adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #2719 from xmatthias/data_handler

Browse Source 
Introduce Data handler
This commit is contained in:
hroff-1902
2020-02-19 21:22:08 +03:00
committed by GitHub
parent 2d2fd968c8 29b369c65e
commit f2f2c281c0
27 changed files with 1282 additions and 522 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
freqtrade/commands/__init__.py
View File

@@ -8,7 +8,8 @@ Note: Be careful with file-scoped imports in these subfiles.
"""
from freqtrade.commands.arguments import Arguments
from freqtrade.commands.build_config_commands import start_new_config
from freqtrade.commands.data_commands import start_download_data
from freqtrade.commands.data_commands import (start_convert_data,
start_download_data)
from freqtrade.commands.deploy_commands import (start_create_userdir,
start_new_hyperopt,
start_new_strategy)

31
freqtrade/commands/arguments.py
View File

@@ -51,8 +51,11 @@ ARGS_BUILD_STRATEGY = ["user_data_dir", "strategy", "template"]
ARGS_BUILD_HYPEROPT = ["user_data_dir", "hyperopt", "template"]
ARGS_CONVERT_DATA = ["pairs", "format_from", "format_to", "erase"]
ARGS_CONVERT_DATA_OHLCV = ARGS_CONVERT_DATA + ["timeframes"]
ARGS_DOWNLOAD_DATA = ["pairs", "pairs_file", "days", "download_trades", "exchange",
"timeframes", "erase"]
"timeframes", "erase", "dataformat_ohlcv", "dataformat_trades"]
ARGS_PLOT_DATAFRAME = ["pairs", "indicators1", "indicators2", "plot_limit",
"db_url", "trade_source", "export", "exportfilename",
@@ -71,8 +74,9 @@ ARGS_HYPEROPT_LIST = ["hyperopt_list_best", "hyperopt_list_profitable",
ARGS_HYPEROPT_SHOW = ["hyperopt_list_best", "hyperopt_list_profitable", "hyperopt_show_index",
"print_json", "hyperopt_show_no_header"]
NO_CONF_REQURIED = ["download-data", "list-timeframes", "list-markets", "list-pairs",
"list-strategies", "list-hyperopts", "hyperopt-list", "hyperopt-show",
NO_CONF_REQURIED = ["convert-data", "convert-trade-data", "download-data", "list-timeframes",
"list-markets", "list-pairs", "list-strategies",
"list-hyperopts", "hyperopt-list", "hyperopt-show",
"plot-dataframe", "plot-profit"]
NO_CONF_ALLOWED = ["create-userdir", "list-exchanges", "new-hyperopt", "new-strategy"]
@@ -151,7 +155,8 @@ class Arguments:
self.parser = argparse.ArgumentParser(description='Free, open source crypto trading bot')
self._build_args(optionlist=['version'], parser=self.parser)
from freqtrade.commands import (start_create_userdir, start_download_data,
from freqtrade.commands import (start_create_userdir, start_convert_data,
start_download_data,
start_hyperopt_list, start_hyperopt_show,
start_list_exchanges, start_list_hyperopts,
start_list_markets, start_list_strategies,
@@ -288,6 +293,24 @@ class Arguments:
download_data_cmd.set_defaults(func=start_download_data)
self._build_args(optionlist=ARGS_DOWNLOAD_DATA, parser=download_data_cmd)
# Add convert-data subcommand
convert_data_cmd = subparsers.add_parser(
'convert-data',
help='Convert OHLCV data from one format to another.',
parents=[_common_parser],
)
convert_data_cmd.set_defaults(func=partial(start_convert_data, ohlcv=True))
self._build_args(optionlist=ARGS_CONVERT_DATA_OHLCV, parser=convert_data_cmd)
# Add convert-trade-data subcommand
convert_trade_data_cmd = subparsers.add_parser(
'convert-trade-data',
help='Convert trade-data from one format to another.',
parents=[_common_parser],
)
convert_trade_data_cmd.set_defaults(func=partial(start_convert_data, ohlcv=False))
self._build_args(optionlist=ARGS_CONVERT_DATA, parser=convert_trade_data_cmd)
# Add Plotting subcommand
plot_dataframe_cmd = subparsers.add_parser(
'plot-dataframe',

24
freqtrade/commands/cli_options.py
View File

@@ -333,6 +333,30 @@ AVAILABLE_CLI_OPTIONS = {
'desired timeframe as specified as --timeframes/-t.',
action='store_true',
),
"format_from": Arg(
'--format-from',
help='Source format for data conversion.',
choices=constants.AVAILABLE_DATAHANDLERS,
required=True,
),
"format_to": Arg(
'--format-to',
help='Destination format for data conversion.',
choices=constants.AVAILABLE_DATAHANDLERS,
required=True,
),
"dataformat_ohlcv": Arg(
'--data-format-ohlcv',
help='Storage format for downloaded ohlcv data. (default: `%(default)s`).',
choices=constants.AVAILABLE_DATAHANDLERS,
default='json'
),
"dataformat_trades": Arg(
'--data-format-trades',
help='Storage format for downloaded trades data. (default: `%(default)s`).',
choices=constants.AVAILABLE_DATAHANDLERS,
default='jsongz'
),
"exchange": Arg(
'--exchange',
help=f'Exchange name (default: `{constants.DEFAULT_EXCHANGE}`). '

30
freqtrade/commands/data_commands.py
View File

@@ -5,6 +5,8 @@ from typing import Any, Dict, List
import arrow
from freqtrade.configuration import TimeRange, setup_utils_configuration
from freqtrade.data.converter import (convert_ohlcv_format,
convert_trades_format)
from freqtrade.data.history import (convert_trades_to_ohlcv,
refresh_backtest_ohlcv_data,
refresh_backtest_trades_data)
@@ -48,18 +50,21 @@ def start_download_data(args: Dict[str, Any]) -> None:
if config.get('download_trades'):
pairs_not_available = refresh_backtest_trades_data(
exchange, pairs=config["pairs"], datadir=config['datadir'],
timerange=timerange, erase=bool(config.get("erase")))
timerange=timerange, erase=bool(config.get("erase")),
data_format=config['dataformat_trades'])
# Convert downloaded trade data to different timeframes
convert_trades_to_ohlcv(
pairs=config["pairs"], timeframes=config["timeframes"],
datadir=config['datadir'], timerange=timerange,
erase=bool(config.get("erase")))
datadir=config['datadir'], timerange=timerange, erase=bool(config.get("erase")),
data_format_ohlcv=config['dataformat_ohlcv'],
data_format_trades=config['dataformat_trades'],
)
else:
pairs_not_available = refresh_backtest_ohlcv_data(
exchange, pairs=config["pairs"], timeframes=config["timeframes"],
datadir=config['datadir'], timerange=timerange,
erase=bool(config.get("erase")))
datadir=config['datadir'], timerange=timerange, erase=bool(config.get("erase")),
data_format=config['dataformat_ohlcv'])
except KeyboardInterrupt:
sys.exit("SIGINT received, aborting ...")
@@ -68,3 +73,18 @@ def start_download_data(args: Dict[str, Any]) -> None:
if pairs_not_available:
logger.info(f"Pairs [{','.join(pairs_not_available)}] not available "
f"on exchange {exchange.name}.")
def start_convert_data(args: Dict[str, Any], ohlcv: bool = True) -> None:
"""
Convert data from one format to another
"""
config = setup_utils_configuration(args, RunMode.UTIL_NO_EXCHANGE)
if ohlcv:
convert_ohlcv_format(config,
convert_from=args['format_from'], convert_to=args['format_to'],
erase=args['erase'])
else:
convert_trades_format(config,
convert_from=args['format_from'], convert_to=args['format_to'],
erase=args['erase'])

7
freqtrade/configuration/configuration.py
View File

@@ -364,9 +364,16 @@ class Configuration:
self._args_to_config(config, argname='days',
logstring='Detected --days: {}')
self._args_to_config(config, argname='download_trades',
logstring='Detected --dl-trades: {}')
self._args_to_config(config, argname='dataformat_ohlcv',
logstring='Using "{}" to store OHLCV data.')
self._args_to_config(config, argname='dataformat_trades',
logstring='Using "{}" to store trades data.')
def _process_runmode(self, config: Dict[str, Any]) -> None:
if not self.runmode:

18
freqtrade/constants.py
View File

@@ -19,8 +19,10 @@ ORDERTYPE_POSSIBILITIES = ['limit', 'market']
ORDERTIF_POSSIBILITIES = ['gtc', 'fok', 'ioc']
AVAILABLE_PAIRLISTS = ['StaticPairList', 'VolumePairList',
'PrecisionFilter', 'PriceFilter', 'SpreadFilter']
AVAILABLE_DATAHANDLERS = ['json', 'jsongz']
DRY_RUN_WALLET = 1000
MATH_CLOSE_PREC = 1e-14 # Precision used for float comparisons
DEFAULT_DATAFRAME_COLUMNS = ['date', 'open', 'high', 'low', 'close', 'volume']
USERPATH_HYPEROPTS = 'hyperopts'
USERPATH_STRATEGIES = 'strategies'
@@ -217,11 +219,22 @@ CONF_SCHEMA = {
'forcebuy_enable': {'type': 'boolean'},
'internals': {
'type': 'object',
'default': {},
'properties': {
'process_throttle_secs': {'type': 'integer'},
'interval': {'type': 'integer'},
'sd_notify': {'type': 'boolean'},
}
},
'dataformat_ohlcv': {
'type': 'string',
'enum': AVAILABLE_DATAHANDLERS,
'default': 'json'
},
'dataformat_trades': {
'type': 'string',
'enum': AVAILABLE_DATAHANDLERS,
'default': 'jsongz'
}
},
'definitions': {
@@ -292,9 +305,14 @@ SCHEMA_TRADE_REQUIRED = [
'unfilledtimeout',
'stoploss',
'minimal_roi',
'internals',
'dataformat_ohlcv',
'dataformat_trades',
]
SCHEMA_MINIMAL_REQUIRED = [
'exchange',
'dry_run',
'dataformat_ohlcv',
'dataformat_trades',
]

