Practical demonstration of using Z-scores to drop outlier rows

Zscore_outliers.py

# Import Z-score function
from scipy.stats import zscore

# Define the SD threshold
thresh = 3

# List of all rows as `True` or `False` depending on if they have a value above the threshold or not
SD_outliers = X_train.apply(lambda x: np.abs(zscore(x, nan_policy = 'omit')) > thresh).any(axis=1)

# Drop (inplace) rows that have True in SD_Norm
X_train.drop(X_train.index[SD_outliers], inplace = True)