python实现集成学习与随机森林（机器学习）
前言
首先，导入几个常用模块，确保MatplotLib绘制图形，并准备一个保存图形的函数。还要检查是否安装了Python 3.5或更高版本(尽管Python 2。x可以工作，它已被弃用，因此建议使用Python 3代替)，以及Scikit-Learn≥0.20。
1.构建投票分类器
python
# Python ≥3.5
import sys
assert sys.version_info >= (3, 5)
# Scikit-Learn ≥0.20
import sklearn
assert sklearn.__version__ >= "0.20"
import numpy as np
import os
np.random.seed(42)
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
#解决制图时不显示中文的方法，先设置字体，字体可替换可见下方补充
plt.rcParams['font.sans-serif'] = 'SimHei'
#当字体支持中文后，必须设置负号，否则当数值中出现负号就无法显示
plt.rcParams['axes.unicode_minus']=False
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "ensembles"
IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID)
os.makedirs(IMAGES_PATH, exist_ok=True)
def save_fig(fig_id, tight_layout=True, fig_extension="png", resolution=300):
path = os.path.join(IMAGES_PATH, fig_id + "." + fig_extension)
print("保存图片：", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(path, format=fig_extension, dpi=resolution)
heads_proba = 0.51
coin_tosses = (np.random.rand(10000, 10) < heads_proba).astype(np.int32)
cumulative_heads_ratio = np.cumsum(coin_tosses, axis=0) / np.arange(1, 10001).reshape(-1, 1)
plt.figure(figsize=(8,3.5))
plt.plot(cumulative_heads_ratio)
plt.plot([0, 10000], [0.51, 0.51], "k--", linewidth=2, label="51%")
plt.plot([0, 10000], [0.5, 0.5], "k-", label="50%")
plt.xlabel("投掷硬币的次数")
plt.ylabel("正面比例")
plt.legend(loc="lower right")
plt.axis([0, 10000, 0.42, 0.58])
save_fig("tu1")
plt.show()
python
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_moons
#这里使用 moons 数据集
X, y = make_moons(n_samples=500, noise=0.30, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
python
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
log_clf = LogisticRegression(solver="lbfgs", random_state=42)
rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)
svm_clf = SVC(gamma="scale", random_state=42)
#这里使用硬投票
voting_clf = VotingClassifier(
estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],
voting='hard')
voting_clf.fit(X_train, y_train)
python
from sklearn.metrics import accuracy_score
for clf in (log_clf, rnd_clf, svm_clf, voting_clf):
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(clf.__class__.__name__, accuracy_score(y_test, y_pred))
下面构建软投票分类器：
python
log_clf = LogisticRegression(solver="lbfgs", random_state=42)
rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)
svm_clf = SVC(gamma="scale", probability=True, random_state=42)
voting_clf = VotingClassifier(
estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],
voting='soft')
voting_clf.fit(X_train, y_train)
python
from sklearn.metrics import accuracy_score
for clf in (log_clf, rnd_clf, svm_clf, voting_clf):
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(clf.__class__.__name__, accuracy_score(y_test, y_pred))
2.Bagging 与Pasting
在数据抽样时，如果是从数据中重复抽样（有放回），这种方法就叫bagging（bootstrap aggregating 的简称，引导聚合）。当抽样是数据不放回采样时，这个称为pasting。
实验过程中对比了BaggingClassifier和决策树的分类准确率
python
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
bag_clf = BaggingClassifier(
DecisionTreeClassifier(), n_estimators=500,
max_samples=100, bootstrap=True, random_state=42)
bag_clf.fit(X_train, y_train)
y_pred = bag_clf.predict(X_test)
#先看BaggingClassifier准确率
from sklearn.metrics import accuracy_score
print(accuracy_score(y_test, y_pred)) #0.904
#再看决策树准确率
tree_clf = DecisionTreeClassifier(random_state=42)
tree_clf.fit(X_train, y_train)
y_pred_tree = tree_clf.predict(X_test)
print(accuracy_score(y_test, y_pred_tree)) #0.856
python
from matplotlib.colors import ListedColormap
def plot_decision_boundary(clf, X, y, axes=[-1.5, 2.45, -1, 1.5], alpha=0.5, contour=True):
x1s = np.linspace(axes[0], axes[1], 100)
x2s = np.linspace(axes[2], axes[3], 100)
x1, x2 = np.meshgrid(x1s, x2s)
X_new = np.c_[x1.ravel(), x2.ravel()]
y_pred = clf.predict(X_new).reshape(x1.shape)
custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])
plt.contourf(x1, x2, y_pred, alpha=0.3, cmap=custom_cmap)
if contour:
custom_cmap2 = ListedColormap(['#7d7d58','#4c4c7f','#507d50'])
plt.contour(x1, x2, y_pred, cmap=custom_cmap2, alpha=0.8)
plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo", alpha=alpha)
plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs", alpha=alpha)
plt.axis(axes)
