Fix bugs related to NaN values

Author: Jacobluke-

dabest/_dabest_object.py

@@ -57,6 +57,18 @@ def __init__(
         self._check_errors(x, y, idx, experiment, experiment_label, x1_level)
 
 
+        # Check if there is NaN under any of the paired settings
+        if self.__is_paired and self.__output_data.isnull().values.any():
+            import warnings
+            warn1 = f"NaN values detected under paired setting and removed,"
+            warn2 = f" please check your data."
+            warnings.warn(warn1 + warn2)
+            if x is not None and y is not None:
+                rmname = self.__output_data[self.__output_data[y].isnull()][self.__id_col].tolist()
+                self.__output_data = self.__output_data[~self.__output_data[self.__id_col].isin(rmname)]
+            elif x is None and y is None:
+                self.__output_data.dropna(inplace=True)
+
         # create new x & idx and record the second variable if this is a valid 2x2 ANOVA case
         if idx is None and x is not None and y is not None:
             # Add a length check for unique values in the first element in list x,
@@ -562,7 +574,16 @@ def _get_plot_data(self, x, y, all_plot_groups):
         """
         Function to prepare some attributes for plotting
         """
-
+        # Check if there is NaN under any of the paired settings
+        if self.__is_paired is not None and self.__output_data.isnull().values.any():
+            print("Nan")
+            import warnings
+            warn1 = f"NaN values detected under paired setting and removed,"
+            warn2 = f" please check your data."
+            warnings.warn(warn1 + warn2)
+            rmname = self.__output_data[self.__output_data[y].isnull()][self.__id_col].tolist()
+            self.__output_data = self.__output_data[~self.__output_data[self.__id_col].isin(rmname)]
+                
         # Identify the type of data that was passed in.
         if x is not None and y is not None:
             # Assume we have a long dataset.
@@ -606,6 +627,13 @@ def _get_plot_data(self, x, y, all_plot_groups):
             self.__xvar = "group"
             self.__yvar = "value"
 
+            # Check if there is NaN under any of the paired settings
+            if self.__is_paired is not None and self.__output_data.isnull().values.any():
+                import warnings
+                warn1 = f"NaN values detected under paired setting and removed,"
+                warn2 = f" please check your data."
+                warnings.warn(warn1 + warn2)
+
             # First, check we have all columns in the dataset.
             for g in all_plot_groups:
                 if g not in self.__output_data.columns:
@@ -625,10 +653,6 @@ def _get_plot_data(self, x, y, all_plot_groups):
                 var_name=self.__xvar,
             )
 
-        if self.__is_paired is not None and plot_data.isnull().values.any():
-            import warnings
-            warnings.warn("NaN values detected in paired setting, please remove NaNs and corresponding rows before proceeding.")
-
         # Added in v0.2.7.
         plot_data.dropna(axis=0, how="any", subset=[self.__yvar], inplace=True)
 

nbs/API/dabest_object.ipynb

@@ -127,6 +127,18 @@
     "        self._check_errors(x, y, idx, experiment, experiment_label, x1_level)\n",
     "        \n",
     "\n",
+    "        # Check if there is NaN under any of the paired settings\n",
+    "        if self.__is_paired and self.__output_data.isnull().values.any():\n",
+    "            import warnings\n",
+    "            warn1 = f\"NaN values detected under paired setting and removed,\"\n",
+    "            warn2 = f\" please check your data.\"\n",
+    "            warnings.warn(warn1 + warn2)\n",
+    "            if x is not None and y is not None:\n",
+    "                rmname = self.__output_data[self.__output_data[y].isnull()][self.__id_col].tolist()\n",
+    "                self.__output_data = self.__output_data[~self.__output_data[self.__id_col].isin(rmname)]\n",
+    "            elif x is None and y is None:\n",
+    "                self.__output_data.dropna(inplace=True)\n",
+    "\n",
     "        # create new x & idx and record the second variable if this is a valid 2x2 ANOVA case\n",
     "        if idx is None and x is not None and y is not None:\n",
     "            # Add a length check for unique values in the first element in list x,\n",
@@ -632,7 +644,16 @@
     "        \"\"\"\n",
     "        Function to prepare some attributes for plotting\n",
     "        \"\"\"\n",
-    "\n",
+    "        # Check if there is NaN under any of the paired settings\n",
+    "        if self.__is_paired is not None and self.__output_data.isnull().values.any():\n",
+    "            print(\"Nan\")\n",
+    "            import warnings\n",
+    "            warn1 = f\"NaN values detected under paired setting and removed,\"\n",
+    "            warn2 = f\" please check your data.\"\n",
+    "            warnings.warn(warn1 + warn2)\n",
+    "            rmname = self.__output_data[self.__output_data[y].isnull()][self.__id_col].tolist()\n",
+    "            self.__output_data = self.__output_data[~self.__output_data[self.__id_col].isin(rmname)]\n",
+    "                \n",
     "        # Identify the type of data that was passed in.\n",
     "        if x is not None and y is not None:\n",
     "            # Assume we have a long dataset.\n",
@@ -676,6 +697,13 @@
     "            self.__xvar = \"group\"\n",
     "            self.__yvar = \"value\"\n",
     "\n",
+    "            # Check if there is NaN under any of the paired settings\n",
+    "            if self.__is_paired is not None and self.__output_data.isnull().values.any():\n",
+    "                import warnings\n",
+    "                warn1 = f\"NaN values detected under paired setting and removed,\"\n",
+    "                warn2 = f\" please check your data.\"\n",
+    "                warnings.warn(warn1 + warn2)\n",
+    "\n",
     "            # First, check we have all columns in the dataset.\n",
     "            for g in all_plot_groups:\n",
     "                if g not in self.__output_data.columns:\n",
@@ -695,10 +723,6 @@
     "                var_name=self.__xvar,\n",
     "            )\n",
     "\n",
-    "        if self.__is_paired is not None and plot_data.isnull().values.any():\n",
-    "            import warnings\n",
-    "            warnings.warn(\"NaN values detected in paired setting, please remove NaNs and corresponding rows before proceeding.\")\n",
-    "\n",
     "        # Added in v0.2.7.\n",
     "        plot_data.dropna(axis=0, how=\"any\", subset=[self.__yvar], inplace=True)\n",
     "\n",