crat.py 文件源码

def classify(y, x, test_y, test_x):
    global data_df, factor_name, left, right, feature, ratio, threshold
    y_c = np.zeros(len(y))
    y_c[y > 0.02] = 1
    y_c[y < -0.02] = -1
    min_n = int(0.05 * len(y))
    clf = DecisionTreeClassifier(max_depth=4, min_samples_leaf=min_n)
    clf.fit(x, y_c)
    y_p = clf.predict(x)
    fname = "D:\\Cache\\tree.txt"
    test_y = y
    with open(fname, 'w') as f:
        tree.export_graphviz(clf, out_file=f)
        f.close()
    factor_exchange(factor_name, fname)
    left = clf.tree_.children_left
    right = clf.tree_.children_right
    feature = clf.tree_.feature
    threshold = clf.tree_.threshold
    disp_tree()
    # precision, recall, thresholds = precision_recall_curve(y_c, clf.predict(x))
    '''''???????'''
    print("mean income is:", str(np.average(test_y)),
          "\nwin ratio is: ", str(np.sum(test_y > 0) / len(test_y)))
    print("after training\n"
          "mean class_1 is: ", str(np.average(test_y[y_p > 0])),
          "\nwin ratio is: ", str(np.sum(test_y[y_p > 0] > 0) / np.sum(y_p > 0)),
          "\ntotal class_1 is:", str(np.sum(np.sum(y_p > 0))),
          "\nmean class_0 is: ", str(np.average(test_y[y_p < 0])))