def train_and_predict(csv_file_name=_DATA_FILE, training_steps=200):
"""Train and predict using a custom time series model."""
# Construct an Estimator from our LSTM model.
estimator = ts_estimators._TimeSeriesRegressor(
model=_LSTMModel(num_features=5, num_units=128),
optimizer=tf.train.AdamOptimizer(0.001))
reader = tf.contrib.timeseries.CSVReader(
csv_file_name,
column_names=((tf.contrib.timeseries.TrainEvalFeatures.TIMES, ) +
(tf.contrib.timeseries.TrainEvalFeatures.VALUES, ) * 5))
train_input_fn = tf.contrib.timeseries.RandomWindowInputFn(reader,
batch_size=4,
window_size=32)
estimator.train(input_fn=train_input_fn, steps=training_steps)
evaluation_input_fn = tf.contrib.timeseries.WholeDatasetInputFn(reader)
evaluation = estimator.evaluate(input_fn=evaluation_input_fn, steps=1)
# Predict starting after the evaluation
(predictions, ) = tuple(
estimator.predict(
input_fn=tf.contrib.timeseries.predict_continuation_input_fn(
evaluation, steps=100)))
times = evaluation["times"][0]
observed = evaluation["observed"][0, :, :]
predicted_mean = numpy.squeeze(
numpy.concatenate([evaluation["mean"][0], predictions["mean"]],
axis=0))
all_times = numpy.concatenate([times, predictions["times"]], axis=0)
return times, observed, all_times, predicted_mean
def train_and_predict(csv_file_name=_DATA_FILE, training_steps=200):
"""Train and predict using a custom time series model."""
# Construct an Estimator from our LSTM model.
estimator = ts_estimators._TimeSeriesRegressor(
model=_LSTMModel(num_features=5, num_units=128),
optimizer=tf.train.AdamOptimizer(0.001))
reader = tf.contrib.timeseries.CSVReader(
csv_file_name,
column_names=((tf.contrib.timeseries.TrainEvalFeatures.TIMES,)
+ (tf.contrib.timeseries.TrainEvalFeatures.VALUES,) * 5))
train_input_fn = tf.contrib.timeseries.RandomWindowInputFn(
reader, batch_size=4, window_size=32)
estimator.train(input_fn=train_input_fn, steps=training_steps)
evaluation_input_fn = tf.contrib.timeseries.WholeDatasetInputFn(reader)
evaluation = estimator.evaluate(input_fn=evaluation_input_fn, steps=1)
# Predict starting after the evaluation
(predictions,) = tuple(estimator.predict(
input_fn=tf.contrib.timeseries.predict_continuation_input_fn(
evaluation, steps=100)))
times = evaluation["times"][0]
observed = evaluation["observed"][0, :, :]
predicted_mean = numpy.squeeze(numpy.concatenate(
[evaluation["mean"][0], predictions["mean"]], axis=0))
all_times = numpy.concatenate([times, predictions["times"]], axis=0)
return times, observed, all_times, predicted_mean
train_y.append(tmp)
train_y_all = np.array(train_y)
train_y = train_y_all[0:900]
train_x = np.array(range(900))
lable_y = train_y_all[900:]
lable_x = np.array(range(900, 1082))
data = {
tf.contrib.timeseries.TrainEvalFeatures.TIMES: train_x,
tf.contrib.timeseries.TrainEvalFeatures.VALUES: train_y,
}
reader = NumpyReader(data)
train_input_fn = tf.contrib.timeseries.RandomWindowInputFn(reader,
batch_size=8,
window_size=180)
estimator = ts_estimators._TimeSeriesRegressor(
model=_LSTMModel(num_features=1, num_units=144),
optimizer=tf.train.AdamOptimizer(0.001))
estimator.train(input_fn=train_input_fn, steps=2000)
evaluation_input_fn = tf.contrib.timeseries.WholeDatasetInputFn(reader)
evaluation = estimator.evaluate(input_fn=evaluation_input_fn, steps=1)
# Predict starting after the evaluation
(predictions, ) = tuple(
estimator.predict(
input_fn=tf.contrib.timeseries.predict_continuation_input_fn(
evaluation, steps=180)))
observed_times = evaluation["times"][0]
observed = evaluation["observed"][0, :, :]
evaluated_times = evaluation["times"][0]
evaluated = evaluation["mean"][0]
def _train_on_generated_data(
generate_fn, generative_model, train_iterations, seed,
learning_rate=0.1, ignore_params_fn=lambda _: (),
derived_param_test_fn=lambda _: (),
train_input_fn_type=input_pipeline.WholeDatasetInputFn,
train_state_manager=state_management.PassthroughStateManager()):
"""The training portion of parameter recovery tests."""
