全文参考 1：http://scikit-learn.org/stable/auto_examples/model_selection/grid_search_digits.html#parameter-estimation-using-grid-search-with-cross-validation
全文参考 2：http://scikit-learn.org/stable/modules/model_evaluation.html#the-scoring-parameter-defining-model-evaluation-rules
全文参考 3：http://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html#sklearn.metrics.roc_auc_score
全文参考 4：http://scikit-learn.org/stable/auto_examples/model_selection/plot_roc.html#sphx-glr-auto-examples-model-selection-plot-roc-py
实验重点：随机森林(RandomForest) + 5折交叉验证(Cross-Validation) + 网格参数寻优(GridSearchCV) + 二分类问题中ROC曲线的绘制。
由于原始数据本身质量很好，且正负样本基本均衡，没有做数据预处理工作。
import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.metrics import roc_curve from sklearn.metrics import roc_auc_score from sklearn.metrics import classification_report from sklearn.model_selection import GridSearchCV from sklearn.ensemble import RandomForestClassifier #导入数据，来源于：http://mldata.org/repository/tags/data/IDA_Benchmark_Repository/，见上图 dataset = pd.read_csv('image_data.csv', header=None, encoding='utf-8') dataset_positive = dataset[dataset[0] == 1.0] dataset_negative = dataset[dataset[0] == -1.0] #训练集和测试集按照7:3分割，分割时兼顾正负样本所占比例 #其中训练集基于5折交叉验证做网格搜索找出最优参数，应用于测试集以评价算法性能 train_dataset = pd.concat([dataset_positive[0:832], dataset_negative[0:628]]) train_recon = train_dataset.sort_index(axis=0, ascending=True) test_dataset = pd.concat([dataset_positive[832:1188], dataset_negative[628:898]]) test_recon = test_dataset.sort_index(axis=0, ascending=True) y_train = np.array(train_recon[0]) X_train = np.array(train_recon.drop([0], axis=1)) y_test = np.array(test_recon[0]) X_test = np.array(test_recon.drop([0], axis=1)) # Set the parameters by cross-validation parameter_space = { "n_estimators": [10, 15, 20], "criterion": ["gini", "entropy"], "min_samples_leaf": [2, 4, 6], } #scores = ['precision', 'recall', 'roc_auc'] scores = ['roc_auc'] for score in scores: print("# Tuning hyper-parameters for %s" % score) print() clf = RandomForestClassifier(random_state=14) grid = GridSearchCV(clf, parameter_space, cv=5, scoring='%s' % score) #scoring='%s_macro' % score：precision_macro、recall_macro是用于multiclass/multilabel任务的 grid.fit(X_train, y_train) print("Best parameters set found on development set:") print() print(grid.best_params_) print() print("Grid scores on development set:") print() means = grid.cv_results_['mean_test_score'] stds = grid.cv_results_['std_test_score'] for mean, std, params in zip(means, stds, grid.cv_results_['params']): print("%0.3f (+/-%0.03f) for %r" % (mean, std * 2, params)) print() print("Detailed classification report:") print() print("The model is trained on the full development set.") print("The scores are computed on the full evaluation set.") print() bclf = grid.best_estimator_ bclf.fit(X_train, y_train) y_true = y_test y_pred = bclf.predict(X_test) y_pred_pro = bclf.predict_proba(X_test) y_scores = pd.DataFrame(y_pred_pro, columns=bclf.classes_.tolist())[1].values print(classification_report(y_true, y_pred)) auc_value = roc_auc_score(y_true, y_scores) 输出结果：#绘制ROC曲线 fpr, tpr, thresholds = roc_curve(y_true, y_scores, pos_label=1.0) plt.figure() lw = 2 plt.plot(fpr, tpr, color='darkorange', linewidth=lw, label='ROC curve (area = %0.4f)' % auc_value) plt.plot([0, 1], [0, 1], color='navy', linewidth=lw, linestyle='--') plt.xlim([0.0, 1.0]) plt.ylim([0.0, 1.05]) plt.xlabel('False Positive Rate') plt.ylabel('True Positive Rate') plt.title('Receiver operating characteristic example') plt.legend(loc="lower right") plt.show()
