Question

试图了解和实现Keras回归的GridSearch方法。这是我简单的可生产回归应用程序。

import pandas as pd
import numpy as np
import sklearn
from sklearn.model_selection import train_test_split
from sklearn import metrics
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint


df = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/concrete/slump/slump_test.data")
df.drop(['No','FLOW(cm)','Compressive Strength (28-day)(Mpa)'],1,inplace=True)

# Convert a Pandas dataframe to the x,y inputs that TensorFlow needs
def to_xy(df, target):
    result = []
    for x in df.columns:
        if x != target:
            result.append(x)
    # find out the type of the target column.  Is it really this hard? :(
    target_type = df[target].dtypes
    target_type = target_type[0] if hasattr(target_type, '__iter__') else target_type
    # Encode to int for classification, float otherwise. TensorFlow likes 32 bits.
    if target_type in (np.int64, np.int32):
        # Classification
        dummies = pd.get_dummies(df[target])
        return df.as_matrix(result).astype(np.float32), dummies.as_matrix().astype(np.float32)
    else:
        # Regression
        return df.as_matrix(result).astype(np.float32), df.as_matrix([target]).astype(np.float32)

x,y = to_xy(df,'SLUMP(cm)')


x_train, x_test, y_train, y_test = train_test_split(    
    x, y, test_size=0.25, random_state=42)


#Create Model
model = Sequential()
model.add(Dense(128, input_dim=x.shape[1], activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')

monitor = EarlyStopping(monitor='val_loss', min_delta=1e-5, patience=5, mode='auto')
checkpointer = ModelCheckpoint(filepath="best_weights.hdf5",save_best_only=True) # save best model

model.fit(x_train,y_train,callbacks=[monitor,checkpointer],verbose=0,epochs=1000)
#model.fit(x_train,y_train,validation_data=(x_test,y_test),callbacks=[monitor,checkpointer],verbose=0,epochs=1000)
pred = model.predict(x_test)

score = np.sqrt(metrics.mean_squared_error(pred,y_test))

print("(RMSE): {}".format(score))

如果运行代码，可以看到loss的数字不是太大。

这是我可生产的GridSearch实现。首先，我只是在网上搜索并找到KerasClassifier的GridSearch应用程序，然后尝试为KerasRegressor对其进行修改。我不确定我的修订是否正确。如果我认为一般概念是正确的，那么此代码中肯定会有问题，因为损失函数没有意义。损失函数为MSE，但输出为负，很遗憾，我无法弄清楚哪里做错了。

from keras.wrappers.scikit_learn import KerasRegressor
import pandas as pd
import numpy as np
import sklearn
from sklearn.model_selection import train_test_split
from sklearn import metrics
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
from sklearn.model_selection import GridSearchCV

df = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/concrete/slump/slump_test.data")
df.drop(['No','FLOW(cm)','Compressive Strength (28-day)(Mpa)'],1,inplace=True)

#Convert a Pandas dataframe to the x,y inputs that TensorFlow needs
def to_xy(df, target):
    result = []
    for x in df.columns:
        if x != target:
            result.append(x)
    # find out the type of the target column.  Is it really this hard? :(
    target_type = df[target].dtypes
    target_type = target_type[0] if hasattr(target_type, '__iter__') else target_type
    # Encode to int for classification, float otherwise. TensorFlow likes 32 bits.
    if target_type in (np.int64, np.int32):
        #Classification
        dummies = pd.get_dummies(df[target])
        return df.as_matrix(result).astype(np.float32), dummies.as_matrix().astype(np.float32)
    else:
        #Regression
        return df.as_matrix(result).astype(np.float32), df.as_matrix([target]).astype(np.float32)

x,y = to_xy(df,'SLUMP(cm)')


x_train, x_test, y_train, y_test = train_test_split(    
    x, y, test_size=0.25, random_state=42)


def create_model(optimizer='adam'):
    # create model
    model = Sequential()
    model.add(Dense(128, input_dim=x.shape[1], activation='relu'))
    model.add(Dense(64, activation='relu'))
    model.add(Dense(1))
    model.compile(loss='mean_squared_error', optimizer=optimizer,metrics=['mse'])
    return model

model = KerasRegressor(build_fn=create_model, epochs=100, batch_size=10, verbose=0)

optimizer = ['SGD', 'RMSprop', 'Adagrad']
param_grid = dict(optimizer=optimizer)

grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=1)
grid_result = grid.fit(x_train, y_train)

#summarize results
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
    print("%f (%f) with: %r" % (mean, stdev, param))

Answer 1

我已经测试了您的代码，并且发现您没有在GridSearchCV中使用评分功能，因此根据文档scikit-learn documentation：

如果为“无”，则使用估算器的默认评分器（如果有）。

似乎默认情况下是否会使用“ neg_mean_absolute_error”（或these scoring functions for regression中的任何一个）来评分模型。

那是因为可能它说最好的模型是：

-75.820078 using {'optimizer':'Adagrad'}

希望对您有帮助。

最好的问候。

Keras回归的GridSearch实现

1 个答案: