improve freqai tests

tests/freqai/conftest.py

@@ -29,15 +29,16 @@ def freqai_conf(default_conf, tmpdir):
                 "enabled": True,
                 "startup_candles": 10000,
                 "purge_old_models": True,
-                "train_period_days": 5,
+                "train_period_days": 2,
                 "backtest_period_days": 2,
                 "live_retrain_hours": 0,
                 "expiration_hours": 1,
                 "identifier": "uniqe-id100",
                 "live_trained_timestamp": 0,
+                "data_kitchen_thread_count": 2,
                 "feature_parameters": {
                     "include_timeframes": ["5m"],
-                    "include_corr_pairlist": ["ADA/BTC", "DASH/BTC"],
+                    "include_corr_pairlist": ["ADA/BTC"],
                     "label_period_candles": 20,
                     "include_shifted_candles": 1,
                     "DI_threshold": 0.9,
@@ -47,7 +48,7 @@ def freqai_conf(default_conf, tmpdir):
                     "stratify_training_data": 0,
                     "indicator_periods_candles": [10],
                 },
-                "data_split_parameters": {"test_size": 0.33, "random_state": 1},
+                "data_split_parameters": {"test_size": 0.33, "shuffle": False},
                 "model_training_parameters": {"n_estimators": 100},
             },
             "config_files": [Path('config_examples', 'config_freqai.example.json')]

tests/freqai/test_freqai_datadrawer.py

@@ -90,5 +90,5 @@ def test_use_strategy_to_populate_indicators(mocker, freqai_conf):
 
     df = freqai.dk.use_strategy_to_populate_indicators(strategy, corr_df, base_df, 'LTC/BTC')
 
-    assert len(df.columns) == 45
+    assert len(df.columns) == 33
     shutil.rmtree(Path(freqai.dk.full_path))

tests/freqai/test_freqai_datakitchen.py

@@ -71,14 +71,14 @@ 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(r"DBSCAN found eps of 2\.3\d\.", caplog)
+    assert log_has_re(r"DBSCAN found eps of 1.75", 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) == 2.54
+    assert round(avg_mean_dist, 2) == 1.99
 
 
 def test_use_SVM_to_remove_outliers_and_outlier_protection(mocker, freqai_conf, caplog):
@@ -86,7 +86,7 @@ def test_use_SVM_to_remove_outliers_and_outlier_protection(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 8.66%",
+        "SVM detected 7.36%",
         caplog,
     )
 
@@ -125,7 +125,7 @@ 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
+    assert len(freqai.dk.data) == 32
 
 
 def test_filter_features(mocker, freqai_conf):
@@ -139,7 +139,7 @@ def test_filter_features(mocker, freqai_conf):
             training_filter=True,
     )
 
-    assert len(filtered_df.columns) == 26
+    assert len(filtered_df.columns) == 14
 
 
 def test_make_train_test_datasets(mocker, freqai_conf):

tests/freqai/test_freqai_interface.py

@@ -7,10 +7,14 @@ import pytest
 
 from freqtrade.configuration import TimeRange
 from freqtrade.data.dataprovider import DataProvider
+from freqtrade.enums import RunMode
 from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+from freqtrade.freqai.utils import download_all_data_for_training, get_required_data_timerange
+from freqtrade.persistence import Trade
 from freqtrade.plugins.pairlistmanager import PairListManager
 from tests.conftest import get_patched_exchange, log_has_re
 from tests.freqai.conftest import get_patched_freqai_strategy
+from freqtrade.optimize.backtesting import Backtesting
 
 
 def is_arm() -> bool:
@@ -18,15 +22,21 @@ def is_arm() -> bool:
     return "arm" in machine or "aarch64" in machine
 
 
+def is_mac() -> bool:
+    machine = platform.system()
+    return "Darwin" in machine
+
+
 @pytest.mark.parametrize('model', [
     'LightGBMRegressor',
     'XGBoostRegressor',
     'CatboostRegressor',
     ])
-def test_extract_data_and_train_model_Regressors(mocker, freqai_conf, model):
+def test_extract_data_and_train_model_Standard(mocker, freqai_conf, model):
     if is_arm() and model == 'CatboostRegressor':
         pytest.skip("CatBoost is not supported on ARM")
 
+    model_save_ext = 'joblib'
     freqai_conf.update({"freqaimodel": model})
     freqai_conf.update({"timerange": "20180110-20180130"})
     freqai_conf.update({"strategy": "freqai_test_strat"})
@@ -43,16 +53,16 @@ def test_extract_data_and_train_model_Regressors(mocker, freqai_conf, model):
 
     freqai.dd.pair_dict = MagicMock()
 
-    data_load_timerange = TimeRange.parse_timerange("20180110-20180130")
+    data_load_timerange = TimeRange.parse_timerange("20180125-20180130")
-    new_timerange = TimeRange.parse_timerange("20180120-20180130")
+    new_timerange = TimeRange.parse_timerange("20180127-20180130")
 
