Merge remote-tracking branch 'origin/sankey'

Author: Jacobluke-

dabest/__init__.py

@@ -23,4 +23,4 @@
 from ._stats_tools import effsize as effsize
 from ._classes import TwoGroupsEffectSize, PermutationTest
 
-__version__ = "0.3.1"
+__version__ = "2023.02.14"

dabest/_classes.py

@@ -1570,7 +1570,8 @@ class TwoGroupsEffectSize(object):
     mean differences between two groups.
     """
 
-    def __init__(self, control, test, effect_size,proportional,
+    def __init__(self, control, test, effect_size,
+                 proportional=False,
                  is_paired=None, ci=95,
                  resamples=5000, 
                  permutation_count=5000, 
@@ -1706,6 +1707,7 @@ def __init__(self, control, test, effect_size,proportional,
         import scipy.stats as spstats
 
         # import statsmodels.stats.power as power
+        import statsmodels
 
         from string import Template
         import warnings
@@ -2661,7 +2663,7 @@ def plot(self, color_col=None,
             #bar plot
             bar_label=None, bar_desat=0.5, bar_width = 0.5,bar_ylim = None,
             # error bar of proportion plot
-            ci=None, err_color=None,
+            ci=None, ci_type='bca', err_color=None,
 
             float_contrast=True,
             show_pairs=True,
@@ -2678,6 +2680,7 @@ def plot(self, color_col=None,
             barplot_kwargs=None,
             violinplot_kwargs=None,
             slopegraph_kwargs=None,
+            sankey_kwargs=None,
             reflines_kwargs=None,
             group_summary_kwargs=None,
             legend_kwargs=None):
@@ -2778,6 +2781,12 @@ def plot(self, color_col=None,
             accepted by matplotlib `plot()` function here, as a dict.
             If None, the following keywords are
             passed to plot() : {'linewidth':1, 'alpha':0.5}.
+        sankey_kwargs: dict, default None
+            Whis will change the appearance of the sankey diagram used to depict
+            paired proportional data when `show_pairs=True` and `proportional=True`. 
+            Pass any keyword arguments accepted by plot_tools.sankeydiag() function
+            here, as a dict. If None, the following keywords are passed to sankey diagram:
+            {"width": 0.5, "align": "center", "alpha": 0.4, "bar_width": 0.1, "rightColor": False}
         reflines_kwargs : dict, default None
             This will change the appearance of the zero reference lines. Pass
             any keyword arguments accepted by the matplotlib Axes `hlines`

dabest/_stats_tools/effsize.py

@@ -7,6 +7,7 @@
 
     two_group_difference
     cohens_d
+    cohens_h
     hedges_g
     cliffs_delta
     func_difference
@@ -71,11 +72,19 @@ def two_group_difference(control, test, is_paired=False,
         float: The desired effect size.
     """
     import numpy as np
+    import warnings
 
     if effect_size == "mean_diff":
         return func_difference(control, test, np.mean, is_paired)
 
     elif effect_size == "median_diff":
+        mes1 = "Using median as the statistic in bootstrapping may \
+                result in a biased estimate and cause problems with \
+                BCa confidence intervals. Consider using a different statistic, such as the mean.\n"
+        mes2 = "When plotting, please consider using percetile confidence intervals\
+                by specifying `ci_type='percentile'`. For detailed information, \
+                refer to https://github.com/ACCLAB/DABEST-python/issues/129"
+        warnings.warn(message=mes1+mes2, category=UserWarning)
         return func_difference(control, test, np.median, is_paired)
 
     elif effect_size == "cohens_d":
@@ -257,7 +266,7 @@ def cohens_h(control, test):
     import pandas as pd
 
     # Check whether dataframe contains only 0s and 1s.
-    if pd.unique(control)==np.array([0,1]).all()==False and (pd.unique(test)==np.array([0,1])).all()==False:
+    if np.isin(control, [0, 1]).all() == False or np.isin(test, [0, 1]).all() == False:
         raise ValueError("Input data must be binary.")
 
     # Convert to numpy arrays for speed.