Added Pandas Drop Duplicates node. Fixed Pandas Drop NA node to output a DataFrame instead of legacy JSON string.

This commit is contained in:
HowToSD
2025-02-20 13:28:37 -08:00
parent 472565908b
commit fff4b58abb
7 changed files with 264 additions and 29 deletions
@@ -0,0 +1,39 @@
from typing import Any, Dict
import pandas as pd
class PandasDropDuplicates:
"""
Drops duplicate rows from a Pandas DataFrame.
category: Data cleansing
"""
@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", {})
}
}
RETURN_TYPES: tuple = ("DATAFRAME",)
FUNCTION: str = "f"
CATEGORY: str = "Data Analysis"
def f(self, dataframe: pd.DataFrame) -> tuple:
"""
Drops duplicate rows from a Pandas DataFrame.
Args:
dataframe (DataFrame): The DataFrame.
Returns:
tuple: A tuple containing the DataFrame.
"""
return (dataframe.drop_duplicates(),)
+1 -1
View File
@@ -37,4 +37,4 @@ class PandasDropNA:
Returns:
tuple: A tuple containing the DataFrame.
"""
return (dataframe.dropna().to_json(),)
return (dataframe.dropna(),)