-
-
Save stanlee321/3fb79e3899224a9019ad030e33c06d70 to your computer and use it in GitHub Desktop.
Remove outliers in pandas
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 | |
from pandas.api.types import is_numeric_dtype | |
np.random.seed(42) | |
age = np.random.randint(20,100,50) | |
name = ['name'+str(i) for i in range(50)] | |
address = ['address'+str(i) for i in range(50)] | |
df = pd.DataFrame(data={'age':age, 'name':name, 'address':address}) | |
def remove_outlier(df): | |
low = .05 | |
high = .95 | |
quant_df = df.quantile([low, high]) | |
for name in list(df.columns): | |
if is_numeric_dtype(df[name]): | |
df = df[(df[name] > quant_df.loc[low, name]) & (df[name] < quant_df.loc[high, name])] | |
return df | |
remove_outlier(df).head() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment