
+        def draw_bar(p, stars, order=0, x1=0, x2=self.n_groups-1, capsize=capsize, linewidth=linewidth, col=col):
+
+            match (self.print_p_label, self.print_stars):
+                case (True, True):
+                    vspace = capsize+0.06
+                    label = '{}\n{}'.format(p, stars)
+                case (True, False):
+                    vspace = capsize+0.03
+                    label = '{}'.format(p)
+                case (False, True):
+                    vspace = capsize+0.03
+                    label = '{}'.format(stars)
+
+            if self.print_p_label or self.print_stars:
+                # Draw significance bar connecting x1 and x2 coords
+                y, h = ((1.05 + (order*vspace)) *
+                        self.y_max), capsize * self.y_max
+                ax.plot([x1, x1, x2, x2], [y, y + h, y + h, y],
+                        lw=linewidth, c=col)
+
+                ax.text((x1 + x2) * 0.5, y + h, label,
+                        ha='center', va='bottom', color=col, fontweight='bold', fontsize=8)
 
         def draw_bar_from_posthoc_matrix(x1, x2, o):
             draw_bar(
@@ -524,8 +531,8 @@ class BaseStatPlot(Helpers):
         if self.y_label:
             ax.set_ylabel(self.y_label, fontsize=10, fontweight='bold')
         fig.text(0.95, 0.0,
-                 '{}\nn={}'.format(self.testname,
-                                   str(self.n)[1:-1] if not self.dependent else str(self.n[0])),
+                 '{}, {}\nn={}'.format(self.testname, self.posthoc_name,
+                                       str(self.n)[1:-1] if not self.dependent else str(self.n[0])),
                  ha='right', va='bottom', fontsize=8, fontweight='regular')
 
     def show(self):

AutoStatLib/_version.py

@@ -1,2 +1,2 @@
 # AutoStatLib package version:
-__version__ = "0.2.10"
+__version__ = "0.2.13"

AutoStatLib/helpers.py

@@ -41,7 +41,7 @@ class Helpers():
         self.stars_str = self.make_stars_printed(self.stars_int)
 
         return {
-            'p-value': self.make_p_value_printed(self.p_value.item()),
+            'p_value': self.make_p_value_printed(self.p_value.item()),
             'Significance(p<0.05)':  True if self.p_value.item() < 0.05 else False,
             'Stars_Printed': self.stars_str,
             'Test_Name': self.test_name,
@@ -51,7 +51,7 @@ class Helpers():
             'Parametric_Test_Applied': True if self.test_id in self.test_ids_parametric else False,
             'Paired_Test_Applied': self.paired,
             'Tails': self.tails,
-            'p-value_exact': self.p_value.item(),
+            'p_value_exact': self.p_value.item(),
             'Stars':  self.stars_int,
             # 'Stat_Value': self.test_stat.item(),
             'Warnings': self.warnings,

AutoStatLib/statistical_tests.py

@@ -1,7 +1,9 @@
 import numpy as np
+import itertools
 import scikit_posthocs as sp
 from statsmodels.stats.anova import AnovaRM
 from statsmodels.stats.multicomp import pairwise_tukeyhsd
+from statsmodels.stats.multitest import multipletests
 from scipy.stats import ttest_rel, ttest_ind, ttest_1samp, wilcoxon, mannwhitneyu, f_oneway, kruskal, friedmanchisquare
 
