Titanic example revisited – all together

In this section, we are going to put all the bits and pieces of feature engineering and dimensionality reduction together:

import re
import numpy as np
import pandas as pd
import random as rd
from sklearn import preprocessing
from sklearn.cluster import KMeans
from sklearn.ensemble import RandomForestRegressor
from sklearn.decomposition import PCA

# Print options
np.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 features
def process_embarked():
    global df_titanic_data

    # replacing the missing values with the most common value in the variable
    df_titanic_data.Embarked[df.Embarked.isnull()] = df_titanic_data.Embarked.dropna().mode().values

    # converting the values into numbers
  ...