Library import typo p.60

[FutureGoose]

"import scikitplot" is a typo, it should be "import scikit-plot"

Creating an XGBoost Model

%matplotlib inline

import dtreeviz
from feature_engine import encoding, imputation
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import base, compose, datasets, ensemble, \
    metrics, model_selection, pipeline, preprocessing, tree
import scikitplot
import xgboost as xgb
import yellowbrick.model_selection as ms
from yellowbrick import classifier

import urllib
import zipfile

import xg_helpers as xhelp

url = 'https://github.com/mattharrison/datasets/raw/master/data/'\
    'kaggle-survey-2018.zip'
fname = 'kaggle-survey-2018.zip'
member_name = 'multipleChoiceResponses.csv'

raw = xhelp.extract_zip(url, fname, member_name)

## Create raw X and raw y
kag_X, kag_y = xhelp.get_rawX_y(raw, 'Q6')

## Split data    
kag_X_train, kag_X_test, kag_y_train, kag_y_test = \
    model_selection.train_test_split(
        kag_X, kag_y, test_size=.3, random_state=42, stratify=kag_y)    

## Transform X with pipeline
X_train = xhelp.kag_pl.fit_transform(kag_X_train)
X_test = xhelp.kag_pl.transform(kag_X_test)

## Transform y with label encoder
label_encoder = preprocessing.LabelEncoder()
label_encoder.fit(kag_y_train)
y_train = label_encoder.transform(kag_y_train)
y_test = label_encoder.transform(kag_y_test)

# Combined Data for cross validation/etc
X = pd.concat([X_train, X_test], axis='index')
y = pd.Series([*y_train, *y_test], index=X.index)