 
@@ -90,14 +92,19 @@ class StatisticalTests():
         # 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)
+        if self.posthoc:  # and p_value < 0.05:
+            data_flat = np.concatenate(self.data)
+            self.posthoc_name = 'Tukey`s posthoc'
+            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)
+            p = tukey_result.pvalues.tolist()
+            self.posthoc_matrix = [
+                [p[2], p[0], p[1]],
+                [p[0], p[2], p[2]],
+                [p[1], p[2], p[2]],
+            ]
         return stat, p_value
 
     def anova_1w_rm(self):
@@ -110,8 +117,25 @@ class StatisticalTests():
 
         df = self.matrix_to_dataframe(self.data)
         res = AnovaRM(df, 'Value', 'Row', within=['Col']).fit()
-        stat = res.anova_table['F Value'][0]
-        p_value = res.anova_table['Pr > F'][0]
+        print(res)
+        stat = res.anova_table.iloc[0][0]
+        p_value = res.anova_table.iloc[0][3]
+
+        # # --- Posthocs: paired t-tests ---
+        # wide = df.pivot(index='Row', columns='Col', values='Value')
+        # conds = wide.columns
+        # pairs = list(itertools.combinations(conds, 2))
+
+        # pvals, stats = [], []
+        # for a, b in pairs:
+        #     t, p = ttest_rel(wide[a], wide[b])
+        #     stats.append(t)
+        #     pvals.append(p)
+
+        # # Adjust p-values
+        # rej, p_corr, _, _ = multipletests(pvals, method='bonferroni')
+
+        # print(p_corr)
 
         self.tails = 2
         return stat, p_value
@@ -125,10 +149,11 @@ class StatisticalTests():
         stat, p_value = kruskal(*self.data)
 
         # Perform Dunn's multiple comparisons if Kruskal-Wallis is significant
-        if p_value < 0.05 and self.posthoc:
+        if self.posthoc:  # and p_value < 0.05:
             self.posthoc_matrix = sp.posthoc_dunn(
                 self.data, p_adjust='bonferroni').values.tolist()
-            self.posthoc_name = 'Dunn`s multiple comparisons'
+            self.posthoc_name = 'Dunn`s posthoc'
+        self.tails = 2
         return stat, p_value
 
     def mann_whitney(self):

{autostatlib-0.2.10.dist-info → autostatlib-0.2.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AutoStatLib
-Version: 0.2.10
+Version: 0.2.13
 Summary: AutoStatLib - a simple statistical analysis tool
 Author: Stemonitis, SciWare LLC
 Author-email: konung-yaropolk <yaropolk1995@gmail.com>
@@ -532,11 +532,12 @@ License-File: LICENSE
 Requires-Dist: numpy
 Requires-Dist: scipy
 Requires-Dist: statsmodels
+Requires-Dist: matplotlib
 Requires-Dist: scikit-posthocs
 Requires-Dist: pandas
 Dynamic: license-file
 
-# AutoStatLib - python library for automated statistical analysis 
+# AutoStatLib - python library for automated statistical analysis
 
 [![pypi_version](https://img.shields.io/pypi/v/AutoStatLib?label=PyPI&color=green)](https://pypi.org/project/AutoStatLib)
 [![GitHub Release](https://img.shields.io/github/v/release/konung-yaropolk/AutoStatLib?label=GitHub&color=green&link=https%3A%2F%2Fgithub.com%2Fkonung-yaropolk%2FAutoStatLib)](https://github.com/konung-yaropolk/AutoStatLib)
@@ -544,17 +545,16 @@ Dynamic: license-file
 [![Python](https://img.shields.io/badge/Python-v3.10%5E-green?logo=python)](https://pypi.org/project/AutoStatLib)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/AutoStatLib?label=PyPI%20stats&color=blue)](https://pypi.org/project/AutoStatLib)
 
-
 ### To install run the command:
+
 ```bash
 pip install autostatlib
 ```
 
-
 ### Example use case:
-See the /demo directory on Git repo or  
-use the following example:
 
