Supprimer les valeurs aberrantes dans DataFrame
# Solution is based on this article:
# http://www.itl.nist.gov/div898/handbook/prc/section1/prc16.htm
import pandas as pd
import numpy as np
def remove_outliers_from_series(series):
q1 = series.quantile(0.25)
q3 = series.quantile(0.75)
intraquartile_range = q3 - q1
fence_low = q1 - 1.5 * intraquartile_range
fence_high = q3 + 1.5 * intraquartile_range
return series[(series > fence_low) & (series < fence_high)]
def remove_outliers_from_dataframe(self, df, col):
q1 = df[col].quantile(0.25)
q3 = df[col].quantile(0.75)
intraquartile_range = q3 - q1
fence_low = q1 - 1.5 * intraquartile_range
fence_high = q3 + 1.5 * intraquartile_range
return df.loc[(df[col] > fence_low) & (df[col] < fence_high)]
def remove_outliers_from_np_array(self, arr):
q1 = np.percentile(arr, 25)
q3 = np.percentile(arr, 75)
intraquartile_range = q3 - q1
fence_low = q1 - 1.5 * intraquartile_range
fence_high = q3 + 1.5 * intraquartile_range
return arr[(arr > fence_low) & (arr < fence_high)]
def remove_outliers_from_python_list(self, _list):
arr = np.array(_list)
return list(remove_outliers_from_np_array(arr))
def remove_outliers(*args, **kwargs):
if isinstance(args[0], pd.DataFrame):
return remove_outliers_from_dataframe(*args, **kwargs)
elif isinstance(args[0], pd.Series):
return remove_outliers_from_series(*args, **kwargs)
elif isinstance(args[0], np.ndarray):
return remove_outliers_from_np_array(*args, **kwargs)
elif isinstance(args[0], list):
return remove_outliers_from_python_list(*args, **kwargs)
else:
raise TypeError(f'{type(args[0])} is not supported.')
Wrong Whale
