In this section, we are going to put all the bits and pieces of feature engineering and dimensionality reduction together:
import reimport numpy as npimport pandas as pdimport random as rdfrom sklearn import preprocessingfrom sklearn.cluster import KMeansfrom sklearn.ensemble import RandomForestRegressorfrom sklearn.decomposition import PCA# Print optionsnp.set_printoptions(precision=4, threshold=10000, linewidth=160, edgeitems=999, suppress=True)pd.set_option('display.max_columns', None)pd.set_option('display.max_rows', None)pd.set_option('display.width', 160)pd.set_option('expand_frame_repr', False)pd.set_option('precision', 4)# constructing binary featuresdef process_embarked(): global df_titanic_data ...
