increase test coverage for dk, improve function naming, extra cleaning

freqtrade/freqai/data_kitchen.py

@@ -1,7 +1,7 @@
 import copy
-import datetime
 import logging
 import shutil
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any, Dict, List, Tuple
 
@@ -345,7 +345,7 @@ class FreqaiDataKitchen:
 
     def denormalize_labels_from_metadata(self, df: DataFrame) -> DataFrame:
         """
-        Normalize a set of data using the mean and standard deviation from
+        Denormalize a set of data using the mean and standard deviation from
         the associated training data.
         :param df: Dataframe of predictions to be denormalized
         """
@@ -384,7 +384,7 @@ class FreqaiDataKitchen:
         config_timerange = TimeRange.parse_timerange(self.config["timerange"])
         if config_timerange.stopts == 0:
             config_timerange.stopts = int(
-                datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+                datetime.now(tz=timezone.utc).timestamp()
             )
         timerange_train = copy.deepcopy(full_timerange)
         timerange_backtest = copy.deepcopy(full_timerange)
@@ -401,8 +401,8 @@ class FreqaiDataKitchen:
             timerange_train.stopts = timerange_train.startts + train_period_days
 
             first = False
-            start = datetime.datetime.utcfromtimestamp(timerange_train.startts)
+            start = datetime.utcfromtimestamp(timerange_train.startts)
-            stop = datetime.datetime.utcfromtimestamp(timerange_train.stopts)
+            stop = datetime.utcfromtimestamp(timerange_train.stopts)
             tr_training_list.append(start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d"))
             tr_training_list_timerange.append(copy.deepcopy(timerange_train))
 
@@ -415,8 +415,8 @@ class FreqaiDataKitchen:
             if timerange_backtest.stopts > config_timerange.stopts:
                 timerange_backtest.stopts = config_timerange.stopts
 
-            start = datetime.datetime.utcfromtimestamp(timerange_backtest.startts)
+            start = datetime.utcfromtimestamp(timerange_backtest.startts)
-            stop = datetime.datetime.utcfromtimestamp(timerange_backtest.stopts)
+            stop = datetime.utcfromtimestamp(timerange_backtest.stopts)
             tr_backtesting_list.append(start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d"))
             tr_backtesting_list_timerange.append(copy.deepcopy(timerange_backtest))
 
@@ -436,8 +436,8 @@ class FreqaiDataKitchen:
                    it is sliced down to just the present training period.
         """
 
-        start = datetime.datetime.fromtimestamp(timerange.startts, tz=datetime.timezone.utc)
+        start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
-        stop = datetime.datetime.fromtimestamp(timerange.stopts, tz=datetime.timezone.utc)
+        stop = datetime.fromtimestamp(timerange.stopts, tz=timezone.utc)
         df = df.loc[df["date"] >= start, :]
         df = df.loc[df["date"] <= stop, :]
 
@@ -808,6 +808,8 @@ class FreqaiDataKitchen:
                 [compute_df, inlier_metric], axis=1)
             self.data_dictionary['prediction_features'].fillna(0, inplace=True)
 
+        logger.info('Inlier metric computed and added to features.')
+
         return None
 
     def remove_beginning_points_from_data_dict(self, set_='train', no_prev_pts: int = 10):
@@ -948,14 +950,14 @@ class FreqaiDataKitchen:
                                        "Please indicate the end date of your desired backtesting. "
                                        "timerange.")
             # backtest_timerange.stopts = int(
-            #     datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+            #     datetime.now(tz=timezone.utc).timestamp()
             # )
 
         backtest_timerange.startts = (
             backtest_timerange.startts - backtest_period_days * SECONDS_IN_DAY
         )
-        start = datetime.datetime.utcfromtimestamp(backtest_timerange.startts)
+        start = datetime.utcfromtimestamp(backtest_timerange.startts)
-        stop = datetime.datetime.utcfromtimestamp(backtest_timerange.stopts)
+        stop = datetime.utcfromtimestamp(backtest_timerange.stopts)
         full_timerange = start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d")
 
         self.full_path = Path(
@@ -981,7 +983,7 @@ class FreqaiDataKitchen:
         :return:
             bool = If the model is expired or not.
         """
-        time = datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+        time = datetime.now(tz=timezone.utc).timestamp()
         elapsed_time = (time - trained_timestamp) / 3600  # hours
         max_time = self.freqai_config.get("expiration_hours", 0)
         if max_time > 0:
@@ -993,7 +995,7 @@ class FreqaiDataKitchen:
         self, trained_timestamp: int
     ) -> Tuple[bool, TimeRange, TimeRange]:
 
