Keras - 如何使用KerasRegressor执行预测？

Question

我是机器学习的新手,我正在尝试处理Keras来执行回归任务.基于此示例,我已实现此代码.

X = df[['full_sq','floor','build_year','num_room','sub_area_2','sub_area_3','state_2.0','state_3.0','state_4.0']]
y = df['price_doc']

X = np.asarray(X)
y = np.asarray(y)

X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=.2)
def baseline_model():
    model = Sequential()
    model.add(Dense(13, input_dim=9, kernel_initializer='normal', 
        activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model

estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=100, verbose=False)
kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(estimator, X_train, Y_train, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))

prediction = estimator.predict(X_test)
accuracy_score(Y_test, prediction)

当我运行代码时,我收到此错误:

AttributeError: 'KerasRegressor' object has no attribute 'model'

我怎样才能在KerasRegressor中正确"插入"模型？

Answer 1

在cross_val_score评估新数据后,你必须再次拟合估算器:

estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=100, verbose=False)
kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(estimator, X_train, Y_train, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))

estimator.fit(X, y)
prediction = estimator.predict(X_test)
accuracy_score(Y_test, prediction)

工作测试版:

from sklearn import datasets, linear_model
from sklearn.model_selection import cross_val_score, KFold
from keras.models import Sequential
from sklearn.metrics import accuracy_score
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
seed = 1

diabetes = datasets.load_diabetes()
X = diabetes.data[:150]
y = diabetes.target[:150]

def baseline_model():
    model = Sequential()
    model.add(Dense(10, input_dim=10, activation='relu'))
    model.add(Dense(1))
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model


estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=100, verbose=False)
kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(estimator, X, y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))

estimator.fit(X, y)
prediction = estimator.predict(X)
accuracy_score(y, prediction)

Answer 2

为了评估您的系统性能，您可以计算如下误差。您也不需要调用 KFold 和 cross_val_score。

import numpy as np
from sklearn import datasets, linear_model
from sklearn.model_selection import cross_val_score, KFold
from keras.models import Sequential
from sklearn.metrics import accuracy_score
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
seed = 1

diabetes = datasets.load_diabetes()
X = diabetes.data[:150]
y = diabetes.target[:150]

def baseline_model():
    model = Sequential()
    model.add(Dense(10, input_dim=10, activation='relu'))
    model.add(Dense(1))
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model


estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=100, verbose=False)
estimator.fit(X, y)
prediction = estimator.predict(X)

train_error =  np.abs(y - prediction)
mean_error = np.mean(train_error)
min_error = np.min(train_error)
max_error = np.max(train_error)
std_error = np.std(train_error)