122
freqtrade/data/converter.py
View File

@@ -2,10 +2,13 @@
Functions to convert data from one format to another
"""
import logging
from datetime import datetime, timezone
from typing import Any, Dict
import pandas as pd
from pandas import DataFrame, to_datetime
from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS
logger = logging.getLogger(__name__)
@@ -24,7 +27,7 @@ def parse_ticker_dataframe(ticker: list, timeframe: str, pair: str, *,
:return: DataFrame
"""
logger.debug("Parsing tickerlist to dataframe")
cols = ['date', 'open', 'high', 'low', 'close', 'volume']
cols = DEFAULT_DATAFRAME_COLUMNS
frame = DataFrame(ticker, columns=cols)
frame['date'] = to_datetime(frame['date'],
@@ -37,9 +40,29 @@ def parse_ticker_dataframe(ticker: list, timeframe: str, pair: str, *,
# and fail with exception...
frame = frame.astype(dtype={'open': 'float', 'high': 'float', 'low': 'float', 'close': 'float',
'volume': 'float'})
return clean_ohlcv_dataframe(frame, timeframe, pair,
fill_missing=fill_missing,
drop_incomplete=drop_incomplete)
def clean_ohlcv_dataframe(data: DataFrame, timeframe: str, pair: str, *,
fill_missing: bool = True,
drop_incomplete: bool = True) -> DataFrame:
"""
Clense a ohlcv dataframe by
* Grouping it by date (removes duplicate tics)
* dropping last candles if requested
* Filling up missing data (if requested)
:param data: DataFrame containing ohlcv data.
:param timeframe: timeframe (e.g. 5m). Used to fill up eventual missing data
:param pair: Pair this data is for (used to warn if fillup was necessary)
:param fill_missing: fill up missing candles with 0 candles
(see ohlcv_fill_up_missing_data for details)
:param drop_incomplete: Drop the last candle of the dataframe, assuming it's incomplete
:return: DataFrame
"""
# group by index and aggregate results to eliminate duplicate ticks
frame = frame.groupby(by='date', as_index=False, sort=True).agg({
data = data.groupby(by='date', as_index=False, sort=True).agg({
'open': 'first',
'high': 'max',
'low': 'min',
@@ -48,13 +71,13 @@ def parse_ticker_dataframe(ticker: list, timeframe: str, pair: str, *,
})
# eliminate partial candle
if drop_incomplete:
frame.drop(frame.tail(1).index, inplace=True)
data.drop(data.tail(1).index, inplace=True)
logger.debug('Dropping last candle')
if fill_missing:
return ohlcv_fill_up_missing_data(frame, timeframe, pair)
return ohlcv_fill_up_missing_data(data, timeframe, pair)
else:
return frame
return data
def ohlcv_fill_up_missing_data(dataframe: DataFrame, timeframe: str, pair: str) -> DataFrame:
@@ -92,8 +115,26 @@ def ohlcv_fill_up_missing_data(dataframe: DataFrame, timeframe: str, pair: str)
return df
def trim_dataframe(df: DataFrame, timerange, df_date_col: str = 'date') -> DataFrame:
"""
Trim dataframe based on given timerange
:param df: Dataframe to trim
:param timerange: timerange (use start and end date if available)
:param: df_date_col: Column in the dataframe to use as Date column
:return: trimmed dataframe
"""
if timerange.starttype == 'date':
start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
df = df.loc[df[df_date_col] >= start, :]
if timerange.stoptype == 'date':
stop = datetime.fromtimestamp(timerange.stopts, tz=timezone.utc)
df = df.loc[df[df_date_col] <= stop, :]
return df
def order_book_to_dataframe(bids: list, asks: list) -> DataFrame:
"""
TODO: This should get a dedicated test
Gets order book list, returns dataframe with below format per suggested by creslin
-------------------------------------------------------------------
b_sum b_size bids asks a_size a_sum
@@ -116,12 +157,13 @@ def order_book_to_dataframe(bids: list, asks: list) -> DataFrame:
return frame
def trades_to_ohlcv(trades: list, timeframe: str) -> list:
def trades_to_ohlcv(trades: list, timeframe: str) -> DataFrame:
"""
Converts trades list to ohlcv list
TODO: This should get a dedicated test
:param trades: List of trades, as returned by ccxt.fetch_trades.
:param timeframe: Ticker timeframe to resample data to
:return: ohlcv timeframe as list (as returned by ccxt.fetch_ohlcv)
:return: ohlcv Dataframe.
"""
from freqtrade.exchange import timeframe_to_minutes
ticker_minutes = timeframe_to_minutes(timeframe)
@@ -131,8 +173,68 @@ def trades_to_ohlcv(trades: list, timeframe: str) -> list:
df_new = df['price'].resample(f'{ticker_minutes}min').ohlc()
df_new['volume'] = df['amount'].resample(f'{ticker_minutes}min').sum()
df_new['date'] = df_new.index.astype("int64") // 10 ** 6
df_new['date'] = df_new.index
# Drop 0 volume rows
df_new = df_new.dropna()
columns = ["date", "open", "high", "low", "close", "volume"]
return list(zip(*[df_new[x].values.tolist() for x in columns]))
return df_new[DEFAULT_DATAFRAME_COLUMNS]
def convert_trades_format(config: Dict[str, Any], convert_from: str, convert_to: str, erase: bool):
"""
Convert trades from one format to another format.
:param config: Config dictionary
:param convert_from: Source format
:param convert_to: Target format
:param erase: Erase souce data (does not apply if source and target format are identical)
"""
from freqtrade.data.history.idatahandler import get_datahandler
src = get_datahandler(config['datadir'], convert_from)
trg = get_datahandler(config['datadir'], convert_to)
if 'pairs' not in config:
config['pairs'] = src.trades_get_pairs(config['datadir'])
logger.info(f"Converting trades for {config['pairs']}")
for pair in config['pairs']:
data = src.trades_load(pair=pair)
logger.info(f"Converting {len(data)} trades for {pair}")
trg.trades_store(pair, data)
if erase and convert_from != convert_to:
logger.info(f"Deleting source Trade data for {pair}.")
src.trades_purge(pair=pair)
def convert_ohlcv_format(config: Dict[str, Any], convert_from: str, convert_to: str, erase: bool):
"""
Convert ohlcv from one format to another format.
:param config: Config dictionary
:param convert_from: Source format
:param convert_to: Target format
:param erase: Erase souce data (does not apply if source and target format are identical)
"""
from freqtrade.data.history.idatahandler import get_datahandler
src = get_datahandler(config['datadir'], convert_from)
trg = get_datahandler(config['datadir'], convert_to)
timeframes = config.get('timeframes', [config.get('ticker_interval')])
logger.info(f"Converting OHLCV for timeframe {timeframes}")
if 'pairs' not in config:
config['pairs'] = []
# Check timeframes or fall back to ticker_interval.
for timeframe in timeframes:
config['pairs'].extend(src.ohlcv_get_pairs(config['datadir'],
timeframe))
logger.info(f"Converting OHLCV for {config['pairs']}")
for timeframe in timeframes:
for pair in config['pairs']:
data = src.ohlcv_load(pair=pair, timeframe=timeframe,
timerange=None,
fill_missing=False,
drop_incomplete=False,
startup_candles=0)
logger.info(f"Converting {len(data)} candles for {pair}")
trg.ohlcv_store(pair=pair, timeframe=timeframe, data=data)
if erase and convert_from != convert_to:
logger.info(f"Deleting source data for {pair} / {timeframe}")
src.ohlcv_purge(pair=pair, timeframe=timeframe)

14
freqtrade/data/history/__init__.py Normal file
View File

@@ -0,0 +1,14 @@
"""
Handle historic data (ohlcv).
Includes:
* load data for a pair (or a list of pairs) from disk
* download data from exchange and store to disk
"""
from .history_utils import (convert_trades_to_ohlcv, # noqa: F401
get_timerange, load_data, load_pair_history,
refresh_backtest_ohlcv_data,
refresh_backtest_trades_data, refresh_data,
validate_backtest_data)
from .idatahandler import get_datahandler # noqa: F401

314
freqtrade/data/history.py → freqtrade/data/history/history_utils.py
View File

@@ -1,138 +1,31 @@
"""
Handle historic data (ohlcv).
Includes:
* load data for a pair (or a list of pairs) from disk
* download data from exchange and store to disk
"""
import logging
import operator
from copy import deepcopy
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Dict, List, Optional, Tuple
from typing import Dict, List, Optional, Tuple
import arrow
from pandas import DataFrame
from freqtrade import misc
from freqtrade.configuration import TimeRange
from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS
from freqtrade.data.converter import parse_ticker_dataframe, trades_to_ohlcv
from freqtrade.data.history.idatahandler import IDataHandler, get_datahandler
from freqtrade.exceptions import OperationalException
from freqtrade.exchange import (Exchange, timeframe_to_minutes,
timeframe_to_seconds)
from freqtrade.exchange import Exchange
logger = logging.getLogger(__name__)
def trim_tickerlist(tickerlist: List[Dict], timerange: TimeRange) -> List[Dict]:
"""
Trim tickerlist based on given timerange
"""
if not tickerlist:
return tickerlist
start_index = 0
stop_index = len(tickerlist)
if timerange.starttype == 'date':
while (start_index < len(tickerlist) and
tickerlist[start_index][0] < timerange.startts * 1000):
start_index += 1
if timerange.stoptype == 'date':
while (stop_index > 0 and
tickerlist[stop_index-1][0] > timerange.stopts * 1000):
stop_index -= 1
if start_index > stop_index:
raise ValueError(f'The timerange [{timerange.startts},{timerange.stopts}] is incorrect')
return tickerlist[start_index:stop_index]
def trim_dataframe(df: DataFrame, timerange: TimeRange, df_date_col: str = 'date') -> DataFrame:
"""
Trim dataframe based on given timerange
:param df: Dataframe to trim
:param timerange: timerange (use start and end date if available)
:param: df_date_col: Column in the dataframe to use as Date column
:return: trimmed dataframe
"""
if timerange.starttype == 'date':
start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
df = df.loc[df[df_date_col] >= start, :]
if timerange.stoptype == 'date':
stop = datetime.fromtimestamp(timerange.stopts, tz=timezone.utc)
df = df.loc[df[df_date_col] <= stop, :]
return df
def load_tickerdata_file(datadir: Path, pair: str, timeframe: str,
timerange: Optional[TimeRange] = None) -> List[Dict]:
"""
Load a pair from file, either .json.gz or .json
:return: tickerlist or None if unsuccessful
"""
filename = pair_data_filename(datadir, pair, timeframe)
pairdata = misc.file_load_json(filename)
if not pairdata:
return []
if timerange:
pairdata = trim_tickerlist(pairdata, timerange)
return pairdata
def store_tickerdata_file(datadir: Path, pair: str,
timeframe: str, data: list, is_zip: bool = False) -> None:
"""
Stores tickerdata to file
"""
filename = pair_data_filename(datadir, pair, timeframe)
misc.file_dump_json(filename, data, is_zip=is_zip)
def load_trades_file(datadir: Path, pair: str,
timerange: Optional[TimeRange] = None) -> List[Dict]:
"""
Load a pair from file, either .json.gz or .json
:return: tradelist or empty list if unsuccesful
"""
filename = pair_trades_filename(datadir, pair)
tradesdata = misc.file_load_json(filename)
if not tradesdata:
return []
return tradesdata
def store_trades_file(datadir: Path, pair: str,
data: list, is_zip: bool = True) -> None:
"""
Stores tickerdata to file
"""
filename = pair_trades_filename(datadir, pair)
misc.file_dump_json(filename, data, is_zip=is_zip)
def _validate_pairdata(pair: str, pairdata: List[Dict], timerange: TimeRange) -> None:
if timerange.starttype == 'date' and pairdata[0][0] > timerange.startts * 1000:
logger.warning('Missing data at start for pair %s, data starts at %s',
pair, arrow.get(pairdata[0][0] // 1000).strftime('%Y-%m-%d %H:%M:%S'))
if timerange.stoptype == 'date' and pairdata[-1][0] < timerange.stopts * 1000:
logger.warning('Missing data at end for pair %s, data ends at %s',
pair, arrow.get(pairdata[-1][0] // 1000).strftime('%Y-%m-%d %H:%M:%S'))
def load_pair_history(pair: str,
timeframe: str,
datadir: Path,
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 ticker history for the given pair.
@@ -140,39 +33,34 @@ def load_pair_history(pair: str,
:param pair: Pair to load data for
:param timeframe: Ticker 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
"""
timerange_startup = deepcopy(timerange)
if startup_candles > 0 and timerange_startup:
timerange_startup.subtract_start(timeframe_to_seconds(timeframe) * startup_candles)
data_handler = get_datahandler(datadir, data_format, data_handler)
pairdata = load_tickerdata_file(datadir, pair, timeframe, timerange=timerange_startup)
if pairdata:
if timerange_startup:
_validate_pairdata(pair, pairdata, timerange_startup)
return parse_ticker_dataframe(pairdata, timeframe, pair=pair,
fill_missing=fill_up_missing,
drop_incomplete=drop_incomplete)
else:
logger.warning(
f'No history data for pair: "{pair}", timeframe: {timeframe}. '
'Use `freqtrade download-data` to download the data'
)
return DataFrame()
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_data(datadir: Path,
timeframe: str,
pairs: List[str],
pairs: List[str], *,
timerange: Optional[TimeRange] = None,
fill_up_missing: bool = True,
startup_candles: int = 0,
fail_without_data: bool = False
fail_without_data: bool = False,
data_format: str = 'json',
) -> Dict[str, DataFrame]:
"""
Load ticker history data for a list of pairs.
@@ -184,17 +72,22 @@ def load_data(datadir: Path,
:param fill_up_missing: Fill missing values with "No action"-candles
:param startup_candles: Additional candles to load at the start of the period
:param fail_without_data: Raise OperationalException if no data is found.
:param data_format: Data format which should be used. Defaults to json
:return: dict(<pair>:<Dataframe>)
"""
result: Dict[str, DataFrame] = {}
if startup_candles > 0 and timerange:
logger.info(f'Using indicator startup period: {startup_candles} ...')
data_handler = get_datahandler(datadir, data_format)
for pair in pairs:
hist = load_pair_history(pair=pair, timeframe=timeframe,
datadir=datadir, timerange=timerange,
fill_up_missing=fill_up_missing,
startup_candles=startup_candles)
startup_candles=startup_candles,
data_handler=data_handler
)
if not hist.empty:
result[pair] = hist
@@ -207,6 +100,7 @@ def refresh_data(datadir: Path,
timeframe: str,
pairs: List[str],
exchange: Exchange,
data_format: str = None,
timerange: Optional[TimeRange] = None,
) -> None:
"""
@@ -218,70 +112,50 @@ def refresh_data(datadir: Path,
:param exchange: Exchange object
:param timerange: Limit data to be loaded to this timerange
"""
data_handler = get_datahandler(datadir, data_format)
for pair in pairs:
_download_pair_history(pair=pair, timeframe=timeframe,
datadir=datadir, timerange=timerange,
exchange=exchange)
exchange=exchange, data_handler=data_handler)
def pair_data_filename(datadir: Path, pair: str, timeframe: str) -> Path:
pair_s = pair.replace("/", "_")
filename = datadir.joinpath(f'{pair_s}-{timeframe}.json')
return filename
def pair_trades_filename(datadir: Path, pair: str) -> Path:
pair_s = pair.replace("/", "_")
filename = datadir.joinpath(f'{pair_s}-trades.json.gz')
return filename
def _load_cached_data_for_updating(datadir: Path, pair: str, timeframe: str,
timerange: Optional[TimeRange]) -> Tuple[List[Any],
Optional[int]]:
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.
Only used by download_pair_history().
Otherwise downloads always start at the end of the available data to avoid data gaps.
Note: Only used by download_pair_history().
"""
since_ms = None
# user sets timerange, so find the start time
start = None
if timerange:
if timerange.starttype == 'date':
since_ms = timerange.startts * 1000
elif timerange.stoptype == 'line':
num_minutes = timerange.stopts * timeframe_to_minutes(timeframe)
since_ms = arrow.utcnow().shift(minutes=num_minutes).timestamp * 1000
