outlierRemove.py

def outlierRemove(data,function):
    '''
    This function is to remove the outliers of the data. Assisted by ChatGPT.
    Interquartile Range (IQR) Method:
    The Interquartile Range is the range between the first quartile (25th percentile) and
    the third quartile (75th percentile) of a dataset. Outliers can be identified by values
    that fall below the first quartile minus a threshold or above the third quartile plus the threshold.
    Typically, a threshold of 1.5 times the IQR is used.

    Input : data = output returning from functions that calculate flow properties
            function = flow properties that we want to calculate
    '''
    import pandas as pd
    import numpy as np

    data = data

    if function == 'Rxy':
        function = 'uv_prime'

    if function == 'Rxx':
        function = 'uu_prime'

    if function == 'Ryy':
        function = 'vv_prime'

    # Calculate the first and third quartiles (25th and 75th percentiles)
    q1 = data[0].reset_index()[function].quantile(0.25)
    q3 = data[0].reset_index()[function].quantile(0.75)
    # Calculate the IQR (Interquartile Range)
    iqr = q3 - q1
    # Set an IQR threshold (e.g., 1.5 times the IQR)
    iqr_threshold = 1.5

    # Remove outliers by filtering based on the IQR
    data_without_outliers = data[0].reset_index()[(data[0].reset_index()[function] >= q1 - iqr_threshold * iqr) & (data[0].reset_index()[function] <= q3 + iqr_threshold * iqr)]
    return data_without_outliers