+See the /demo directory on Git repo or
+use the following example:
 
 ```python
 import numpy as np
@@ -583,11 +583,13 @@ analysis = AutoStatLib.StatisticalAnalysis(
 ```
 
 now you can preform automated statistical test selection:
+
 ```python
 analysis.RunAuto()
 ```
 
 or you can choose specific tests:
+
 ```python
 # 2 groups independent:
 analysis.RunTtest()
@@ -614,15 +616,18 @@ Test summary will be printed to the console.
 You can also get it as a python string via *GetSummary()* method.
 
 ---
+
 Test results are accessible as a dictionary via *GetResult()* method:
+
 ```python
 results = analysis.GetResult()
 ```
 
 The results dictionary keys with representing value types:
+
 ```
 {
-    'p-value' :                    String
+    'p_value' :                    String
     'Significance(p<0.05)' :       Boolean
     'Stars_Printed' :              String
     'Test_Name' :                  String
@@ -632,7 +637,7 @@ The results dictionary keys with representing value types:
     'Parametric_Test_Applied' :    Boolean
     'Paired_Test_Applied' :        Boolean
     'Tails' :                      Integer (taken from the input)
-    'p-value_exact' :              Float
+    'p_value_exact' :              Float
     'Stars' :                      Integer
     'Warnings' :                   String
     'Groups_N' :                   List of integers
@@ -648,50 +653,44 @@ The results dictionary keys with representing value types:
     'Posthoc_Matrix_stars':        2D List of String
 }
 ```
-If errors occured, *GetResult()* returns an empty dictionary
-
 
+If errors occured, *GetResult()* returns an empty dictionary
 
+---
 
+## Pre-Alpha dev status.
 
+### TODO:
 
----
-## Pre-Alpha dev status.  
-  
-### TODO:  
-  
--- Anova: posthocs  
--- Anova: add 2-way anova and 3-way anova  
--- onevay Anova: add repeated measures (for normal dependent values) with and without Gaisser-Greenhouse correction  
--- onevay Anova: add Brown-Forsithe and Welch (for normal independent values with unequal SDs between groups)  
--- paired T-test: add ratio-paired t-test (ratios of paired values are consistent)  
+-- Anova: posthocs
+-- Anova: add 2-way anova and 3-way anova
+-- onevay Anova: add repeated measures (for normal dependent values) with and without Gaisser-Greenhouse correction
+-- onevay Anova: add Brown-Forsithe and Welch (for normal independent values with unequal SDs between groups)
+-- paired T-test: add ratio-paired t-test (ratios of paired values are consistent)
 -- add Welch test (for norm data unequal variances)
--- add Kolmogorov-smirnov test (unpaired nonparametric 2 sample, compare cumulative distributions)  
--- add independent t-test with Welch correction (do not assume equal SDs in groups)  
--- add correlation test, correlation diagram  
--- add linear regression, regression diagram  
+-- add Kolmogorov-smirnov test (unpaired nonparametric 2 sample, compare cumulative distributions)
+-- add independent t-test with Welch correction (do not assume equal SDs in groups)
+-- add correlation test, correlation diagram
+-- add linear regression, regression diagram