# TODO: convert to date for conversion
start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
# read the cached file
# Intentionally don't pass timerange in - since we need to load the full dataset.
data = load_tickerdata_file(datadir, pair, timeframe)
# remove the last item, could be incomplete candle
if data:
data.pop()
else:
data = []
if data:
if since_ms and since_ms < data[0][0]:
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 = []
data = DataFrame(columns=DEFAULT_DATAFRAME_COLUMNS)
else:
# a part of the data was already downloaded, so download unexist data only
since_ms = data[-1][0] + 1
start = data.iloc[-1]['date']
return (data, since_ms)
start_ms = int(start.timestamp() * 1000) if start else None
return data, start_ms
def _download_pair_history(datadir: Path,
exchange: Exchange,
pair: str,
pair: str, *,
timeframe: str = '5m',
timerange: Optional[TimeRange] = None) -> bool:
timerange: Optional[TimeRange] = None,
data_handler: IDataHandler = None) -> bool:
"""
Download latest candles from the exchange for the pair and timeframe passed in parameters
The data is downloaded starting from the last correct data that
@@ -295,16 +169,22 @@ def _download_pair_history(datadir: Path,
:param timerange: range of time to download
:return: bool with success state
"""
data_handler = get_datahandler(datadir, data_handler=data_handler)
try:
logger.info(
f'Download history data for pair: "{pair}", timeframe: {timeframe} '
f'and store in {datadir}.'
)
data, since_ms = _load_cached_data_for_updating(datadir, pair, timeframe, timerange)
# data, since_ms = _load_cached_data_for_updating_old(datadir, pair, timeframe, timerange)
data, since_ms = _load_cached_data_for_updating(pair, timeframe, timerange,
data_handler=data_handler)
logger.debug("Current Start: %s", misc.format_ms_time(data[1][0]) if data else 'None')
logger.debug("Current End: %s", misc.format_ms_time(data[-1][0]) if data else 'None')
logger.debug("Current Start: %s",
f"{data.iloc[0]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
logger.debug("Current End: %s",
f"{data.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
# Default since_ms to 30 days if nothing is given
new_data = exchange.get_historic_ohlcv(pair=pair,
@@ -313,12 +193,20 @@ def _download_pair_history(datadir: Path,
int(arrow.utcnow().shift(
days=-30).float_timestamp) * 1000
)
data.extend(new_data)
# TODO: Maybe move parsing to exchange class (?)
new_dataframe = parse_ticker_dataframe(new_data, timeframe, pair,
fill_missing=False, drop_incomplete=True)
if data.empty:
data = new_dataframe
else:
data = data.append(new_dataframe)
logger.debug("New Start: %s", misc.format_ms_time(data[0][0]))
logger.debug("New End: %s", misc.format_ms_time(data[-1][0]))
logger.debug("New Start: %s",
f"{data.iloc[0]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
logger.debug("New End: %s",
f"{data.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
store_tickerdata_file(datadir, pair, timeframe, data=data)
data_handler.ohlcv_store(pair, timeframe, data=data)
return True
except Exception as e:
@@ -331,13 +219,14 @@ def _download_pair_history(datadir: Path,
def refresh_backtest_ohlcv_data(exchange: Exchange, pairs: List[str], timeframes: List[str],
datadir: Path, timerange: Optional[TimeRange] = None,
erase: bool = False) -> List[str]:
erase: bool = False, data_format: str = None) -> List[str]:
"""
Refresh stored ohlcv data for backtesting and hyperopt operations.
Used by freqtrade download-data subcommand.
:return: List of pairs that are not available.
"""
pairs_not_available = []
data_handler = get_datahandler(datadir, data_format)
for pair in pairs:
if pair not in exchange.markets:
pairs_not_available.append(pair)
@@ -345,23 +234,23 @@ def refresh_backtest_ohlcv_data(exchange: Exchange, pairs: List[str], timeframes
continue
for timeframe in timeframes:
dl_file = pair_data_filename(datadir, pair, timeframe)
if erase and dl_file.exists():
logger.info(
f'Deleting existing data for pair {pair}, interval {timeframe}.')
dl_file.unlink()
if erase:
if data_handler.ohlcv_purge(pair, timeframe):
logger.info(
f'Deleting existing data for pair {pair}, interval {timeframe}.')
logger.info(f'Downloading pair {pair}, interval {timeframe}.')
_download_pair_history(datadir=datadir, exchange=exchange,
pair=pair, timeframe=str(timeframe),
timerange=timerange)
timerange=timerange, data_handler=data_handler)
return pairs_not_available
def _download_trades_history(datadir: Path,
exchange: Exchange,
pair: str,
timerange: Optional[TimeRange] = None) -> bool:
def _download_trades_history(exchange: Exchange,
pair: str, *,
timerange: Optional[TimeRange] = None,
data_handler: IDataHandler
) -> bool:
"""
Download trade history from the exchange.
Appends to previously downloaded trades data.
@@ -370,7 +259,7 @@ def _download_trades_history(datadir: Path,
since = timerange.startts * 1000 if timerange and timerange.starttype == 'date' else None
trades = load_trades_file(datadir, pair)
trades = data_handler.trades_load(pair)
from_id = trades[-1]['id'] if trades else None
@@ -385,7 +274,7 @@ def _download_trades_history(datadir: Path,
from_id=from_id,
)
trades.extend(new_trades[1])
store_trades_file(datadir, pair, trades)
data_handler.trades_store(pair, data=trades)
logger.debug("New Start: %s", trades[0]['datetime'])
logger.debug("New End: %s", trades[-1]['datetime'])
@@ -401,47 +290,52 @@ def _download_trades_history(datadir: Path,
def refresh_backtest_trades_data(exchange: Exchange, pairs: List[str], datadir: Path,
timerange: TimeRange, erase: bool = False) -> List[str]:
timerange: TimeRange, erase: bool = False,
data_format: str = 'jsongz') -> List[str]:
"""
Refresh stored trades data for backtesting and hyperopt operations.
Used by freqtrade download-data subcommand.
:return: List of pairs that are not available.
"""
pairs_not_available = []
data_handler = get_datahandler(datadir, data_format=data_format)
for pair in pairs:
if pair not in exchange.markets:
pairs_not_available.append(pair)
logger.info(f"Skipping pair {pair}...")
continue
dl_file = pair_trades_filename(datadir, pair)
if erase and dl_file.exists():
logger.info(
f'Deleting existing data for pair {pair}.')
dl_file.unlink()
if erase:
if data_handler.trades_purge(pair):
logger.info(f'Deleting existing data for pair {pair}.')
logger.info(f'Downloading trades for pair {pair}.')
_download_trades_history(datadir=datadir, exchange=exchange,
_download_trades_history(exchange=exchange,
pair=pair,
timerange=timerange)
timerange=timerange,
data_handler=data_handler)
return pairs_not_available
def convert_trades_to_ohlcv(pairs: List[str], timeframes: List[str],
datadir: Path, timerange: TimeRange, erase: bool = False) -> None:
datadir: Path, timerange: TimeRange, erase: bool = False,
data_format_ohlcv: str = 'json',
data_format_trades: str = 'jsongz') -> None:
"""
Convert stored trades data to ohlcv data
"""
data_handler_trades = get_datahandler(datadir, data_format=data_format_trades)
data_handler_ohlcv = get_datahandler(datadir, data_format=data_format_ohlcv)
for pair in pairs:
trades = load_trades_file(datadir, pair)
trades = data_handler_trades.trades_load(pair)
for timeframe in timeframes:
ohlcv_file = pair_data_filename(datadir, pair, timeframe)
if erase and ohlcv_file.exists():
logger.info(f'Deleting existing data for pair {pair}, interval {timeframe}.')
ohlcv_file.unlink()
if erase:
if data_handler_ohlcv.ohlcv_purge(pair, timeframe):
logger.info(f'Deleting existing data for pair {pair}, interval {timeframe}.')
ohlcv = trades_to_ohlcv(trades, timeframe)
# Store ohlcv
store_tickerdata_file(datadir, pair, timeframe, data=ohlcv)
data_handler_ohlcv.ohlcv_store(pair, timeframe, data=ohlcv)
def get_timerange(data: Dict[str, DataFrame]) -> Tuple[arrow.Arrow, arrow.Arrow]:

