Skewed - data analysis and transformations

    Distribution on the basis of skewness value:
    Skewness = 0: Then normally distributed.
    Skewness > 0: Then more weight in the left tail of the distribution; right skewed distribution
    Skewness < 0: Then more weight in the right tail of the distribution; left skewed distribution

# skip the na values
# over the column axis
df.skew(axis = 1, skipna = True)

# skip the na values
# find skewness in each row
df.skew(axis = 0, skipna = True)

OR

from scipy.stats import skew

# Creating a dataset
dataset = [88, 85, 82, 97, 67, 77, 74, 86,
           81, 95, 77, 88, 85, 76, 81]
# Calculate the skewness
print(skew(dataset, axis=0, bias=False))

#############################################
 Power Transform
>>> import numpy as np
>>> from sklearn.preprocessing import PowerTransformer
>>> pt = PowerTransformer()
>>> data = [[1, 2], [3, 2], [4, 5]]
>>> print(pt.fit(data))
PowerTransformer()
>>> print(pt.lambdas_)
[ 1.386... -3.100...]
>>> print(pt.transform(data))
[[-1.316... -0.707...]
 [ 0.209... -0.707...]
 [ 1.106...  1.414...]]
##############################################
QuantileTransformer
>>> import numpy as np
>>> from sklearn.preprocessing import QuantileTransformer
>>> rng = np.random.RandomState(0)
>>> X = np.sort(rng.normal(loc=0.5, scale=0.25, size=(25, 1)), axis=0)
>>> qt = QuantileTransformer(n_quantiles=10, random_state=0)
>>> qt.fit_transform(X)
array([...])