stable/freqtrade/freqai/base_models/BaseClassifierModel.py
Robert Caulk 03256fc776 Merge pull request #7508 from aemr3/fix-pca-errors
Fix feature list match for PCA
2022-10-02 06:53:08 +02:00

106 lines
4.0 KiB
Python

import logging
from time import time
from typing import Any, Tuple
import numpy as np
import numpy.typing as npt
import pandas as pd
from pandas import DataFrame
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.freqai_interface import IFreqaiModel
logger = logging.getLogger(__name__)
class BaseClassifierModel(IFreqaiModel):
"""
Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
User *must* inherit from this class and set fit() and predict(). See example scripts
such as prediction_models/CatboostPredictionModel.py for guidance.
"""
def train(
self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
) -> Any:
"""
Filter the training data and train a model to it. Train makes heavy use of the datakitchen
for storing, saving, loading, and analyzing the data.
:param unfiltered_df: Full dataframe for the current training period
:param metadata: pair metadata from strategy.
:return:
:model: Trained model which can be used to inference (self.predict)
"""
logger.info(f"-------------------- Starting training {pair} --------------------")
start_time = time()
# filter the features requested by user in the configuration file and elegantly handle NaNs
features_filtered, labels_filtered = dk.filter_features(
unfiltered_df,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
logger.info(f"-------------------- Training on data from {start_date} to "
f"{end_date} --------------------")
# split data into train/test data.
data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
if not self.freqai_info.get("fit_live_predictions", 0) or not self.live:
dk.fit_labels()
# normalize all data based on train_dataset only
data_dictionary = dk.normalize_data(data_dictionary)
# optional additional data cleaning/analysis
self.data_cleaning_train(dk)
logger.info(
f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"
)
logger.info(f"Training model on {len(data_dictionary['train_features'])} data points")
model = self.fit(data_dictionary, dk)
end_time = time()
logger.info(f"-------------------- Done training {pair} "
f"({end_time - start_time:.2f} secs) --------------------")
return model
def predict(
self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
"""
Filter the prediction features data and predict with it.
:param: unfiltered_df: Full dataframe for the current backtest period.
:return:
:pred_df: dataframe containing the predictions
:do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
data (NaNs) or felt uncertain about data (PCA and DI index)
"""
dk.find_features(unfiltered_df)
filtered_df, _ = dk.filter_features(
unfiltered_df, dk.training_features_list, training_filter=False
)
filtered_df = dk.normalize_data_from_metadata(filtered_df)
dk.data_dictionary["prediction_features"] = filtered_df
self.data_cleaning_predict(dk)
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
pred_df = DataFrame(predictions, columns=dk.label_list)
predictions_prob = self.model.predict_proba(dk.data_dictionary["prediction_features"])
pred_df_prob = DataFrame(predictions_prob, columns=self.model.classes_)
pred_df = pd.concat([pred_df, pred_df_prob], axis=1)
return (pred_df, dk.do_predict)