-        time = datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+        time = datetime.now(tz=timezone.utc).timestamp()
         trained_timerange = TimeRange()
         data_load_timerange = TimeRange()
 

freqtrade/freqai/freqai_interface.py

@@ -1,10 +1,10 @@
 # import contextlib
-import datetime
 import logging
 import shutil
 import threading
 import time
 from abc import ABC, abstractmethod
+from datetime import datetime
 from pathlib import Path
 from threading import Lock
 from typing import Any, Dict, Tuple
@@ -174,7 +174,7 @@ class IFreqaiModel(ABC):
 
                 if retrain:
                     self.train_timer('start')
-                    self.train_model_in_series(
+                    self.extract_data_and_train_model(
                         new_trained_timerange, pair, strategy, dk, data_load_timerange
                     )
                     self.train_timer('stop')
@@ -214,10 +214,10 @@ class IFreqaiModel(ABC):
             dataframe_backtest = dk.slice_dataframe(tr_backtest, dataframe)
 
             trained_timestamp = tr_train
-            tr_train_startts_str = datetime.datetime.utcfromtimestamp(tr_train.startts).strftime(
+            tr_train_startts_str = datetime.utcfromtimestamp(tr_train.startts).strftime(
                 "%Y-%m-%d %H:%M:%S"
             )
-            tr_train_stopts_str = datetime.datetime.utcfromtimestamp(tr_train.stopts).strftime(
+            tr_train_stopts_str = datetime.utcfromtimestamp(tr_train.stopts).strftime(
                 "%Y-%m-%d %H:%M:%S"
             )
             logger.info(
@@ -495,7 +495,7 @@ class IFreqaiModel(ABC):
             Path(self.full_path, Path(self.config["config_files"][0]).name),
         )
 
-    def train_model_in_series(
+    def extract_data_and_train_model(
         self,
         new_trained_timerange: TimeRange,
         pair: str,

tests/freqai/conftest.py

@@ -82,6 +82,38 @@ def get_patched_freqaimodel(mocker, freqaiconf):
     return freqaimodel
 
 
+def make_unfiltered_dataframe(mocker, freqai_conf):
+    freqai_conf.update({"timerange": "20180110-20180130"})
+
+    strategy = get_patched_freqai_strategy(mocker, freqai_conf)
+    exchange = get_patched_exchange(mocker, freqai_conf)
+    strategy.dp = DataProvider(freqai_conf, exchange)
+    strategy.freqai_info = freqai_conf.get("freqai", {})
+    freqai = strategy.freqai
+    freqai.live = True
+    freqai.dk = FreqaiDataKitchen(freqai_conf)
+    freqai.dk.pair = "ADA/BTC"
+    timerange = TimeRange.parse_timerange("20180110-20180130")
+    freqai.dd.load_all_pair_histories(timerange, freqai.dk)
+
+    freqai.dd.pair_dict = MagicMock()
+
+    data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
+    new_timerange = TimeRange.parse_timerange("20180120-20180130")
+
+    corr_dataframes, base_dataframes = freqai.dd.get_base_and_corr_dataframes(
+            data_load_timerange, freqai.dk.pair, freqai.dk
+        )
+
+    unfiltered_dataframe = freqai.dk.use_strategy_to_populate_indicators(
+                strategy, corr_dataframes, base_dataframes, freqai.dk.pair
+            )
+
+    unfiltered_dataframe = freqai.dk.slice_dataframe(new_timerange, unfiltered_dataframe)
+
+    return freqai, unfiltered_dataframe
+
+
 def make_data_dictionary(mocker, freqai_conf):
     freqai_conf.update({"timerange": "20180110-20180130"})
 

tests/freqai/test_freqai_datakitchen.py

@@ -6,7 +6,8 @@ import pytest
 
 from freqtrade.exceptions import OperationalException
 from tests.conftest import log_has_re
-from tests.freqai.conftest import get_patched_data_kitchen, make_data_dictionary
+from tests.freqai.conftest import (get_patched_data_kitchen, make_data_dictionary,
+                                   make_unfiltered_dataframe)
 
