Fix Upgrading Error

Author: Jacobluke-

.github/workflows/test-pytest.yaml

@@ -8,7 +8,7 @@ jobs:
       - uses: actions/checkout@v3
       - uses: actions/setup-python@v4
         with:
-          python-version: 3.8
+          python-version: 3.9
           cache: "pip"
           cache-dependency-path: settings.ini
       - name: Run pytest

dabest/_modidx.py

@@ -65,7 +65,9 @@
                                                                               'dabest/forest_plot.py'),
                                     'dabest.forest_plot.forest_plot': ('API/forest_plot.html#forest_plot', 'dabest/forest_plot.py'),
                                     'dabest.forest_plot.load_plot_data': ('API/forest_plot.html#load_plot_data', 'dabest/forest_plot.py')},
-            'dabest.misc_tools': { 'dabest.misc_tools.get_varname': ('API/misc_tools.html#get_varname', 'dabest/misc_tools.py'),
+            'dabest.misc_tools': { 'dabest.misc_tools.get_unique_categories': ( 'API/misc_tools.html#get_unique_categories',
+                                                                                'dabest/misc_tools.py'),
+                                   'dabest.misc_tools.get_varname': ('API/misc_tools.html#get_varname', 'dabest/misc_tools.py'),
                                    'dabest.misc_tools.merge_two_dicts': ('API/misc_tools.html#merge_two_dicts', 'dabest/misc_tools.py'),
                                    'dabest.misc_tools.print_greeting': ('API/misc_tools.html#print_greeting', 'dabest/misc_tools.py'),
                                    'dabest.misc_tools.unpack_and_add': ('API/misc_tools.html#unpack_and_add', 'dabest/misc_tools.py')},

dabest/misc_tools.py

@@ -1,10 +1,12 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/API/misc_tools.ipynb.
 
 # %% auto 0
-__all__ = ['merge_two_dicts', 'unpack_and_add', 'print_greeting', 'get_varname']
+__all__ = ['merge_two_dicts', 'unpack_and_add', 'print_greeting', 'get_varname', 'get_unique_categories']
 
 # %% ../nbs/API/misc_tools.ipynb 4
 import datetime as dt
+import numpy as np
+import pandas as pd
 from numpy import repeat
 
 # %% ../nbs/API/misc_tools.ipynb 5
@@ -68,3 +70,15 @@ def get_varname(obj):
     if len(matching_vars) > 0:
         return matching_vars[0]
     return ""
+
+def get_unique_categories(names):
+    """
+    Extract unique categories from various input types.
+    """
+    if isinstance(names, np.ndarray):
+        return names  # numpy.unique() returns a sorted array
+    elif isinstance(names, (pd.Categorical, pd.Series)):
+        return names.cat.categories if hasattr(names, 'cat') else names.unique()
+    else:
+        # For dict_keys and other iterables
+        return np.unique(list(names))

dabest/plot_tools.py

@@ -1136,9 +1136,10 @@ def _swarm(
             raise ValueError("`dsize` must be a scalar or float.")
 
         # Sorting algorithm based off of: https://github.com/mgymrek/pybeeswarm
-        points_data = pd.DataFrame(
-            {"y": [yval * 1.0 / dsize for yval in values], "x": [0] * len(values)}
-        )
+        points_data = pd.DataFrame({
+            "y": [yval * 1.0 / dsize for yval in values],
+            "x": np.zeros(len(values), dtype=float)  # Initialize with float zeros
+        })
         for i in range(1, points_data.shape[0]):
             y_i = points_data["y"].values[i]
             points_placed = points_data[0:i]
@@ -1271,7 +1272,7 @@ def plot(
             0  # x-coordinate of center of each individual swarm of the swarm plot
         )
         x_tick_tabels = []
-        for group_i, values_i in self.__data_copy.groupby(self.__x):
+        for group_i, values_i in self.__data_copy.groupby(self.__x, observed=False):
             x_new = []
             values_i_y = values_i[self.__y]
             x_offset = self._swarm(

dabest/plotter.py

@@ -54,7 +54,7 @@ def effectsize_df_plotter(effectsize_df, **plot_kwargs):
         fontsize_contrastxlabel=12, fontsize_contrastylabel=12,
         fontsize_delta2label=12
     """
-    from .misc_tools import merge_two_dicts
+    from .misc_tools import merge_two_dicts, get_unique_categories
     from .plot_tools import (
         halfviolin,
         get_swarm_spans,
@@ -298,14 +298,16 @@ def effectsize_df_plotter(effectsize_df, **plot_kwargs):
                 raise ValueError(err1 + err2)
 
     if custom_pal is None and color_col is None:
+        categories = get_unique_categories(names)
+        
         swarm_colors = [sns.desaturate(c, swarm_desat) for c in unsat_colors]
-        plot_palette_raw = dict(zip(names.categories, swarm_colors))
-
         bar_color = [sns.desaturate(c, bar_desat) for c in unsat_colors]
-        plot_palette_bar = dict(zip(names.categories, bar_color))
-
         contrast_colors = [sns.desaturate(c, contrast_desat) for c in unsat_colors]
-        plot_palette_contrast = dict(zip(names.categories, contrast_colors))
+
+        
+        plot_palette_raw = dict(zip(categories, swarm_colors))
+        plot_palette_bar = dict(zip(categories, bar_color))
+        plot_palette_contrast = dict(zip(categories, contrast_colors))
 
         # For Sankey Diagram plot, no need to worry about the color, each bar will have the same two colors
         # default color palette will be set to "hls"
@@ -1081,10 +1083,10 @@ def effectsize_df_plotter(effectsize_df, **plot_kwargs):
             )
         elif effect_size_type == "median_diff":
             control_group_summary = (
-                plot_data.groupby(xvar).median().loc[current_control, yvar]
+                plot_data.groupby(xvar).median(numeric_only=True).loc[current_control, yvar]
             )
             test_group_summary = (
-                plot_data.groupby(xvar).median().loc[current_group, yvar]
+                plot_data.groupby(xvar).median(numeric_only=True).loc[current_group, yvar]
             )
 
         if swarm_ylim is None:

nbs/API/misc_tools.ipynb

@@ -55,6 +55,8 @@
    "source": [
     "#| export\n",
     "import datetime as dt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
     "from numpy import repeat"
    ]
   },
@@ -125,7 +127,19 @@
     "    matching_vars = [k for k, v in globals().items() if v is obj]\n",
     "    if len(matching_vars) > 0:\n",
     "        return matching_vars[0]\n",
-    "    return \"\""
+    "    return \"\"\n",
+    "\n",
+    "def get_unique_categories(names):\n",
+    "    \"\"\"\n",
+    "    Extract unique categories from various input types.\n",
+    "    \"\"\"\n",
+    "    if isinstance(names, np.ndarray):\n",
+    "        return names  # numpy.unique() returns a sorted array\n",
+    "    elif isinstance(names, (pd.Categorical, pd.Series)):\n",
+    "        return names.cat.categories if hasattr(names, 'cat') else names.unique()\n",
+    "    else:\n",
+    "        # For dict_keys and other iterables\n",
+    "        return np.unique(list(names))"
    ]
   }
  ],

