enron_poi_ml_ci.py 文件源码

def varius_classifiers():
    # List of tuples of a classifier and its parameters.
    clf_list = []

    clf_linearsvm = LinearSVC()
    params_linearsvm = {"C": [0.5, 1, 5, 10, 100, 10**10],"tol":[0.1, 0.0000000001],"class_weight":['balanced']}
    clf_list.append( (clf_linearsvm, params_linearsvm) )

    clf_tree = DecisionTreeClassifier()
    params_tree = { "min_samples_split":[2, 5, 10, 20],"criterion": ('gini', 'entropy')}
    clf_list.append( (clf_tree, params_tree) )

    clf_random_tree = RandomForestClassifier()
    params_random_tree = {  "n_estimators":[2, 3, 5],"criterion": ('gini', 'entropy')}
    clf_list.append( (clf_random_tree, params_random_tree) )

    clf_adaboost = AdaBoostClassifier()
    params_adaboost = { "n_estimators":[20, 30, 50, 100]}
    clf_list.append( (clf_adaboost, params_adaboost) )

    clf_knn = KNeighborsClassifier()
    params_knn = {"n_neighbors":[2, 5], "p":[2,3]}
    clf_list.append( (clf_knn, params_knn) )

    clf_log = LogisticRegression()
    params_log = {"C":[0.5, 1, 10, 10**2,10**10, 10**20],"tol":[0.1, 0.00001, 0.0000000001],"class_weight":['balanced']}
    clf_list.append( (clf_log, params_log) )

    clf_lda = LinearDiscriminantAnalysis()
    params_lda = {"n_components":[0, 1, 2, 5, 10]}
    clf_list.append( (clf_lda, params_lda) )

    logistic = LogisticRegression()
    rbm = BernoulliRBM()
    clf_rbm = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])
    params_rbm = {"logistic__tol":[0.0000000001, 10**-20],"logistic__C":[0.05, 1, 10, 10**2,10**10, 10**20],"logistic__class_weight":['balanced'],"rbm__n_components":[2,3,4]}
    clf_list.append( (clf_rbm, params_rbm) )

    return clf_list