merge in inference timer and historic predictions handling improvements.

This commit is contained in:
robcaulk 2022-08-14 16:41:50 +02:00
parent ad846cdb76
commit 8961b8d560
2 changed files with 46 additions and 15 deletions

View File

@ -85,6 +85,7 @@ class FreqaiDataDrawer:
self.training_queue: Dict[str, int] = {}
self.history_lock = threading.Lock()
self.save_lock = threading.Lock()
self.pair_dict_lock = threading.Lock()
self.old_DBSCAN_eps: Dict[str, float] = {}
self.empty_pair_dict: pair_info = {
"model_filename": "", "trained_timestamp": 0,
@ -228,6 +229,7 @@ class FreqaiDataDrawer:
def pair_to_end_of_training_queue(self, pair: str) -> None:
# march all pairs up in the queue
with self.pair_dict_lock:
for p in self.pair_dict:
self.pair_dict[p]["priority"] -= 1
# send pair to end of queue
@ -261,13 +263,14 @@ class FreqaiDataDrawer:
the strategy originally. Doing this allows FreqUI to always display the correct
historic predictions.
"""
df = self.historic_predictions[pair]
# here are some pandas hula hoops to accommodate the possibility of a series
# or dataframe depending number of labels requested by user
nan_df = pd.DataFrame(np.nan, index=df.index[-2:] + 2, columns=df.columns)
df = pd.concat([df, nan_df], ignore_index=True, axis=0)
df = self.historic_predictions[pair] = df[:-1]
index = self.historic_predictions[pair].index[-1:]
columns = self.historic_predictions[pair].columns
nan_df = pd.DataFrame(np.nan, index=index, columns=columns)
self.historic_predictions[pair] = pd.concat(
[self.historic_predictions[pair], nan_df], ignore_index=True, axis=0)
df = self.historic_predictions[pair]
# model outputs and associated statistics
for label in predictions.columns:
@ -523,7 +526,7 @@ class FreqaiDataDrawer:
history_data[pair][tf] = pd.concat(
[
history_data[pair][tf],
strategy.dp.get_pair_dataframe(pair, tf).iloc[index:],
df_dp.iloc[index:],
],
ignore_index=True,
axis=0,

View File

@ -7,11 +7,11 @@ import time
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Any, Dict, Tuple
import numpy as np
import pandas as pd
from numpy.typing import NDArray
from pandas import DataFrame
from freqtrade.exchange import timeframe_to_seconds
from threading import Lock
from freqtrade.configuration import TimeRange
from freqtrade.enums import RunMode
@ -82,6 +82,9 @@ class IFreqaiModel(ABC):
self.last_trade_database_summary: DataFrame = {}
self.current_trade_database_summary: DataFrame = {}
self.analysis_lock = Lock()
self.inference_time: float = 0
self.begin_time: float = 0
self.base_tf_seconds = timeframe_to_seconds(self.config['timeframe'])
def assert_config(self, config: Dict[str, Any]) -> None:
@ -104,6 +107,7 @@ class IFreqaiModel(ABC):
self.dd.set_pair_dict_info(metadata)
if self.live:
self.inference_timer('start')
self.dk = FreqaiDataKitchen(self.config, self.live, metadata["pair"])
dk = self.start_live(dataframe, metadata, strategy, self.dk)
@ -123,6 +127,8 @@ class IFreqaiModel(ABC):
dataframe = dk.remove_features_from_df(dk.return_dataframe)
del dk
if self.live:
self.inference_timer('stop')
return dataframe
@threaded
@ -155,6 +161,8 @@ class IFreqaiModel(ABC):
new_trained_timerange, pair, strategy, dk, data_load_timerange
)
self.dd.save_historic_predictions_to_disk()
def start_backtesting(
self, dataframe: DataFrame, metadata: dict, dk: FreqaiDataKitchen
) -> FreqaiDataKitchen:
@ -340,7 +348,6 @@ class IFreqaiModel(ABC):
# historical accuracy reasons.
pred_df, do_preds = self.predict(dataframe.iloc[-self.CONV_WIDTH:], dk, first=False)
self.dd.save_historic_predictions_to_disk()
if self.freqai_info.get('fit_live_predictions_candles', 0) and self.live:
self.fit_live_predictions(dk, pair)
self.dd.append_model_predictions(pair, pred_df, do_preds, dk, len(dataframe))
@ -503,7 +510,6 @@ class IFreqaiModel(ABC):
dk.set_new_model_names(pair, new_trained_timerange)
self.dd.pair_dict[pair]["first"] = False
if self.dd.pair_dict[pair]["priority"] == 1 and self.scanning:
with self.analysis_lock:
self.dd.pair_to_end_of_training_queue(pair)
self.dd.save_data(model, pair, dk)
@ -582,6 +588,28 @@ class IFreqaiModel(ABC):
return
def inference_timer(self, do='start'):
"""
Timer designed to track the cumulative time spent in FreqAI for one pass through
the whitelist. This will check if the time spent is more than 1/4 the time
of a single candle, and if so, it will warn the user of degraded performance
"""
if do == 'start':
self.pair_it += 1
self.begin_time = time.time()
elif do == 'stop':
end = time.time()
self.inference_time += (end - self.begin_time)
if self.pair_it == self.total_pairs:
logger.info(
f'Total time spent inferencing pairlist {self.inference_time:.2f} seconds')
if self.inference_time > 0.25 * self.base_tf_seconds:
logger.warning('Inference took over 25/% of the candle time. Reduce pairlist to'
' avoid blinding open trades and degrading performance.')
self.pair_it = 0
self.inference_time = 0
return
# Following methods which are overridden by user made prediction models.
# See freqai/prediction_models/CatboostPredictionModel.py for an example.