     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}_model.{model_save_ext}").is_file()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").is_file()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_trained_df.pkl").is_file()
-    assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_svm_model.joblib").is_file()
 
     shutil.rmtree(Path(freqai.dk.full_path))
 
@@ -92,7 +102,7 @@ def test_extract_data_and_train_model_MultiTargets(mocker, freqai_conf, model):
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").is_file()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_trained_df.pkl").is_file()
     assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_svm_model.joblib").is_file()
-    assert len(freqai.dk.data['training_features_list']) == 26
+    assert len(freqai.dk.data['training_features_list']) == 14
 
     shutil.rmtree(Path(freqai.dk.full_path))
 
@@ -136,9 +146,28 @@ def test_extract_data_and_train_model_Classifiers(mocker, freqai_conf, model):
     shutil.rmtree(Path(freqai.dk.full_path))
 
 
-def test_start_backtesting(mocker, freqai_conf):
+@pytest.mark.parametrize(
-    freqai_conf.update({"timerange": "20180120-20180130"})
+    "model, num_files, strat",
+    [
+        ("LightGBMRegressor", 6, "freqai_test_strat"),
+        ("XGBoostRegressor", 6, "freqai_test_strat"),
+        ("CatboostRegressor", 6, "freqai_test_strat"),
+        ("XGBoostClassifier", 6, "freqai_test_classifier"),
+        ("LightGBMClassifier", 6, "freqai_test_classifier"),
+        ("CatboostClassifier", 6, "freqai_test_classifier")
+    ],
+    )
+def test_start_backtesting(mocker, freqai_conf, model, num_files, strat):
     freqai_conf.get("freqai", {}).update({"save_backtest_models": True})
+    freqai_conf['runmode'] = RunMode.BACKTEST
+    Trade.use_db = False
+    if is_arm() and "Catboost" in model:
+        pytest.skip("CatBoost is not supported on ARM")
+
+    freqai_conf.update({"freqaimodel": model})
+    freqai_conf.update({"timerange": "20180120-20180130"})
+    freqai_conf.update({"strategy": strat})
+
     strategy = get_patched_freqai_strategy(mocker, freqai_conf)
     exchange = get_patched_exchange(mocker, freqai_conf)
     strategy.dp = DataProvider(freqai_conf, exchange)
@@ -157,8 +186,8 @@ def test_start_backtesting(mocker, freqai_conf):
     freqai.start_backtesting(df, metadata, freqai.dk)
     model_folders = [x for x in freqai.dd.full_path.iterdir() if x.is_dir()]
 
-    assert len(model_folders) == 6
+    assert len(model_folders) == num_files
-
+    Backtesting.cleanup()
     shutil.rmtree(Path(freqai.dk.full_path))
 
 
@@ -211,7 +240,7 @@ def test_start_backtesting_from_existing_folder(mocker, freqai_conf, caplog):
 
     assert len(model_folders) == 6
 
-    # without deleting the exiting folder structure, re-run
+    # without deleting the existing folder structure, re-run
 
     freqai_conf.update({"timerange": "20180120-20180130"})
     strategy = get_patched_freqai_strategy(mocker, freqai_conf)
@@ -375,3 +404,40 @@ def test_freqai_informative_pairs(mocker, freqai_conf, timeframes, corr_pairs):
     pairs_b = strategy.gather_informative_pairs()
     # we expect unique pairs * timeframes
     assert len(pairs_b) == len(set(pairlist + corr_pairs)) * len(timeframes)
+
+
+def test_start_set_train_queue(mocker, freqai_conf, caplog):
+    strategy = get_patched_freqai_strategy(mocker, freqai_conf)
+    exchange = get_patched_exchange(mocker, freqai_conf)
+    pairlist = PairListManager(exchange, freqai_conf)
+    strategy.dp = DataProvider(freqai_conf, exchange, pairlist)
+    strategy.freqai_info = freqai_conf.get("freqai", {})
+    freqai = strategy.freqai
+    freqai.live = False
+
+    freqai.train_queue = freqai._set_train_queue()
+
+    assert log_has_re(
+        "Set fresh train queue from whitelist.",
+        caplog,
+    )
+
+
+def test_get_required_data_timerange(mocker, freqai_conf):
+    time_range = get_required_data_timerange(freqai_conf)
+    assert (time_range.stopts - time_range.startts) == 177300
+
+
+def test_download_all_data_for_training(mocker, freqai_conf, caplog, tmpdir):
+    strategy = get_patched_freqai_strategy(mocker, freqai_conf)
+    exchange = get_patched_exchange(mocker, freqai_conf)
+    pairlist = PairListManager(exchange, freqai_conf)
+    strategy.dp = DataProvider(freqai_conf, exchange, pairlist)
+    freqai_conf['pairs'] = freqai_conf['exchange']['pair_whitelist']
+    freqai_conf['datadir'] = Path(tmpdir)
+    download_all_data_for_training(strategy.dp, freqai_conf)
+
+    assert log_has_re(
+        "Downloading",
+        caplog,
+    )