Я застрял при попытке настроить гиперпараметры для LSTM через RandomizedSearchCV.
Мой код указан ниже:
X_train = X_train.reshape((X_train.shape[0], 1, X_train.shape[1]))
X_test = X_test.reshape((X_test.shape[0], 1, X_test.shape[1]))
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)
from imblearn.pipeline import Pipeline
from keras.initializers import RandomNormal
def create_model(activation_1='relu', activation_2='relu',
neurons_input = 1, neurons_hidden_1=1,
optimizer='Adam' ,
#input_shape = (X_train.shape[1], X_train.shape[2])
#input_shape=(X_train.shape[0],X_train.shape[1]) #input shape should be timesteps, features
):
model = Sequential()
model.add(LSTM(neurons_input, activation=activation_1, input_shape=(X_train.shape[1], X_train.shape[2]),
kernel_initializer=RandomNormal(mean=0.0, stddev=0.05, seed=42),
bias_initializer=RandomNormal(mean=0.0, stddev=0.05, seed=42)))
model.add(Dense(2, activation='sigmoid'))
model.compile (loss = 'sparse_categorical_crossentropy', optimizer=optimizer)
return model
clf=KerasClassifier(build_fn=create_model, epochs=10, verbose=0)
param_grid = {
'clf__neurons_input': [20, 25, 30, 35],
'clf__batch_size': [40,60,80,100],
'clf__optimizer': ['Adam', 'Adadelta']}
pipe = Pipeline([
('oversample', SMOTE(random_state=12)),
('clf', clf)
])
my_cv = TimeSeriesSplit(n_splits=5).split(X_train)
rs_keras = RandomizedSearchCV(pipe, param_grid, cv=my_cv, scoring='f1_macro',
refit='f1_macro', verbose=3,n_jobs=1, random_state=42)
rs_keras.fit(X_train, y_train)
Я продолжаю иметь ошибку:
Found array with dim 3. Estimator expected <= 2.
, что имеет смысл, поскольку и GridSearch, и RandomizedSearch нуждаются в типе массива [n_samples, n_features]. У кого-нибудь есть опыт или предложение, как бороться с этим ограничением?
Спасибо.
Вот полный ответ об ошибке:
Traceback (most recent call last):
File "<ipython-input-2-b0be4634c98a>", line 1, in <module>
runfile('Scratch/prediction_lstm.py', wdir='/Simulations/2017-2018/Scratch')
File "\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 786, in runfile
execfile(filename, namespace)
File "\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 110, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "Scratch/prediction_lstm.py", line 204, in <module>
rs_keras.fit(X_train, y_train)
File "Anaconda3\lib\site-packages\sklearn\model_selection\_search.py", line 722, in fit
self._run_search(evaluate_candidates)
File "\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py", line 1515, in _run_search
random_state=self.random_state))
File "\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py", line 711, in evaluate_candidates
cv.split(X, y, groups)))
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py", line 917, in __call__
if self.dispatch_one_batch(iterator):
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py", line 759, in dispatch_one_batch
self._dispatch(tasks)
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py", line 716, in _dispatch
job = self._backend.apply_async(batch, callback=cb)
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py", line 182, in apply_async
result = ImmediateResult(func)
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py", line 549, in __init__
self.results = batch()
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py", line 225, in __call__
for func, args, kwargs in self.items]
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py", line 225, in <listcomp>
for func, args, kwargs in self.items]
File "\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 528, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "\Anaconda3\lib\site-packages\imblearn\pipeline.py", line 237, in fit
Xt, yt, fit_params = self._fit(X, y, **fit_params)
File "\Anaconda3\lib\site-packages\imblearn\pipeline.py", line 200, in _fit
cloned_transformer, Xt, yt, **fit_params_steps[name])
File "\Anaconda3\lib\site-packages\sklearn\externals\joblib\memory.py", line 342, in __call__
return self.func(*args, **kwargs)
File "\Anaconda3\lib\site-packages\imblearn\pipeline.py", line 576, in _fit_resample_one
X_res, y_res = sampler.fit_resample(X, y, **fit_params)
File "\Anaconda3\lib\site-packages\imblearn\base.py", line 80, in fit_resample
X, y, binarize_y = self._check_X_y(X, y)
File "\Anaconda3\lib\site-packages\imblearn\base.py", line 138, in _check_X_y
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'])
File "\Anaconda3\lib\site-packages\sklearn\utils\validation.py", line 756, in check_X_y
estimator=estimator)
File "\Anaconda3\lib\site-packages\sklearn\utils\validation.py", line 570, in check_array
% (array.ndim, estimator_name))
ValueError: Found array with dim 3. Estimator expected <= 2.