tasks/data/dataAugmentation.py

import pandas as pd


def augmentDataWithVectorSpaceAlgorithm(data: pd.DataFrame) -> pd.DataFrame:
    """
    Augment the Data
    =================
    Parameters:
    -----------
        data:
            description: Data to augment
            type: pd.DataFrame
    -----------
    Returns:
    --------
        data:
            description: Augmented data
            type: pd.DataFrame
    --------------------------------------------------------------------------------------------
    Working:
    --------
        - Create a DataFrame from data
        - Remove a symptom or cause from the new DataFrame
        - Check if the resulting row is present in the original data
        - If not present, add the resulting row to the new DataFrame
        - Repeat steps 1-3 for all symptoms and causes
        - Remove the rows with sum = 0
        - Remove the same rows from the new DataFrame
        - Add the new DataFrame to the original data
        - Return the Resulting DataFrame
    --------------------------------------------------------------------------------------------
    """
    
    # Get the number of columns with symptoms_ prefix
    numberOfSymptoms = len([col for col in data.columns if col.startswith('symptoms_')])
    
    symptoms = data.columns[1:numberOfSymptoms]
    causes = data.columns[numberOfSymptoms:]   
    df = data
    
    for index, row in data.iterrows():
        for symptom in symptoms:
            if row[symptom] == 1: # type: ignore
                row[symptom] = 0
                df = df.append(row, ignore_index=True) # type: ignore
                row[symptom] = 1
                df.append(row, ignore_index=True)
        
        for cause in causes:
            if row[cause] == 1:   # type: ignore
                row[cause] = 0
                df = df.append(row, ignore_index=True) # type: ignore
                row[cause] = 1
                df.append(row, ignore_index=True)
    
    
    print(f"data before drop_duplicates: {df}")
    
    df = df[(df.sum(axis=1, numeric_only=True) != 0)]
    data = data.append(df, ignore_index=True) # type: ignore
    data = data.drop_duplicates(subset=df.columns.difference(['disease']), keep=False)
    data.reset_index(drop=True, inplace=True)
    
    print(f"final data: {data}")
    
    return data