Added Pandas Kurtosis & Pandas Skew nodes. Fixed docstrings for various nodes to address doc inaccuracies from v1.1.0 changes.

modules/pandas_wrapper/pandas_create.py

@@ -30,13 +30,13 @@ class PandasCreate:
 
     def create(self, data: str) -> tuple:
         """
-        Create a pandas DataFrame using values entered in the text field and converts it to a JSON string.
+        Create a pandas DataFrame using values entered in the text field and converts it to a DataFrame.
 
         Args:
             data (str): String value in the text field.
 
         Returns:
-            tuple: A tuple containing a JSON string representation of the DataFrame.
+            tuple: A tuple containing a the DataFrame.
         """
         # Read CSV file into DataFrame
         df = pd.read_csv(StringIO(data))

modules/pandas_wrapper/pandas_create_with_index.py

@@ -31,7 +31,7 @@ class PandasCreateWithIndex:
 
     def create(self, data: str, index_col: int=0) -> tuple:
         """
-        Create a pandas DataFrame using values entered in the text field and converts it to a JSON string.
+        Create a pandas DataFrame using values entered in the text field and converts it to a DataFrame.
         Input data is assume to have an index.
 
         Args:
@@ -39,7 +39,7 @@ class PandasCreateWithIndex:
             index_col (int): Position of the index column.
 
         Returns:
-            tuple: A tuple containing a JSON string representation of the DataFrame.
+            tuple: A tuple containing the DataFrame.
         """
         # Read CSV file into DataFrame
         df = pd.read_csv(StringIO(data), index_col=index_col)

modules/pandas_wrapper/pandas_cummax.py

@@ -37,7 +37,7 @@ class PandasCummax:
             axis (str): Specify the direction to compute: Index (row label) or column label.
 
         Returns:
-            tuple: A tuple containing a JSON string of the renamed DataFrame.
+            tuple: A tuple containing the DataFrame.
         """
         if axis=="index":
             df_out = dataframe.cummax(axis=0)

modules/pandas_wrapper/pandas_cummin.py

@@ -37,7 +37,7 @@ class PandasCummin:
             axis (str): Specify the direction to compute: Index (row label) or column label.
 
         Returns:
-            tuple: A tuple containing a JSON string of the renamed DataFrame.
+            tuple: A tuple containing the DataFrame.
         """
         if axis=="index":
             df_out = dataframe.cummin(axis=0)

modules/pandas_wrapper/pandas_cumprod.py

@@ -37,7 +37,7 @@ class PandasCumprod:
             axis (str): Specify the direction to compute: Index (row label) or column label.
 
         Returns:
-            tuple: A tuple containing a JSON string of the renamed DataFrame.
+            tuple: A tuple containing the DataFrame.
         """
         if axis=="index":
             df_out = dataframe.cumprod(axis=0)

modules/pandas_wrapper/pandas_cumsum.py

@@ -37,7 +37,7 @@ class PandasCumsum:
             axis (str): Specify the direction to compute: Index (row label) or column label.
 
         Returns:
-            tuple: A tuple containing a JSON string of the renamed DataFrame.
+            tuple: A tuple containing the DataFrame.
         """
         if axis=="index":
             df_out = dataframe.cumsum(axis=0)

modules/pandas_wrapper/pandas_group_by.py

@@ -44,7 +44,7 @@ class PandasGroupBy:
             aggregate_function (str): The type of aggregate function to perform.
 
         Returns:
-            tuple: A tuple containing a JSON string of the merged DataFrame.
+            tuple: A tuple containing the merged DataFrame.
         """
         if aggragate_function == "max":
             df_out = dataframe.groupby(column_name).max()

modules/pandas_wrapper/pandas_head.py

@@ -38,7 +38,7 @@ class PandasHead:
             rows (int): The number of rows to retrieve.
 
         Returns:
-            tuple: A tuple containing a JSON string of the resulting DataFrame.
+            tuple: A tuple containing the resulting DataFrame.
         """
         df2 = dataframe.head(rows)
         return (df2,)

modules/pandas_wrapper/pandas_iloc_rows_dataframe.py

@@ -43,8 +43,7 @@ class PandasIlocRowsDataFrame:
             row_int_pos_list_json (str): A list containing row integer positions.
 
         Returns:
-            tuple: A tuple containing the value of the row in string. The string is
-                   a JSON string containing the serialized Pandas Series object.
+            tuple: A tuple containing the DataFrame.
         """
         row_int_pos_list = json.loads(row_int_pos_list_json)
         df2 = dataframe.iloc[row_int_pos_list]

modules/pandas_wrapper/pandas_join.py

@@ -42,7 +42,7 @@ class PandasJoin:
             join_method (str): The type of join to perform ("inner", "left", "right", "outer").
 
         Returns:
-            tuple: A tuple containing a JSON string of the merged DataFrame.
+            tuple: A tuple containing the merged DataFrame.
         """
         df_out = pd.merge(left_dataframe, right_dataframe, on=on_column_name, how=join_method)
         return (df_out,)

modules/pandas_wrapper/pandas_kurtosis.py

@@ -0,0 +1,52 @@
+from typing import Any, Dict
+import pandas as pd
+
+
+class PandasKurtosis:
+    """
+    Computes the unbiased kurtosis of the DataFrame.
+
+    This method returns the excess kurtosis rather than the raw kurtosis. 
+    Excess kurtosis is calculated by subtracting 3 from the raw kurtosis, 
+    which offsets it relative to the kurtosis of a normal distribution.
+
+    category: Summary statistics
+    """
+
+    @classmethod
+    def INPUT_TYPES(cls) -> Dict[str, Any]:
+        """
+        Defines the input types for the function.
+
+        Returns:
+            Dict[str, Any]: A dictionary specifying required input types.
+        """
+        return {
+            "required": {
+                "dataframe": ("DATAFRAME", {}),
+                "axis": (("index", "columns"),),
+            }
+        }
+
+    RETURN_TYPES: tuple = ("PDSERIES",)
+    FUNCTION: str = "f"
+    CATEGORY: str = "Data Analysis"
+
+    def f(self, dataframe: pd.DataFrame, axis: str) -> tuple:
+        """
+        Computes the unbiased kurtosis of the DataFrame.
+
+        Args:
+            dataframe (DataFrame): The DataFrame.
+            axis (str): Specify the direction to compute: Index (row label) or column label.
+
+        Returns:
+            tuple: A tuple containing the series.
+        """
+        if axis=="index":
+            series = dataframe.kurtosis(axis=0)
+        elif axis=="columns":
+            series = dataframe.kurtosis(axis=1)
+        else:
+            raise ValueError("Invalid axis. Only index or columns are supported.")
+        return (series,)

modules/pandas_wrapper/pandas_rename.py

@@ -45,7 +45,7 @@ class PandasRename:
             new_label (str): The new label.
 
         Returns:
-            tuple: A tuple containing a JSON string of the renamed DataFrame.
+            tuple: A tuple containing the DataFrame.
         """
         if axis=="index":
             df_out = dataframe.rename(index={current_label:new_label})

modules/pandas_wrapper/pandas_select_rows.py

@@ -37,7 +37,7 @@ class PandasSelectRows:
             condition (str): A string representing the condition to filter rows.
 
         Returns:
-            tuple: A tuple containing a JSON string of the filtered DataFrame.
+            tuple: A tuple containing the filtered DataFrame.
         """
         # Apply condition
         df2 = dataframe.query(condition)

modules/pandas_wrapper/pandas_skew.py

@@ -0,0 +1,48 @@
+from typing import Any, Dict
+import pandas as pd
+
+
+class PandasSkew:
+    """
+    Computes the unbiased skewness of the DataFrame.
+
+    category: Summary statistics
+    """
+
+    @classmethod
+    def INPUT_TYPES(cls) -> Dict[str, Any]:
+        """
+        Defines the input types for the function.
+
+        Returns:
+            Dict[str, Any]: A dictionary specifying required input types.
+        """
+        return {
+            "required": {
+                "dataframe": ("DATAFRAME", {}),
+                "axis": (("index", "columns"),),
+            }
+        }
+
+    RETURN_TYPES: tuple = ("PDSERIES",)
+    FUNCTION: str = "f"
+    CATEGORY: str = "Data Analysis"
+
+    def f(self, dataframe: pd.DataFrame, axis: str) -> tuple:
+        """
+        Computes the unbiased skewness of the DataFrame.
+
+        Args:
+            dataframe (DataFrame): The DataFrame.
+            axis (str): Specify the direction to compute: Index (row label) or column label.
+
+        Returns:
+            tuple: A tuple containing the series.
+        """
+        if axis=="index":
+            series = dataframe.skew(axis=0)
+        elif axis=="columns":
+            series = dataframe.skew(axis=1)
+        else:
+            raise ValueError("Invalid axis. Only index or columns are supported.")
+        return (series,)

modules/pandas_wrapper/pandas_sort.py

@@ -39,7 +39,7 @@ class PandasSort:
             ascending (bool): Whether to sort in ascending order.
 
         Returns:
-            tuple: A tuple containing a JSON string of the sorted DataFrame.
+            tuple: A tuple containing the sorted DataFrame.
         """
         df2 = dataframe.sort_values(by=column_name, ascending=ascending)
         return (df2,)

modules/pandas_wrapper/pandas_transpose.py

@@ -34,6 +34,6 @@ class PandasTranspose:
             dataframe (DataFrame): The DataFrame.
 
         Returns:
-            tuple: A tuple containing a JSON string of the transposed DataFrame.
+            tuple: A tuple containing the transposed DataFrame.
         """
         return (dataframe.transpose(),)