Outliers removal

Outliers removal pandas

df = pd.DataFrame(np.random.randn(100, 3))

from scipy import stats
df[(np.abs(stats.zscore(df)) < 3).all(axis=1)]

Source: stackoverflow.com

Outlier removal

q1 = df['column'].quantile(0.25)
q3 = df['column'].quantile(0.75)
iqr = q3 - q1

df.loc[df['column'] > (q3 + 1.5 * iqr) | df['column'] < (q1 - 1.5 * iqr), 'column'] = df['column'].mean()

Outliers removal

#Removing outliers first then skewness
from scipy.stats import zscore
z=abs(zscore(df))
print(z.shape)
df=df[(z<3).all(axis=1)]
df.shape

Similar codes

1 vote193 views1 answer
Show number as 3 digit python
Python
8 votes179 views2 answers
Determinant of a matrix in python
Python
2 votes191 views2 answers
Check multiple keys in python dict
Python
0 vote182 views1 answer
Install ansible with pip
Python
0 vote160 views1 answer
How to use cv2.COLOR_BGR2GRAY
Python
1 vote193 views4 answers
How to do a print statement in python
Python
0 vote173 views1 answer
The Bytearray Type
Python
0 vote164 views1 answer
How to search over a notebook in python
Python
6 votes170 views2 answers
Iterable meaning
Python
21 votes188 views6 answers
Pandas convert column to datetime
Python