Update pandas to 2.1.4

Author: Jacobluke-

dabest/_dabest_object.py

@@ -667,7 +667,7 @@ def _get_plot_data(self, x, y, all_plot_groups):
                 all_plot_groups, ordered=True, inplace=True
             )
         else:
-            plot_data.loc[:, self.__xvar] = pd.Categorical(
+            plot_data[self.__xvar] = pd.Categorical(
                 plot_data[self.__xvar], categories=all_plot_groups, ordered=True
             )
 

dabest/plot_tools.py

@@ -117,25 +117,25 @@ def error_bar(
     else:
         group_order = pd.unique(data[x])
 
-    means = data.groupby(x)[y].mean().reindex(index=group_order)
+    means = data.groupby(x, observed=False)[y].mean().reindex(index=group_order)
 
     if method in ["proportional_error_bar", "sankey_error_bar"]:
         g = lambda x: np.sqrt(
             (np.sum(x) * (len(x) - np.sum(x))) / (len(x) * len(x) * len(x))
         )
-        sd = data.groupby(x)[y].apply(g)
+        sd = data.groupby(x, observed=False)[y].apply(g)
     else:
-        sd = data.groupby(x)[y].std().reindex(index=group_order)
+        sd = data.groupby(x, observed=False)[y].std().reindex(index=group_order)
 
     lower_sd = means - sd
     upper_sd = means + sd
 
     if (lower_sd < ax_ylims[0]).any() or (upper_sd > ax_ylims[1]).any():
         kwargs["clip_on"] = True
 
-    medians = data.groupby(x)[y].median().reindex(index=group_order)
+    medians = data.groupby(x, observed=False)[y].median().reindex(index=group_order)
     quantiles = (
-        data.groupby(x)[y].quantile([0.25, 0.75]).unstack().reindex(index=group_order)
+        data.groupby(x, observed=False)[y].quantile([0.25, 0.75]).unstack().reindex(index=group_order)
     )
     lower_quartiles = quantiles[0.25]
     upper_quartiles = quantiles[0.75]

dabest/plotter.py

@@ -780,7 +780,7 @@ def effectsize_df_plotter(effectsize_df, **plot_kwargs):
             )
 
     # Add the counts to the rawdata axes xticks.
-    counts = plot_data.groupby(xvar).count()[yvar]
+    counts = plot_data.groupby(xvar, observed=False).count()[yvar]
     ticks_with_counts = []
     ticks_loc = rawdata_axes.get_xticks()
     rawdata_axes.xaxis.set_major_locator(matplotlib.ticker.FixedLocator(ticks_loc))
@@ -1076,19 +1076,19 @@ def effectsize_df_plotter(effectsize_df, **plot_kwargs):
         # Check that the effect size is within the swarm ylims.
         if effect_size_type in ["mean_diff", "cohens_d", "hedges_g", "cohens_h"]:
             control_group_summary = (
-                plot_data.groupby(xvar)
+                plot_data.groupby(xvar, observed=False)
                 .mean(numeric_only=True)
                 .loc[current_control, yvar]
             )
             test_group_summary = (
-                plot_data.groupby(xvar).mean(numeric_only=True).loc[current_group, yvar]
+                plot_data.groupby(xvar, observed=False).mean(numeric_only=True).loc[current_group, yvar]
             )
         elif effect_size_type == "median_diff":
             control_group_summary = (
-                plot_data.groupby(xvar).median(numeric_only=True).loc[current_control, yvar]
+                plot_data.groupby(xvar, observed=False).median(numeric_only=True).loc[current_control, yvar]
             )
             test_group_summary = (
-                plot_data.groupby(xvar).median(numeric_only=True).loc[current_group, yvar]
+                plot_data.groupby(xvar, observed=False).median(numeric_only=True).loc[current_group, yvar]
             )
 
         if swarm_ylim is None:
@@ -1132,7 +1132,7 @@ def effectsize_df_plotter(effectsize_df, **plot_kwargs):
                 pooled_sd = stds[0]
 
             if effect_size_type == "hedges_g":
-                gby_count = plot_data.groupby(xvar).count()
+                gby_count = plot_data.groupby(xvar, observed=False).count()
                 len_control = gby_count.loc[current_control, yvar]
                 len_test = gby_count.loc[current_group, yvar]
 

nbs/API/dabest_object.ipynb

@@ -735,7 +735,7 @@
     "                all_plot_groups, ordered=True, inplace=True\n",
     "            )\n",
     "        else:\n",
-    "            plot_data.loc[:, self.__xvar] = pd.Categorical(\n",
+    "            plot_data[self.__xvar] = pd.Categorical(\n",
     "                plot_data[self.__xvar], categories=all_plot_groups, ordered=True\n",
     "            )\n",
     "\n",

nbs/API/plot_tools.ipynb

@@ -170,25 +170,25 @@
     "    else:\n",
     "        group_order = pd.unique(data[x])\n",
     "\n",
-    "    means = data.groupby(x)[y].mean().reindex(index=group_order)\n",
+    "    means = data.groupby(x, observed=False)[y].mean().reindex(index=group_order)\n",
     "\n",
     "    if method in [\"proportional_error_bar\", \"sankey_error_bar\"]:\n",
     "        g = lambda x: np.sqrt(\n",
     "            (np.sum(x) * (len(x) - np.sum(x))) / (len(x) * len(x) * len(x))\n",
     "        )\n",
-    "        sd = data.groupby(x)[y].apply(g)\n",
+    "        sd = data.groupby(x, observed=False)[y].apply(g)\n",
     "    else:\n",
-    "        sd = data.groupby(x)[y].std().reindex(index=group_order)\n",
+    "        sd = data.groupby(x, observed=False)[y].std().reindex(index=group_order)\n",
     "\n",
     "    lower_sd = means - sd\n",
     "    upper_sd = means + sd\n",
     "\n",
     "    if (lower_sd < ax_ylims[0]).any() or (upper_sd > ax_ylims[1]).any():\n",
     "        kwargs[\"clip_on\"] = True\n",
     "\n",
-    "    medians = data.groupby(x)[y].median().reindex(index=group_order)\n",
+    "    medians = data.groupby(x, observed=False)[y].median().reindex(index=group_order)\n",
     "    quantiles = (\n",
-    "        data.groupby(x)[y].quantile([0.25, 0.75]).unstack().reindex(index=group_order)\n",
+    "        data.groupby(x, observed=False)[y].quantile([0.25, 0.75]).unstack().reindex(index=group_order)\n",
     "    )\n",
     "    lower_quartiles = quantiles[0.25]\n",
     "    upper_quartiles = quantiles[0.75]\n",

nbs/API/plotter.ipynb

@@ -837,7 +837,7 @@
     "            )\n",
     "\n",
     "    # Add the counts to the rawdata axes xticks.\n",
-    "    counts = plot_data.groupby(xvar).count()[yvar]\n",
+    "    counts = plot_data.groupby(xvar, observed=False).count()[yvar]\n",
     "    ticks_with_counts = []\n",
     "    ticks_loc = rawdata_axes.get_xticks()\n",
     "    rawdata_axes.xaxis.set_major_locator(matplotlib.ticker.FixedLocator(ticks_loc))\n",
@@ -1133,19 +1133,19 @@
     "        # Check that the effect size is within the swarm ylims.\n",
     "        if effect_size_type in [\"mean_diff\", \"cohens_d\", \"hedges_g\", \"cohens_h\"]:\n",
     "            control_group_summary = (\n",
-    "                plot_data.groupby(xvar)\n",
+    "                plot_data.groupby(xvar, observed=False)\n",
     "                .mean(numeric_only=True)\n",
     "                .loc[current_control, yvar]\n",
     "            )\n",
     "            test_group_summary = (\n",
-    "                plot_data.groupby(xvar).mean(numeric_only=True).loc[current_group, yvar]\n",
+    "                plot_data.groupby(xvar, observed=False).mean(numeric_only=True).loc[current_group, yvar]\n",
     "            )\n",
     "        elif effect_size_type == \"median_diff\":\n",
     "            control_group_summary = (\n",
-    "                plot_data.groupby(xvar).median(numeric_only=True).loc[current_control, yvar]\n",
+    "                plot_data.groupby(xvar, observed=False).median(numeric_only=True).loc[current_control, yvar]\n",
     "            )\n",
     "            test_group_summary = (\n",
-    "                plot_data.groupby(xvar).median(numeric_only=True).loc[current_group, yvar]\n",
+    "                plot_data.groupby(xvar, observed=False).median(numeric_only=True).loc[current_group, yvar]\n",
     "            )\n",
     "\n",
     "        if swarm_ylim is None:\n",
@@ -1189,7 +1189,7 @@
     "                pooled_sd = stds[0]\n",
     "\n",
     "            if effect_size_type == \"hedges_g\":\n",
-    "                gby_count = plot_data.groupby(xvar).count()\n",
+    "                gby_count = plot_data.groupby(xvar, observed=False).count()\n",
     "                len_control = gby_count.loc[current_control, yvar]\n",
     "                len_test = gby_count.loc[current_group, yvar]\n",
     "\n",

settings.ini

@@ -37,7 +37,7 @@ language = English
 status = 3
 user = acclab
 
-requirements = fastcore pandas~=1.5.3 numpy~=1.26 matplotlib~=3.8.4 seaborn~=0.12.2 scipy~=1.12 datetime statsmodels lqrt
+requirements = fastcore pandas~=2.1.4 numpy~=1.26 matplotlib~=3.8.4 seaborn~=0.12.2 scipy~=1.12 datetime statsmodels lqrt
 dev_requirements = pytest~=7.2.1 pytest-mpl~=0.16.1
 
 ### Optional ###