Skip to content

forecasting stock #187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
binhbinh22 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

forecasting stock #187

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
timellm/
__pycache__/
1 change: 1 addition & 0 deletions data_provider/data_factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
'ECL': Dataset_Custom,
'Traffic': Dataset_Custom,
'Weather': Dataset_Custom,
'custom': Dataset_Custom,
'm4': Dataset_M4,
}

Expand Down
88 changes: 45 additions & 43 deletions data_provider/data_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,7 @@

warnings.filterwarnings('ignore')


class Dataset_ETT_hour(Dataset):
class Dataset_Custom(Dataset):
def __init__(self, root_path, flag='train', size=None,
features='S', data_path='ETTh1.csv',
target='OT', scale=True, timeenc=0, freq='h', percent=100,
Expand All @@ -28,14 +27,13 @@ def __init__(self, root_path, flag='train', size=None,
type_map = {'train': 0, 'val': 1, 'test': 2}
self.set_type = type_map[flag]

self.percent = percent
self.features = features
self.target = target
self.scale = scale
self.timeenc = timeenc
self.freq = freq
self.percent = percent

# self.percent = percent
self.root_path = root_path
self.data_path = data_path
self.__read_data__()
Expand All @@ -48,9 +46,18 @@ def __read_data__(self):
df_raw = pd.read_csv(os.path.join(self.root_path,
self.data_path))

border1s = [0, 12 * 30 * 24 - self.seq_len, 12 * 30 * 24 + 4 * 30 * 24 - self.seq_len]
border2s = [12 * 30 * 24, 12 * 30 * 24 + 4 * 30 * 24, 12 * 30 * 24 + 8 * 30 * 24]

'''
df_raw.columns: ['Date', ...(other features), target feature]
'''
cols = list(df_raw.columns)
cols.remove(self.target)
cols.remove('Date')
df_raw = df_raw[['Date'] + cols + [self.target]]
num_train = int(len(df_raw) * 0.7)
num_test = int(len(df_raw) * 0.2)
num_vali = len(df_raw) - num_train - num_test
border1s = [0, num_train - self.seq_len, len(df_raw) - num_test - self.seq_len]
border2s = [num_train, num_train + num_vali, len(df_raw)]
border1 = border1s[self.set_type]
border2 = border2s[self.set_type]

Expand All @@ -70,23 +77,22 @@ def __read_data__(self):
else:
data = df_data.values

df_stamp = df_raw[['date']][border1:border2]
df_stamp['date'] = pd.to_datetime(df_stamp.date)
df_stamp = df_raw[['Date']][border1:border2]
df_stamp['Date'] = pd.to_datetime(df_stamp.Date)
if self.timeenc == 0:
df_stamp['month'] = df_stamp.date.apply(lambda row: row.month, 1)
df_stamp['day'] = df_stamp.date.apply(lambda row: row.day, 1)
df_stamp['weekday'] = df_stamp.date.apply(lambda row: row.weekday(), 1)
df_stamp['hour'] = df_stamp.date.apply(lambda row: row.hour, 1)
data_stamp = df_stamp.drop(['date'], 1).values
data_stamp = df_stamp.drop(['Date'], 1).values
elif self.timeenc == 1:
data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq)
data_stamp = time_features(pd.to_datetime(df_stamp['Date'].values), freq=self.freq)
data_stamp = data_stamp.transpose(1, 0)

self.data_x = data[border1:border2]
self.data_y = data[border1:border2]
self.data_stamp = data_stamp


def __getitem__(self, index):
feat_id = index // self.tot_len
s_begin = index % self.tot_len
Expand All @@ -108,10 +114,11 @@ def inverse_transform(self, data):
return self.scaler.inverse_transform(data)


class Dataset_ETT_minute(Dataset):

class Dataset_ETT_hour(Dataset):
def __init__(self, root_path, flag='train', size=None,
features='S', data_path='ETTm1.csv',
target='OT', scale=True, timeenc=0, freq='t', percent=100,
features='S', data_path='ETTh1.csv',
target='OT', scale=True, timeenc=0, freq='h', percent=100,
seasonal_patterns=None):
if size == None:
self.seq_len = 24 * 4 * 4
Expand All @@ -133,6 +140,7 @@ def __init__(self, root_path, flag='train', size=None,
self.timeenc = timeenc
self.freq = freq

# self.percent = percent
self.root_path = root_path
self.data_path = data_path
self.__read_data__()
Expand All @@ -145,8 +153,8 @@ def __read_data__(self):
df_raw = pd.read_csv(os.path.join(self.root_path,
self.data_path))

border1s = [0, 12 * 30 * 24 * 4 - self.seq_len, 12 * 30 * 24 * 4 + 4 * 30 * 24 * 4 - self.seq_len]
border2s = [12 * 30 * 24 * 4, 12 * 30 * 24 * 4 + 4 * 30 * 24 * 4, 12 * 30 * 24 * 4 + 8 * 30 * 24 * 4]
border1s = [0, 12 * 30 * 24 - self.seq_len, 12 * 30 * 24 + 4 * 30 * 24 - self.seq_len]
border2s = [12 * 30 * 24, 12 * 30 * 24 + 4 * 30 * 24, 12 * 30 * 24 + 8 * 30 * 24]

