main_CV.py 文件源码

def models():

    extra_params_kaggle_cla = {'n_estimators':1200,'max_features':30,'criterion':'entropy',
                           'min_samples_leaf': 2, 'min_samples_split': 2,'max_depth': 30,
                           'min_samples_leaf': 2, 'n_jobs':nthread, 'random_state':seed}

    extra_params_kaggle_reg = {'n_estimators':1200,'max_features':30,'criterion':'mse',
                           'min_samples_leaf': 2, 'min_samples_split': 2,'max_depth': 30,
                           'min_samples_leaf': 2, 'n_jobs':nthread, 'random_state':seed}


    xgb_reg = {'objective':'reg:linear', 'max_depth': 11, 'learning_rate':0.01, 'subsample':.9,
           'n_estimators':10000, 'colsample_bytree':0.45, 'nthread':nthread, 'seed':seed}

    xgb_cla = {'objective':'binary:logistic', 'max_depth': 11, 'learning_rate':0.01, 'subsample':.9,
           'n_estimators':10000, 'colsample_bytree':0.45, 'nthread':nthread, 'seed':seed}


    #NN params
    nb_epoch = 3
    batch_size = 128
    esr = 402

    param1 = {
        'hidden_units': (256, 256),
        'activation': (advanced_activations.PReLU(),advanced_activations.PReLU(),core.activations.sigmoid),
        'dropout': (0., 0.), 'optimizer': RMSprop(), 'nb_epoch': nb_epoch,
    }
    param2 = {
        'hidden_units': (1024, 1024),
        'activation': (advanced_activations.PReLU(),advanced_activations.PReLU(),core.activations.sigmoid),
        'dropout': (0., 0.), 'optimizer': RMSprop(), 'nb_epoch': nb_epoch,
    }
    clfs = [
        (D2, XGBClassifier(**xgb_cla)),
        (D11, XGBClassifier(**xgb_cla)),

        (D2, XGBRegressor(**xgb_reg)),
        (D11, XGBRegressor(**xgb_reg)),

        (D2, ensemble.ExtraTreesClassifier(**extra_params_kaggle_cla)),
        (D11, ensemble.ExtraTreesClassifier(**extra_params_kaggle_cla)),

        (D2, ensemble.ExtraTreesRegressor(**extra_params_kaggle_reg)),
        (D11, ensemble.ExtraTreesRegressor(**extra_params_kaggle_reg)),

    # (D1, NN(input_dim=D1[0].shape[1], output_dim=1, batch_size=batch_size, early_stopping_epoch=esr, verbose=2, loss='binary_crossentropy', class_mode='binary', **param1)),
    # (D3, NN(input_dim=D3[0].shape[1], output_dim=1, batch_size=batch_size, early_stopping_epoch=esr, verbose=2,loss='binary_crossentropy', class_mode='binary', **param1)),
    # (D5, NN(input_dim=D5[0].shape[1], output_dim=1, batch_size=batch_size, early_stopping_epoch=esr, verbose=2,loss='binary_crossentropy', class_mode='binary', **param1)),
    #
    # (D1, NN(input_dim=D1[0].shape[1], output_dim=1, batch_size=batch_size, early_stopping_epoch=esr, verbose=2,loss='binary_crossentropy', class_mode='binary', **param2)),
    # (D3, NN(input_dim=D3[0].shape[1], output_dim=1, batch_size=batch_size, early_stopping_epoch=esr, verbose=2,loss='binary_crossentropy', class_mode='binary', **param2)),
    # (D5, NN(input_dim=D5[0].shape[1], output_dim=1, batch_size=batch_size, early_stopping_epoch=esr, verbose=2,loss='binary_crossentropy', class_mode='binary', **param2))

    ]
    for clf in clfs:
        yield clf