def load_pair_history(pair: str,
timeframe: str,
datadir: Path, *,
timerange: Optional[TimeRange] = None,
fill_up_missing: bool = True,
drop_incomplete: bool = True,
startup_candles: int = 0,
data_format: str = None,
data_handler: IDataHandler = None,
) -> DataFrame:
"""
Load cached ohlcv history for the given pair.
:param pair: Pair to load data for
:param timeframe: Timeframe (e.g. "5m")
:param datadir: Path to the data storage location.
:param data_format: Format of the data. Ignored if data_handler is set.
:param timerange: Limit data to be loaded to this timerange
:param fill_up_missing: Fill missing values with "No action"-candles
:param drop_incomplete: Drop last candle assuming it may be incomplete.
:param startup_candles: Additional candles to load at the start of the period
:param data_handler: Initialized data-handler to use.
Will be initialized from data_format if not set
:return: DataFrame with ohlcv data, or empty DataFrame
"""
data_handler = get_datahandler(datadir, data_format, data_handler)
return data_handler.ohlcv_load(pair=pair,
timeframe=timeframe,
timerange=timerange,
fill_missing=fill_up_missing,
drop_incomplete=drop_incomplete,
startup_candles=startup_candles,
)
def _load_cached_data_for_updating(pair: str, timeframe: str, timerange: Optional[TimeRange],
data_handler: IDataHandler) -> Tuple[DataFrame, Optional[int]]:
"""
Load cached data to download more data.
If timerange is passed in, checks whether data from an before the stored data will be
downloaded.
If that's the case then what's available should be completely overwritten.
Otherwise downloads always start at the end of the available data to avoid data gaps.
Note: Only used by download_pair_history().
"""
start = None
if timerange:
if timerange.starttype == 'date':
# TODO: convert to date for conversion
start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
# Intentionally don't pass timerange in - since we need to load the full dataset.
data = data_handler.ohlcv_load(pair, timeframe=timeframe,
timerange=None, fill_missing=False,
drop_incomplete=True, warn_no_data=False)
if not data.empty:
if start and start < data.iloc[0]['date']:
# Earlier data than existing data requested, redownload all
data = DataFrame(columns=DEFAULT_DATAFRAME_COLUMNS)
else:
start = data.iloc[-1]['date']
start_ms = int(start.timestamp() * 1000) if start else None
return data, start_ms