 -- add QQ plot
 -- n-sample tests: add onetail option
-  
-✅ done -- detailed normality test results  
-✅ done -- added posthoc: Kruskal-Wallis Dunn's multiple comparisons 
-
-  
-tests check:  
-1-sample:  
---Wilcoxon 2,1 tails - ok  
---t-tests 2,1 tails -ok  
-  
-2-sample:  
---Wilcoxon 2,1 tails - ok  
---Mann-whitney 2,1 tails - ok  
---t-tests 2,1 tails -ok  
-  
-n-sample:  
---Kruskal-Wallis 2 tail - ok  
---Dunn's multiple comparisons - ??
---Friedman 2 tail - ok  
---one-way ANOWA 2 tail - ok  
-
-
 
+✅ done -- detailed normality test results
+✅ done -- added posthoc: Kruskal-Wallis Dunn's multiple comparisons
+
+tests check:
+1-sample:
+--Wilcoxon 2,1 tails - ✅ok
+--t-tests 2,1 tails -✅ok
+
+2-sample:
+--Wilcoxon 2,1 tails - ✅ok
+--Mann-whitney 2,1 tails - ✅ok
+--t-tests 2,1 tails -✅ok
+
+n-sample:
+--Kruskal-Wallis 2 tail - ✅ok
+--Dunn's multiple comparisons - ✅ok
+--Friedman 2 tail - ✅ok
+--one-way ANOWA 2 tail - ✅ok
+--Tukey`s multiple comparisons - ✅ok

autostatlib-0.2.13.dist-info/RECORD

@@ -0,0 +1,14 @@
+AutoStatLib/AutoStatLib.py,sha256=5kiJInUvaa3kB8YfWEeWSpHyUZiHPlDU0fbvxeLdzRM,9750
+AutoStatLib/StatPlots.py,sha256=YOfacQM7HKs4istcVJzt1FUrjXzSl_Ebk01iaR-AcFc,24340
+AutoStatLib/__init__.py,sha256=r7VdcL7F4UCRxEFh8WFBd9y61KavX_qt7fFbKjtjfjo,137
+AutoStatLib/__main__.py,sha256=0OIv5sqFNI-diyHFtYL6HPcYrOWdLiqYYOO_nxrHuTk,283
+AutoStatLib/_version.py,sha256=O3YpbOpmXJZMCHlKDn67yUpAqB2IkWeieWNU_JA526g,54
+AutoStatLib/helpers.py,sha256=Bxe9TkFe5Rtg_F5tBbZKgnbJ0dKDKgsAHq91-o7Nfj4,3646
+AutoStatLib/normality_tests.py,sha256=TYeKpfpJRzOHvDZucObuZhPktjiZpSZwh381eJ8ENC4,2381
+AutoStatLib/statistical_tests.py,sha256=OYU4_PqHBxXv8RyodNqu2YIMn6T-SXKtBrI4tc9LqOA,7313
+AutoStatLib/text_formatting.py,sha256=rWDsrlZdquook7lUg8t2mb3az8nR12BDprxfy_NwE2o,3576
+autostatlib-0.2.13.dist-info/licenses/LICENSE,sha256=IMF9i4xIpgCADf0U-V1cuf9HBmqWQd3qtI3FSuyW4zE,26526
+autostatlib-0.2.13.dist-info/METADATA,sha256=xlfCX8VWNHQPxTDcy3959pDPUFxf7zZhyqqLQIxYxT8,36920
+autostatlib-0.2.13.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+autostatlib-0.2.13.dist-info/top_level.txt,sha256=BuHzVyE2andc7RwD_UPmDjLl9CUAyBH6WHZGjaIReUI,12
+autostatlib-0.2.13.dist-info/RECORD,,

autostatlib-0.2.10.dist-info/RECORD

@@ -1,14 +0,0 @@
-AutoStatLib/AutoStatLib.py,sha256=06kmj2v2lANxYmgKHxPjAeQo1O0JOsMPY5RIwivE6zU,9673
-AutoStatLib/StatPlots.py,sha256=OreCVScPiq2vWGJl5THnH8l2bXTjJC_BWFwXu2GQeRE,23928
-AutoStatLib/__init__.py,sha256=r7VdcL7F4UCRxEFh8WFBd9y61KavX_qt7fFbKjtjfjo,137
-AutoStatLib/__main__.py,sha256=0OIv5sqFNI-diyHFtYL6HPcYrOWdLiqYYOO_nxrHuTk,283
-AutoStatLib/_version.py,sha256=bjH3F6RUMJZM_JtUVM-mMr_l1mPGAxwWzUeOxEQUe-8,54
-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-0.2.10.dist-info/licenses/LICENSE,sha256=IMF9i4xIpgCADf0U-V1cuf9HBmqWQd3qtI3FSuyW4zE,26526
-autostatlib-0.2.10.dist-info/METADATA,sha256=RF5WCmDgsl0alMxqpmCx7Nia77djYgJjNsbBhR8F628,36895
-autostatlib-0.2.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-autostatlib-0.2.10.dist-info/top_level.txt,sha256=BuHzVyE2andc7RwD_UPmDjLl9CUAyBH6WHZGjaIReUI,12
-autostatlib-0.2.10.dist-info/RECORD,,