def __init__ (self):
self.data = []
self.training = (0, 0.6)
self.validation = (0.6, 0.8)
self.testing = (0.8, 1)
self.data_size = 7
self.num_queries = 200
#with open ('timeseriesOnlineRetailCleaned2.csv', 'r') as f:
with open ('../data/randomizedOnlineRetail.csv', 'r' ) as f:
reader = csv.reader(f, delimiter=',')
title_row = True
for row in reader:
if title_row:
self.products = row
title_row = False
else:
integer_data = [int(row[i]) for i in range (self.num_queries)]
self.data.append (integer_data)
#print (self.data)
self.predictor1 = QLearn(threshold=0.5, svd=True, regularization=True)
#self.predictor2 = GRUModel ()
self.baseline1 = NaiveModel()
self.baseline2 = EarliestModel()
self.baseline3 = AverageModel(threshold=0.75, regularization=True)
def __init__(self):
self.data = []
self.training = (0, 0.6)
self.validation = (0.6, 0.8)
self.testing = (0.8, 1)
#self.data_size = 24
self.data_size = 7
self.num_queries = 2000
# q = 1, epochs = 100
# q = 5, epochs = 20
# q = 100, epochs = 10
# q = 2000, epochs = 3
with open(DATA_DIR, 'r') as f:
#with open ('hourlyTimeSeriesOnlineRetailCleaned.csv', 'r') as f:
reader = csv.reader(f, delimiter=',')
title_row = True
for row in reader:
if title_row:
self.products = row
title_row = False
else:
integer_data = [
int(row[i]) for i in range(self.num_queries)
]
self.data.append(integer_data)
#print (self.data)
self.predictor1 = QLearn(threshold=0.5, regularization=True)
#self.predictor2 = RNNModel ()
self.baseline1 = NaiveModel()
self.baseline2 = EarliestModel()
self.predictor3 = simple_model((None, self.num_queries + 1), 2)
def __init__(self):
self.data = []
self.training = (0, 0.6)
self.validation = (0.6, 0.8)
self.testing = (0.8, 0.95)
#self.data_size = 24
self.data_size = 7
self.num_queries = 200
# q = 1, epochs = 100
# q = 5, epochs = 20
# q = 100, epochs = 10
# q = 2000, epochs = 3
#print (self.data)
#self.predictor1 = QLearn(threshold=0.5, regularization=True)
self.baseline1 = NaiveModel()
self.baseline2 = EarliestModel()
saved_models = [(
10, "LSTM", "sgd", 0.001, 2, 32,
"../results/10Qs/LSTM/2L/32HS/sgd-0.001lr/20180731-134128-683987/900epochs.h5"
)]
model_num = 0
self.num_queries = saved_models[model_num][0]
# q = 1, epochs = 100
# q = 5, epochs = 20
# q = 100, epochs = 10
# q = 2000, epochs = 3
with open(DATA_DIR, 'r') as f:
#with open ('hourlyTimeSeriesOnlineRetailCleaned.csv', 'r') as f:
reader = csv.reader(f, delimiter=',')
title_row = True
for row in reader:
if title_row:
self.products = row
title_row = False
else:
integer_data = [
int(row[i]) for i in range(self.num_queries)
]
self.data.append(integer_data)
self.predictor3 = RNNModel(saved_models[model_num][0],
rnn_type=saved_models[model_num][1],
optimizer_type=saved_models[model_num][2],
learning_rate=saved_models[model_num][3],
layers=saved_models[model_num][4],
hidden_size=saved_models[model_num][5])
self.predictor3.load_model(saved_models[model_num][6])
def __init__(self):
self.data = []
self.training = (0, 0.5)
self.validation = (0.5, 0.8)
self.testing = (0.8, 0.95)
#self.data_size = 24
self.data_size = 96
self.num_queries = 10
# q = 1, epochs = 100
# q = 5, epochs = 20
# q = 100, epochs = 10
# q = 2000, epochs = 3
self.ds = Electricity()
data = self.ds.get_data()
transpose = np.transpose(data)
transpose = transpose[:self.num_queries]
data = np.transpose(transpose)
self.training_data = data[int(self.training[0] *
len(data)):int(self.training[1] *
len(data))]
self.validation_data = data[int(self.validation[0] *
len(data)):int(self.validation[1] *
len(data))]
self.testing_data = data[int(self.training[0] *
len(data)):int(self.training[1] *
len(data))]
#for i in range (int(len (transpose) / self.num_queries)):
#print (self.data)
self.predictor1 = QLearn(threshold=0.5, regularization=False)
self.baseline1 = NaiveModel()
self.baseline2 = EarliestModel()
self.predictor3 = RNNModel(self.num_queries,
rnn_type="LSTM",
optimizer_type="adam",
learning_rate=0.001,
layers=2,
hidden_size=64,
recurrent_dropout=0.2)
def __init__(self):
self.data = []
self.training = (0, 0.6)
self.validation = (0.6, 0.8)
self.testing = (0.8, 0.95)
#self.data_size = 24
self.data_size = 7
self.num_queries = 10
# q = 1, epochs = 100
# q = 5, epochs = 20
# q = 100, epochs = 10
# q = 2000, epochs = 3
with open(DATA_DIR, 'r') as f:
#with open ('hourlyTimeSeriesOnlineRetailCleaned.csv', 'r') as f:
reader = csv.reader(f, delimiter=',')
title_row = True
for row in reader:
if title_row:
self.products = row
title_row = False
else:
integer_data = [
int(row[i]) for i in range(self.num_queries)
]
self.data.append(integer_data)
#print (self.data)
self.predictor1 = QLearn(threshold=0.5, regularization=True)
self.baseline1 = NaiveModel()
self.baseline2 = EarliestModel()
self.predictor3 = RNNModel(self.num_queries,
rnn_type="LSTM",
optimizer_type="sgd",
learning_rate=0.001,
layers=1,
hidden_size=128,
recurrent_dropout=0.2)