add tests for outlier detection and removal functions

freqtrade/freqai/data_drawer.py

@@ -566,7 +566,7 @@ class FreqaiDataDrawer:
         for training according to user defined train_period_days
         metadata: dict = strategy furnished pair metadata
         """
-
+        import pytest 
         with self.history_lock:
             corr_dataframes: Dict[Any, Any] = {}
             base_dataframes: Dict[Any, Any] = {}
@@ -576,6 +576,7 @@ class FreqaiDataDrawer:
             )
 
             for tf in self.freqai_info["feature_parameters"].get("include_timeframes"):
+                # pytest.set_trace()
                 base_dataframes[tf] = dk.slice_dataframe(timerange, historic_data[pair][tf])
                 if pairs:
                     for p in pairs:

freqtrade/freqai/data_kitchen.py

@@ -657,7 +657,7 @@ class FreqaiDataKitchen:
                 return (x, y)
 
             MinPts = int(len(self.data_dictionary['train_features'].index) * 0.25)
-            # measure pairwise distances to train_features.shape[1]*2 nearest neighbours
+            # measure pairwise distances to nearest neighbours
             neighbors = NearestNeighbors(
                 n_neighbors=MinPts, n_jobs=self.thread_count)
             neighbors_fit = neighbors.fit(self.data_dictionary['train_features'])

tests/freqai/conftest.py

@@ -2,7 +2,7 @@ from copy import deepcopy
 from pathlib import Path
 
 import pytest
-
+from unittest.mock import MagicMock
 from freqtrade.configuration import TimeRange
 from freqtrade.data.dataprovider import DataProvider
 from freqtrade.freqai.data_drawer import FreqaiDataDrawer
@@ -81,6 +81,51 @@ def get_patched_freqaimodel(mocker, freqaiconf):
     return freqaimodel
 
 
+def make_data_dictionary(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)
+
+    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)
+
+    data_dictionary = freqai.dk.normalize_data(data_dictionary)
+
+    return freqai
+
+
 def get_freqai_live_analyzed_dataframe(mocker, freqaiconf):
     strategy = get_patched_freqai_strategy(mocker, freqaiconf)
     exchange = get_patched_exchange(mocker, freqaiconf)

tests/freqai/test_freqai_datakitchen.py

@@ -5,8 +5,8 @@ from pathlib import Path
 import pytest
 
 from freqtrade.exceptions import OperationalException
-from tests.freqai.conftest import get_patched_data_kitchen
-
+from tests.freqai.conftest import get_patched_data_kitchen, make_data_dictionary
+from tests.conftest import log_has_re
 
 @pytest.mark.parametrize(
     "timerange, train_period_days, expected_result",
@@ -66,3 +66,30 @@ def test_check_if_model_expired(mocker, freqai_conf, timestamp, expected):
     dk = get_patched_data_kitchen(mocker, freqai_conf)
     assert dk.check_if_model_expired(timestamp) == expected
     shutil.rmtree(Path(dk.full_path))
+
+
+def test_use_DBSCAN_to_remove_outliers(mocker, freqai_conf, caplog):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    # freqai_conf['freqai']['feature_parameters'].update({"outlier_protection_percentage": 1})
+    freqai.dk.use_DBSCAN_to_remove_outliers(predict=False)
+    assert log_has_re(
+        "DBSCAN found eps of 2.42.",
+        caplog,
+    )
+
+
+def test_compute_distances(mocker, freqai_conf):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    freqai_conf['freqai']['feature_parameters'].update({"DI_threshold": 1})
+    avg_mean_dist = freqai.dk.compute_distances()
+    assert round(avg_mean_dist, 2) == 2.56
+
+
+def test_use_SVM_to_remove_outliers_and_outlier_protection(mocker, freqai_conf, caplog):
+    freqai = make_data_dictionary(mocker, freqai_conf)
+    freqai_conf['freqai']['feature_parameters'].update({"outlier_protection_percentage": 0.1})
+    freqai.dk.use_SVM_to_remove_outliers(predict=False)
+    assert log_has_re(
+        "SVM detected 8.46%",
+        caplog,
+    )