plt.xlabel(r"$x_1$", fontsize=18)
plt.ylabel(r"$x_2$", fontsize=18, rotation=0)
python
fig, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)
plt.sca(axes[0])
plot_decision_boundary(tree_clf, X, y)
plt.title("Decision Tree", fontsize=14)
plt.sca(axes[1])
plot_decision_boundary(bag_clf, X, y)
plt.title("Decision Trees with Bagging", fontsize=14)
plt.ylabel("")
save_fig("decision_tree_without_and_with_bagging_plot")
plt.show()
python
bag_clf = BaggingClassifier(
DecisionTreeClassifier(), n_estimators=500,
bootstrap=True, oob_score=True, random_state=40)
bag_clf.fit(X_train, y_train)
bag_clf.oob_score_ #0.8986666666666666
python
from sklearn.metrics import accuracy_score
y_pred = bag_clf.predict(X_test)
accuracy_score(y_test, y_pred) #0.9123.随机森林 - Random Forests
python
from sklearn.ensemble import RandomForestClassifier
rnd_clf = RandomForestClassifier(n_estimators=500, max_leaf_nodes=16, random_state=42)
rnd_clf.fit(X_train, y_train)
y_pred_rf = rnd_clf.predict(X_test)
bag_clf = BaggingClassifier(
DecisionTreeClassifier(max_features="sqrt", max_leaf_nodes=16),
n_estimators=500, random_state=42)
bag_clf.fit(X_train, y_train)
y_pred = bag_clf.predict(X_test)
np.sum(y_pred == y_pred_rf) / len(y_pred) #14.特征的重要性
python
from sklearn.datasets import load_iris
iris = load_iris()
rnd_clf = RandomForestClassifier(n_estimators=500, random_state=42)
rnd_clf.fit(iris["data"], iris["target"])
for name, score in zip(iris["feature_names"], rnd_clf.feature_importances_):
print(name, score)
python
plt.figure(figsize=(6, 4))
for i in range(15):
tree_clf = DecisionTreeClassifier(max_leaf_nodes=16, random_state=42 + i)
indices_with_replacement = np.random.randint(0, len(X_train), len(X_train))
tree_clf.fit(X_train[indices_with_replacement], y_train[indices_with_replacement])
plot_decision_boundary(tree_clf, X, y, axes=[-1.5, 2.45, -1, 1.5], alpha=0.02, contour=False)
plt.show()
5. AdaBoost
python
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
DecisionTreeClassifier(max_depth=1), n_estimators=200,
algorithm="SAMME.R", learning_rate=0.5, random_state=42)
ada_clf.fit(X_train, y_train)
python
plot_decision_boundary(ada_clf, X, y)
python
m = len(X_train)
fix, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)
for subplot, learning_rate in ((0, 1), (1, 0.5)):
sample_weights = np.ones(m) / m
plt.sca(axes[subplot])
for i in range(5):
svm_clf = SVC(kernel="rbf", C=0.2, gamma=0.6, random_state=42)
svm_clf.fit(X_train, y_train, sample_weight=sample_weights * m)
y_pred = svm_clf.predict(X_train)
r = sample_weights[y_pred != y_train].sum() / sample_weights.sum() # equation 7-1
alpha = learning_rate * np.log((1 - r) / r) # equation 7-2
sample_weights[y_pred != y_train] *= np.exp(alpha) # equation 7-3
sample_weights /= sample_weights.sum() # normalization step
plot_decision_boundary(svm_clf, X, y, alpha=0.2)
plt.title("learning_rate = {}".format(learning_rate), fontsize=16)
if subplot == 0:
plt.text(-0.75, -0.95, "1", fontsize=14)
plt.text(-1.05, -0.95, "2", fontsize=14)
plt.text(1.0, -0.95, "3", fontsize=14)
plt.text(-1.45, -0.5, "4", fontsize=14)
plt.text(1.36, -0.95, "5", fontsize=14)
else:
plt.ylabel("")
save_fig("boosting_plot")
plt.show()
6.Gradient(梯度) Boosting
python
np.random.seed(42)
X = np.random.rand(100, 1) - 0.5
y = 3*X[:, 0]**2 + 0.05 * np.random.randn(100)
from sklearn.tree import DecisionTreeRegressor
tree_reg1 = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg1.fit(X, y)
python
y2 = y - tree_reg1.predict(X)
tree_reg2 = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg2.fit(X, y2)
python
y3 = y2 - tree_reg2.predict(X)
tree_reg3 = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg3.fit(X, y3)
python
X_new = np.array([[0.8]])
y_pred = sum(tree.predict(X_new) for tree in (tree_reg1, tree_reg2, tree_reg3))
python
def plot_predictions(regressors, X, y, axes, label=None, style="r-", data_style="b.", data_label=None):
x1 = np.linspace(axes[0], axes[1], 500)
y_pred = sum(regressor.predict(x1.reshape(-1, 1)) for regressor in regressors)
plt.plot(X[:, 0], y, data_style, label=data_label)
plt.plot(x1, y_pred, style, linewidth=2, label=label)
if label or data_label:
plt.legend(loc="upper center", fontsize=16)
plt.axis(axes)
plt.figure(figsize=(11,11))
plt.subplot(321)