220
freqtrade/data/history/idatahandler.py Normal file
View File

@@ -0,0 +1,220 @@
"""
Abstract datahandler interface.
It's subclasses handle and storing data from disk.
"""
import logging
from abc import ABC, abstractclassmethod, abstractmethod
from copy import deepcopy
from datetime import datetime, timezone
from pathlib import Path
from typing import Dict, List, Optional, Type
from pandas import DataFrame
from freqtrade.configuration import TimeRange
from freqtrade.data.converter import clean_ohlcv_dataframe, trim_dataframe
from freqtrade.exchange import timeframe_to_seconds
logger = logging.getLogger(__name__)
class IDataHandler(ABC):
def __init__(self, datadir: Path) -> None:
self._datadir = datadir
@abstractclassmethod
def ohlcv_get_pairs(cls, datadir: Path, timeframe: str) -> List[str]:
"""
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
:return: List of Pairs
"""
@abstractmethod
def ohlcv_store(self, pair: str, timeframe: str, data: DataFrame) -> None:
"""
Store data in json format "values".
format looks as follows:
[[<date>,<open>,<high>,<low>,<close>]]
:param pair: Pair - used to generate filename
:timeframe: Timeframe - used to generate filename
:data: Dataframe containing OHLCV data
:return: None
"""
@abstractmethod
def _ohlcv_load(self, pair: str, timeframe: str,
timerange: Optional[TimeRange] = None,
) -> DataFrame:
"""
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.
:param pair: Pair to load data
:param timeframe: Ticker 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.
:return: DataFrame with ohlcv data, or empty DataFrame
"""
@abstractmethod
def ohlcv_purge(self, pair: str, timeframe: str) -> bool:
"""
Remove data for this pair
:param pair: Delete data for this pair.
:param timeframe: Ticker timeframe (e.g. "5m")
:return: True when deleted, false if file did not exist.
"""
@abstractmethod
def ohlcv_append(self, pair: str, timeframe: str, data: DataFrame) -> None:
"""
Append data to existing data structures
:param pair: Pair
:param timeframe: Timeframe this ohlcv data is for
:param data: Data to append.
"""
@abstractclassmethod
def trades_get_pairs(cls, datadir: Path) -> List[str]:
"""
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
"""
@abstractmethod
def trades_store(self, pair: str, data: List[Dict]) -> None:
"""
Store trades data (list of Dicts) to file
:param pair: Pair - used for filename
:param data: List of Dicts containing trade data
"""
@abstractmethod
def trades_append(self, pair: str, data: List[Dict]):
"""
Append data to existing files
:param pair: Pair - used for filename
:param data: List of Dicts containing trade data
"""
@abstractmethod
def trades_load(self, pair: str, timerange: Optional[TimeRange] = None) -> List[Dict]:
"""
Load a pair from file, either .json.gz or .json
:param pair: Load trades for this pair
:param timerange: Timerange to load trades for - currently not implemented
:return: List of trades
"""
@abstractmethod
def trades_purge(self, pair: str) -> bool:
"""
Remove data for this pair
:param pair: Delete data for this pair.
:return: True when deleted, false if file did not exist.
"""
def ohlcv_load(self, pair, timeframe: str,
timerange: Optional[TimeRange] = None,
fill_missing: bool = True,
drop_incomplete: bool = True,
startup_candles: int = 0,
warn_no_data: bool = True
) -> DataFrame:
"""
Load cached ticker history for the given pair.
:param pair: Pair to load data for
:param timeframe: Ticker timeframe (e.g. "5m")
:param timerange: Limit data to be loaded to this timerange
:param fill_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 warn_no_data: Log a warning message when no data is found
:return: DataFrame with ohlcv data, or empty DataFrame
"""
# Fix startup period
timerange_startup = deepcopy(timerange)
if startup_candles > 0 and timerange_startup:
timerange_startup.subtract_start(timeframe_to_seconds(timeframe) * startup_candles)
pairdf = self._ohlcv_load(pair, timeframe,
timerange=timerange_startup)
if pairdf.empty:
if warn_no_data:
logger.warning(
f'No history data for pair: "{pair}", timeframe: {timeframe}. '
'Use `freqtrade download-data` to download the data'
)
return pairdf
else:
enddate = pairdf.iloc[-1]['date']
if timerange_startup:
self._validate_pairdata(pair, pairdf, timerange_startup)
pairdf = trim_dataframe(pairdf, timerange_startup)
# incomplete candles should only be dropped if we didn't trim the end beforehand.
return clean_ohlcv_dataframe(pairdf, timeframe,
pair=pair,
fill_missing=fill_missing,
drop_incomplete=(drop_incomplete and
enddate == pairdf.iloc[-1]['date']))
def _validate_pairdata(self, pair, pairdata: DataFrame, timerange: TimeRange):
"""
Validates pairdata for missing data at start end end and logs warnings.
:param pairdata: Dataframe to validate
:param timerange: Timerange specified for start and end dates
"""
if timerange.starttype == 'date':
start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
if pairdata.iloc[0]['date'] > start:
logger.warning(f"Missing data at start for pair {pair}, "
f"data starts at {pairdata.iloc[0]['date']:%Y-%m-%d %H:%M:%S}")
if timerange.stoptype == 'date':
stop = datetime.fromtimestamp(timerange.stopts, tz=timezone.utc)
if pairdata.iloc[-1]['date'] < stop:
logger.warning(f"Missing data at end for pair {pair}, "
f"data ends at {pairdata.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}")
def get_datahandlerclass(datatype: str) -> Type[IDataHandler]:
"""
Get datahandler class.
Could be done using Resolvers, but since this may be called often and resolvers
are rather expensive, doing this directly should improve performance.
:param datatype: datatype to use.
:return: Datahandler class
"""
if datatype == 'json':
from .jsondatahandler import JsonDataHandler
return JsonDataHandler
elif datatype == 'jsongz':
from .jsondatahandler import JsonGzDataHandler
return JsonGzDataHandler
else:
raise ValueError(f"No datahandler for datatype {datatype} available.")
def get_datahandler(datadir: Path, data_format: str = None,
data_handler: IDataHandler = None) -> IDataHandler:
"""
:param datadir: Folder to save data
:data_format: dataformat to use
:data_handler: returns this datahandler if it exists or initializes a new one
"""
if not data_handler:
HandlerClass = get_datahandlerclass(data_format or 'json')
data_handler = HandlerClass(datadir)
return data_handler

