def __init__(self,
file_path,
metric,
num_prev_bars=3,
exp_num_ticks_init=100000,
batch_size=2e7):
"""
Constructor
:param file_path: (String) Path to the csv file containing raw tick data in the format[date_time, price, volume]
:param metric: (String) type of imbalance bar to create. Example: "dollar_imbalance"
:param num_prev_bars: (Int) Window size for E[T]
:param exp_num_ticks_init: (Int) Initial number of expected ticks
:param batch_size: (Int) Number of rows to read in from the csv, per batch
"""
BaseBars.__init__(self, file_path, metric, batch_size)
# Information bar properties
self.exp_num_ticks_init = exp_num_ticks_init
# Expected number of ticks extracted from prev bars
self.exp_num_ticks = self.exp_num_ticks_init
self.num_prev_bars = num_prev_bars
self.num_ticks_bar = [] # List of number of ticks from previous bars
# Named tuple to help with storing the cache
self.cache_tuple = namedtuple('CacheData', [
'date_time', 'price', 'high', 'low', 'cum_ticks', 'cum_volume',
'cum_theta_buy', 'cum_theta_sell'
])
self.imbalance_array = {'buy': [], 'sell': []}
self.exp_buy_proportion, self.exp_sell_proportion = np.nan, np.nan
def __init__(self, file_path_or_df: Tuple[str, pd.DataFrame], metric: str, threshold: int = 50000,
batch_size: int = 20000000):
BaseBars.__init__(self, file_path_or_df, metric, batch_size)
# Threshold at which to sample
self.threshold = threshold
def __init__(self,
resolution: str,
num_units: int,
batch_size: int = 20000000):
"""
Constructor
:param resolution: (str) Type of bar resolution: ['D', 'H', 'MIN', 'S']
:param num_units: (int) Number of days, minutes, etc.
:param batch_size: (int) Number of rows to read in from the csv, per batch
"""
BaseBars.__init__(self, metric=None, batch_size=batch_size)
# Threshold at which to sample (in seconds)
self.time_bar_thresh_mapping = {
'D': 86400,
'H': 3600,
'MIN': 60,
'S': 1
} # Number of seconds
assert resolution in self.time_bar_thresh_mapping, "{} resolution is not implemented".format(
resolution)
self.resolution = resolution # Type of bar resolution: 'D', 'H', 'MIN', 'S'
self.num_units = num_units # Number of days/minutes/...
self.threshold = self.num_units * self.time_bar_thresh_mapping[
self.resolution]
self.timestamp = None # Current bar timestamp
def __init__(self, file_path_or_df, resolution, num_units, batch_size=20000000):
BaseBars.__init__(self, file_path_or_df, metric=None, batch_size=batch_size)
# Threshold at which to sample (in seconds)
self.resolution = resolution # Type of bar resolution: 'D', 'H', 'MIN', 'S'
self.num_units = num_units # Number of days/minutes/...
self.time_bar_thresh_mapping = {'D': 86400, 'H': 3600, 'MIN': 60, 'S': 1} # Number of seconds
self.threshold = self.num_units * self.time_bar_thresh_mapping[self.resolution]
self.timestamp = None # Next bar timestamp
def __init__(self, resolution: str, num_units: int, batch_size: int = 20000000):
BaseBars.__init__(self, metric=None, batch_size=batch_size)
# Threshold at which to sample (in seconds)
self.time_bar_thresh_mapping = {'D': 86400, 'H': 3600, 'MIN': 60, 'S': 1} # Number of seconds
assert resolution in self.time_bar_thresh_mapping, "{} resolution is not implemented".format(resolution)
self.resolution = resolution # Type of bar resolution: 'D', 'H', 'MIN', 'S'
self.num_units = num_units # Number of days/minutes/...
self.threshold = self.num_units * self.time_bar_thresh_mapping[self.resolution]
self.timestamp = None # Current bar timestamp
def __init__(self,
metric: str,
threshold: int = 50000,
batch_size: int = 20000000):
"""
Constructor
:param metric: (str) Type of run bar to create. Example: "dollar_run"
:param threshold: (int) Threshold at which to sample
:param batch_size: (int) Number of rows to read in from the csv, per batch
"""
BaseBars.__init__(self, metric, batch_size)
# Threshold at which to sample
self.threshold = threshold
def __init__(self,
file_path,
metric,
threshold=50000,
batch_size=20000000):
BaseBars.__init__(self, file_path, metric, batch_size)
# Threshold at which to sample
self.threshold = threshold
# Named tuple to help with the cache
self.cache_tuple = namedtuple('CacheData', [
'date_time', 'price', 'high', 'low', 'cum_ticks', 'cum_volume',
'cum_dollar'
])
def __init__(self, metric: str, threshold: int = 50000, batch_size: int = 20000000):
BaseBars.__init__(self, metric, batch_size)
# Threshold at which to sample
self.threshold = threshold