plot_predictions([tree_reg1], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h_1(x_1)$", style="g-", data_label="Training set")
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.title("Residuals and tree predictions", fontsize=16)
plt.subplot(322)
plot_predictions([tree_reg1], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h(x_1) = h_1(x_1)$", data_label="Training set")
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.title("Ensemble predictions", fontsize=16)
plt.subplot(323)
plot_predictions([tree_reg2], X, y2, axes=[-0.5, 0.5, -0.5, 0.5], label="$h_2(x_1)$", style="g-", data_style="k+", data_label="Residuals")
plt.ylabel("$y - h_1(x_1)$", fontsize=16)
plt.subplot(324)
plot_predictions([tree_reg1, tree_reg2], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h(x_1) = h_1(x_1) + h_2(x_1)$")
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.subplot(325)
plot_predictions([tree_reg3], X, y3, axes=[-0.5, 0.5, -0.5, 0.5], label="$h_3(x_1)$", style="g-", data_style="k+")
plt.ylabel("$y - h_1(x_1) - h_2(x_1)$", fontsize=16)
plt.xlabel("$x_1$", fontsize=16)
plt.subplot(326)
plot_predictions([tree_reg1, tree_reg2, tree_reg3], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h(x_1) = h_1(x_1) + h_2(x_1) + h_3(x_1)$")
plt.xlabel("$x_1$", fontsize=16)
plt.ylabel("$y$", fontsize=16, rotation=0)
save_fig("gradient_boosting_plot")
plt.show()
这里尝试梯度增强回归器
python
from sklearn.ensemble import GradientBoostingRegressor
gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=3, learning_rate=1.0, random_state=42)
gbrt.fit(X, y)
python
gbrt_slow = GradientBoostingRegressor(max_depth=2, n_estimators=200, learning_rate=0.1, random_state=42)
gbrt_slow.fit(X, y)
python
fix, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)
plt.sca(axes[0])
plot_predictions([gbrt], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="Ensemble predictions")
plt.title("learning_rate={}, n_estimators={}".format(gbrt.learning_rate, gbrt.n_estimators), fontsize=14)
plt.xlabel("$x_1$", fontsize=16)
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.sca(axes[1])
plot_predictions([gbrt_slow], X, y, axes=[-0.5, 0.5, -0.1, 0.8])
plt.title("learning_rate={}, n_estimators={}".format(gbrt_slow.learning_rate, gbrt_slow.n_estimators), fontsize=14)
plt.xlabel("$x_1$", fontsize=16)
save_fig("gbrt_learning_rate_plot")
plt.show()
提前停止（Early stopping）梯度增强（Gradient Boosting）:
python
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
X_train, X_val, y_train, y_val = train_test_split(X, y, random_state=49)
gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=120, random_state=42)
gbrt.fit(X_train, y_train)
errors = [mean_squared_error(y_val, y_pred)
for y_pred in gbrt.staged_predict(X_val)]
bst_n_estimators = np.argmin(errors) + 1
gbrt_best = GradientBoostingRegressor(max_depth=2, n_estimators=bst_n_estimators, random_state=42)
gbrt_best.fit(X_train, y_train)
python
min_error = np.min(errors)
plt.figure(figsize=(10, 4))
plt.subplot(121)
plt.plot(np.arange(1, len(errors) + 1), errors, "b.-")
plt.plot([bst_n_estimators, bst_n_estimators], [0, min_error], "k--")
plt.plot([0, 120], [min_error, min_error], "k--")
plt.plot(bst_n_estimators, min_error, "ko")
plt.text(bst_n_estimators, min_error*1.2, "Minimum", ha="center", fontsize=14)
plt.axis([0, 120, 0, 0.01])
plt.xlabel("Number of trees")
plt.ylabel("Error", fontsize=16)
plt.title("Validation error", fontsize=14)
plt.subplot(122)
plot_predictions([gbrt_best], X, y, axes=[-0.5, 0.5, -0.1, 0.8])
plt.title("Best model (%d trees)" % bst_n_estimators, fontsize=14)
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.xlabel("$x_1$", fontsize=16)
save_fig("early_stopping_gbrt_plot")
plt.show()
python
gbrt = GradientBoostingRegressor(max_depth=2, warm_start=True, random_state=42)
min_val_error = float("inf")
error_going_up = 0
for n_estimators in range(1, 120):
gbrt.n_estimators = n_estimators
gbrt.fit(X_train, y_train)
y_pred = gbrt.predict(X_val)
val_error = mean_squared_error(y_val, y_pred)
if val_error < min_val_error:
min_val_error = val_error
error_going_up = 0
else:
error_going_up += 1
if error_going_up == 5:
break # early stopping
print("Minimum validation MSE:", min_val_error) #Minimum validation MSE: 0.002712853325235463