border1 = border1s[self.set_type]
border2 = border2s[self.set_type]
Expand All @@ -167,24 +175,23 @@ def __read_data__(self):
else:
data = df_data.values

df_stamp = df_raw[['date']][border1:border2]
df_stamp['date'] = pd.to_datetime(df_stamp.date)
df_stamp = df_raw[['Date']][border1:border2]
df_stamp['Date'] = pd.to_datetime(df_stamp.date)
if self.timeenc == 0:
df_stamp['month'] = df_stamp.date.apply(lambda row: row.month, 1)
df_stamp['day'] = df_stamp.date.apply(lambda row: row.day, 1)
df_stamp['weekday'] = df_stamp.date.apply(lambda row: row.weekday(), 1)
df_stamp['hour'] = df_stamp.date.apply(lambda row: row.hour, 1)
df_stamp['minute'] = df_stamp.date.apply(lambda row: row.minute, 1)
df_stamp['minute'] = df_stamp.minute.map(lambda x: x // 15)
data_stamp = df_stamp.drop(['date'], 1).values
data_stamp = df_stamp.drop(['Date'], 1).values
elif self.timeenc == 1:
data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq)
data_stamp = time_features(pd.to_datetime(df_stamp['Date'].values), freq=self.freq)
data_stamp = data_stamp.transpose(1, 0)

self.data_x = data[border1:border2]
self.data_y = data[border1:border2]
self.data_stamp = data_stamp


def __getitem__(self, index):
feat_id = index // self.tot_len
s_begin = index % self.tot_len
Expand All @@ -206,10 +213,10 @@ def inverse_transform(self, data):
return self.scaler.inverse_transform(data)


class Dataset_Custom(Dataset):
class Dataset_ETT_minute(Dataset):
def __init__(self, root_path, flag='train', size=None,
features='S', data_path='ETTh1.csv',
target='OT', scale=True, timeenc=0, freq='h', percent=100,
features='S', data_path='ETTm1.csv',
target='OT', scale=True, timeenc=0, freq='t', percent=100,
seasonal_patterns=None):
if size == None:
self.seq_len = 24 * 4 * 4
Expand All @@ -224,12 +231,12 @@ def __init__(self, root_path, flag='train', size=None,
type_map = {'train': 0, 'val': 1, 'test': 2}
self.set_type = type_map[flag]

self.percent = percent
self.features = features
self.target = target
self.scale = scale
self.timeenc = timeenc
self.freq = freq
self.percent = percent

self.root_path = root_path
self.data_path = data_path
Expand All @@ -243,18 +250,9 @@ def __read_data__(self):
df_raw = pd.read_csv(os.path.join(self.root_path,
self.data_path))

'''
df_raw.columns: ['date', ...(other features), target feature]
'''
cols = list(df_raw.columns)
cols.remove(self.target)
cols.remove('date')
df_raw = df_raw[['date'] + cols + [self.target]]
num_train = int(len(df_raw) * 0.7)
num_test = int(len(df_raw) * 0.2)
num_vali = len(df_raw) - num_train - num_test
border1s = [0, num_train - self.seq_len, len(df_raw) - num_test - self.seq_len]
border2s = [num_train, num_train + num_vali, len(df_raw)]
border1s = [0, 12 * 30 * 24 * 4 - self.seq_len, 12 * 30 * 24 * 4 + 4 * 30 * 24 * 4 - self.seq_len]
border2s = [12 * 30 * 24 * 4, 12 * 30 * 24 * 4 + 4 * 30 * 24 * 4, 12 * 30 * 24 * 4 + 8 * 30 * 24 * 4]

border1 = border1s[self.set_type]
border2 = border2s[self.set_type]

Expand All @@ -274,16 +272,18 @@ def __read_data__(self):
else:
data = df_data.values

df_stamp = df_raw[['date']][border1:border2]
df_stamp['date'] = pd.to_datetime(df_stamp.date)
df_stamp = df_raw[['Date']][border1:border2]
df_stamp['Date'] = pd.to_datetime(df_stamp.date)
if self.timeenc == 0:
df_stamp['month'] = df_stamp.date.apply(lambda row: row.month, 1)
df_stamp['day'] = df_stamp.date.apply(lambda row: row.day, 1)
df_stamp['weekday'] = df_stamp.date.apply(lambda row: row.weekday(), 1)
df_stamp['hour'] = df_stamp.date.apply(lambda row: row.hour, 1)
data_stamp = df_stamp.drop(['date'], 1).values
df_stamp['minute'] = df_stamp.date.apply(lambda row: row.minute, 1)
df_stamp['minute'] = df_stamp.minute.map(lambda x: x // 15)
data_stamp = df_stamp.drop(['Date'], 1).values
elif self.timeenc == 1:
data_stamp = time_features(pd.to_datetime(df_stamp['date'].values), freq=self.freq)
data_stamp = time_features(pd.to_datetime(df_stamp['Date'].values), freq=self.freq)
data_stamp = data_stamp.transpose(1, 0)

self.data_x = data[border1:border2]
Expand Down Expand Up @@ -311,6 +311,8 @@ def inverse_transform(self, data):
return self.scaler.inverse_transform(data)




class Dataset_M4(Dataset):
def __init__(self, root_path, flag='pred', size=None,
features='S', data_path='ETTh1.csv',
Expand Down
Loading