nbs/API/plot_tools.ipynb

@@ -1199,9 +1199,10 @@
     "            raise ValueError(\"`dsize` must be a scalar or float.\")\n",
     "\n",
     "        # Sorting algorithm based off of: https://github.com/mgymrek/pybeeswarm\n",
-    "        points_data = pd.DataFrame(\n",
-    "            {\"y\": [yval * 1.0 / dsize for yval in values], \"x\": [0] * len(values)}\n",
-    "        )\n",
+    "        points_data = pd.DataFrame({\n",
+    "            \"y\": [yval * 1.0 / dsize for yval in values],\n",
+    "            \"x\": np.zeros(len(values), dtype=float)  # Initialize with float zeros\n",
+    "        })\n",
     "        for i in range(1, points_data.shape[0]):\n",
     "            y_i = points_data[\"y\"].values[i]\n",
     "            points_placed = points_data[0:i]\n",
@@ -1334,7 +1335,7 @@
     "            0  # x-coordinate of center of each individual swarm of the swarm plot\n",
     "        )\n",
     "        x_tick_tabels = []\n",
-    "        for group_i, values_i in self.__data_copy.groupby(self.__x):\n",
+    "        for group_i, values_i in self.__data_copy.groupby(self.__x, observed=False):\n",
     "            x_new = []\n",
     "            values_i_y = values_i[self.__y]\n",
     "            x_offset = self._swarm(\n",

nbs/API/plotter.ipynb

@@ -113,7 +113,7 @@
     "        fontsize_contrastxlabel=12, fontsize_contrastylabel=12,\n",
     "        fontsize_delta2label=12\n",
     "    \"\"\"\n",
-    "    from .misc_tools import merge_two_dicts\n",
+    "    from .misc_tools import merge_two_dicts, get_unique_categories\n",
     "    from .plot_tools import (\n",
     "        halfviolin,\n",
     "        get_swarm_spans,\n",
@@ -357,14 +357,16 @@
     "                raise ValueError(err1 + err2)\n",
     "\n",
     "    if custom_pal is None and color_col is None:\n",
+    "        categories = get_unique_categories(names)\n",
+    "        \n",
     "        swarm_colors = [sns.desaturate(c, swarm_desat) for c in unsat_colors]\n",
-    "        plot_palette_raw = dict(zip(names.categories, swarm_colors))\n",
-    "\n",
     "        bar_color = [sns.desaturate(c, bar_desat) for c in unsat_colors]\n",
-    "        plot_palette_bar = dict(zip(names.categories, bar_color))\n",
-    "\n",
     "        contrast_colors = [sns.desaturate(c, contrast_desat) for c in unsat_colors]\n",
-    "        plot_palette_contrast = dict(zip(names.categories, contrast_colors))\n",
+    "\n",
+    "        \n",
+    "        plot_palette_raw = dict(zip(categories, swarm_colors))\n",
+    "        plot_palette_bar = dict(zip(categories, bar_color))\n",
+    "        plot_palette_contrast = dict(zip(categories, contrast_colors))\n",
     "\n",
     "        # For Sankey Diagram plot, no need to worry about the color, each bar will have the same two colors\n",
     "        # default color palette will be set to \"hls\"\n",
@@ -1140,10 +1142,10 @@
     "            )\n",
     "        elif effect_size_type == \"median_diff\":\n",
     "            control_group_summary = (\n",
-    "                plot_data.groupby(xvar).median().loc[current_control, yvar]\n",
+    "                plot_data.groupby(xvar).median(numeric_only=True).loc[current_control, yvar]\n",
     "            )\n",
     "            test_group_summary = (\n",
-    "                plot_data.groupby(xvar).median().loc[current_group, yvar]\n",
+    "                plot_data.groupby(xvar).median(numeric_only=True).loc[current_group, yvar]\n",
     "            )\n",
     "\n",
     "        if swarm_ylim is None:\n",

settings.ini

@@ -3,7 +3,7 @@
 repo = DABEST-python
 lib_name = dabest
 version = 2024.03.29
-min_python = 3.8
+min_python = 3.9
 license = apache2
 
 ### nbdev ###
@@ -37,7 +37,7 @@ language = English
 status = 3
 user = acclab
 
-requirements = fastcore pandas~=1.5.0 numpy~=1.23.5 matplotlib~=3.8.4 seaborn~=0.12.2 scipy~=1.9.3 datetime statsmodels lqrt
+requirements = fastcore pandas~=1.5.3 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 ###