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

use logger in favor of print

Browse Source
This commit is contained in:
robcaulk
2022-05-04 17:53:40 +02:00
parent 99f7e44c30
commit 29c2d1d189
3 changed files with 34 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
freqtrade/freqai/data_handler.py
View File

@@ -1,6 +1,7 @@
import copy
import datetime
import json
import logging
import pickle as pk
from pathlib import Path
from typing import Any, Dict, List, Tuple
@@ -17,6 +18,8 @@ from freqtrade.configuration import TimeRange
SECONDS_IN_DAY = 86400
logger = logging.getLogger(__name__)
class DataHandler:
"""
@@ -175,7 +178,7 @@ class DataHandler:
labels = labels[
(drop_index == 0) & (drop_index_labels == 0)
] # assuming the labels depend entirely on the dataframe here.
print(
logger.info(
"dropped",
len(unfiltered_dataframe) - len(filtered_dataframe),
"training data points due to NaNs, ensure you have downloaded",
@@ -193,7 +196,7 @@ class DataHandler:
# that was based on a single NaN is ultimately protected from buys with do_predict
drop_index = ~drop_index
self.do_predict = np.array(drop_index.replace(True, 1).replace(False, 0))
print(
logger.info(
"dropped",
len(self.do_predict) - self.do_predict.sum(),
"of",
@@ -350,8 +353,8 @@ class DataHandler:
pca2 = PCA(n_components=n_keep_components)
self.data["n_kept_components"] = n_keep_components
pca2 = pca2.fit(self.data_dictionary["train_features"])
print("reduced feature dimension by", n_components - n_keep_components)
print("explained variance", np.sum(pca2.explained_variance_ratio_))
logger.info("reduced feature dimension by", n_components - n_keep_components)
logger.info("explained variance", np.sum(pca2.explained_variance_ratio_))
train_components = pca2.transform(self.data_dictionary["train_features"])
test_components = pca2.transform(self.data_dictionary["test_features"])
@@ -377,10 +380,10 @@ class DataHandler:
return None
def compute_distances(self) -> float:
print("computing average mean distance for all training points")
logger.info("computing average mean distance for all training points")
pairwise = pairwise_distances(self.data_dictionary["train_features"], n_jobs=-1)
avg_mean_dist = pairwise.mean(axis=1).mean()
print("avg_mean_dist", avg_mean_dist)
logger.info("avg_mean_dist", avg_mean_dist)
return avg_mean_dist
@@ -407,7 +410,7 @@ class DataHandler:
drop_index = ~drop_index
do_predict = np.array(drop_index.replace(True, 1).replace(False, 0))
print(
logger.info(
"remove_outliers() tossed",
len(do_predict) - do_predict.sum(),
"predictions because they were beyond 3 std deviations from training data.",
@@ -472,7 +475,7 @@ class DataHandler:
for p in config["freqai"]["corr_pairlist"]:
features.append(p.split("/")[0] + "-" + ft + shift + "_" + tf)
print("number of features", len(features))
logger.info("number of features", len(features))
return features
def check_if_pred_in_training_spaces(self) -> None:
@@ -483,7 +486,7 @@ class DataHandler:
from the training data set.
"""
print("checking if prediction features are in AOA")
logger.info("checking if prediction features are in AOA")
distance = pairwise_distances(
self.data_dictionary["train_features"],
self.data_dictionary["prediction_features"],
@@ -497,7 +500,7 @@ class DataHandler:
0,
)
print(
logger.info(
"Distance checker tossed",
len(do_predict) - do_predict.sum(),
"predictions for being too far from training data",

15
freqtrade/freqai/freqai_interface.py
View File

@@ -1,6 +1,7 @@
import gc
import logging
import shutil
from abc import ABC
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Any, Dict, Tuple
@@ -12,6 +13,7 @@ from freqtrade.freqai.data_handler import DataHandler
pd.options.mode.chained_assignment = None
logger = logging.getLogger(__name__)
class IFreqaiModel(ABC):
@@ -67,7 +69,7 @@ class IFreqaiModel(ABC):
self.pair = metadata["pair"]
self.dh = DataHandler(self.config, dataframe)
print(
logger.info(
"going to train",
len(self.dh.training_timeranges),
"timeranges:",
@@ -88,7 +90,7 @@ class IFreqaiModel(ABC):
self.freqai_info["training_timerange"] = tr_train
dataframe_train = self.dh.slice_dataframe(tr_train, dataframe)
dataframe_backtest = self.dh.slice_dataframe(tr_backtest, dataframe)
print("training", self.pair, "for", tr_train)
logger.info("training", self.pair, "for", tr_train)
# self.dh.model_path = self.full_path + "/" + "sub-train" + "-" + str(tr_train) + "/"
self.dh.model_path = Path(self.full_path / str("sub-train" + "-" + str(tr_train)))
if not self.model_exists(self.pair, training_timerange=tr_train):
@@ -114,6 +116,7 @@ class IFreqaiModel(ABC):
return dataframe
@abstractmethod
def train(self, unfiltered_dataframe: DataFrame, metadata: dict) -> Any:
"""
Filter the training data and train a model to it. Train makes heavy use of the datahandler
@@ -127,6 +130,7 @@ class IFreqaiModel(ABC):
return Any
@abstractmethod
def fit(self) -> Any:
"""
Most regressors use the same function names and arguments e.g. user
@@ -139,6 +143,7 @@ class IFreqaiModel(ABC):
return Any
@abstractmethod
def predict(self, dataframe: DataFrame) -> Tuple[np.array, np.array]:
"""
Filter the prediction features data and predict with it.
@@ -162,7 +167,7 @@ class IFreqaiModel(ABC):
path_to_modelfile = Path(self.dh.model_path / str(self.dh.model_filename + "_model.joblib"))
file_exists = path_to_modelfile.is_file()
if file_exists:
print("Found model at", self.dh.model_path / self.dh.model_filename)
logger.info("Found model at", self.dh.model_path / self.dh.model_filename)
else:
print("Could not find model at", self.dh.model_path / self.dh.model_filename)
logger.info("Could not find model at", self.dh.model_path / self.dh.model_filename)
return file_exists