Created
February 3, 2017 17:32
-
-
Save usmcamp0811/868738a2eba9dbb38d43eb27607b2085 to your computer and use it in GitHub Desktop.
A Function to check if a field has any outliers using IQR
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
def is_outlier(value, p25, p75): | |
"""Check if value is an outlier | |
""" | |
lower = p25 - 1.5 * (p75 - p25) | |
upper = p75 + 1.5 * (p75 - p25) | |
return value <= lower or value >= upper | |
def get_indices_of_outliers(values): | |
"""Get outlier indices (if any) | |
""" | |
p25 = values.quantile(.25) | |
p75 = values.quantile(.75) | |
lower = p25 - 1.5 * (p75 - p25) | |
upper = p75 + 1.5 * (p75 - p25) | |
indices_of_outliers = [] | |
for ind, value in enumerate(values): | |
if is_outlier(value, p25, p75): | |
indices_of_outliers.append(ind) | |
return indices_of_outliers | |
def IQR_outliers(dataframe, field): | |
indices_of_outliers = get_indices_of_outliers(df[field]) | |
outlier = dataframe[field][indices_of_outliers] | |
dataframe.loc[dataframe[field].index.isin(outlier.index) == True, | |
field + '_outlier'] = 'Outlier' | |
dataframe.loc[dataframe[field].index.isin(outlier.index) == False, | |
field + '_outlier'] = 'Not Outlier' | |
return dataframe | |
if __name__ == "__main__": | |
df = pd.DataFrame(np.random.uniform(0, 100, size=(100, 3))) | |
df.columns = ['A', 'B', 'C'] | |
print(IQR_outliers(df, 'C')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment