outliers.py

import pandas as pd

def showoutliers(df, column_name = ""):
        iqr = df[column_name].quantile(.75) - df[column_name].quantile(.25)
        lowerbound = (df[column_name].quantile(.25)) - iqr * 1.5
        upperbound = (df[column_name].quantile(.75)) + iqr * 1.5
        lowerbound_outliers = df[df[column_name] < lowerbound]
        higherbound_outliers = df[df[column_name] > upperbound]
        outliers = pd.concat([lowerbound_outliers,higherbound_outliers])
        return outliers


def countoutliers(df, column_name = ""):
        iqr = df[column_name].quantile(.75) - df[column_name].quantile(.25)
        lowerbound = (df[column_name].quantile(.25)) - iqr * 1.5
        upperbound = (df[column_name].quantile(.75)) + iqr * 1.5
        lowerbound_outliers = df[df[column_name] < lowerbound]
        higherbound_outliers = df[df[column_name] > upperbound]
        outliers = pd.concat([lowerbound_outliers,higherbound_outliers])
        return len(outliers)


def removeoutliers(df, column_name = ""):
        iqr = df[column_name].quantile(.75) - df[column_name].quantile(.25)
        lowerbound = (df[column_name].quantile(.25)) - iqr * 1.5
        upperbound = (df[column_name].quantile(.75)) + iqr * 1.5
        lowerbound_outliers = df[df[column_name] < lowerbound]
        higherbound_outliers = df[df[column_name] > upperbound]
        outliers = pd.concat([lowerbound_outliers,higherbound_outliers])
        normal = df[~ df.index.isin(outliers.index)]
        return normal