random_seed.set_random_seed(seed)
generate_graph = ops.Graph()
with generate_graph.as_default():
with session.Session(graph=generate_graph):
generative_model.initialize_graph()
time_series_reader, true_parameters = generate_fn(generative_model)
true_parameters = {
tensor.name: value for tensor, value in true_parameters.items()}
eval_input_fn = input_pipeline.WholeDatasetInputFn(time_series_reader)
eval_state_manager = state_management.PassthroughStateManager()
true_parameter_eval_graph = ops.Graph()
with true_parameter_eval_graph.as_default():
generative_model.initialize_graph()
ignore_params = ignore_params_fn(generative_model)
feature_dict, _ = eval_input_fn()
eval_state_manager.initialize_graph(generative_model)
feature_dict[TrainEvalFeatures.VALUES] = math_ops.cast(
feature_dict[TrainEvalFeatures.VALUES], generative_model.dtype)
model_outputs = eval_state_manager.define_loss(
model=generative_model,
features=feature_dict,
mode=estimator_lib.ModeKeys.EVAL)
with session.Session(graph=true_parameter_eval_graph) as sess:
variables.global_variables_initializer().run()
coordinator = coordinator_lib.Coordinator()
queue_runner_impl.start_queue_runners(sess, coord=coordinator)
true_param_loss = model_outputs.loss.eval(feed_dict=true_parameters)
true_transformed_params = {
param: param.eval(feed_dict=true_parameters)
for param in derived_param_test_fn(generative_model)}
coordinator.request_stop()
coordinator.join()
saving_hook = _SavingTensorHook(
tensors=true_parameters.keys(),
every_n_iter=train_iterations - 1)
class _RunConfig(estimator_lib.RunConfig):
@property
def tf_random_seed(self):
return seed
estimator = estimators._TimeSeriesRegressor( # pylint: disable=protected-access
model=generative_model,
config=_RunConfig(),
state_manager=train_state_manager,
optimizer=adam.AdamOptimizer(learning_rate))
train_input_fn = train_input_fn_type(time_series_reader=time_series_reader)
trained_loss = (estimator.train(
input_fn=train_input_fn,
max_steps=train_iterations,
hooks=[saving_hook]).evaluate(
input_fn=eval_input_fn, steps=1))["loss"]
logging.info("Final trained loss: %f", trained_loss)
logging.info("True parameter loss: %f", true_param_loss)
return (ignore_params, true_parameters, true_transformed_params,
trained_loss, true_param_loss, saving_hook,
true_parameter_eval_graph)
def _train_on_generated_data(
generate_fn,
generative_model,
train_iterations,
seed,
learning_rate=0.1,
ignore_params_fn=lambda _: (),
derived_param_test_fn=lambda _: (),
train_input_fn_type=input_pipeline.WholeDatasetInputFn,
train_state_manager=state_management.PassthroughStateManager()):
"""The training portion of parameter recovery tests."""
