def test_single_price(self):
df1 = pd.DataFrame(
{
'Open': [10.2, 12, 32.1, 9.32],
'Close': [2.3, 3.6, 4.5, 11.11]
},
index=pd.to_datetime(
['2020-01-01', '2020-02-01', '2020-03-01', '2020-04-01']))
expected1 = pd.DataFrame({'Fake_1': [2.3, 3.6, 4.5, 11.11]},
index=pd.to_datetime([
'2020-01-01', '2020-02-01', '2020-03-01',
'2020-04-01'
]))
df2 = pd.DataFrame({'FakeSPY': [10.2, 12, 32.1, 9.32]},
index=pd.to_datetime([
'2020-01-01', '2020-02-01', '2020-03-01',
'2020-04-01'
]))
expected2 = pd.DataFrame({'FakeSPY': [10.2, 12, 32.1, 9.32]},
index=pd.to_datetime([
'2020-01-01', '2020-02-01', '2020-03-01',
'2020-04-01'
]))
new_df1 = DataPreprocessing.single_price(df1, 'Fake_1')
new_df2 = DataPreprocessing.single_price(df2, 'FakeSPY')
assert_frame_equal(new_df1, expected1)
assert_frame_equal(new_df2, expected2)
def run_ESRNN():
import torch
device = 'cuda' if torch.cuda.is_available() else 'cpu'
path_daily = r'C:\Users\xxxli\Desktop\Daily'
dic_daily = preprocess.read_file(path_daily)
series_list = []
for k, v in dic_daily.items():
ticker_name = k
df, cat = v
df = preprocess.single_price(df, ticker_name) # column = [ticker]
series_list.append(DataSeries(cat, 'daily', df))
collect = DataCollection('universe daily', series_list)
train_dc, test_dc = collect.split(numTest = 24)
m = ModelESRNN( max_epochs = 15,
batch_size = 32, dilations=[[1,3], [7, 14]],
input_size = 12, output_size = 24,
device = device)
m.train(train_dc)
y_test = m.predict(test_dc)
y_test_df = y_test.to_df()
y_test_df.to_csv('hyper_ESRNN_1.csv')
def dc_generator(path: str, frequency: str):
dic, recover_list, ticker_list = DataPreprocessing.read_file(path)
series_list = []
for k, v in dic.items():
df, cat = v
df = DataPreprocessing.single_price(df, k)
series_list.append(DataSeries(cat, frequency, df))
collect = DataCollection(frequency + ' Collection', series_list)
return collect, recover_list, ticker_list
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# An example of how to use Telescope model
path_monthly = os.path.join('test', 'Data', 'Monthly')
dic_monthly = preprocess.read_file(path_monthly)
series_list = []
for k, v in dic_monthly.items():
df, cat = v
df = preprocess.single_price(df, k)
series_list.append(DataSeries(cat, 'monthly', df))
self.collect = DataCollection('test1', series_list)
def test_Naive2(self):
path_monthly = os.path.join('test', 'Data', 'Monthly')
dic_monthly = preprocess.read_file(path_monthly)
series_list = []
for k, v in dic_monthly.items():
df, cat = v
df = preprocess.single_price(df, k)
series_list.append(DataSeries(cat, 'monthly', df))
collect = DataCollection('test1', series_list)
train_dc, test_dc = collect.split(numTest=12)
m = ModelNaive2(12, train_dc, test_dc)
y_hat_Naive2_dc = m.fit_and_generate_prediction(12, freq='MS')
y_hat_Naive2_dc.to_df().to_csv('test_Naive2_result.csv')
def test_ESRNN(self):
# An example of how to use ESRNN
import torch
device = 'cuda' if torch.cuda.is_available() else 'cpu'
path_daily = os.path.join('test','Data','daily')
dic_daily = preprocess.read_file(path_daily)
series_list = []
for k, v in dic_daily.items():
df, cat = v
df = preprocess.single_price(df, k)
series_list.append(DataSeries(cat, 'daily', df))
collect = DataCollection('test1', series_list)
m = ModelESRNN(max_epochs = 5, seasonality = [], batch_size = 64, input_size = 12, output_size = 12, device = device)
train_dc, test_dc = collect.split(numTest = 12)
m.train(train_dc)
y_test = m.predict(test_dc)
assert(isinstance(y_test, DataCollection))
y_test_df = y_test.to_df()
y_test_df.to_csv('predict_result.csv')
learning_rate = 1e-2
lr_scheduler_step_size = 9
lr_decay = 0.9
noise_std = 0.001
level_variability_penalty = 80
state_hsize = 40
dilation = [[1]]
add_nl_layer = False
seasonality = [5]
# action
path = os.path.join('test', 'Data', 'Daily')
dic = preprocess.read_file(path)
series_list = []
for k, v in dic.items():
df, cat = v
df = preprocess.single_price(df, k)
series_list.append(DataSeries(cat, 'daily', df))
collect = DataCollection('RollingValidation', series_list)
input_dc, _ = collect.split(numTest=2 * numTest)
score, _ = validation_simple(
input_dc,
numTest=numTest,
max_epochs=max_epochs,
batch_size=batch_size,
learning_rate=learning_rate,
lr_scheduler_step_size=lr_scheduler_step_size,
lr_decay=lr_decay,
noise_std=noise_std,
level_variability_penalty=level_variability_penalty,
state_hsize=state_hsize,