COMP7404 Machine Learing——Decision Tree & Random Forests

Decision Tree

一个很大的不同点是决策树模型在预处理阶段不需要标准化。

因为决策树不需要考虑特征的值，只需要考虑划分界限

我们都知道决策树有ID3, C4.5, CART等，但是在sklearn.tree的DecisionTreeClassifier是使用的CART的分类树，但是其criterion是可以改的，criterion=gini那就是正常的CART，criterion=entropy就有点像ID3,C4.5了

而CART的回归树就是DecisionTreeRegressor

import numpy as np
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y)

from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='gini', max_depth=7, random_state=1)
tree.fit(X_train, y_train)
y_pred = tree.predict(X_train)
print('Misclassified training samples:',(y_train!=y_pred).sum())
 
y_pred = tree.predict(X_test)
print('Misclassified samples:', (y_test != y_pred).sum())
 
from sklearn.metrics import accuracy_score
print('Accuracy: %.3f' % accuracy_score(y_test, y_pred))


#下面是可视化
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])
    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=colors[idx], marker=markers[idx], 
                    label=cl, edgecolor='black')
    if test_idx:
        X_test, y_test = X[test_idx, :], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1,
                    marker='o', s=100, label='test set')
 
 
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='gini', max_depth=7, random_state=1)
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined, y_combined, 
                      classifier=tree, test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()

import pandas as pd
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

iris = datasets.load_iris()

X = iris.data[:,[2,3]]
y = iris.target

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3, random_state=1, stratify=y)

tree = DecisionTreeClassifier(criterion='gini', max_depth=7, random_state=1)
tree.fit(X_train, y_train)
y_pred = tree.predict(X_train)

print('misclassified training samples: ', (y_pred!=y_train).sum())
y_pred = tree.predict(X_test)
print('misclassified testing samples: ', (y_pred!=y_test).sum())

print('Accuracy: %0.3f' % accuracy_score(y_pred,y_test))

 

 

Visualizing Decision Tree

import numpy as np
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y)
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])
    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=colors[idx], marker=markers[idx], 
                    label=cl, edgecolor='black')
    if test_idx:
        X_test, y_test = X[test_idx, :], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1,
                    marker='o', s=100, label='test set')


from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='gini', max_depth=7, random_state=1)
tree.fit(X_train, y_train)

from pydotplus import graph_from_dot_data
from sklearn.tree import export_graphviz
dot_data = export_graphviz(tree, filled=True, rounded=True, 
                           class_names=['Setosa', 
                                        'Versicolor',
                                        'Virginica'],
                           feature_names=['petal length', 
                                          'petal width'],
                           out_file=None)
graph = graph_from_dot_data(dot_data) 
graph.write_png('tree.png')

 

random forests

Combining multiple decision trees via random forests

同样，既有RandomForestClassifier又有RandomForestRegression

import numpy as np
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y)

from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(criterion='gini', n_estimators=25, 
                                random_state=1, n_jobs=2)
forest.fit(X_train, y_train)
y_pred = forest.predict(X_train)
print('Misclassified training samples:',(y_train!=y_pred).sum())
 
y_pred = forest.predict(X_test)
print('Misclassified samples:', (y_test != y_pred).sum())
 
from sklearn.metrics import accuracy_score
print('Accuracy: %.3f' % accuracy_score(y_test, y_pred))


from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])
    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=colors[idx], marker=markers[idx], 
                    label=cl, edgecolor='black')
    if test_idx:
        X_test, y_test = X[test_idx, :], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1,
                    marker='o', s=100, label='test set')


X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))

from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(criterion='gini', n_estimators=25, 
                                random_state=1, n_jobs=2)
forest.fit(X_train, y_train)
plot_decision_regions(X_combined, y_combined, 
                      classifier=forest, test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()

import pandas as pd
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

iris = datasets.load_iris()

X = iris.data[:,[2,3]]
y = iris.target

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3, random_state=1, stratify=y)

forest = RandomForestClassifier(criterion='gini', n_estimators=25,
                                random_state=1, n_jobs=2)
forest.fit(X_train, y_train)
y_pred = forest.predict(X_train)

print('misclassified training samples: ', (y_pred!=y_train).sum())
y_pred = forest.predict(X_test)
print('misclassified testing samples: ', (y_pred!=y_test).sum())

print('Accuracy: %0.3f' % accuracy_score(y_pred,y_test))