2019-03-07 20:20:32 +00:00
|
|
|
"""
|
|
|
|
Helpers when analyzing backtest data
|
|
|
|
"""
|
2019-06-16 08:41:05 +00:00
|
|
|
import logging
|
2019-03-07 20:20:32 +00:00
|
|
|
from pathlib import Path
|
2019-06-30 08:04:43 +00:00
|
|
|
from typing import Dict
|
2019-03-07 20:20:32 +00:00
|
|
|
|
|
|
|
import numpy as np
|
|
|
|
import pandas as pd
|
2019-06-16 08:41:05 +00:00
|
|
|
import pytz
|
2019-03-07 20:20:32 +00:00
|
|
|
|
2019-06-16 08:41:05 +00:00
|
|
|
from freqtrade import persistence
|
2019-03-07 20:20:32 +00:00
|
|
|
from freqtrade.misc import json_load
|
2019-06-16 08:41:05 +00:00
|
|
|
from freqtrade.persistence import Trade
|
|
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
2019-03-07 20:20:32 +00:00
|
|
|
|
2019-03-07 20:23:53 +00:00
|
|
|
# must align with columns in backtest.py
|
|
|
|
BT_DATA_COLUMNS = ["pair", "profitperc", "open_time", "close_time", "index", "duration",
|
|
|
|
"open_rate", "close_rate", "open_at_end", "sell_reason"]
|
|
|
|
|
2019-03-07 20:20:32 +00:00
|
|
|
|
|
|
|
def load_backtest_data(filename) -> pd.DataFrame:
|
|
|
|
"""
|
|
|
|
Load backtest data file.
|
|
|
|
:param filename: pathlib.Path object, or string pointing to the file.
|
2019-06-23 20:10:37 +00:00
|
|
|
:return: a dataframe with the analysis results
|
2019-03-07 20:20:32 +00:00
|
|
|
"""
|
|
|
|
if isinstance(filename, str):
|
|
|
|
filename = Path(filename)
|
|
|
|
|
|
|
|
if not filename.is_file():
|
2019-08-02 07:37:59 +00:00
|
|
|
raise ValueError(f"File {filename} does not exist.")
|
2019-03-07 20:20:32 +00:00
|
|
|
|
|
|
|
with filename.open() as file:
|
|
|
|
data = json_load(file)
|
|
|
|
|
2019-03-07 20:23:53 +00:00
|
|
|
df = pd.DataFrame(data, columns=BT_DATA_COLUMNS)
|
2019-03-07 20:20:32 +00:00
|
|
|
|
|
|
|
df['open_time'] = pd.to_datetime(df['open_time'],
|
|
|
|
unit='s',
|
|
|
|
utc=True,
|
|
|
|
infer_datetime_format=True
|
|
|
|
)
|
|
|
|
df['close_time'] = pd.to_datetime(df['close_time'],
|
|
|
|
unit='s',
|
|
|
|
utc=True,
|
|
|
|
infer_datetime_format=True
|
|
|
|
)
|
|
|
|
df['profitabs'] = df['close_rate'] - df['open_rate']
|
|
|
|
df = df.sort_values("open_time").reset_index(drop=True)
|
|
|
|
return df
|
|
|
|
|
|
|
|
|
|
|
|
def evaluate_result_multi(results: pd.DataFrame, freq: str, max_open_trades: int) -> pd.DataFrame:
|
|
|
|
"""
|
|
|
|
Find overlapping trades by expanding each trade once per period it was open
|
|
|
|
and then counting overlaps
|
|
|
|
:param results: Results Dataframe - can be loaded
|
|
|
|
:param freq: Frequency used for the backtest
|
|
|
|
:param max_open_trades: parameter max_open_trades used during backtest run
|
|
|
|
:return: dataframe with open-counts per time-period in freq
|
|
|
|
"""
|
|
|
|
dates = [pd.Series(pd.date_range(row[1].open_time, row[1].close_time, freq=freq))
|
|
|
|
for row in results[['open_time', 'close_time']].iterrows()]
|
|
|
|
deltas = [len(x) for x in dates]
|
|
|
|
dates = pd.Series(pd.concat(dates).values, name='date')
|
|
|
|
df2 = pd.DataFrame(np.repeat(results.values, deltas, axis=0), columns=results.columns)
|
|
|
|
|
|
|
|
df2 = pd.concat([dates, df2], axis=1)
|
|
|
|
df2 = df2.set_index('date')
|
|
|
|
df_final = df2.resample(freq)[['pair']].count()
|
|
|
|
return df_final[df_final['pair'] > max_open_trades]
|
2019-06-16 08:41:05 +00:00
|
|
|
|
|
|
|
|
2019-06-22 13:45:20 +00:00
|
|
|
def load_trades_from_db(db_url: str) -> pd.DataFrame:
|
2019-06-16 08:41:05 +00:00
|
|
|
"""
|
2019-06-22 13:45:20 +00:00
|
|
|
Load trades from a DB (using dburl)
|
2019-06-16 08:41:05 +00:00
|
|
|
:param db_url: Sqlite url (default format sqlite:///tradesv3.dry-run.sqlite)
|
2019-06-23 20:10:37 +00:00
|
|
|
:return: Dataframe containing Trades
|
2019-06-16 08:41:05 +00:00
|
|
|
"""
|
|
|
|
trades: pd.DataFrame = pd.DataFrame([], columns=BT_DATA_COLUMNS)
|
2019-06-22 13:45:20 +00:00
|
|
|
persistence.init(db_url, clean_open_orders=False)
|
2019-06-22 14:20:41 +00:00
|
|
|
|
2019-08-03 17:55:54 +00:00
|
|
|
columns = ["pair", "open_time", "close_time", "profit", "profitperc",
|
|
|
|
"open_rate", "close_rate", "amount", "duration", "sell_reason",
|
|
|
|
"fee_open", "fee_close", "open_rate_requested", "close_rate_requested",
|
|
|
|
"stake_amount", "max_rate", "min_rate", "id", "exchange",
|
|
|
|
"stop_loss", "initial_stop_loss", "strategy", "ticker_interval"]
|
|
|
|
|
|
|
|
trades = pd.DataFrame([(t.pair,
|
2019-06-22 14:20:41 +00:00
|
|
|
t.open_date.replace(tzinfo=pytz.UTC),
|
|
|
|
t.close_date.replace(tzinfo=pytz.UTC) if t.close_date else None,
|
2019-08-03 17:55:54 +00:00
|
|
|
t.calc_profit(), t.calc_profit_percent(),
|
|
|
|
t.open_rate, t.close_rate, t.amount,
|
2019-10-19 11:18:52 +00:00
|
|
|
(round((t.close_date.timestamp() - t.open_date.timestamp()) / 60, 2)
|
2019-08-04 08:38:37 +00:00
|
|
|
if t.close_date else None),
|
2019-06-22 14:20:41 +00:00
|
|
|
t.sell_reason,
|
2019-08-03 17:55:54 +00:00
|
|
|
t.fee_open, t.fee_close,
|
|
|
|
t.open_rate_requested,
|
|
|
|
t.close_rate_requested,
|
|
|
|
t.stake_amount,
|
2019-06-22 14:20:41 +00:00
|
|
|
t.max_rate,
|
|
|
|
t.min_rate,
|
2019-08-03 17:55:54 +00:00
|
|
|
t.id, t.exchange,
|
|
|
|
t.stop_loss, t.initial_stop_loss,
|
|
|
|
t.strategy, t.ticker_interval
|
2019-06-22 14:20:41 +00:00
|
|
|
)
|
2019-10-29 14:01:10 +00:00
|
|
|
for t in Trade.get_trades().all()],
|
2019-06-22 14:20:41 +00:00
|
|
|
columns=columns)
|
2019-06-16 08:41:05 +00:00
|
|
|
|
|
|
|
return trades
|
2019-06-16 09:12:19 +00:00
|
|
|
|
|
|
|
|
2019-08-22 18:17:36 +00:00
|
|
|
def load_trades(source: str, db_url: str, exportfilename: str) -> pd.DataFrame:
|
2019-06-29 18:50:31 +00:00
|
|
|
"""
|
|
|
|
Based on configuration option "trade_source":
|
|
|
|
* loads data from DB (using `db_url`)
|
2019-07-03 04:26:39 +00:00
|
|
|
* loads data from backtestfile (using `exportfilename`)
|
2019-06-29 18:50:31 +00:00
|
|
|
"""
|
2019-08-22 18:17:36 +00:00
|
|
|
if source == "DB":
|
|
|
|
return load_trades_from_db(db_url)
|
|
|
|
elif source == "file":
|
|
|
|
return load_backtest_data(Path(exportfilename))
|
2019-06-29 18:50:31 +00:00
|
|
|
|
|
|
|
|
2019-06-16 09:12:19 +00:00
|
|
|
def extract_trades_of_period(dataframe: pd.DataFrame, trades: pd.DataFrame) -> pd.DataFrame:
|
|
|
|
"""
|
|
|
|
Compare trades and backtested pair DataFrames to get trades performed on backtested period
|
|
|
|
:return: the DataFrame of a trades of period
|
|
|
|
"""
|
|
|
|
trades = trades.loc[(trades['open_time'] >= dataframe.iloc[0]['date']) &
|
|
|
|
(trades['close_time'] <= dataframe.iloc[-1]['date'])]
|
|
|
|
return trades
|
2019-06-29 14:57:04 +00:00
|
|
|
|
|
|
|
|
2019-06-30 08:04:43 +00:00
|
|
|
def combine_tickers_with_mean(tickers: Dict[str, pd.DataFrame], column: str = "close"):
|
|
|
|
"""
|
|
|
|
Combine multiple dataframes "column"
|
|
|
|
:param tickers: Dict of Dataframes, dict key should be pair.
|
|
|
|
:param column: Column in the original dataframes to use
|
|
|
|
:return: DataFrame with the column renamed to the dict key, and a column
|
|
|
|
named mean, containing the mean of all pairs.
|
|
|
|
"""
|
|
|
|
df_comb = pd.concat([tickers[pair].set_index('date').rename(
|
|
|
|
{column: pair}, axis=1)[pair] for pair in tickers], axis=1)
|
|
|
|
|
|
|
|
df_comb['mean'] = df_comb.mean(axis=1)
|
|
|
|
|
|
|
|
return df_comb
|
|
|
|
|
|
|
|
|
2019-10-28 13:24:12 +00:00
|
|
|
def create_cum_profit(df: pd.DataFrame, trades: pd.DataFrame, col_name: str,
|
|
|
|
timeframe: str) -> pd.DataFrame:
|
2019-06-29 14:57:04 +00:00
|
|
|
"""
|
|
|
|
Adds a column `col_name` with the cumulative profit for the given trades array.
|
2019-06-29 15:19:42 +00:00
|
|
|
:param df: DataFrame with date index
|
|
|
|
:param trades: DataFrame containing trades (requires columns close_time and profitperc)
|
2019-10-28 13:24:12 +00:00
|
|
|
:param col_name: Column name that will be assigned the results
|
|
|
|
:param timeframe: Timeframe used during the operations
|
2019-06-29 15:19:42 +00:00
|
|
|
:return: Returns df with one additional column, col_name, containing the cumulative profit.
|
2019-06-29 14:57:04 +00:00
|
|
|
"""
|
2019-10-28 13:24:12 +00:00
|
|
|
from freqtrade.exchange import timeframe_to_minutes
|
|
|
|
ticker_minutes = timeframe_to_minutes(timeframe)
|
|
|
|
# Resample to ticker_interval to make sure trades match candles
|
|
|
|
_trades_sum = trades.resample(f'{ticker_minutes}min', on='close_time')[['profitperc']].sum()
|
|
|
|
df.loc[:, col_name] = _trades_sum.cumsum()
|
2019-06-29 14:57:04 +00:00
|
|
|
# Set first value to 0
|
|
|
|
df.loc[df.iloc[0].name, col_name] = 0
|
|
|
|
# FFill to get continuous
|
|
|
|
df[col_name] = df[col_name].ffill()
|
|
|
|
return df
|