Boosting in ensemble methods

import pandas as pd

df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/'
                      'machine-learning-databases/wine/wine.data',
                      header=None)

df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
                   'Alcalinity of ash', 'Magnesium', 'Total phenols',
                   'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
                   'Color intensity', 'Hue', 'OD280/OD315 of diluted wines',
                   'Proline']

# if the Wine dataset is temporarily unavailable from the
# UCI machine learning repository, un-comment the following line
# of code to load the dataset from a local path:

# df_wine = pd.read_csv('wine.data', header=None)

# drop 1 class
df_wine = df_wine[df_wine['Class label'] != 1]

y = df_wine['Class label'].values
X = df_wine[['Alcohol', 'OD280/OD315 of diluted wines']].values

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split


le = LabelEncoder()
y = le.fit_transform(y)

X_train, X_test, y_train, y_test =\
            train_test_split(X, y, 
                             test_size=0.2, 
                             random_state=1,
                             stratify=y)

from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import AdaBoostClassifier

tree = DecisionTreeClassifier(criterion='entropy', 
                              max_depth=1,
                              random_state=1)

ada = AdaBoostClassifier(base_estimator=tree,
                         n_estimators=500, 
                         learning_rate=0.1,
                         random_state=1)

from sklearn.metrics import accuracy_score

tree = tree.fit(X_train, y_train)
y_train_pred = tree.predict(X_train)
y_test_pred = tree.predict(X_test)

tree_train = accuracy_score(y_train, y_train_pred)
tree_test = accuracy_score(y_test, y_test_pred)
print('Decision tree train/test accuracies %.3f/%.3f'
      % (tree_train, tree_test))

ada = ada.fit(X_train, y_train)
y_train_pred = ada.predict(X_train)
y_test_pred = ada.predict(X_test)

ada_train = accuracy_score(y_train, y_train_pred) 
ada_test = accuracy_score(y_test, y_test_pred) 
print('AdaBoost train/test accuracies %.3f/%.3f'
      % (ada_train, ada_test))

import numpy as np
import matplotlib.pyplot as plt

x_min, x_max = X_train[:, 0].min() - 1, X_train[:, 0].max() + 1
y_min, y_max = X_train[:, 1].min() - 1, X_train[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
                     np.arange(y_min, y_max, 0.1))

f, axarr = plt.subplots(1, 2, sharex='col', sharey='row', figsize=(8, 3))


for idx, clf, tt in zip([0, 1],
                        [tree, ada],
                        ['Decision tree', 'AdaBoost']):
    clf.fit(X_train, y_train)

    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)

    axarr[idx].contourf(xx, yy, Z, alpha=0.3)
    axarr[idx].scatter(X_train[y_train == 0, 0],
                       X_train[y_train == 0, 1],
                       c='blue', marker='^')
    axarr[idx].scatter(X_train[y_train == 1, 0],
                       X_train[y_train == 1, 1],
                       c='green', marker='o')
    axarr[idx].set_title(tt)

axarr[0].set_ylabel('Alcohol', fontsize=12)

plt.tight_layout()
plt.text(0, -0.2,
         s='OD280/OD315 of diluted wines',
         ha='center',
         va='center',
         fontsize=12,
         transform=axarr[1].transAxes)

#plt.savefig('images/07_11.png', dpi=300, bbox_inches='tight')
plt.show()