 
 @pytest.mark.parametrize(
@@ -94,3 +95,72 @@ def test_use_SVM_to_remove_outliers_and_outlier_protection(mocker, freqai_conf,
         "SVM detected 8.46%",
         caplog,
     )
+
+
+def test_compute_inlier_metric(mocker, freqai_conf, caplog):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    freqai_conf['freqai']['feature_parameters'].update({"inlier_metric_window": 10})
+    freqai.dk.compute_inlier_metric(set_='train')
+    assert log_has_re(
+        "Inlier metric computed and added to features.",
+        caplog,
+    )
+
+
+def test_add_noise_to_training_features(mocker, freqai_conf):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    freqai_conf['freqai']['feature_parameters'].update({"noise_standard_deviation": 0.1})
+    freqai.dk.add_noise_to_training_features()
+
+
+def test_remove_beginning_points_from_data_dict(mocker, freqai_conf):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    freqai.dk.remove_beginning_points_from_data_dict(set_='train')
+
+
+def test_principal_component_analysis(mocker, freqai_conf, caplog):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    freqai.dk.principal_component_analysis()
+    assert log_has_re(
+        "reduced feature dimension by",
+        caplog,
+    )
+
+
+def test_normalize_data(mocker, freqai_conf):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    data_dict = freqai.dk.data_dictionary
+    freqai.dk.normalize_data(data_dict)
+    assert len(freqai.dk.data) == 56
+
+
+def test_filter_features(mocker, freqai_conf):
+    freqai, unfiltered_dataframe = make_unfiltered_dataframe(mocker, freqai_conf)
+    freqai.dk.find_features(unfiltered_dataframe)
+
+    filtered_df, labels = freqai.dk.filter_features(
+            unfiltered_dataframe,
+            freqai.dk.training_features_list,
+            freqai.dk.label_list,
+            training_filter=True,
+    )
+
+    assert len(filtered_df.columns) == 26
+
+
+def test_make_train_test_datasets(mocker, freqai_conf):
+    freqai, unfiltered_dataframe = make_unfiltered_dataframe(mocker, freqai_conf)
+    freqai.dk.find_features(unfiltered_dataframe)
+
+    features_filtered, labels_filtered = freqai.dk.filter_features(
+            unfiltered_dataframe,
+            freqai.dk.training_features_list,
+            freqai.dk.label_list,
+            training_filter=True,
+        )
+
+    data_dictionary = freqai.dk.make_train_test_datasets(features_filtered, labels_filtered)
+
+    assert data_dictionary
+    assert len(data_dictionary) == 7
+    assert len(data_dictionary['train_features'].index) == 1916

tests/freqai/test_freqai_interface.py

@@ -17,7 +17,7 @@ def is_arm() -> bool:
     return "arm" in machine or "aarch64" in machine
 
 
-def test_train_model_in_series_LightGBM(mocker, freqai_conf):
+def test_extract_data_and_train_model_LightGBM(mocker, freqai_conf):
     freqai_conf.update({"timerange": "20180110-20180130"})
 
     strategy = get_patched_freqai_strategy(mocker, freqai_conf)
@@ -35,7 +35,8 @@ def test_train_model_in_series_LightGBM(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
+    freqai.extract_data_and_train_model(
+        new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
 
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_model.joblib").is_file()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").is_file()
@@ -45,7 +46,7 @@ def test_train_model_in_series_LightGBM(mocker, freqai_conf):
     shutil.rmtree(Path(freqai.dk.full_path))
 
