stable/freqtrade/data/history/jsondatahandler.py

182 lines
7.1 KiB
Python
Raw Normal View History

import logging
import re
from pathlib import Path
from typing import List, Optional
import numpy as np
from pandas import DataFrame, read_json, to_datetime
from freqtrade import misc
from freqtrade.configuration import TimeRange
2022-08-19 11:44:39 +00:00
from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS, TradeList
2020-03-31 18:46:42 +00:00
from freqtrade.data.converter import trades_dict_to_list
2022-08-19 11:44:39 +00:00
from freqtrade.enums import CandleType
from .idatahandler import IDataHandler
2020-09-28 17:39:41 +00:00
logger = logging.getLogger(__name__)
class JsonDataHandler(IDataHandler):
_use_zip = False
_columns = DEFAULT_DATAFRAME_COLUMNS
@classmethod
2021-12-07 19:30:58 +00:00
def ohlcv_get_pairs(cls, datadir: Path, timeframe: str, candle_type: CandleType) -> List[str]:
"""
2019-12-25 18:53:52 +00:00
Returns a list of all pairs with ohlcv data available in this datadir
for the specified timeframe
:param datadir: Directory to search for ohlcv files
:param timeframe: Timeframe to search pairs for
2021-12-03 11:23:35 +00:00
:param candle_type: Any of the enum CandleType (must match trading mode!)
2019-12-25 18:53:52 +00:00
:return: List of Pairs
"""
2021-12-03 11:12:33 +00:00
candle = ""
2021-12-08 13:35:15 +00:00
if candle_type != CandleType.SPOT:
datadir = datadir.joinpath('futures')
2021-12-03 11:12:33 +00:00
candle = f"-{candle_type}"
2019-12-25 09:21:30 +00:00
2021-12-03 11:12:33 +00:00
_tmp = [re.search(r'^(\S+)(?=\-' + timeframe + candle + '.json)', p.name)
for p in datadir.glob(f"*{timeframe}{candle}.{cls._get_file_extension()}")]
2019-12-25 09:21:30 +00:00
# Check if regex found something and only return these results
return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
def ohlcv_store(
2021-12-07 19:30:58 +00:00
self, pair: str, timeframe: str, data: DataFrame, candle_type: CandleType) -> None:
"""
Store data in json format "values".
format looks as follows:
[[<date>,<open>,<high>,<low>,<close>]]
:param pair: Pair - used to generate filename
2021-06-25 17:13:31 +00:00
:param timeframe: Timeframe - used to generate filename
:param data: Dataframe containing OHLCV data
2021-12-03 11:23:35 +00:00
:param candle_type: Any of the enum CandleType (must match trading mode!)
:return: None
"""
2022-05-16 17:53:01 +00:00
filename = self._pair_data_filename(self._datadir, pair, timeframe, candle_type)
self.create_dir_if_needed(filename)
_data = data.copy()
# Convert date to int
_data['date'] = _data['date'].view(np.int64) // 1000 // 1000
# Reset index, select only appropriate columns and save as json
_data.reset_index(drop=True).loc[:, self._columns].to_json(
filename, orient="values",
compression='gzip' if self._use_zip else None)
def _ohlcv_load(self, pair: str, timeframe: str,
2021-12-07 19:30:58 +00:00
timerange: Optional[TimeRange], candle_type: CandleType
) -> DataFrame:
"""
2019-12-25 14:07:49 +00:00
Internal method used to load data for one pair from disk.
Implements the loading and conversion to a Pandas dataframe.
Timerange trimming and dataframe validation happens outside of this method.
2019-12-25 18:53:52 +00:00
:param pair: Pair to load data
:param timeframe: Timeframe (e.g. "5m")
:param timerange: Limit data to be loaded to this timerange.
Optionally implemented by subclasses to avoid loading
all data where possible.
