from pandas import concat
# from lstm_predictor import generate_data, lstm_model
warnings.filterwarnings("ignore")
LOG_DIR = 'resources/logs/'
TIMESTEPS = 1
RNN_LAYERS = [{'num_units': 400}]
DENSE_LAYERS = None
TRAINING_STEPS = 3000
PRINT_STEPS = TRAINING_STEPS # / 10
BATCH_SIZE = 1
regressor = SKCompat(
learn.Estimator(model_fn=predictor.lstm_model(TIMESTEPS, RNN_LAYERS,
DENSE_LAYERS), ))
# model_dir=LOG_DIR)
from pandas import read_csv
from pandas import Series
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
series = read_csv(
'../CorpData/InventoryHistory/2010_2018_books_sortable inventory.csv',
header=0,
parse_dates=[0],
index_col=0,
squeeze=True,
usecols=[0, 4])
import lstm_predictior as predictor
# from lstm_predictor import generate_data, lstm_model
warnings.filterwarnings("ignore")
LOG_DIR = 'resources/logs/'
TIMESTEPS = 1
RNN_LAYERS = [{'num_units': 400}]
DENSE_LAYERS = None
TRAINING_STEPS = 500
PRINT_STEPS = TRAINING_STEPS # / 10
BATCH_SIZE = 100
regressor = SKCompat(learn.Estimator(model_fn=predictor.lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS), ))
# model_dir=LOG_DIR)
X, y = predictor.generate_data(np.sin, np.linspace(0, 100, 10000, dtype=np.float32), TIMESTEPS, seperate=False)
noise_train = np.asmatrix(np.random.normal(0, 0.2, len(y['train'])), dtype=np.float32)
noise_val = np.asmatrix(np.random.normal(0, 0.2, len(y['val'])), dtype=np.float32)
noise_test = np.asmatrix(np.random.normal(0, 0.2, len(y['test'])), dtype=np.float32) # asmatrix
noise_train = np.transpose(noise_train)
noise_val = np.transpose(noise_val)
noise_test = np.transpose(noise_test)
y['train'] = np.add(y['train'], noise_train)
y['val'] = np.add(y['val'], noise_val)
y['test'] = np.add(y['test'], noise_test)
DENSE_LAYERS = None
TRAINING_STEPS = 100
PRINT_STEPS = TRAINING_STEPS / 10
BATCH_SIZE = 100
''' org
LOG_DIR = 'resources/logs/'
TIMESTEPS = 1
RNN_LAYERS = [{'num_units': 4}]
DENSE_LAYERS = None
TRAINING_STEPS = 100
PRINT_STEPS = TRAINING_STEPS / 10
BATCH_SIZE = 100
'''
regressor = SKCompat(
learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),
model_dir=LOG_DIR)) # new
# regressor = learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),model_dir=LOG_DIR) # old
X, y = generate_data(np.sin,
np.arange(600, dtype=np.int32),
TIMESTEPS,
seperate=False)
print(X['train'].shape)
print(y['train'].shape)
print(X['train'])
print(y['train'])
# create a lstm instance and validation monitor
TRAINING_STEPS = 100
PRINT_STEPS = TRAINING_STEPS / 10
BATCH_SIZE = 100
''' org
LOG_DIR = 'resources/logs/'
TIMESTEPS = 1
RNN_LAYERS = [{'num_units': 4}]
DENSE_LAYERS = None
TRAINING_STEPS = 100
PRINT_STEPS = TRAINING_STEPS / 10
BATCH_SIZE = 100
'''
regressor = SKCompat(learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),model_dir=LOG_DIR)) # new
# regressor = learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),model_dir=LOG_DIR) # old
X, y = generate_data(np.sin, np.linspace(0, 100, 10000, dtype=np.float32), TIMESTEPS, seperate=False)
print(X['train'].shape)
print(y['train'].shape)
# create a lstm instance and validation monitor
validation_monitor = learn.monitors.ValidationMonitor(X['val'], y['val'], every_n_steps=PRINT_STEPS, early_stopping_rounds=1000)
#validation_monitor = tf.train.SessionRunHook(X['val'], y['val'], every_n_steps=PRINT_STEPS, early_stopping_rounds=1000)
# print(X['train'])
# print(y['train'])