def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
"""Adapt OHLCV columns into uint32 columns.
Parameters
----------
cols : dict
A dict mapping each column name (open, high, low, close, volume)
to a float column to convert to uint32.
scale_factor : int
Factor to use to scale float values before converting to uint32.
sid : int
Sid of the relevant asset, for logging.
invalid_data_behavior : str
Specifies behavior when data cannot be converted to uint32.
If 'raise', raises an exception.
If 'warn', logs a warning and filters out incompatible values.
If 'ignore', silently filters out incompatible values.
"""
scaled_opens = np.nan_to_num(cols['open']) * scale_factor
scaled_highs = np.nan_to_num(cols['high']) * scale_factor
scaled_lows = np.nan_to_num(cols['low']) * scale_factor
scaled_closes = np.nan_to_num(cols['close']) * scale_factor
exclude_mask = np.zeros_like(scaled_opens, dtype=bool)
for col_name, scaled_col in [
('open', scaled_opens),
('high', scaled_highs),
('low', scaled_lows),
('close', scaled_closes),
]:
max_val = scaled_col.max()
try:
check_uint32_safe(max_val, col_name)
except ValueError:
if invalid_data_behavior == 'raise':
raise
if invalid_data_behavior == 'warn':
logger.warn(
'Values for sid={}, col={} contain some too large for '
'uint32 (max={}), filtering them out',
sid,
col_name,
max_val,
)
# We want to exclude all rows that have an unsafe value in
# this column.
exclude_mask &= (scaled_col >= np.iinfo(np.uint32).max)
# Convert all cols to uint32.
opens = scaled_opens.astype(np.uint32)
highs = scaled_highs.astype(np.uint32)
lows = scaled_lows.astype(np.uint32)
closes = scaled_closes.astype(np.uint32)
volumes = cols['volume'].astype(np.uint32)
# Exclude rows with unsafe values by setting to zero.
opens[exclude_mask] = 0
highs[exclude_mask] = 0
lows[exclude_mask] = 0
closes[exclude_mask] = 0
volumes[exclude_mask] = 0
return opens, highs, lows, closes, volumes
def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
"""Adapt OHLCV columns into uint32 columns.
Parameters
----------
cols : dict
A dict mapping each column name (open, high, low, close, volume)
to a float column to convert to uint32.
scale_factor : int
Factor to use to scale float values before converting to uint32.
sid : int
Sid of the relevant asset, for logging.
invalid_data_behavior : str
Specifies behavior when data cannot be converted to uint32.
If 'raise', raises an exception.
If 'warn', logs a warning and filters out incompatible values.
If 'ignore', silently filters out incompatible values.
"""
scaled_opens = np.nan_to_num(cols['open']) * scale_factor
scaled_highs = np.nan_to_num(cols['high']) * scale_factor
scaled_lows = np.nan_to_num(cols['low']) * scale_factor
scaled_closes = np.nan_to_num(cols['close']) * scale_factor
exclude_mask = np.zeros_like(scaled_opens, dtype=bool)
for col_name, scaled_col in [
('open', scaled_opens),
('high', scaled_highs),
('low', scaled_lows),
('close', scaled_closes),
]:
max_val = scaled_col.max()
try:
check_uint32_safe(max_val, col_name)
except ValueError:
if invalid_data_behavior == 'raise':
raise
if invalid_data_behavior == 'warn':
logger.warn(
'Values for sid={}, col={} contain some too large for '
'uint32 (max={}), filtering them out',
sid, col_name, max_val,
)
# We want to exclude all rows that have an unsafe value in
# this column.
exclude_mask &= (scaled_col >= np.iinfo(np.uint32).max)
# Convert all cols to uint32.
opens = scaled_opens.astype(np.uint32)
highs = scaled_highs.astype(np.uint32)
lows = scaled_lows.astype(np.uint32)
closes = scaled_closes.astype(np.uint32)
volumes = cols['volume'].astype(np.uint32)
# Exclude rows with unsafe values by setting to zero.
opens[exclude_mask] = 0
highs[exclude_mask] = 0
lows[exclude_mask] = 0
closes[exclude_mask] = 0
volumes[exclude_mask] = 0
return opens, highs, lows, closes, volumes