random_seed.set_random_seed(seed)
generate_graph = ops.Graph()
with generate_graph.as_default():
with session.Session(graph=generate_graph):
generative_model.initialize_graph()
time_series_reader, true_parameters = generate_fn(generative_model)
true_parameters = {
tensor.name: value
for tensor, value in true_parameters.items()
}
eval_input_fn = input_pipeline.WholeDatasetInputFn(time_series_reader)
eval_state_manager = state_management.PassthroughStateManager()
true_parameter_eval_graph = ops.Graph()
with true_parameter_eval_graph.as_default():
generative_model.initialize_graph()
ignore_params = ignore_params_fn(generative_model)
feature_dict, _ = eval_input_fn()
eval_state_manager.initialize_graph(generative_model)
feature_dict[TrainEvalFeatures.VALUES] = math_ops.cast(
feature_dict[TrainEvalFeatures.VALUES], generative_model.dtype)
model_outputs = eval_state_manager.define_loss(
model=generative_model,
features=feature_dict,
mode=estimator_lib.ModeKeys.EVAL)
with session.Session(graph=true_parameter_eval_graph) as sess:
variables.global_variables_initializer().run()
coordinator = coordinator_lib.Coordinator()
queue_runner_impl.start_queue_runners(sess, coord=coordinator)
true_param_loss = model_outputs.loss.eval(
feed_dict=true_parameters)
true_transformed_params = {
param: param.eval(feed_dict=true_parameters)
for param in derived_param_test_fn(generative_model)
}
coordinator.request_stop()
coordinator.join()
saving_hook = _SavingTensorHook(tensors=true_parameters.keys(),
every_n_iter=train_iterations - 1)
class _RunConfig(estimator_lib.RunConfig):
@property
def tf_random_seed(self):
return seed
estimator = estimators._TimeSeriesRegressor( # pylint: disable=protected-access
model=generative_model,
config=_RunConfig(),
state_manager=train_state_manager,
optimizer=adam.AdamOptimizer(learning_rate))
train_input_fn = train_input_fn_type(time_series_reader=time_series_reader)
trained_loss = (estimator.train(input_fn=train_input_fn,
max_steps=train_iterations,
hooks=[saving_hook
]).evaluate(input_fn=eval_input_fn,
steps=1))["loss"]
logging.info("Final trained loss: %f", trained_loss)
logging.info("True parameter loss: %f", true_param_loss)
return (ignore_params, true_parameters, true_transformed_params,
trained_loss, true_param_loss, saving_hook,
true_parameter_eval_graph)
raise NotImplementedError(
"Exogenous inputs are not implemented for this example.")
csv_file_name = './data/multivariate_periods.csv'
# reader = tf.contrib.timeseries.CSVReader(csv_file_name)
# csv_file_name = './data/red_bule_balls_2003.csv'
reader = tf.contrib.timeseries.CSVReader(
csv_file_name,
column_names=((tf.contrib.timeseries.TrainEvalFeatures.TIMES,)
+ (tf.contrib.timeseries.TrainEvalFeatures.VALUES,) * 5))
print(reader)
data = reader.read_full()
print(data)
# estimator
# @see:https://mp.weixin.qq.com/s?__biz=MzI0ODcxODk5OA==&mid=2247489403&idx=1&sn=9f004963889104fd83307e48e9ec8709&chksm=e99d2482deeaad94ae1f1154b7c4de91eafa678d2feaebe9183987efd9b38287fdf8d2f3f04a&mpshare=1&scene=1&srcid=0925uD5dshUAN3UoUe9PD4mV&key=f32e811df94f16bf6c056cd27bde2d6cf2de557b042b10eebff3ec8204d94d8b19d5502a0f108ced8ea7006b76087c025b93cb3864bafee6a311dfd9990f974fe965643704ab1c791d9a2355d4b21f1e&ascene=0&uin=MTkyNTE5ODcwMw%3D%3D&devicetype=iMac+MacBookAir6%2C2+OSX+OSX+10.12.6+build(16G29)&version=12020810&nettype=WIFI&fontScale=100&pass_ticket=LQXTGodGb%2B7%2BPVkkVqV4W1EEZLoNH7Wi%2BnJxlbUYnFVsrEsp3ZsvKzcliL9Ezrm7
estimator = ts_estimators._TimeSeriesRegressor(
model= _LSTMModel(num_features=5,num_units=128),
optimizer = tf.train.AdamOptimizer(0.001)
)
print(estimator)
plt.figure(figsize=(15, 5))
# plt.plot(data['times'], data['values'], label='origin')
# plt.plot(evaluation['times'].reshape(-1), evaluation['mean'].reshape(-1), label='evaluation')
# plt.plot(predictions['times'].reshape(-1), predictions['mean'].reshape(-1), label='prediction')
# plt.xlabel('time_step')
plt.show()