AI技术百科
payititi-AI助手
2021-12-06 16:48:29
随机森林的Python实现
利用Python的两个模块,分别为pandas和scikit-learn来实现随机森林。
from sklearn.datasets import load_iris from sklearn.ensemble import RandomForestClassifier import pandas as pd import numpy as np iris = load_iris() df = pd.Dataframe(iris.data, columns=iris.feature_names) df['is_train'] = np.random.uniform(0, 1, len(df)) <= .75 df['species'] = pd.Factor(iris.target, iris.target_names) df.head() train, test = df[df['is_train']==True], df[df['is_train']==False] features = df.columns[:4] clf = RandomForestClassifier(n_jobs=2) y, _ = pd.factorize(train['species']) clf.fit(train[features], y) preds = iris.target_names[clf.predict(test[features])] pd.crosstab(test['species'], preds, rownames=['actual'], colnames=['preds'])
分类结果:
与其他机器学习分类算法进行对比:
import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap from sklearn.cross_validation import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.datasets import make_moons, make_circles, make_classification from sklearn.neighbors import KNeighborsClassifier from sklearn.svm import SVC from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier from sklearn.naive_bayes import GaussianNB from sklearn.lda import LDA from sklearn.qda import QDA h = .02 # step size in the mesh names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree", "Random Forest", "AdaBoost", "Naive Bayes", "LDA", "QDA"] classifiers = [ KNeighborsClassifier(3), SVC(kernel="linear", C=0.025), SVC(gamma=2, C=1), DecisionTreeClassifier(max_depth=5), RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1), AdaBoostClassifier(), GaussianNB(), LDA(), QDA()] X, y = make_classification(n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1) rng = np.random.RandomState(2) X += 2 * rng.uniform(size=X.shape) linearly_separable = (X, y) datasets = [make_moons(noise=0.3, random_state=0), make_circles(noise=0.2, factor=0.5, random_state=1), linearly_separable ] figure = plt.figure(figsize=(27, 9)) i = 1 # iterate over datasets for ds in datasets: # preprocess dataset, split into training and test part X, y = ds X = StandardScaler().fit_transform(X) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4) x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5 y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5 xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h)) # just plot the dataset first cm = plt.cm.RdBu cm_bright = ListedColormap(['#FF0000', '#0000FF']) ax = plt.subplot(len(datasets), len(classifiers) + 1, i) # Plot the training points ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) # and testing points ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6) ax.set_xlim(xx.min(), xx.max()) ax.set_ylim(yy.min(), yy.max()) ax.set_xticks(()) ax.set_yticks(()) i += 1 # iterate over classifiers for name, clf in zip(names, classifiers): ax = plt.subplot(len(datasets), len(classifiers) + 1, i) clf.fit(X_train, y_train) score = clf.score(X_test, y_test) # Plot the decision boundary. For that, we will assign a color to each # point in the mesh [x_min, m_max]x[y_min, y_max]. if hasattr(clf, "decision_function"): Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()]) else: Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1] # Put the result into a color plot Z = Z.reshape(xx.shape) ax.contourf(xx, yy, Z, cmap=cm, alpha=.8) # Plot also the training points ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) # and testing points ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6) ax.set_xlim(xx.min(), xx.max()) ax.set_ylim(yy.min(), yy.max()) ax.set_xticks(()) ax.set_yticks(()) ax.set_title(name) ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'), size=15, horizontalalignment='right') i += 1 figure.subplots_adjust(left=.02, right=.98) plt.show()
这里随机生成了三个样本集,分割面近似为月形、圆形和线形的。我们可以重点对比一下决策树和随机森林对样本空间的分割:
1)从准确率上可以看出,随机森林在这三个测试集上都要优于单棵决策树,90%>85%,82%>80%,95%=95%;
2)从特征空间上直观地可以看出,随机森林比决策树拥有更强的分割能力(非线性拟合能力)。
更多有关随机森林的代码:
2)OpenCV版本
3)Matlab版本
4)R版本
6
条内容
随机森林(Random Forest,简称RF)拥有广泛的应用前景,从市场营销到医疗保健保险,既可以用来做市场营销模拟的建模,统计客户来源,保留和流失,也可用来预测疾病的风险和病患者的易感性。最初,我是在参加校外竞赛时接触到随机森林算法的。最近几年的国内外大赛,包括2013年百度校园电影推荐系统大赛、2014年阿里巴巴天池大数据竞赛以及Kaggle数据科学竞赛,参赛者对随机森林的使用占有相当高的比例。此外,据我的个人了解来看,一大部分成功进入答辩的队伍也都选择了Random Forest 或者 GBDT 算法。所以可以看出,Random Forest在准确率方面还是相当有优势的。