 
-def test_train_model_in_series_LightGBMMultiModel(mocker, freqai_conf):
+def test_extract_data_and_train_model_LightGBMMultiModel(mocker, freqai_conf):
     freqai_conf.update({"timerange": "20180110-20180130"})
     freqai_conf.update({"strategy": "freqai_test_multimodel_strat"})
     freqai_conf.update({"freqaimodel": "LightGBMRegressorMultiTarget"})
@@ -64,7 +65,8 @@ def test_train_model_in_series_LightGBMMultiModel(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
+    freqai.extract_data_and_train_model(
+        new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
 
     assert len(freqai.dk.label_list) == 2
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_model.joblib").is_file()
@@ -77,7 +79,7 @@ def test_train_model_in_series_LightGBMMultiModel(mocker, freqai_conf):
 
 
 @pytest.mark.skipif(is_arm(), reason="no ARM for Catboost ...")
-def test_train_model_in_series_Catboost(mocker, freqai_conf):
+def test_extract_data_and_train_model_Catboost(mocker, freqai_conf):
     freqai_conf.update({"timerange": "20180110-20180130"})
     freqai_conf.update({"freqaimodel": "CatboostRegressor"})
     # freqai_conf.get('freqai', {}).update(
@@ -98,8 +100,8 @@ def test_train_model_in_series_Catboost(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC",
+    freqai.extract_data_and_train_model(new_timerange, "ADA/BTC",
-                                 strategy, freqai.dk, data_load_timerange)
+                                        strategy, freqai.dk, data_load_timerange)
 
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_model.joblib").exists()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").exists()
@@ -110,7 +112,7 @@ def test_train_model_in_series_Catboost(mocker, freqai_conf):
 
 
 @pytest.mark.skipif(is_arm(), reason="no ARM for Catboost ...")
-def test_train_model_in_series_CatboostClassifier(mocker, freqai_conf):
+def test_extract_data_and_train_model_CatboostClassifier(mocker, freqai_conf):
     freqai_conf.update({"timerange": "20180110-20180130"})
     freqai_conf.update({"freqaimodel": "CatboostClassifier"})
     freqai_conf.update({"strategy": "freqai_test_classifier"})
@@ -130,8 +132,8 @@ def test_train_model_in_series_CatboostClassifier(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC",
+    freqai.extract_data_and_train_model(new_timerange, "ADA/BTC",
-                                 strategy, freqai.dk, data_load_timerange)
+                                        strategy, freqai.dk, data_load_timerange)
 
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_model.joblib").exists()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").exists()
@@ -141,7 +143,7 @@ def test_train_model_in_series_CatboostClassifier(mocker, freqai_conf):
     shutil.rmtree(Path(freqai.dk.full_path))
 
 
-def test_train_model_in_series_LightGBMClassifier(mocker, freqai_conf):
+def test_extract_data_and_train_model_LightGBMClassifier(mocker, freqai_conf):
     freqai_conf.update({"timerange": "20180110-20180130"})
     freqai_conf.update({"freqaimodel": "LightGBMClassifier"})
     freqai_conf.update({"strategy": "freqai_test_classifier"})
@@ -161,8 +163,8 @@ def test_train_model_in_series_LightGBMClassifier(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC",
+    freqai.extract_data_and_train_model(new_timerange, "ADA/BTC",
-                                 strategy, freqai.dk, data_load_timerange)
+                                        strategy, freqai.dk, data_load_timerange)
 
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_model.joblib").exists()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").exists()
@@ -289,7 +291,8 @@ def test_follow_mode(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
+    freqai.extract_data_and_train_model(
+        new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
 
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_model.joblib").is_file()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").is_file()
@@ -338,7 +341,8 @@ def test_principal_component_analysis(mocker, freqai_conf):
     data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
     new_timerange = TimeRange.parse_timerange("20180120-20180130")
 
-    freqai.train_model_in_series(new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
+    freqai.extract_data_and_train_model(
+        new_timerange, "ADA/BTC", strategy, freqai.dk, data_load_timerange)
 
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_pca_object.pkl")