import pandas as pd
import numpy as np
from sklearn.datasets import load_boston
boston = load_boston()

boston_features = pd.DataFrame(boston.data, columns = boston.feature_names)
boston_features = boston_features.drop(["NOX","ZN"],axis=1)

# first, create bins for based on the values observed. 3 values will result in 2 bins
bins = [0,6,  24]
bins_rad = pd.cut(boston_features['RAD'], bins)
bins_rad = bins_rad.cat.as_unordered()

# first, create bins for based on the values observed. 4 values will result in 3 bins
bins = [0, 270, 360, 712]
bins_tax = pd.cut(boston_features['TAX'], bins)
bins_tax = bins_tax.cat.as_unordered()

tax_dummy = pd.get_dummies(bins_tax, prefix="TAX")
rad_dummy = pd.get_dummies(bins_rad, prefix="RAD")
boston_features = boston_features.drop(["RAD","TAX"], axis=1)
boston_features = pd.concat([boston_features, rad_dummy, tax_dummy], axis=1)

age = boston_features["AGE"]
b = boston_features["B"]
logcrim = np.log(boston_features["CRIM"])
logdis = np.log(boston_features["DIS"])
logindus = np.log(boston_features["INDUS"])
loglstat = np.log(boston_features["LSTAT"])
logptratio = np.log(boston_features["PTRATIO"])

# minmax scaling
boston_features["B"] = (b-min(b))/(max(b)-min(b))
boston_features["CRIM"] = (logcrim-min(logcrim))/(max(logcrim)-min(logcrim))
boston_features["DIS"] = (logdis-min(logdis))/(max(logdis)-min(logdis))

#standardization
boston_features["AGE"] = (age-np.mean(age))/np.sqrt(np.var(age))
boston_features["INDUS"] = (logindus-np.mean(logindus))/np.sqrt(np.var(logindus))
boston_features["LSTAT"] = (loglstat-np.mean(loglstat))/np.sqrt(np.var(loglstat))
boston_features["PTRATIO"] = (logptratio-np.mean(logptratio))/(np.sqrt(np.var(logptratio)))

boston_features.head()