AutoStatLib 0.2.14__tar.gz → 0.2.18__tar.gz

{autostatlib-0.2.14/src/AutoStatLib.egg-info → autostatlib-0.2.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AutoStatLib
-Version: 0.2.14
+Version: 0.2.18
 Summary: AutoStatLib - a simple statistical analysis tool
 Author: Stemonitis, SciWare LLC
 Author-email: konung-yaropolk <yaropolk1995@gmail.com>
@@ -533,6 +533,7 @@ Requires-Dist: numpy
 Requires-Dist: scipy
 Requires-Dist: statsmodels
 Requires-Dist: matplotlib
+Requires-Dist: seaborn
 Requires-Dist: scikit-posthocs
 Requires-Dist: pandas
 Dynamic: license-file
@@ -672,25 +673,25 @@ If errors occured, *GetResult()* returns an empty dictionary
 -- 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
+-- add QQ plot  
+-- n-sample tests: add onetail option  
 
-✅ done -- detailed normality test results
-✅ done -- added posthoc: Kruskal-Wallis Dunn's multiple comparisons
+✅ 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
+✅ok --Wilcoxon 2,1 tails  
+✅ok --t-tests 2,1 tails
 
 2-sample:
---Wilcoxon 2,1 tails - ✅ok
---Mann-whitney 2,1 tails - ✅ok
---t-tests 2,1 tails -✅ok
+✅ok --Wilcoxon 2,1 tails  
+✅ok --Mann-whitney 2,1 tails
+✅ok --t-tests 2,1 tails
 
 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
+✅ok --Kruskal-Wallis 2 tail  
+✅ok --Dunn's multiple comparisons
+✅ok --Friedman 2 tail
+✅ok --one-way ANOWA 2 tail
+✅ok --Tukey`s multiple comparisons

{autostatlib-0.2.14 → autostatlib-0.2.18}/README.md

@@ -133,25 +133,25 @@ If errors occured, *GetResult()* returns an empty dictionary
 -- 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
+-- add QQ plot  
+-- n-sample tests: add onetail option  
 
-✅ done -- detailed normality test results
-✅ done -- added posthoc: Kruskal-Wallis Dunn's multiple comparisons
+✅ 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
+✅ok --Wilcoxon 2,1 tails  
+✅ok --t-tests 2,1 tails
 
 2-sample:
---Wilcoxon 2,1 tails - ✅ok
---Mann-whitney 2,1 tails - ✅ok
---t-tests 2,1 tails -✅ok
+✅ok --Wilcoxon 2,1 tails  
+✅ok --Mann-whitney 2,1 tails
+✅ok --t-tests 2,1 tails
 
 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
+✅ok --Kruskal-Wallis 2 tail  
+✅ok --Dunn's multiple comparisons
+✅ok --Friedman 2 tail
+✅ok --one-way ANOWA 2 tail
+✅ok --Tukey`s multiple comparisons

{autostatlib-0.2.14 → autostatlib-0.2.18}/requirements.txt

@@ -2,5 +2,6 @@ numpy
 scipy
 statsmodels
 matplotlib
+seaborn
 scikit-posthocs
 pandas

{autostatlib-0.2.14 → autostatlib-0.2.18}/src/AutoStatLib/StatPlots.py

@@ -1,3 +1,4 @@
+import seaborn as sns
 import random
 # from math import comb
 import numpy as np
@@ -149,31 +150,6 @@ class BaseStatPlot(Helpers):
 
         return fig, ax
 
-    def add_scatter(self, ax,
-                    color='k',
-                    alpha=0.5,
-                    marker='o',
-                    markersize=6,
-                    linewidth=1,
-                    zorder=1):
-        # Generate x jitter pool.
-        spread_pool = []  # storing x positions of data points
-        for i, data in enumerate(self.data_groups):
-            spread = tuple(random.uniform(-.10, .10) for _ in data)
-            spread_pool.append(tuple(i + s for s in spread))
-
-        for i, data in enumerate(self.transpose(self.data_groups)):
-            # Plot individual data points with x jitter.
-            ax.plot(self.transpose(spread_pool)[i], data,
-                    color=color,
-                    alpha=alpha,
-                    marker=marker,
-                    markersize=markersize*self.figure_scale_factor,
-                    linewidth=linewidth*self.figure_scale_factor,
-                    # Connect the data points if desired.
-                    linestyle='-' if self.dependent else '',
-                    zorder=zorder)
-
     def add_barplot(self, ax, x,
                     fill=True,
                     linewidth=2,
@@ -359,6 +335,83 @@ class BaseStatPlot(Helpers):
                 patch.set_facecolor(
                     self.colors_fill[x % len(self.colors_fill)])
 
+    def add_scatter(self, ax,
+                    color='k',
+                    alpha=0.5,
+                    marker='o',
+                    markersize=8,
+                    linewidth=1.2,
+                    zorder=2):
+        # Generate x jitter pool.
+        spread_pool = []  # storing x positions of data points
+        for i, data in enumerate(self.data_groups):
+            spread = tuple(random.uniform(-.10, .10) for _ in data)
+            spread_pool.append(tuple(i + s for s in spread))
+
+        for i, data in enumerate(self.transpose(self.data_groups)):
+            # Plot individual data points with x jitter.
+            ax.plot(self.transpose(spread_pool)[i], data,
+                    color=color,
+                    alpha=alpha,
+                    marker=marker,
+                    markersize=markersize*self.figure_scale_factor,
+                    linewidth=linewidth*self.figure_scale_factor,
+                    # Connect the data points if desired.
+                    linestyle='-' if self.dependent else '',
+                    zorder=zorder-1)
+
+    def add_swarm(self, ax,
+                  color='grey',
+                  alpha=1,
+                  marker='o',
+                  markersize=8,
+                  linewidth=1.4,
+                  zorder=2):
+        """
+        Add a swarmplot (scatter-like plot with non-overlapping points)
+        to the provided Axes. Automatically reduce point size if overcrowded.
+        """
+
+        # Prepare flattened data
+        values = [v for i, group in enumerate(self.data_groups) for v in group]
+        groups = [i for i, group in enumerate(self.data_groups) for _ in group]
+
+        # Estimate overcrowding for adaptive sizing
+        group_counts = [len(g) for g in self.data_groups]
+        max_points = max(group_counts) if group_counts else 1
+
+        # Determine horizontal space per category
+        num_groups = len(self.data_groups)
+        xlim = ax.get_xlim()
+        width_per_group = (xlim[1] - xlim[0]) / max(num_groups, 1)
+
+        # Empirical density threshold: if points are too dense, shrink
+        density = max_points / (width_per_group + 1e-6)
+
+        # Tunable constants to approximate best function of size adjustment
+        size_scale = max(0.1, min(1, 3.5 / (density ** 0.5)))
+
+        sns.swarmplot(
+            x=groups,
+            y=values,
+            ax=ax,
+            color=color,
+            alpha=alpha,
+            size=markersize * self.figure_scale_factor * size_scale,
+            marker=marker,
+            linewidth=linewidth * self.figure_scale_factor * size_scale,
+            zorder=zorder,
+        )
+
+        # Connect points if data paired
+        if self.dependent == True:
+            for i, data in enumerate(self.transpose(self.data_groups)):
+                ax.plot(range(len(data)), data,
+                        color=color,
+                        alpha=alpha * 0.7,
+                        linewidth=linewidth * self.figure_scale_factor,
+                        zorder=zorder - 1)
+
     def add_errorbar_sd(self, ax, x,
                         capsize=8,
                         ecolor='r',
@@ -589,7 +642,7 @@ class BarStatPlot(BaseStatPlot):
             self.add_mean_marker(ax, x)
             self.add_errorbar_sd(ax, x)
 
-        self.add_scatter(ax)
+        self.add_swarm(ax)
         self.add_significance_bars(ax, linewidth)
         self.add_titles_and_labels(fig, ax)
         self.axes_formatting(ax, linewidth)
@@ -622,11 +675,14 @@ class ViolinStatPlot(BaseStatPlot):
             self.add_mean_marker(ax, x)
             # self.add_errorbar_sd(ax, x)
 
-        self.add_scatter(ax)
+        self.add_swarm(ax)
         self.add_significance_bars(ax, linewidth)
         self.add_titles_and_labels(fig, ax)
         self.axes_formatting(ax, linewidth)
 
+        xmin, xmax = ax.get_xlim()
+        ax.set_xlim(xmin - 0.3, xmax + 0.3)
+
 
 class BoxStatPlot(BaseStatPlot):
 
@@ -635,7 +691,7 @@ class BoxStatPlot(BaseStatPlot):
         linewidth = 2
 
         self.add_boxplot(ax)
-        self.add_scatter(ax)
+        self.add_swarm(ax)
         self.add_significance_bars(ax, linewidth)
         self.add_titles_and_labels(fig, ax)
         self.axes_formatting(ax, linewidth)
@@ -658,3 +714,28 @@ class ScatterStatPlot(BaseStatPlot):
         self.add_significance_bars(ax, linewidth)
         self.add_titles_and_labels(fig, ax)
         self.axes_formatting(ax, linewidth)
+
+        xmin, xmax = ax.get_xlim()
+        ax.set_xlim(xmin - 0.3, xmax + 0.3)
+
+
+class SwarmStatPlot(BaseStatPlot):
+
+    def plot(self):
+        fig, ax = self.setup_figure()
+        linewidth = 2
+
+        for x in range(len(self.data_groups)):
+
+            # Overlay errbars, and markers.
+            self.add_median_marker(ax, x)
+            self.add_mean_marker(ax, x)
+            self.add_errorbar_sd(ax, x)
+
+        self.add_swarm(ax)
+        self.add_significance_bars(ax, linewidth)
+        self.add_titles_and_labels(fig, ax)
+        self.axes_formatting(ax, linewidth)
+
+        xmin, xmax = ax.get_xlim()
+        ax.set_xlim(xmin - 0.3, xmax + 0.3)

{autostatlib-0.2.14 → autostatlib-0.2.18}/src/AutoStatLib/_version.py

@@ -1,2 +1,2 @@
 # AutoStatLib package version:
-__version__ = "0.2.14"
+__version__ = "0.2.18"

{autostatlib-0.2.14 → autostatlib-0.2.18}/src/AutoStatLib/helpers.py

@@ -21,6 +21,16 @@ class Helpers():
             {'Row': rows, 'Col': cols, 'Value': data})
         return df
 
+    def list_to_matrix(self, list, n):
+        i = 0
+        matrix = [[1.0 for _ in range(n)] for _ in range(n)]
+        for ax0 in range(n):
+            for ax1 in range(ax0+1, n):
+                matrix[ax0][ax1] = list[i]
+                matrix[ax1][ax0] = list[i]
+                i += 1
+        return matrix
+
     def floatify_recursive(self, data):
         if isinstance(data, list):
             # Recursively process sublists and filter out None values

{autostatlib-0.2.14 → autostatlib-0.2.18}/src/AutoStatLib/statistical_tests.py

@@ -99,12 +99,12 @@ class StatisticalTests():
                 [[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]],
-            ]
+
+            list = tukey_result.pvalues.tolist()
+            n = self.n_groups
+            # prepare posthoc matrix
+            self.posthoc_matrix = self.list_to_matrix(list, n)
+
         return stat, p_value
 
     def anova_1w_rm(self):

{autostatlib-0.2.14 → autostatlib-0.2.18/src/AutoStatLib.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AutoStatLib
-Version: 0.2.14
+Version: 0.2.18
 Summary: AutoStatLib - a simple statistical analysis tool
 Author: Stemonitis, SciWare LLC
 Author-email: konung-yaropolk <yaropolk1995@gmail.com>
@@ -533,6 +533,7 @@ Requires-Dist: numpy
 Requires-Dist: scipy
 Requires-Dist: statsmodels
 Requires-Dist: matplotlib
+Requires-Dist: seaborn
 Requires-Dist: scikit-posthocs
 Requires-Dist: pandas
 Dynamic: license-file
@@ -672,25 +673,25 @@ If errors occured, *GetResult()* returns an empty dictionary
 -- 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
+-- add QQ plot  
+-- n-sample tests: add onetail option  
 
-✅ done -- detailed normality test results
-✅ done -- added posthoc: Kruskal-Wallis Dunn's multiple comparisons
+✅ 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
+✅ok --Wilcoxon 2,1 tails  
+✅ok --t-tests 2,1 tails
 
 2-sample:
---Wilcoxon 2,1 tails - ✅ok
---Mann-whitney 2,1 tails - ✅ok
---t-tests 2,1 tails -✅ok
+✅ok --Wilcoxon 2,1 tails  
+✅ok --Mann-whitney 2,1 tails
+✅ok --t-tests 2,1 tails
 
 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
+✅ok --Kruskal-Wallis 2 tail  
+✅ok --Dunn's multiple comparisons
+✅ok --Friedman 2 tail
+✅ok --one-way ANOWA 2 tail
+✅ok --Tukey`s multiple comparisons

{autostatlib-0.2.14 → autostatlib-0.2.18}/src/AutoStatLib.egg-info/requires.txt

@@ -2,5 +2,6 @@ numpy
 scipy
 statsmodels
 matplotlib
+seaborn
 scikit-posthocs
 pandas