2021-12-03 11:23:35 +00:00
:param candle_type: Any of the enum CandleType (must match trading mode!)
2019-12-25 14:07:49 +00:00
:return: DataFrame with ohlcv data, or empty DataFrame
"""
filename = self._pair_data_filename(
2022-05-16 17:53:01 +00:00
self._datadir, pair, timeframe, candle_type=candle_type)
2019-12-27 10:08:47 +00:00
if not filename.exists():
# Fallback mode for 1M files
filename = self._pair_data_filename(
2022-05-16 17:53:01 +00:00
self._datadir, pair, timeframe, candle_type=candle_type, no_timeframe_modify=True)
if not filename.exists():
return DataFrame(columns=self._columns)
try:
pairdata = read_json(filename, orient='values')
pairdata.columns = self._columns
except ValueError:
logger.error(f"Could not load data for {pair}.")
return DataFrame(columns=self._columns)
pairdata = pairdata.astype(dtype={'open': 'float', 'high': 'float',
2020-02-22 16:46:40 +00:00
'low': 'float', 'close': 'float', 'volume': 'float'})
pairdata['date'] = to_datetime(pairdata['date'],
unit='ms',
utc=True,
infer_datetime_format=True)
return pairdata
def ohlcv_append(
self,
pair: str,
timeframe: str,
data: DataFrame,
2021-12-03 11:23:35 +00:00
candle_type: CandleType
) -> None:
"""
Append data to existing data structures
:param pair: Pair
:param timeframe: Timeframe this ohlcv data is for
:param data: Data to append.
2021-12-03 11:23:35 +00:00
:param candle_type: Any of the enum CandleType (must match trading mode!)
"""
raise NotImplementedError()
@classmethod
def trades_get_pairs(cls, datadir: Path) -> List[str]:
"""
2019-12-25 18:53:52 +00:00
Returns a list of all pairs for which trade data is available in this
:param datadir: Directory to search for ohlcv files
:return: List of Pairs
"""
2019-12-25 09:21:30 +00:00
_tmp = [re.search(r'^(\S+)(?=\-trades.json)', p.name)
for p in datadir.glob(f"*trades.{cls._get_file_extension()}")]
2019-12-25 09:21:30 +00:00
# Check if regex found something and only return these results to avoid exceptions.
return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
def trades_store(self, pair: str, data: TradeList) -> None:
"""
2019-12-25 18:53:52 +00:00
Store trades data (list of Dicts) to file
:param pair: Pair - used for filename
:param data: List of Lists containing trade data,
column sequence as in DEFAULT_TRADES_COLUMNS
"""
filename = self._pair_trades_filename(self._datadir, pair)
misc.file_dump_json(filename, data, is_zip=self._use_zip)
def trades_append(self, pair: str, data: TradeList):
"""
Append data to existing files
2019-12-25 18:53:52 +00:00
:param pair: Pair - used for filename
:param data: List of Lists containing trade data,
column sequence as in DEFAULT_TRADES_COLUMNS
"""
raise NotImplementedError()
2020-04-01 05:58:39 +00:00
def _trades_load(self, pair: str, timerange: Optional[TimeRange] = None) -> TradeList:
"""
Load a pair from file, either .json.gz or .json
2019-12-25 18:53:52 +00:00
# TODO: respect timerange ...
:param pair: Load trades for this pair
:param timerange: Timerange to load trades for - currently not implemented
:return: List of trades
"""
filename = self._pair_trades_filename(self._datadir, pair)
tradesdata = misc.file_load_json(filename)
if not tradesdata:
return []
if isinstance(tradesdata[0], dict):
# Convert trades dict to list
logger.info("Old trades format detected - converting")
tradesdata = trades_dict_to_list(tradesdata)
pass
return tradesdata
@classmethod
def _get_file_extension(cls):
return "json.gz" if cls._use_zip else "json"
class JsonGzDataHandler(JsonDataHandler):
_use_zip = True