177
freqtrade/data/history/jsondatahandler.py Normal file
View File

@@ -0,0 +1,177 @@
import re
from pathlib import Path
from typing import Dict, List, Optional
import numpy as np
from pandas import DataFrame, read_json, to_datetime
from freqtrade import misc
from freqtrade.configuration import TimeRange
from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS
from .idatahandler import IDataHandler
class JsonDataHandler(IDataHandler):
_use_zip = False
_columns = DEFAULT_DATAFRAME_COLUMNS
@classmethod
def ohlcv_get_pairs(cls, datadir: Path, timeframe: str) -> List[str]:
"""
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
:return: List of Pairs
"""
_tmp = [re.search(r'^(\S+)(?=\-' + timeframe + '.json)', p.name)
for p in datadir.glob(f"*{timeframe}.{cls._get_file_extension()}")]
# Check if regex found something and only return these results
return [match[0].replace('_', '/') for match in _tmp if match]
def ohlcv_store(self, pair: str, timeframe: str, data: DataFrame) -> None:
"""
Store data in json format "values".
format looks as follows:
[[<date>,<open>,<high>,<low>,<close>]]
:param pair: Pair - used to generate filename
:timeframe: Timeframe - used to generate filename
:data: Dataframe containing OHLCV data
:return: None
"""
filename = self._pair_data_filename(self._datadir, pair, timeframe)
_data = data.copy()
# Convert date to int
_data['date'] = _data['date'].astype(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,
timerange: Optional[TimeRange] = None,
) -> DataFrame:
"""
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.
:param pair: Pair to load data
:param timeframe: Ticker 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.
:return: DataFrame with ohlcv data, or empty DataFrame
"""
filename = self._pair_data_filename(self._datadir, pair, timeframe)
if not filename.exists():
return DataFrame(columns=self._columns)
pairdata = read_json(filename, orient='values')
pairdata.columns = self._columns
pairdata['date'] = to_datetime(pairdata['date'],
unit='ms',
utc=True,
infer_datetime_format=True)
return pairdata
def ohlcv_purge(self, pair: str, timeframe: str) -> bool:
"""
Remove data for this pair
:param pair: Delete data for this pair.
:param timeframe: Ticker timeframe (e.g. "5m")
:return: True when deleted, false if file did not exist.
"""
filename = self._pair_data_filename(self._datadir, pair, timeframe)
if filename.exists():
filename.unlink()
return True
return False
def ohlcv_append(self, pair: str, timeframe: str, data: DataFrame) -> None:
"""
Append data to existing data structures
:param pair: Pair
:param timeframe: Timeframe this ohlcv data is for
:param data: Data to append.
"""
raise NotImplementedError()
@classmethod
def trades_get_pairs(cls, datadir: Path) -> List[str]:
"""
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
"""
_tmp = [re.search(r'^(\S+)(?=\-trades.json)', p.name)
for p in datadir.glob(f"*trades.{cls._get_file_extension()}")]
# Check if regex found something and only return these results to avoid exceptions.
return [match[0].replace('_', '/') for match in _tmp if match]
def trades_store(self, pair: str, data: List[Dict]) -> None:
"""
Store trades data (list of Dicts) to file
:param pair: Pair - used for filename
:param data: List of Dicts containing trade data
"""
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: List[Dict]):
"""
Append data to existing files
:param pair: Pair - used for filename
:param data: List of Dicts containing trade data
"""
raise NotImplementedError()
def trades_load(self, pair: str, timerange: Optional[TimeRange] = None) -> List[Dict]:
"""
Load a pair from file, either .json.gz or .json
# 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 []
return tradesdata
def trades_purge(self, pair: str) -> bool:
"""
Remove data for this pair
:param pair: Delete data for this pair.
:return: True when deleted, false if file did not exist.
"""
filename = self._pair_trades_filename(self._datadir, pair)
if filename.exists():
filename.unlink()
return True
return False
@classmethod
def _pair_data_filename(cls, datadir: Path, pair: str, timeframe: str) -> Path:
pair_s = misc.pair_to_filename(pair)
filename = datadir.joinpath(f'{pair_s}-{timeframe}.{cls._get_file_extension()}')
return filename
@classmethod
def _get_file_extension(cls):
return "json.gz" if cls._use_zip else "json"
@classmethod
def _pair_trades_filename(cls, datadir: Path, pair: str) -> Path:
pair_s = misc.pair_to_filename(pair)
filename = datadir.joinpath(f'{pair_s}-trades.{cls._get_file_extension()}')
return filename
class JsonGzDataHandler(JsonDataHandler):
_use_zip = True

1
freqtrade/edge/edge_positioning.py
View File

@@ -110,6 +110,7 @@ class Edge:
timeframe=self.strategy.ticker_interval,
timerange=self._timerange,
startup_candles=self.strategy.startup_candle_count,
data_format=self.config.get('dataformat_ohlcv', 'json'),
)
if not data:

10
freqtrade/misc.py
View File

@@ -48,14 +48,16 @@ def file_dump_json(filename: Path, data: Any, is_zip: bool = False) -> None:
:param data: JSON Data to save
:return:
"""
logger.info(f'dumping json to "{filename}"')
if is_zip:
if filename.suffix != '.gz':
filename = filename.with_suffix('.gz')
logger.info(f'dumping json to "{filename}"')
with gzip.open(filename, 'w') as fp:
rapidjson.dump(data, fp, default=str, number_mode=rapidjson.NM_NATIVE)
else:
logger.info(f'dumping json to "{filename}"')
with open(filename, 'w') as fp:
rapidjson.dump(data, fp, default=str, number_mode=rapidjson.NM_NATIVE)
@@ -91,6 +93,12 @@ def file_load_json(file):
return pairdata
def pair_to_filename(pair: str) -> str:
for ch in ['/', '-', ' ', '.', '@', '$', '+', ':']:
pair = pair.replace(ch, '_')
return pair
def format_ms_time(date: int) -> str:
"""
convert MS date to readable format.

4
freqtrade/optimize/backtesting.py
View File

@@ -15,6 +15,7 @@ from pandas import DataFrame
from freqtrade.configuration import (TimeRange, remove_credentials,
validate_config_consistency)
from freqtrade.data import history
from freqtrade.data.converter import trim_dataframe
from freqtrade.data.dataprovider import DataProvider
from freqtrade.exceptions import OperationalException
from freqtrade.exchange import timeframe_to_minutes, timeframe_to_seconds
@@ -118,6 +119,7 @@ class Backtesting:
timerange=timerange,
startup_candles=self.required_startup,
fail_without_data=True,
data_format=self.config.get('dataformat_ohlcv', 'json'),
)
min_date, max_date = history.get_timerange(data)
@@ -397,7 +399,7 @@ class Backtesting:
# Trim startup period from analyzed dataframe
for pair, df in preprocessed.items():
preprocessed[pair] = history.trim_dataframe(df, timerange)
preprocessed[pair] = trim_dataframe(df, timerange)
min_date, max_date = history.get_timerange(preprocessed)
logger.info(

3
freqtrade/optimize/hyperopt.py
View File

@@ -22,7 +22,8 @@ from joblib import (Parallel, cpu_count, delayed, dump, load,
wrap_non_picklable_objects)
from pandas import DataFrame
from freqtrade.data.history import get_timerange, trim_dataframe
from freqtrade.data.converter import trim_dataframe
from freqtrade.data.history import get_timerange
from freqtrade.exceptions import OperationalException
from freqtrade.misc import plural, round_dict
from freqtrade.optimize.backtesting import Backtesting

14
freqtrade/plot/plotting.py
View File

@@ -3,11 +3,14 @@ from pathlib import Path
from typing import Any, Dict, List
import pandas as pd
from freqtrade.configuration import TimeRange
from freqtrade.data import history
from freqtrade.data.btanalysis import (combine_tickers_with_mean,
create_cum_profit,
extract_trades_of_period, load_trades)
from freqtrade.data.converter import trim_dataframe
from freqtrade.data.history import load_data
from freqtrade.misc import pair_to_filename
from freqtrade.resolvers import StrategyResolver
logger = logging.getLogger(__name__)
@@ -36,18 +39,19 @@ def init_plotscript(config):
# Set timerange to use
timerange = TimeRange.parse_timerange(config.get("timerange"))
tickers = history.load_data(
tickers = load_data(
datadir=config.get("datadir"),
pairs=pairs,
timeframe=config.get('ticker_interval', '5m'),
timerange=timerange,
data_format=config.get('dataformat_ohlcv', 'json'),
)
trades = load_trades(config['trade_source'],
db_url=config.get('db_url'),
exportfilename=config.get('exportfilename'),
)
trades = history.trim_dataframe(trades, timerange, 'open_time')
trades = trim_dataframe(trades, timerange, 'open_time')
return {"tickers": tickers,
"trades": trades,
"pairs": pairs,
@@ -374,8 +378,8 @@ def generate_plot_filename(pair: str, timeframe: str) -> str:
"""
Generate filenames per pair/timeframe to be used for storing plots
"""
pair_name = pair.replace("/", "_")
file_name = 'freqtrade-plot-' + pair_name + '-' + timeframe + '.html'
pair_s = pair_to_filename(pair)
file_name = 'freqtrade-plot-' + pair_s + '-' + timeframe + '.html'
logger.info('Generate plot file for %s', pair)

2
freqtrade/strategy/interface.py
View File

@@ -439,7 +439,7 @@ class IStrategy(ABC):
else:
return current_profit > roi
def tickerdata_to_dataframe(self, tickerdata: Dict[str, List]) -> Dict[str, DataFrame]:
def tickerdata_to_dataframe(self, tickerdata: Dict[str, DataFrame]) -> Dict[str, DataFrame]:
"""
Creates a dataframe and populates indicators for given ticker data
Used by optimize operations only, not during dry / live runs.