Last active
March 20, 2020 05:08
-
-
Save aniruddha27/1a37a944370e06c65e0fa77035ba9d5b to your computer and use it in GitHub Desktop.
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
Q1 = [] | |
Q3 = [] | |
Lower_bound = [] | |
Upper_bound = [] | |
Outliers = [] | |
for i in top_features: | |
# 25th and 75th percentiles | |
q1, q3 = np.percentile(train[i],25), np.percentile(train[i],75) | |
# Interquartile range | |
iqr = q3 - q1 | |
# Outlier cutoff | |
cut_off = 1.5*iqr | |
# Lower and Upper bounds | |
lower_bound = q1-cut_off | |
upper_bound = q3+cut_off | |
# save outlier indexes | |
outlier = [x for x in train.index if train.loc[x,i]<lower_bound or train.loc[x,i]>upper_bound] | |
# append values for DataFrame | |
Q1.append(q1) | |
Q3.append(q3) | |
Lower_bound.append(lower_bound) | |
Upper_bound.append(upper_bound) | |
Outliers.append(len(outlier)) | |
try: | |
train.drop(outlier,inplace=True,axis=0) | |
except: | |
continue | |
df_out = pd.DataFrame({'Column':top_features,'Q1':Q1,'Q3':Q3,'Lower bound':Lower_bound,'Upper_bound':Upper_bound,'No. of outliers':Outliers}) | |
df_out.sort_values(by='No. of outliers',ascending=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment