diff --git a/Dockerfile b/Dockerfile index e84a4d095..b3e5d5e88 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,4 +1,4 @@ -FROM python:3.10.6-slim-bullseye as base +FROM python:3.10.7-slim-bullseye as base # Setup env ENV LANG C.UTF-8 diff --git a/docs/backtesting.md b/docs/backtesting.md index 8b2fdc345..f20a53d22 100644 --- a/docs/backtesting.md +++ b/docs/backtesting.md @@ -107,7 +107,7 @@ Strategy arguments: ## Test your strategy with Backtesting -Now you have good Buy and Sell strategies and some historic data, you want to test it against +Now you have good Entry and exit strategies and some historic data, you want to test it against real data. This is what we call [backtesting](https://en.wikipedia.org/wiki/Backtesting). Backtesting will use the crypto-currencies (pairs) from your config file and load historical candle (OHLCV) data from `user_data/data/` by default. @@ -215,7 +215,7 @@ Sometimes your account has certain fee rebates (fee reductions starting with a c To account for this in backtesting, you can use the `--fee` command line option to supply this value to backtesting. This fee must be a ratio, and will be applied twice (once for trade entry, and once for trade exit). -For example, if the buying and selling commission fee is 0.1% (i.e., 0.001 written as ratio), then you would run backtesting as the following: +For example, if the commission fee per order is 0.1% (i.e., 0.001 written as ratio), then you would run backtesting as the following: ```bash freqtrade backtesting --fee 0.001 @@ -252,41 +252,41 @@ The most important in the backtesting is to understand the result. A backtesting result will look like that: ``` -========================================================= BACKTESTING REPORT ========================================================== -| Pair | Buys | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % | Avg Duration | Wins Draws Loss Win% | -|:---------|-------:|---------------:|---------------:|-----------------:|---------------:|:-------------|-------------------------:| -| ADA/BTC | 35 | -0.11 | -3.88 | -0.00019428 | -1.94 | 4:35:00 | 14 0 21 40.0 | -| ARK/BTC | 11 | -0.41 | -4.52 | -0.00022647 | -2.26 | 2:03:00 | 3 0 8 27.3 | -| BTS/BTC | 32 | 0.31 | 9.78 | 0.00048938 | 4.89 | 5:05:00 | 18 0 14 56.2 | -| DASH/BTC | 13 | -0.08 | -1.07 | -0.00005343 | -0.53 | 4:39:00 | 6 0 7 46.2 | -| ENG/BTC | 18 | 1.36 | 24.54 | 0.00122807 | 12.27 | 2:50:00 | 8 0 10 44.4 | -| EOS/BTC | 36 | 0.08 | 3.06 | 0.00015304 | 1.53 | 3:34:00 | 16 0 20 44.4 | -| ETC/BTC | 26 | 0.37 | 9.51 | 0.00047576 | 4.75 | 6:14:00 | 11 0 15 42.3 | -| ETH/BTC | 33 | 0.30 | 9.96 | 0.00049856 | 4.98 | 7:31:00 | 16 0 17 48.5 | -| IOTA/BTC | 32 | 0.03 | 1.09 | 0.00005444 | 0.54 | 3:12:00 | 14 0 18 43.8 | -| LSK/BTC | 15 | 1.75 | 26.26 | 0.00131413 | 13.13 | 2:58:00 | 6 0 9 40.0 | -| LTC/BTC | 32 | -0.04 | -1.38 | -0.00006886 | -0.69 | 4:49:00 | 11 0 21 34.4 | -| NANO/BTC | 17 | 1.26 | 21.39 | 0.00107058 | 10.70 | 1:55:00 | 10 0 7 58.5 | -| NEO/BTC | 23 | 0.82 | 18.97 | 0.00094936 | 9.48 | 2:59:00 | 10 0 13 43.5 | -| REQ/BTC | 9 | 1.17 | 10.54 | 0.00052734 | 5.27 | 3:47:00 | 4 0 5 44.4 | -| XLM/BTC | 16 | 1.22 | 19.54 | 0.00097800 | 9.77 | 3:15:00 | 7 0 9 43.8 | -| XMR/BTC | 23 | -0.18 | -4.13 | -0.00020696 | -2.07 | 5:30:00 | 12 0 11 52.2 | -| XRP/BTC | 35 | 0.66 | 22.96 | 0.00114897 | 11.48 | 3:49:00 | 12 0 23 34.3 | -| ZEC/BTC | 22 | -0.46 | -10.18 | -0.00050971 | -5.09 | 2:22:00 | 7 0 15 31.8 | -| TOTAL | 429 | 0.36 | 152.41 | 0.00762792 | 76.20 | 4:12:00 | 186 0 243 43.4 | +========================================================= BACKTESTING REPORT ========================================================= +| Pair | Entries | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % | Avg Duration | Wins Draws Loss Win% | +|:---------|--------:|---------------:|---------------:|-----------------:|---------------:|:-------------|-------------------------:| +| ADA/BTC | 35 | -0.11 | -3.88 | -0.00019428 | -1.94 | 4:35:00 | 14 0 21 40.0 | +| ARK/BTC | 11 | -0.41 | -4.52 | -0.00022647 | -2.26 | 2:03:00 | 3 0 8 27.3 | +| BTS/BTC | 32 | 0.31 | 9.78 | 0.00048938 | 4.89 | 5:05:00 | 18 0 14 56.2 | +| DASH/BTC | 13 | -0.08 | -1.07 | -0.00005343 | -0.53 | 4:39:00 | 6 0 7 46.2 | +| ENG/BTC | 18 | 1.36 | 24.54 | 0.00122807 | 12.27 | 2:50:00 | 8 0 10 44.4 | +| EOS/BTC | 36 | 0.08 | 3.06 | 0.00015304 | 1.53 | 3:34:00 | 16 0 20 44.4 | +| ETC/BTC | 26 | 0.37 | 9.51 | 0.00047576 | 4.75 | 6:14:00 | 11 0 15 42.3 | +| ETH/BTC | 33 | 0.30 | 9.96 | 0.00049856 | 4.98 | 7:31:00 | 16 0 17 48.5 | +| IOTA/BTC | 32 | 0.03 | 1.09 | 0.00005444 | 0.54 | 3:12:00 | 14 0 18 43.8 | +| LSK/BTC | 15 | 1.75 | 26.26 | 0.00131413 | 13.13 | 2:58:00 | 6 0 9 40.0 | +| LTC/BTC | 32 | -0.04 | -1.38 | -0.00006886 | -0.69 | 4:49:00 | 11 0 21 34.4 | +| NANO/BTC | 17 | 1.26 | 21.39 | 0.00107058 | 10.70 | 1:55:00 | 10 0 7 58.5 | +| NEO/BTC | 23 | 0.82 | 18.97 | 0.00094936 | 9.48 | 2:59:00 | 10 0 13 43.5 | +| REQ/BTC | 9 | 1.17 | 10.54 | 0.00052734 | 5.27 | 3:47:00 | 4 0 5 44.4 | +| XLM/BTC | 16 | 1.22 | 19.54 | 0.00097800 | 9.77 | 3:15:00 | 7 0 9 43.8 | +| XMR/BTC | 23 | -0.18 | -4.13 | -0.00020696 | -2.07 | 5:30:00 | 12 0 11 52.2 | +| XRP/BTC | 35 | 0.66 | 22.96 | 0.00114897 | 11.48 | 3:49:00 | 12 0 23 34.3 | +| ZEC/BTC | 22 | -0.46 | -10.18 | -0.00050971 | -5.09 | 2:22:00 | 7 0 15 31.8 | +| TOTAL | 429 | 0.36 | 152.41 | 0.00762792 | 76.20 | 4:12:00 | 186 0 243 43.4 | ========================================================= EXIT REASON STATS ========================================================== -| Exit Reason | Sells | Wins | Draws | Losses | +| Exit Reason | Exits | Wins | Draws | Losses | |:-------------------|--------:|------:|-------:|--------:| | trailing_stop_loss | 205 | 150 | 0 | 55 | | stop_loss | 166 | 0 | 0 | 166 | | exit_signal | 56 | 36 | 0 | 20 | | force_exit | 2 | 0 | 0 | 2 | ====================================================== LEFT OPEN TRADES REPORT ====================================================== -| Pair | Buys | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % | Avg Duration | Win Draw Loss Win% | -|:---------|-------:|---------------:|---------------:|-----------------:|---------------:|:---------------|--------------------:| -| ADA/BTC | 1 | 0.89 | 0.89 | 0.00004434 | 0.44 | 6:00:00 | 1 0 0 100 | -| LTC/BTC | 1 | 0.68 | 0.68 | 0.00003421 | 0.34 | 2:00:00 | 1 0 0 100 | -| TOTAL | 2 | 0.78 | 1.57 | 0.00007855 | 0.78 | 4:00:00 | 2 0 0 100 | +| Pair | Entries | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % | Avg Duration | Win Draw Loss Win% | +|:---------|---------:|---------------:|---------------:|-----------------:|---------------:|:---------------|--------------------:| +| ADA/BTC | 1 | 0.89 | 0.89 | 0.00004434 | 0.44 | 6:00:00 | 1 0 0 100 | +| LTC/BTC | 1 | 0.68 | 0.68 | 0.00003421 | 0.34 | 2:00:00 | 1 0 0 100 | +| TOTAL | 2 | 0.78 | 1.57 | 0.00007855 | 0.78 | 4:00:00 | 2 0 0 100 | ================== SUMMARY METRICS ================== | Metric | Value | |-----------------------------+---------------------| @@ -356,7 +356,7 @@ The column `Avg Profit %` shows the average profit for all trades made while the The column `Tot Profit %` shows instead the total profit % in relation to the starting balance. In the above results, we have a starting balance of 0.01 BTC and an absolute profit of 0.00762792 BTC - so the `Tot Profit %` will be `(0.00762792 / 0.01) * 100 ~= 76.2%`. -Your strategy performance is influenced by your buy strategy, your exit strategy, and also by the `minimal_roi` and `stop_loss` you have set. +Your strategy performance is influenced by your entry strategy, your exit strategy, and also by the `minimal_roi` and `stop_loss` you have set. For example, if your `minimal_roi` is only `"0": 0.01` you cannot expect the bot to make more profit than 1% (because it will exit every time a trade reaches 1%). @@ -515,7 +515,7 @@ You can then load the trades to perform further analysis as shown in the [data a Since backtesting lacks some detailed information about what happens within a candle, it needs to take a few assumptions: - Exchange [trading limits](#trading-limits-in-backtesting) are respected -- Buys happen at open-price +- Entries happen at open-price - All orders are filled at the requested price (no slippage, no unfilled orders) - Exit-signal exits happen at open-price of the consecutive candle - Exit-signal is favored over Stoploss, because exit-signals are assumed to trigger on candle's open @@ -612,11 +612,11 @@ There will be an additional table comparing win/losses of the different strategi Detailed output for all strategies one after the other will be available, so make sure to scroll up to see the details per strategy. ``` -=========================================================== STRATEGY SUMMARY ========================================================================= -| Strategy | Buys | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % | Avg Duration | Wins | Draws | Losses | Drawdown % | -|:------------|-------:|---------------:|---------------:|-----------------:|---------------:|:---------------|------:|-------:|-------:|-----------:| -| Strategy1 | 429 | 0.36 | 152.41 | 0.00762792 | 76.20 | 4:12:00 | 186 | 0 | 243 | 45.2 | -| Strategy2 | 1487 | -0.13 | -197.58 | -0.00988917 | -98.79 | 4:43:00 | 662 | 0 | 825 | 241.68 | +=========================================================== STRATEGY SUMMARY =========================================================================== +| Strategy | Entries | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % | Avg Duration | Wins | Draws | Losses | Drawdown % | +|:------------|---------:|---------------:|---------------:|-----------------:|---------------:|:---------------|------:|-------:|-------:|-----------:| +| Strategy1 | 429 | 0.36 | 152.41 | 0.00762792 | 76.20 | 4:12:00 | 186 | 0 | 243 | 45.2 | +| Strategy2 | 1487 | -0.13 | -197.58 | -0.00988917 | -98.79 | 4:43:00 | 662 | 0 | 825 | 241.68 | ``` ## Next step diff --git a/docs/freqai.md b/docs/freqai.md index 4ffc0198b..5f523f58a 100644 --- a/docs/freqai.md +++ b/docs/freqai.md @@ -98,6 +98,7 @@ Mandatory parameters are marked as **Required**, which means that they are requi | `expiration_hours` | Avoid making predictions if a model is more than `expiration_hours` old.
Defaults set to 0, which means models never expire.
**Datatype:** Positive integer. | `fit_live_predictions_candles` | Number of historical candles to use for computing target (label) statistics from prediction data, instead of from the training data set.
**Datatype:** Positive integer. | `follow_mode` | If true, this instance of FreqAI will look for models associated with `identifier` and load those for inferencing. A `follower` will **not** train new models.
**Datatype:** Boolean. Default: `False`. +| `continual_learning` | If true, FreqAI will start training new models from the final state of the most recently trained model.
**Datatype:** Boolean. Default: `False`. | | **Feature parameters** | `feature_parameters` | A dictionary containing the parameters used to engineer the feature set. Details and examples are shown [here](#feature-engineering).
**Datatype:** Dictionary. | `include_timeframes` | A list of timeframes that all indicators in `populate_any_indicators` will be created for. The list is added as features to the base asset feature set.
**Datatype:** List of timeframes (strings). @@ -281,6 +282,8 @@ The FreqAI strategy requires the user to include the following lines of code in Notice how the `populate_any_indicators()` is where the user adds their own features ([more information](#feature-engineering)) and labels ([more information](#setting-classifier-targets)). See a full example at `templates/FreqaiExampleStrategy.py`. +*Important*: The `self.freqai.start()` function cannot be called outside the `populate_indicators()`. + ### Setting the `startup_candle_count` Users need to take care to set the `startup_candle_count` in their strategy the same way they would for any normal Freqtrade strategy (see details [here](strategy-customization.md#strategy-startup-period)). This value is used by Freqtrade to ensure that a sufficient amount of data is provided when calling on the `dataprovider` to avoid any NaNs at the beginning of the first training. Users can easily set this value by identifying the longest period (in candle units) that they pass to their indicator creation functions (e.g. talib functions). In the present example, the user would pass 20 to as this value (since it is the maximum value in their `indicators_periods_candles`). @@ -534,6 +537,31 @@ for each pair, for each backtesting window within the expanded `--timerange`. --- +### Hyperopt + +Users can hyperopt using the same command as typical [hyperopt](hyperopt.md): + +```bash +freqtrade hyperopt --hyperopt-loss SharpeHyperOptLoss --strategy FreqaiExampleStrategy --freqaimodel LightGBMRegressor --strategy-path freqtrade/templates --config config_examples/config_freqai.example.json --timerange 20220428-20220507 +``` + +Users need to have the data pre-downloaded in the same fashion as if they were doing a FreqAI [backtest](#backtesting). In addition, users must consider some restrictions when trying to [Hyperopt](hyperopt.md) FreqAI strategies: + +- The `--analyze-per-epoch` hyperopt parameter is not compatible with FreqAI. +- It's not possible to hyperopt indicators in `populate_any_indicators()` function. This means that the user cannot optimize model parameters using hyperopt. Apart from this exception, it is possible to optimize all other [spaces](hyperopt.md#running-hyperopt-with-smaller-search-space). +- The [Backtesting](#backtesting) instructions also apply to Hyperopt. + +The best method for combining hyperopt and FreqAI is to focus on hyperopting entry/exit thresholds/criteria. Users need to focus on hyperopting parameters that are not used in their FreqAI features. For example, users should not try to hyperopt rolling window lengths in their feature creation, or any of their FreqAI config which changes predictions. In order to efficiently hyperopt the FreqAI strategy, FreqAI stores predictions as dataframes and reuses them. Hence the requirement to hyperopt entry/exit thresholds/criteria only. + +A good example of a hyperoptable parameter in FreqAI is a value for `DI_values` beyond which we consider outliers and below which we consider inliers: + +```python +di_max = IntParameter(low=1, high=20, default=10, space='buy', optimize=True, load=True) +dataframe['outlier'] = np.where(dataframe['DI_values'] > self.di_max.value/10, 1, 0) +``` + +Which would help the user understand the appropriate Dissimilarity Index values for their particular parameter space. + ### Deciding the size of the sliding training window and backtesting duration The user defines the backtesting timerange with the typical `--timerange` parameter in the diff --git a/freqtrade/commands/db_commands.py b/freqtrade/commands/db_commands.py index 618b5cb6e..c424016b1 100644 --- a/freqtrade/commands/db_commands.py +++ b/freqtrade/commands/db_commands.py @@ -4,7 +4,7 @@ from typing import Any, Dict from sqlalchemy import func from freqtrade.configuration.config_setup import setup_utils_configuration -from freqtrade.enums.runmode import RunMode +from freqtrade.enums import RunMode logger = logging.getLogger(__name__) diff --git a/freqtrade/configuration/config_validation.py b/freqtrade/configuration/config_validation.py index ee846e7e6..8d9112bef 100644 --- a/freqtrade/configuration/config_validation.py +++ b/freqtrade/configuration/config_validation.py @@ -84,6 +84,7 @@ def validate_config_consistency(conf: Dict[str, Any], preliminary: bool = False) _validate_protections(conf) _validate_unlimited_amount(conf) _validate_ask_orderbook(conf) + _validate_freqai_hyperopt(conf) validate_migrated_strategy_settings(conf) # validate configuration before returning @@ -323,6 +324,14 @@ def _validate_pricing_rules(conf: Dict[str, Any]) -> None: del conf['ask_strategy'] +def _validate_freqai_hyperopt(conf: Dict[str, Any]) -> None: + freqai_enabled = conf.get('freqai', {}).get('enabled', False) + analyze_per_epoch = conf.get('analyze_per_epoch', False) + if analyze_per_epoch and freqai_enabled: + raise OperationalException( + 'Using analyze-per-epoch parameter is not supported with a FreqAI strategy.') + + def _strategy_settings(conf: Dict[str, Any]) -> None: process_deprecated_setting(conf, None, 'use_sell_signal', None, 'use_exit_signal') diff --git a/freqtrade/data/history/history_utils.py b/freqtrade/data/history/history_utils.py index 7a3fa4e0c..6a6e29429 100644 --- a/freqtrade/data/history/history_utils.py +++ b/freqtrade/data/history/history_utils.py @@ -228,9 +228,9 @@ def _download_pair_history(pair: str, *, ) logger.debug("Current Start: %s", - f"{data.iloc[0]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None') + f"{data.iloc[0]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None') logger.debug("Current End: %s", - f"{data.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None') + f"{data.iloc[-1]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None') # Default since_ms to 30 days if nothing is given new_data = exchange.get_historic_ohlcv(pair=pair, @@ -254,9 +254,9 @@ def _download_pair_history(pair: str, *, fill_missing=False, drop_incomplete=False) logger.debug("New Start: %s", - f"{data.iloc[0]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None') + f"{data.iloc[0]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None') logger.debug("New End: %s", - f"{data.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None') + f"{data.iloc[-1]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None') data_handler.ohlcv_store(pair, timeframe, data=data, candle_type=candle_type) return True diff --git a/freqtrade/exchange/okx.py b/freqtrade/exchange/okx.py index 9340dd0e4..49f8ea107 100644 --- a/freqtrade/exchange/okx.py +++ b/freqtrade/exchange/okx.py @@ -4,8 +4,7 @@ from typing import Dict, List, Optional, Tuple import ccxt from freqtrade.constants import BuySell -from freqtrade.enums import MarginMode, TradingMode -from freqtrade.enums.candletype import CandleType +from freqtrade.enums import CandleType, MarginMode, TradingMode from freqtrade.exceptions import DDosProtection, OperationalException, TemporaryError from freqtrade.exchange import Exchange, date_minus_candles from freqtrade.exchange.common import retrier diff --git a/freqtrade/freqai/prediction_models/BaseClassifierModel.py b/freqtrade/freqai/base_models/BaseClassifierModel.py similarity index 76% rename from freqtrade/freqai/prediction_models/BaseClassifierModel.py rename to freqtrade/freqai/base_models/BaseClassifierModel.py index 2edbf3b51..5142ffb0d 100644 --- a/freqtrade/freqai/prediction_models/BaseClassifierModel.py +++ b/freqtrade/freqai/base_models/BaseClassifierModel.py @@ -21,12 +21,12 @@ class BaseClassifierModel(IFreqaiModel): """ def train( - self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen + 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_dataframe: Full dataframe for the current training period + :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) @@ -36,14 +36,14 @@ class BaseClassifierModel(IFreqaiModel): # filter the features requested by user in the configuration file and elegantly handle NaNs features_filtered, labels_filtered = dk.filter_features( - unfiltered_dataframe, + unfiltered_df, dk.training_features_list, dk.label_list, training_filter=True, ) - start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d") - end_date = unfiltered_dataframe["date"].iloc[-1].strftime("%Y-%m-%d") + 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. @@ -61,32 +61,32 @@ class BaseClassifierModel(IFreqaiModel): ) logger.info(f'Training model on {len(data_dictionary["train_features"])} data points') - model = self.fit(data_dictionary) + model = self.fit(data_dictionary, dk) logger.info(f"--------------------done training {pair}--------------------") return model def predict( - self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False + self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs ) -> Tuple[DataFrame, npt.NDArray[np.int_]]: """ Filter the prediction features data and predict with it. - :param: unfiltered_dataframe: Full dataframe for the current backtest period. + :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_dataframe) - filtered_dataframe, _ = dk.filter_features( - unfiltered_dataframe, dk.training_features_list, training_filter=False + dk.find_features(unfiltered_df) + filtered_df, _ = dk.filter_features( + unfiltered_df, dk.training_features_list, training_filter=False ) - filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe) - dk.data_dictionary["prediction_features"] = filtered_dataframe + filtered_df = dk.normalize_data_from_metadata(filtered_df) + dk.data_dictionary["prediction_features"] = filtered_df - self.data_cleaning_predict(dk, filtered_dataframe) + self.data_cleaning_predict(dk, filtered_df) predictions = self.model.predict(dk.data_dictionary["prediction_features"]) pred_df = DataFrame(predictions, columns=dk.label_list) diff --git a/freqtrade/freqai/prediction_models/BaseRegressionModel.py b/freqtrade/freqai/base_models/BaseRegressionModel.py similarity index 75% rename from freqtrade/freqai/prediction_models/BaseRegressionModel.py rename to freqtrade/freqai/base_models/BaseRegressionModel.py index 2ef175a2e..1d87e42c0 100644 --- a/freqtrade/freqai/prediction_models/BaseRegressionModel.py +++ b/freqtrade/freqai/base_models/BaseRegressionModel.py @@ -20,12 +20,12 @@ class BaseRegressionModel(IFreqaiModel): """ def train( - self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen + 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_dataframe: Full dataframe for the current training period + :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) @@ -35,14 +35,14 @@ class BaseRegressionModel(IFreqaiModel): # filter the features requested by user in the configuration file and elegantly handle NaNs features_filtered, labels_filtered = dk.filter_features( - unfiltered_dataframe, + unfiltered_df, dk.training_features_list, dk.label_list, training_filter=True, ) - start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d") - end_date = unfiltered_dataframe["date"].iloc[-1].strftime("%Y-%m-%d") + 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. @@ -60,33 +60,33 @@ class BaseRegressionModel(IFreqaiModel): ) logger.info(f'Training model on {len(data_dictionary["train_features"])} data points') - model = self.fit(data_dictionary) + model = self.fit(data_dictionary, dk) logger.info(f"--------------------done training {pair}--------------------") return model def predict( - self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False + self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs ) -> Tuple[DataFrame, npt.NDArray[np.int_]]: """ Filter the prediction features data and predict with it. - :param: unfiltered_dataframe: Full dataframe for the current backtest period. + :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_dataframe) - filtered_dataframe, _ = dk.filter_features( - unfiltered_dataframe, dk.training_features_list, training_filter=False + dk.find_features(unfiltered_df) + filtered_df, _ = dk.filter_features( + unfiltered_df, dk.training_features_list, training_filter=False ) - filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe) - dk.data_dictionary["prediction_features"] = filtered_dataframe + filtered_df = dk.normalize_data_from_metadata(filtered_df) + dk.data_dictionary["prediction_features"] = filtered_df # optional additional data cleaning/analysis - self.data_cleaning_predict(dk, filtered_dataframe) + self.data_cleaning_predict(dk, filtered_df) predictions = self.model.predict(dk.data_dictionary["prediction_features"]) pred_df = DataFrame(predictions, columns=dk.label_list) diff --git a/freqtrade/freqai/prediction_models/BaseTensorFlowModel.py b/freqtrade/freqai/base_models/BaseTensorFlowModel.py similarity index 83% rename from freqtrade/freqai/prediction_models/BaseTensorFlowModel.py rename to freqtrade/freqai/base_models/BaseTensorFlowModel.py index 04eff045f..eea80f3a2 100644 --- a/freqtrade/freqai/prediction_models/BaseTensorFlowModel.py +++ b/freqtrade/freqai/base_models/BaseTensorFlowModel.py @@ -17,12 +17,12 @@ class BaseTensorFlowModel(IFreqaiModel): """ def train( - self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen + 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_dataframe: Full dataframe for the current training period + :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) @@ -32,14 +32,14 @@ class BaseTensorFlowModel(IFreqaiModel): # filter the features requested by user in the configuration file and elegantly handle NaNs features_filtered, labels_filtered = dk.filter_features( - unfiltered_dataframe, + unfiltered_df, dk.training_features_list, dk.label_list, training_filter=True, ) - start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d") - end_date = unfiltered_dataframe["date"].iloc[-1].strftime("%Y-%m-%d") + 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. @@ -57,7 +57,7 @@ class BaseTensorFlowModel(IFreqaiModel): ) logger.info(f'Training model on {len(data_dictionary["train_features"])} data points') - model = self.fit(data_dictionary) + model = self.fit(data_dictionary, dk) logger.info(f"--------------------done training {pair}--------------------") diff --git a/freqtrade/freqai/base_models/FreqaiMultiOutputRegressor.py b/freqtrade/freqai/base_models/FreqaiMultiOutputRegressor.py new file mode 100644 index 000000000..a9db81e31 --- /dev/null +++ b/freqtrade/freqai/base_models/FreqaiMultiOutputRegressor.py @@ -0,0 +1,65 @@ + +from joblib import Parallel +from sklearn.multioutput import MultiOutputRegressor, _fit_estimator +from sklearn.utils.fixes import delayed +from sklearn.utils.validation import has_fit_parameter + + +class FreqaiMultiOutputRegressor(MultiOutputRegressor): + + def fit(self, X, y, sample_weight=None, fit_params=None): + """Fit the model to data, separately for each output variable. + Parameters + ---------- + X : {array-like, sparse matrix} of shape (n_samples, n_features) + The input data. + y : {array-like, sparse matrix} of shape (n_samples, n_outputs) + Multi-output targets. An indicator matrix turns on multilabel + estimation. + sample_weight : array-like of shape (n_samples,), default=None + Sample weights. If `None`, then samples are equally weighted. + Only supported if the underlying regressor supports sample + weights. + fit_params : A list of dicts for the fit_params + Parameters passed to the ``estimator.fit`` method of each step. + Each dict may contain same or different values (e.g. different + eval_sets or init_models) + .. versionadded:: 0.23 + Returns + ------- + self : object + Returns a fitted instance. + """ + + if not hasattr(self.estimator, "fit"): + raise ValueError("The base estimator should implement a fit method") + + y = self._validate_data(X="no_validation", y=y, multi_output=True) + + if y.ndim == 1: + raise ValueError( + "y must have at least two dimensions for " + "multi-output regression but has only one." + ) + + if sample_weight is not None and not has_fit_parameter( + self.estimator, "sample_weight" + ): + raise ValueError("Underlying estimator does not support sample weights.") + + if not fit_params: + fit_params = [None] * y.shape[1] + + self.estimators_ = Parallel(n_jobs=self.n_jobs)( + delayed(_fit_estimator)( + self.estimator, X, y[:, i], sample_weight, **fit_params[i] + ) + for i in range(y.shape[1]) + ) + + if hasattr(self.estimators_[0], "n_features_in_"): + self.n_features_in_ = self.estimators_[0].n_features_in_ + if hasattr(self.estimators_[0], "feature_names_in_"): + self.feature_names_in_ = self.estimators_[0].feature_names_in_ + + return diff --git a/freqtrade/freqai/data_kitchen.py b/freqtrade/freqai/data_kitchen.py index 7670cfd45..e96a945eb 100644 --- a/freqtrade/freqai/data_kitchen.py +++ b/freqtrade/freqai/data_kitchen.py @@ -184,7 +184,7 @@ class FreqaiDataKitchen: def filter_features( self, - unfiltered_dataframe: DataFrame, + unfiltered_df: DataFrame, training_feature_list: List, label_list: List = list(), training_filter: bool = True, @@ -195,31 +195,35 @@ class FreqaiDataKitchen: 0s in the prediction dataset. However, prediction dataset do_predict will reflect any row that had a NaN and will shield user from that prediction. :params: - :unfiltered_dataframe: the full dataframe for the present training period + :unfiltered_df: the full dataframe for the present training period :training_feature_list: list, the training feature list constructed by self.build_feature_list() according to user specified parameters in the configuration file. :labels: the labels for the dataset :training_filter: boolean which lets the function know if it is training data or prediction data to be filtered. :returns: - :filtered_dataframe: dataframe cleaned of NaNs and only containing the user + :filtered_df: dataframe cleaned of NaNs and only containing the user requested feature set. :labels: labels cleaned of NaNs. """ - filtered_dataframe = unfiltered_dataframe.filter(training_feature_list, axis=1) - filtered_dataframe = filtered_dataframe.replace([np.inf, -np.inf], np.nan) + filtered_df = unfiltered_df.filter(training_feature_list, axis=1) + filtered_df = filtered_df.replace([np.inf, -np.inf], np.nan) - drop_index = pd.isnull(filtered_dataframe).any(1) # get the rows that have NaNs, + drop_index = pd.isnull(filtered_df).any(1) # get the rows that have NaNs, drop_index = drop_index.replace(True, 1).replace(False, 0) # pep8 requirement. if (training_filter): + const_cols = list((filtered_df.nunique() == 1).loc[lambda x: x].index) + if const_cols: + filtered_df = filtered_df.filter(filtered_df.columns.difference(const_cols)) + logger.warning(f"Removed features {const_cols} with constant values.") # we don't care about total row number (total no. datapoints) in training, we only care # about removing any row with NaNs # if labels has multiple columns (user wants to train multiple modelEs), we detect here - labels = unfiltered_dataframe.filter(label_list, axis=1) + labels = unfiltered_df.filter(label_list, axis=1) drop_index_labels = pd.isnull(labels).any(1) drop_index_labels = drop_index_labels.replace(True, 1).replace(False, 0) - dates = unfiltered_dataframe['date'] - filtered_dataframe = filtered_dataframe[ + dates = unfiltered_df['date'] + filtered_df = filtered_df[ (drop_index == 0) & (drop_index_labels == 0) ] # dropping values labels = labels[ @@ -229,13 +233,13 @@ class FreqaiDataKitchen: (drop_index == 0) & (drop_index_labels == 0) ] logger.info( - f"dropped {len(unfiltered_dataframe) - len(filtered_dataframe)} training points" - f" due to NaNs in populated dataset {len(unfiltered_dataframe)}." + f"dropped {len(unfiltered_df) - len(filtered_df)} training points" + f" due to NaNs in populated dataset {len(unfiltered_df)}." ) - if (1 - len(filtered_dataframe) / len(unfiltered_dataframe)) > 0.1 and self.live: - worst_indicator = str(unfiltered_dataframe.count().idxmin()) + if (1 - len(filtered_df) / len(unfiltered_df)) > 0.1 and self.live: + worst_indicator = str(unfiltered_df.count().idxmin()) logger.warning( - f" {(1 - len(filtered_dataframe)/len(unfiltered_dataframe)) * 100:.0f} percent " + f" {(1 - len(filtered_df)/len(unfiltered_df)) * 100:.0f} percent " " of training data dropped due to NaNs, model may perform inconsistent " f"with expectations. Verify {worst_indicator}" ) @@ -244,9 +248,9 @@ class FreqaiDataKitchen: else: # we are backtesting so we need to preserve row number to send back to strategy, # so now we use do_predict to avoid any prediction based on a NaN - drop_index = pd.isnull(filtered_dataframe).any(1) + drop_index = pd.isnull(filtered_df).any(1) self.data["filter_drop_index_prediction"] = drop_index - filtered_dataframe.fillna(0, inplace=True) + filtered_df.fillna(0, inplace=True) # replacing all NaNs with zeros to avoid issues in 'prediction', but any prediction # that was based on a single NaN is ultimately protected from buys with do_predict drop_index = ~drop_index @@ -255,11 +259,11 @@ class FreqaiDataKitchen: logger.info( "dropped %s of %s prediction data points due to NaNs.", len(self.do_predict) - self.do_predict.sum(), - len(filtered_dataframe), + len(filtered_df), ) labels = [] - return filtered_dataframe, labels + return filtered_df, labels def build_data_dictionary( self, @@ -461,6 +465,27 @@ class FreqaiDataKitchen: return df + def remove_training_from_backtesting( + self + ) -> DataFrame: + """ + Function which takes the backtesting time range and + remove training data from dataframe, keeping only the + startup_candle_count candles + """ + startup_candle_count = self.config.get('startup_candle_count', 0) + tf = self.config['timeframe'] + tr = self.config["timerange"] + + backtesting_timerange = TimeRange.parse_timerange(tr) + if startup_candle_count > 0 and backtesting_timerange: + backtesting_timerange.subtract_start(timeframe_to_seconds(tf) * startup_candle_count) + + start = datetime.fromtimestamp(backtesting_timerange.startts, tz=timezone.utc) + df = self.return_dataframe + df = df.loc[df["date"] >= start, :] + return df + def principal_component_analysis(self) -> None: """ Performs Principal Component Analysis on the data for dimensionality reduction @@ -954,6 +979,7 @@ class FreqaiDataKitchen: to_keep = [col for col in dataframe.columns if not col.startswith("&")] self.return_dataframe = pd.concat([dataframe[to_keep], self.full_df], axis=1) + self.return_dataframe = self.remove_training_from_backtesting() self.full_df = DataFrame() return @@ -1200,7 +1226,6 @@ class FreqaiDataKitchen: def save_backtesting_prediction( self, append_df: DataFrame ) -> None: - """ Save prediction dataframe from backtesting to h5 file format :param append_df: dataframe for backtesting period @@ -1214,7 +1239,6 @@ class FreqaiDataKitchen: def get_backtesting_prediction( self ) -> DataFrame: - """ Get prediction dataframe from h5 file format """ diff --git a/freqtrade/freqai/freqai_interface.py b/freqtrade/freqai/freqai_interface.py index c5ac17a3a..78931bed4 100644 --- a/freqtrade/freqai/freqai_interface.py +++ b/freqtrade/freqai/freqai_interface.py @@ -14,6 +14,7 @@ from numpy.typing import NDArray from pandas import DataFrame from freqtrade.configuration import TimeRange +from freqtrade.constants import DATETIME_PRINT_FORMAT from freqtrade.enums import RunMode from freqtrade.exceptions import OperationalException from freqtrade.exchange import timeframe_to_seconds @@ -87,10 +88,17 @@ class IFreqaiModel(ABC): self.begin_time: float = 0 self.begin_time_train: float = 0 self.base_tf_seconds = timeframe_to_seconds(self.config['timeframe']) + self.continual_learning = self.freqai_info.get('continual_learning', False) self._threads: List[threading.Thread] = [] self._stop_event = threading.Event() + def __getstate__(self): + """ + Return an empty state to be pickled in hyperopt + """ + return ({}) + def assert_config(self, config: Dict[str, Any]) -> None: if not config.get("freqai", {}): @@ -232,10 +240,10 @@ class IFreqaiModel(ABC): trained_timestamp = tr_train tr_train_startts_str = datetime.fromtimestamp( tr_train.startts, - tz=timezone.utc).strftime("%Y-%m-%d %H:%M:%S") + tz=timezone.utc).strftime(DATETIME_PRINT_FORMAT) tr_train_stopts_str = datetime.fromtimestamp( tr_train.stopts, - tz=timezone.utc).strftime("%Y-%m-%d %H:%M:%S") + tz=timezone.utc).strftime(DATETIME_PRINT_FORMAT) logger.info( f"Training {metadata['pair']}, {self.pair_it}/{self.total_pairs} pairs" f" from {tr_train_startts_str} to {tr_train_stopts_str}, {train_it}/{total_trains} " @@ -669,21 +677,30 @@ class IFreqaiModel(ABC): self.train_time = 0 return + def get_init_model(self, pair: str) -> Any: + if pair not in self.dd.model_dictionary or not self.continual_learning: + init_model = None + else: + init_model = self.dd.model_dictionary[pair] + + return init_model + # Following methods which are overridden by user made prediction models. # See freqai/prediction_models/CatboostPredictionModel.py for an example. @abstractmethod - def train(self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen) -> Any: + 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 datahandler for storing, saving, loading, and analyzing the data. - :param unfiltered_dataframe: Full dataframe for the current training period + :param unfiltered_df: Full dataframe for the current training period :param metadata: pair metadata from strategy. :return: Trained model which can be used to inference (self.predict) """ @abstractmethod - def fit(self, data_dictionary: Dict[str, Any]) -> Any: + def fit(self, data_dictionary: Dict[str, Any], dk: FreqaiDataKitchen, **kwargs) -> Any: """ Most regressors use the same function names and arguments e.g. user can drop in LGBMRegressor in place of CatBoostRegressor and all data @@ -696,11 +713,11 @@ class IFreqaiModel(ABC): @abstractmethod def predict( - self, dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = True + self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs ) -> Tuple[DataFrame, NDArray[np.int_]]: """ Filter the prediction features data and predict with it. - :param unfiltered_dataframe: Full dataframe for the current backtest period. + :param unfiltered_df: Full dataframe for the current backtest period. :param dk: FreqaiDataKitchen = Data management/analysis tool associated to present pair only :param first: boolean = whether this is the first prediction or not. :return: diff --git a/freqtrade/freqai/prediction_models/CatboostClassifier.py b/freqtrade/freqai/prediction_models/CatboostClassifier.py index b88b28b25..60536e6de 100644 --- a/freqtrade/freqai/prediction_models/CatboostClassifier.py +++ b/freqtrade/freqai/prediction_models/CatboostClassifier.py @@ -3,7 +3,8 @@ from typing import Any, Dict from catboost import CatBoostClassifier, Pool -from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel +from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen logger = logging.getLogger(__name__) @@ -16,7 +17,7 @@ class CatboostClassifier(BaseClassifierModel): has its own DataHandler where data is held, saved, loaded, and managed. """ - def fit(self, data_dictionary: Dict) -> Any: + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: """ User sets up the training and test data to fit their desired model here :params: @@ -36,6 +37,8 @@ class CatboostClassifier(BaseClassifierModel): **self.model_training_parameters, ) - cbr.fit(train_data) + init_model = self.get_init_model(dk.pair) + + cbr.fit(train_data, init_model=init_model) return cbr diff --git a/freqtrade/freqai/prediction_models/CatboostRegressor.py b/freqtrade/freqai/prediction_models/CatboostRegressor.py index d93569c91..73cf6c88a 100644 --- a/freqtrade/freqai/prediction_models/CatboostRegressor.py +++ b/freqtrade/freqai/prediction_models/CatboostRegressor.py @@ -1,10 +1,10 @@ -import gc import logging from typing import Any, Dict from catboost import CatBoostRegressor, Pool -from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen logger = logging.getLogger(__name__) @@ -17,7 +17,7 @@ class CatboostRegressor(BaseRegressionModel): has its own DataHandler where data is held, saved, loaded, and managed. """ - def fit(self, data_dictionary: Dict) -> Any: + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: """ User sets up the training and test data to fit their desired model here :param data_dictionary: the dictionary constructed by DataHandler to hold @@ -38,16 +38,13 @@ class CatboostRegressor(BaseRegressionModel): weight=data_dictionary["test_weights"], ) + init_model = self.get_init_model(dk.pair) + model = CatBoostRegressor( allow_writing_files=False, **self.model_training_parameters, ) - model.fit(X=train_data, eval_set=test_data) - - # some evidence that catboost pools have memory leaks: - # https://github.com/catboost/catboost/issues/1835 - del train_data, test_data - gc.collect() + model.fit(X=train_data, eval_set=test_data, init_model=init_model) return model diff --git a/freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py b/freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py index 9894decd1..7fa4e293e 100644 --- a/freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py +++ b/freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py @@ -1,10 +1,11 @@ import logging from typing import Any, Dict -from catboost import CatBoostRegressor # , Pool -from sklearn.multioutput import MultiOutputRegressor +from catboost import CatBoostRegressor, Pool -from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen logger = logging.getLogger(__name__) @@ -17,7 +18,7 @@ class CatboostRegressorMultiTarget(BaseRegressionModel): has its own DataHandler where data is held, saved, loaded, and managed. """ - def fit(self, data_dictionary: Dict) -> Any: + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: """ User sets up the training and test data to fit their desired model here :param data_dictionary: the dictionary constructed by DataHandler to hold @@ -31,14 +32,37 @@ class CatboostRegressorMultiTarget(BaseRegressionModel): X = data_dictionary["train_features"] y = data_dictionary["train_labels"] - eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"]) + sample_weight = data_dictionary["train_weights"] - model = MultiOutputRegressor(estimator=cbr) - model.fit(X=X, y=y, sample_weight=sample_weight) # , eval_set=eval_set) + eval_sets = [None] * y.shape[1] if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0: - train_score = model.score(X, y) - test_score = model.score(*eval_set) - logger.info(f"Train score {train_score}, Test score {test_score}") + eval_sets = [None] * data_dictionary['test_labels'].shape[1] + + for i in range(data_dictionary['test_labels'].shape[1]): + eval_sets[i] = Pool( + data=data_dictionary["test_features"], + label=data_dictionary["test_labels"].iloc[:, i], + weight=data_dictionary["test_weights"], + ) + + init_model = self.get_init_model(dk.pair) + + if init_model: + init_models = init_model.estimators_ + else: + init_models = [None] * y.shape[1] + + fit_params = [] + for i in range(len(eval_sets)): + fit_params.append( + {'eval_set': eval_sets[i], 'init_model': init_models[i]}) + + model = FreqaiMultiOutputRegressor(estimator=cbr) + thread_training = self.freqai_info.get('multitarget_parallel_training', False) + if thread_training: + model.n_jobs = y.shape[1] + model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params) + return model diff --git a/freqtrade/freqai/prediction_models/LightGBMClassifier.py b/freqtrade/freqai/prediction_models/LightGBMClassifier.py index 4ac2c448b..3eec516ba 100644 --- a/freqtrade/freqai/prediction_models/LightGBMClassifier.py +++ b/freqtrade/freqai/prediction_models/LightGBMClassifier.py @@ -3,7 +3,8 @@ from typing import Any, Dict from lightgbm import LGBMClassifier -from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel +from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen logger = logging.getLogger(__name__) @@ -16,7 +17,7 @@ class LightGBMClassifier(BaseClassifierModel): has its own DataHandler where data is held, saved, loaded, and managed. """ - def fit(self, data_dictionary: Dict) -> Any: + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: """ User sets up the training and test data to fit their desired model here :params: @@ -35,9 +36,11 @@ class LightGBMClassifier(BaseClassifierModel): y = data_dictionary["train_labels"].to_numpy()[:, 0] train_weights = data_dictionary["train_weights"] + init_model = self.get_init_model(dk.pair) + model = LGBMClassifier(**self.model_training_parameters) model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights, - eval_sample_weight=[test_weights]) + eval_sample_weight=[test_weights], init_model=init_model) return model diff --git a/freqtrade/freqai/prediction_models/LightGBMRegressor.py b/freqtrade/freqai/prediction_models/LightGBMRegressor.py index 2431fd2ad..85c9b691c 100644 --- a/freqtrade/freqai/prediction_models/LightGBMRegressor.py +++ b/freqtrade/freqai/prediction_models/LightGBMRegressor.py @@ -3,7 +3,8 @@ from typing import Any, Dict from lightgbm import LGBMRegressor -from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen logger = logging.getLogger(__name__) @@ -16,7 +17,7 @@ class LightGBMRegressor(BaseRegressionModel): has its own DataHandler where data is held, saved, loaded, and managed. """ - def fit(self, data_dictionary: Dict) -> Any: + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: """ Most regressors use the same function names and arguments e.g. user can drop in LGBMRegressor in place of CatBoostRegressor and all data @@ -35,9 +36,11 @@ class LightGBMRegressor(BaseRegressionModel): y = data_dictionary["train_labels"] train_weights = data_dictionary["train_weights"] + init_model = self.get_init_model(dk.pair) + model = LGBMRegressor(**self.model_training_parameters) model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights, - eval_sample_weight=[eval_weights]) + eval_sample_weight=[eval_weights], init_model=init_model) return model diff --git a/freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py b/freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py index ecd405369..37c6bb186 100644 --- a/freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py +++ b/freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py @@ -2,9 +2,10 @@ import logging from typing import Any, Dict from lightgbm import LGBMRegressor -from sklearn.multioutput import MultiOutputRegressor -from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen logger = logging.getLogger(__name__) @@ -17,7 +18,7 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel): has its own DataHandler where data is held, saved, loaded, and managed. """ - def fit(self, data_dictionary: Dict) -> Any: + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: """ User sets up the training and test data to fit their desired model here :param data_dictionary: the dictionary constructed by DataHandler to hold @@ -28,12 +29,36 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel): X = data_dictionary["train_features"] y = data_dictionary["train_labels"] - eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"]) sample_weight = data_dictionary["train_weights"] - model = MultiOutputRegressor(estimator=lgb) - model.fit(X=X, y=y, sample_weight=sample_weight) # , eval_set=eval_set) - train_score = model.score(X, y) - test_score = model.score(*eval_set) - logger.info(f"Train score {train_score}, Test score {test_score}") + eval_weights = None + eval_sets = [None] * y.shape[1] + + if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0: + eval_weights = [data_dictionary["test_weights"]] + eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1] # type: ignore + for i in range(data_dictionary['test_labels'].shape[1]): + eval_sets[i] = ( # type: ignore + data_dictionary["test_features"], + data_dictionary["test_labels"].iloc[:, i] + ) + + init_model = self.get_init_model(dk.pair) + if init_model: + init_models = init_model.estimators_ + else: + init_models = [None] * y.shape[1] + + fit_params = [] + for i in range(len(eval_sets)): + fit_params.append( + {'eval_set': eval_sets[i], 'eval_sample_weight': eval_weights, + 'init_model': init_models[i]}) + + model = FreqaiMultiOutputRegressor(estimator=lgb) + thread_training = self.freqai_info.get('multitarget_parallel_training', False) + if thread_training: + model.n_jobs = y.shape[1] + model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params) + return model diff --git a/freqtrade/freqai/prediction_models/XGBoostRegressor.py b/freqtrade/freqai/prediction_models/XGBoostRegressor.py new file mode 100644 index 000000000..c9be9ce74 --- /dev/null +++ b/freqtrade/freqai/prediction_models/XGBoostRegressor.py @@ -0,0 +1,45 @@ +import logging +from typing import Any, Dict + +from xgboost import XGBRegressor + +from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen + + +logger = logging.getLogger(__name__) + + +class XGBoostRegressor(BaseRegressionModel): + """ + User created prediction model. The class needs to override three necessary + functions, predict(), train(), fit(). The class inherits ModelHandler which + has its own DataHandler where data is held, saved, loaded, and managed. + """ + + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: + """ + User sets up the training and test data to fit their desired model here + :param data_dictionary: the dictionary constructed by DataHandler to hold + all the training and test data/labels. + """ + + X = data_dictionary["train_features"] + y = data_dictionary["train_labels"] + + if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) == 0: + eval_set = None + else: + eval_set = [(data_dictionary["test_features"], data_dictionary["test_labels"])] + eval_weights = [data_dictionary['test_weights']] + + sample_weight = data_dictionary["train_weights"] + + xgb_model = self.get_init_model(dk.pair) + + model = XGBRegressor(**self.model_training_parameters) + + model.fit(X=X, y=y, sample_weight=sample_weight, eval_set=eval_set, + sample_weight_eval_set=eval_weights, xgb_model=xgb_model) + + return model diff --git a/freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py b/freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py new file mode 100644 index 000000000..920745ec9 --- /dev/null +++ b/freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py @@ -0,0 +1,63 @@ +import logging +from typing import Any, Dict + +from xgboost import XGBRegressor + +from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel +from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor +from freqtrade.freqai.data_kitchen import FreqaiDataKitchen + + +logger = logging.getLogger(__name__) + + +class XGBoostRegressorMultiTarget(BaseRegressionModel): + """ + User created prediction model. The class needs to override three necessary + functions, predict(), train(), fit(). The class inherits ModelHandler which + has its own DataHandler where data is held, saved, loaded, and managed. + """ + + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: + """ + User sets up the training and test data to fit their desired model here + :param data_dictionary: the dictionary constructed by DataHandler to hold + all the training and test data/labels. + """ + + xgb = XGBRegressor(**self.model_training_parameters) + + X = data_dictionary["train_features"] + y = data_dictionary["train_labels"] + sample_weight = data_dictionary["train_weights"] + + eval_weights = None + eval_sets = [None] * y.shape[1] + + if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0: + eval_weights = [data_dictionary["test_weights"]] + for i in range(data_dictionary['test_labels'].shape[1]): + eval_sets[i] = [( # type: ignore + data_dictionary["test_features"], + data_dictionary["test_labels"].iloc[:, i] + )] + + init_model = self.get_init_model(dk.pair) + if init_model: + init_models = init_model.estimators_ + else: + init_models = [None] * y.shape[1] + + fit_params = [] + for i in range(len(eval_sets)): + fit_params.append( + {'eval_set': eval_sets[i], 'sample_weight_eval_set': eval_weights, + 'xgb_model': init_models[i]}) + + model = FreqaiMultiOutputRegressor(estimator=xgb) + thread_training = self.freqai_info.get('multitarget_parallel_training', False) + if thread_training: + model.n_jobs = y.shape[1] + model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params) + + return model diff --git a/freqtrade/optimize/optimize_reports.py b/freqtrade/optimize/optimize_reports.py index 519022db2..fa6c3f161 100644 --- a/freqtrade/optimize/optimize_reports.py +++ b/freqtrade/optimize/optimize_reports.py @@ -75,7 +75,8 @@ def _get_line_floatfmt(stake_currency: str) -> List[str]: '.2f', 'd', 's', 's'] -def _get_line_header(first_column: str, stake_currency: str, direction: str = 'Buys') -> List[str]: +def _get_line_header(first_column: str, stake_currency: str, + direction: str = 'Entries') -> List[str]: """ Generate header lines (goes in line with _generate_result_line()) """ @@ -642,7 +643,7 @@ def text_table_tags(tag_type: str, tag_results: List[Dict[str, Any]], stake_curr if (tag_type == "enter_tag"): headers = _get_line_header("TAG", stake_currency) else: - headers = _get_line_header("TAG", stake_currency, 'Sells') + headers = _get_line_header("TAG", stake_currency, 'Exits') floatfmt = _get_line_floatfmt(stake_currency) output = [ [ diff --git a/freqtrade/rpc/discord.py b/freqtrade/rpc/discord.py index 5991f7126..85acfae4e 100644 --- a/freqtrade/rpc/discord.py +++ b/freqtrade/rpc/discord.py @@ -1,7 +1,7 @@ import logging from typing import Any, Dict -from freqtrade.enums.rpcmessagetype import RPCMessageType +from freqtrade.enums import RPCMessageType from freqtrade.rpc import RPC from freqtrade.rpc.webhook import Webhook diff --git a/freqtrade/strategy/interface.py b/freqtrade/strategy/interface.py index 0a9a155ea..85f5277dc 100644 --- a/freqtrade/strategy/interface.py +++ b/freqtrade/strategy/interface.py @@ -12,9 +12,8 @@ from pandas import DataFrame from freqtrade.constants import ListPairsWithTimeframes from freqtrade.data.dataprovider import DataProvider -from freqtrade.enums import (CandleType, ExitCheckTuple, ExitType, SignalDirection, SignalTagType, - SignalType, TradingMode) -from freqtrade.enums.runmode import RunMode +from freqtrade.enums import (CandleType, ExitCheckTuple, ExitType, RunMode, SignalDirection, + SignalTagType, SignalType, TradingMode) from freqtrade.exceptions import OperationalException, StrategyError from freqtrade.exchange import timeframe_to_minutes, timeframe_to_next_date, timeframe_to_seconds from freqtrade.misc import remove_entry_exit_signals diff --git a/freqtrade/strategy/parameters.py b/freqtrade/strategy/parameters.py index c6037ae0b..796fb9514 100644 --- a/freqtrade/strategy/parameters.py +++ b/freqtrade/strategy/parameters.py @@ -7,7 +7,7 @@ from abc import ABC, abstractmethod from contextlib import suppress from typing import Any, Optional, Sequence, Union -from freqtrade.enums.hyperoptstate import HyperoptState +from freqtrade.enums import HyperoptState from freqtrade.optimize.hyperopt_tools import HyperoptStateContainer diff --git a/freqtrade/templates/FreqaiExampleStrategy.py b/freqtrade/templates/FreqaiExampleStrategy.py index b172ab805..15b2c6c83 100644 --- a/freqtrade/templates/FreqaiExampleStrategy.py +++ b/freqtrade/templates/FreqaiExampleStrategy.py @@ -6,9 +6,7 @@ import talib.abstract as ta from pandas import DataFrame from technical import qtpylib -from freqtrade.exchange import timeframe_to_prev_date -from freqtrade.persistence import Trade -from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy, merge_informative_pair +from freqtrade.strategy import CategoricalParameter, IStrategy, merge_informative_pair logger = logging.getLogger(__name__) @@ -31,9 +29,6 @@ class FreqaiExampleStrategy(IStrategy): "main_plot": {}, "subplots": { "prediction": {"prediction": {"color": "blue"}}, - "target_roi": { - "target_roi": {"color": "brown"}, - }, "do_predict": { "do_predict": {"color": "brown"}, }, @@ -47,10 +42,10 @@ class FreqaiExampleStrategy(IStrategy): startup_candle_count: int = 40 can_short = False - linear_roi_offset = DecimalParameter( - 0.00, 0.02, default=0.005, space="sell", optimize=False, load=True - ) - max_roi_time_long = IntParameter(0, 800, default=400, space="sell", optimize=False, load=True) + std_dev_multiplier_buy = CategoricalParameter( + [0.75, 1, 1.25, 1.5, 1.75], default=1.25, space="buy", optimize=True) + std_dev_multiplier_sell = CategoricalParameter( + [0.1, 0.25, 0.4], space="sell", default=0.2, optimize=True) def informative_pairs(self): whitelist_pairs = self.dp.current_whitelist() @@ -187,21 +182,26 @@ class FreqaiExampleStrategy(IStrategy): # `populate_any_indicators()` for each training period. dataframe = self.freqai.start(dataframe, metadata, self) - - dataframe["target_roi"] = dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * 1.25 - dataframe["sell_roi"] = dataframe["&-s_close_mean"] - dataframe["&-s_close_std"] * 1.25 + for val in self.std_dev_multiplier_buy.range: + dataframe[f'target_roi_{val}'] = dataframe["&-s_close_mean"] + \ + dataframe["&-s_close_std"] * val + for val in self.std_dev_multiplier_sell.range: + dataframe[f'sell_roi_{val}'] = dataframe["&-s_close_mean"] - \ + dataframe["&-s_close_std"] * val return dataframe def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame: - enter_long_conditions = [df["do_predict"] == 1, df["&-s_close"] > df["target_roi"]] + enter_long_conditions = [df["do_predict"] == 1, df["&-s_close"] + > df[f"target_roi_{self.std_dev_multiplier_buy.value}"]] if enter_long_conditions: df.loc[ reduce(lambda x, y: x & y, enter_long_conditions), ["enter_long", "enter_tag"] ] = (1, "long") - enter_short_conditions = [df["do_predict"] == 1, df["&-s_close"] < df["sell_roi"]] + enter_short_conditions = [df["do_predict"] == 1, df["&-s_close"] + < df[f"sell_roi_{self.std_dev_multiplier_sell.value}"]] if enter_short_conditions: df.loc[ @@ -211,11 +211,13 @@ class FreqaiExampleStrategy(IStrategy): return df def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame: - exit_long_conditions = [df["do_predict"] == 1, df["&-s_close"] < df["sell_roi"] * 0.25] + exit_long_conditions = [df["do_predict"] == 1, df["&-s_close"] < + df[f"sell_roi_{self.std_dev_multiplier_sell.value}"] * 0.25] if exit_long_conditions: df.loc[reduce(lambda x, y: x & y, exit_long_conditions), "exit_long"] = 1 - exit_short_conditions = [df["do_predict"] == 1, df["&-s_close"] > df["target_roi"] * 0.25] + exit_short_conditions = [df["do_predict"] == 1, df["&-s_close"] > + df[f"target_roi_{self.std_dev_multiplier_buy.value}"] * 0.25] if exit_short_conditions: df.loc[reduce(lambda x, y: x & y, exit_short_conditions), "exit_short"] = 1 @@ -224,83 +226,6 @@ class FreqaiExampleStrategy(IStrategy): def get_ticker_indicator(self): return int(self.config["timeframe"][:-1]) - def custom_exit( - self, pair: str, trade: Trade, current_time, current_rate, current_profit, **kwargs - ): - - dataframe, _ = self.dp.get_analyzed_dataframe(pair=pair, timeframe=self.timeframe) - - trade_date = timeframe_to_prev_date(self.config["timeframe"], trade.open_date_utc) - trade_candle = dataframe.loc[(dataframe["date"] == trade_date)] - - if trade_candle.empty: - return None - trade_candle = trade_candle.squeeze() - - follow_mode = self.config.get("freqai", {}).get("follow_mode", False) - - if not follow_mode: - pair_dict = self.freqai.dd.pair_dict - else: - pair_dict = self.freqai.dd.follower_dict - - entry_tag = trade.enter_tag - - if ( - "prediction" + entry_tag not in pair_dict[pair] - or pair_dict[pair]['extras']["prediction" + entry_tag] == 0 - ): - pair_dict[pair]['extras']["prediction" + entry_tag] = abs(trade_candle["&-s_close"]) - if not follow_mode: - self.freqai.dd.save_drawer_to_disk() - else: - self.freqai.dd.save_follower_dict_to_disk() - - roi_price = pair_dict[pair]['extras']["prediction" + entry_tag] - roi_time = self.max_roi_time_long.value - - roi_decay = roi_price * ( - 1 - ((current_time - trade.open_date_utc).seconds) / (roi_time * 60) - ) - if roi_decay < 0: - roi_decay = self.linear_roi_offset.value - else: - roi_decay += self.linear_roi_offset.value - - if current_profit > roi_decay: - return "roi_custom_win" - - if current_profit < -roi_decay: - return "roi_custom_loss" - - def confirm_trade_exit( - self, - pair: str, - trade: Trade, - order_type: str, - amount: float, - rate: float, - time_in_force: str, - exit_reason: str, - current_time, - **kwargs, - ) -> bool: - - entry_tag = trade.enter_tag - follow_mode = self.config.get("freqai", {}).get("follow_mode", False) - if not follow_mode: - pair_dict = self.freqai.dd.pair_dict - else: - pair_dict = self.freqai.dd.follower_dict - - pair_dict[pair]['extras']["prediction" + entry_tag] = 0 - if not follow_mode: - self.freqai.dd.save_drawer_to_disk() - else: - self.freqai.dd.save_follower_dict_to_disk() - - return True - def confirm_trade_entry( self, pair: str, diff --git a/requirements-freqai.txt b/requirements-freqai.txt index 26e4617af..e8d950382 100644 --- a/requirements-freqai.txt +++ b/requirements-freqai.txt @@ -6,3 +6,4 @@ scikit-learn==1.1.2 joblib==1.1.0 catboost==1.0.6; platform_machine != 'aarch64' lightgbm==3.3.2 +xgboost==1.6.2 diff --git a/tests/data/test_history.py b/tests/data/test_history.py index 9709e7ad0..8081e984f 100644 --- a/tests/data/test_history.py +++ b/tests/data/test_history.py @@ -13,7 +13,7 @@ from pandas import DataFrame from pandas.testing import assert_frame_equal from freqtrade.configuration import TimeRange -from freqtrade.constants import AVAILABLE_DATAHANDLERS +from freqtrade.constants import AVAILABLE_DATAHANDLERS, DATETIME_PRINT_FORMAT from freqtrade.data.converter import ohlcv_to_dataframe from freqtrade.data.history.hdf5datahandler import HDF5DataHandler from freqtrade.data.history.history_utils import (_download_pair_history, _download_trades_history, @@ -386,7 +386,7 @@ def test_load_partial_missing(testdatadir, caplog) -> None: assert td != len(data['UNITTEST/BTC']) start_real = data['UNITTEST/BTC'].iloc[0, 0] assert log_has(f'UNITTEST/BTC, spot, 5m, ' - f'data starts at {start_real.strftime("%Y-%m-%d %H:%M:%S")}', + f'data starts at {start_real.strftime(DATETIME_PRINT_FORMAT)}', caplog) # Make sure we start fresh - test missing data at end caplog.clear() @@ -401,7 +401,7 @@ def test_load_partial_missing(testdatadir, caplog) -> None: # Shift endtime with +5 - as last candle is dropped (partial candle) end_real = arrow.get(data['UNITTEST/BTC'].iloc[-1, 0]).shift(minutes=5) assert log_has(f'UNITTEST/BTC, spot, 5m, ' - f'data ends at {end_real.strftime("%Y-%m-%d %H:%M:%S")}', + f'data ends at {end_real.strftime(DATETIME_PRINT_FORMAT)}', caplog) diff --git a/tests/exchange/test_ccxt_compat.py b/tests/exchange/test_ccxt_compat.py index 49b7684f8..f57b0b366 100644 --- a/tests/exchange/test_ccxt_compat.py +++ b/tests/exchange/test_ccxt_compat.py @@ -267,13 +267,8 @@ class TestCCXTExchange(): now = datetime.now(timezone.utc) - timedelta(minutes=(timeframe_to_minutes(timeframe) * 2)) assert exchange.klines(pair_tf).iloc[-1]['date'] >= timeframe_to_prev_date(timeframe, now) - def test_ccxt__async_get_candle_history(self, exchange): - exchange, exchangename = exchange - # For some weired reason, this test returns random lengths for bittrex. - if not exchange._ft_has['ohlcv_has_history'] or exchangename == 'bittrex': - return - pair = EXCHANGES[exchangename]['pair'] - timeframe = EXCHANGES[exchangename]['timeframe'] + def ccxt__async_get_candle_history(self, exchange, exchangename, pair, timeframe): + candle_type = CandleType.SPOT timeframe_ms = timeframe_to_msecs(timeframe) now = timeframe_to_prev_date( @@ -299,6 +294,24 @@ class TestCCXTExchange(): assert len(candles) >= min(candle_count, candle_count1) assert candles[0][0] == since_ms or (since_ms + timeframe_ms) + def test_ccxt__async_get_candle_history(self, exchange): + exchange, exchangename = exchange + # For some weired reason, this test returns random lengths for bittrex. + if not exchange._ft_has['ohlcv_has_history'] or exchangename in ('bittrex', 'gateio'): + return + pair = EXCHANGES[exchangename]['pair'] + timeframe = EXCHANGES[exchangename]['timeframe'] + self.ccxt__async_get_candle_history(exchange, exchangename, pair, timeframe) + + def test_ccxt__async_get_candle_history_futures(self, exchange_futures): + exchange, exchangename = exchange_futures + if not exchange: + # exchange_futures only returns values for supported exchanges + return + pair = EXCHANGES[exchangename].get('futures_pair', EXCHANGES[exchangename]['pair']) + timeframe = EXCHANGES[exchangename]['timeframe'] + self.ccxt__async_get_candle_history(exchange, exchangename, pair, timeframe) + def test_ccxt_fetch_funding_rate_history(self, exchange_futures): exchange, exchangename = exchange_futures if not exchange: diff --git a/tests/exchange/test_okx.py b/tests/exchange/test_okx.py index b475b84ff..12322acae 100644 --- a/tests/exchange/test_okx.py +++ b/tests/exchange/test_okx.py @@ -4,8 +4,7 @@ from unittest.mock import MagicMock, PropertyMock import pytest -from freqtrade.enums import MarginMode, TradingMode -from freqtrade.enums.candletype import CandleType +from freqtrade.enums import CandleType, MarginMode, TradingMode from freqtrade.exchange.exchange import timeframe_to_minutes from tests.conftest import get_mock_coro, get_patched_exchange, log_has from tests.exchange.test_exchange import ccxt_exceptionhandlers diff --git a/tests/freqai/test_freqai_interface.py b/tests/freqai/test_freqai_interface.py index 6364cb04f..2a7cfeb73 100644 --- a/tests/freqai/test_freqai_interface.py +++ b/tests/freqai/test_freqai_interface.py @@ -17,8 +17,18 @@ def is_arm() -> bool: return "arm" in machine or "aarch64" in machine -def test_extract_data_and_train_model_LightGBM(mocker, freqai_conf): +@pytest.mark.parametrize('model', [ + 'LightGBMRegressor', + 'XGBoostRegressor', + 'CatboostRegressor', + ]) +def test_extract_data_and_train_model_Regressors(mocker, freqai_conf, model): + if is_arm() and model == 'CatboostRegressor': + pytest.skip("CatBoost is not supported on ARM") + + freqai_conf.update({"freqaimodel": model}) freqai_conf.update({"timerange": "20180110-20180130"}) + freqai_conf.update({"strategy": "freqai_test_strat"}) strategy = get_patched_freqai_strategy(mocker, freqai_conf) exchange = get_patched_exchange(mocker, freqai_conf) @@ -46,10 +56,18 @@ def test_extract_data_and_train_model_LightGBM(mocker, freqai_conf): shutil.rmtree(Path(freqai.dk.full_path)) -def test_extract_data_and_train_model_LightGBMMultiModel(mocker, freqai_conf): +@pytest.mark.parametrize('model', [ + 'LightGBMRegressorMultiTarget', + 'XGBoostRegressorMultiTarget', + 'CatboostRegressorMultiTarget', + ]) +def test_extract_data_and_train_model_MultiTargets(mocker, freqai_conf, model): + if is_arm() and model == 'CatboostRegressorMultiTarget': + pytest.skip("CatBoost is not supported on ARM") + freqai_conf.update({"timerange": "20180110-20180130"}) freqai_conf.update({"strategy": "freqai_test_multimodel_strat"}) - freqai_conf.update({"freqaimodel": "LightGBMRegressorMultiTarget"}) + freqai_conf.update({"freqaimodel": model}) strategy = get_patched_freqai_strategy(mocker, freqai_conf) exchange = get_patched_exchange(mocker, freqai_conf) strategy.dp = DataProvider(freqai_conf, exchange) @@ -78,75 +96,17 @@ def test_extract_data_and_train_model_LightGBMMultiModel(mocker, freqai_conf): shutil.rmtree(Path(freqai.dk.full_path)) -@pytest.mark.skipif(is_arm(), reason="no ARM for Catboost ...") -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( - # {'model_training_parameters': {"n_estimators": 100, "verbose": 0}}) - strategy = get_patched_freqai_strategy(mocker, freqai_conf) - exchange = get_patched_exchange(mocker, freqai_conf) - strategy.dp = DataProvider(freqai_conf, exchange) +@pytest.mark.parametrize('model', [ + 'LightGBMClassifier', + 'CatboostClassifier', + ]) +def test_extract_data_and_train_model_Classifiers(mocker, freqai_conf, model): + if is_arm() and model == 'CatboostClassifier': + pytest.skip("CatBoost is not supported on ARM") - strategy.freqai_info = freqai_conf.get("freqai", {}) - freqai = strategy.freqai - freqai.live = True - freqai.dk = FreqaiDataKitchen(freqai_conf) - 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") - - 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").exists() - assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").exists() - assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_trained_df.pkl").exists() - assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_svm_model.joblib").exists() - - shutil.rmtree(Path(freqai.dk.full_path)) - - -@pytest.mark.skipif(is_arm(), reason="no ARM for Catboost ...") -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({"freqaimodel": model}) freqai_conf.update({"strategy": "freqai_test_classifier"}) - 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) - 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") - - 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").exists() - assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_metadata.json").exists() - assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_trained_df.pkl").exists() - assert Path(freqai.dk.data_path / f"{freqai.dk.model_filename}_svm_model.joblib").exists() - - shutil.rmtree(Path(freqai.dk.full_path)) - - -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"}) strategy = get_patched_freqai_strategy(mocker, freqai_conf) exchange = get_patched_exchange(mocker, freqai_conf) strategy.dp = DataProvider(freqai_conf, exchange) diff --git a/tests/optimize/test_optimize_reports.py b/tests/optimize/test_optimize_reports.py index 562e12820..5095f2fde 100644 --- a/tests/optimize/test_optimize_reports.py +++ b/tests/optimize/test_optimize_reports.py @@ -40,14 +40,14 @@ def test_text_table_bt_results(): ) result_str = ( - '| Pair | Buys | Avg Profit % | Cum Profit % | Tot Profit BTC | Tot Profit % |' - ' Avg Duration | Win Draw Loss Win% |\n' - '|---------+--------+----------------+----------------+------------------+----------------+' - '----------------+-------------------------|\n' - '| ETH/BTC | 3 | 8.33 | 25.00 | 0.50000000 | 12.50 |' - ' 0:20:00 | 2 0 1 66.7 |\n' - '| TOTAL | 3 | 8.33 | 25.00 | 0.50000000 | 12.50 |' - ' 0:20:00 | 2 0 1 66.7 |' + '| Pair | Entries | Avg Profit % | Cum Profit % | Tot Profit BTC | ' + 'Tot Profit % | Avg Duration | Win Draw Loss Win% |\n' + '|---------+-----------+----------------+----------------+------------------+' + '----------------+----------------+-------------------------|\n' + '| ETH/BTC | 3 | 8.33 | 25.00 | 0.50000000 | ' + '12.50 | 0:20:00 | 2 0 1 66.7 |\n' + '| TOTAL | 3 | 8.33 | 25.00 | 0.50000000 | ' + '12.50 | 0:20:00 | 2 0 1 66.7 |' ) pair_results = generate_pair_metrics(['ETH/BTC'], stake_currency='BTC', @@ -402,13 +402,13 @@ def test_text_table_strategy(testdatadir): bt_res_data_comparison = bt_res_data.pop('strategy_comparison') result_str = ( - '| Strategy | Buys | Avg Profit % | Cum Profit % | Tot Profit BTC |' + '| Strategy | Entries | Avg Profit % | Cum Profit % | Tot Profit BTC |' ' Tot Profit % | Avg Duration | Win Draw Loss Win% | Drawdown |\n' - '|----------------+--------+----------------+----------------+------------------+' + '|----------------+-----------+----------------+----------------+------------------+' '----------------+----------------+-------------------------+-----------------------|\n' - '| StrategyTestV2 | 179 | 0.08 | 14.39 | 0.02608550 |' + '| StrategyTestV2 | 179 | 0.08 | 14.39 | 0.02608550 |' ' 260.85 | 3:40:00 | 170 0 9 95.0 | 0.00308222 BTC 8.67% |\n' - '| TestStrategy | 179 | 0.08 | 14.39 | 0.02608550 |' + '| TestStrategy | 179 | 0.08 | 14.39 | 0.02608550 |' ' 260.85 | 3:40:00 | 170 0 9 95.0 | 0.00308222 BTC 8.67% |' ) diff --git a/tests/strategy/test_interface.py b/tests/strategy/test_interface.py index 65ee05d71..070e78b1d 100644 --- a/tests/strategy/test_interface.py +++ b/tests/strategy/test_interface.py @@ -11,8 +11,7 @@ from pandas import DataFrame from freqtrade.configuration import TimeRange from freqtrade.data.dataprovider import DataProvider from freqtrade.data.history import load_data -from freqtrade.enums import ExitCheckTuple, ExitType, SignalDirection -from freqtrade.enums.hyperoptstate import HyperoptState +from freqtrade.enums import ExitCheckTuple, ExitType, HyperoptState, SignalDirection from freqtrade.exceptions import OperationalException, StrategyError from freqtrade.optimize.hyperopt_tools import HyperoptStateContainer from freqtrade.optimize.space import SKDecimal diff --git a/tests/test_persistence.py b/tests/test_persistence.py index cdca3bc4d..e7f218c02 100644 --- a/tests/test_persistence.py +++ b/tests/test_persistence.py @@ -9,7 +9,7 @@ import arrow import pytest from sqlalchemy import create_engine, text -from freqtrade import constants +from freqtrade.constants import DATETIME_PRINT_FORMAT, DEFAULT_DB_PROD_URL from freqtrade.enums import TradingMode from freqtrade.exceptions import DependencyException, OperationalException from freqtrade.persistence import LocalTrade, Order, Trade, init_db @@ -52,7 +52,7 @@ def test_init_invalid_db_url(): def test_init_prod_db(default_conf, mocker): default_conf.update({'dry_run': False}) - default_conf.update({'db_url': constants.DEFAULT_DB_PROD_URL}) + default_conf.update({'db_url': DEFAULT_DB_PROD_URL}) create_engine_mock = mocker.patch('freqtrade.persistence.models.create_engine', MagicMock()) @@ -1739,7 +1739,7 @@ def test_to_json(fee): 'base_currency': 'ADA', 'quote_currency': 'USDT', 'is_open': None, - 'open_date': trade.open_date.strftime("%Y-%m-%d %H:%M:%S"), + 'open_date': trade.open_date.strftime(DATETIME_PRINT_FORMAT), 'open_timestamp': int(trade.open_date.timestamp() * 1000), 'open_order_id': 'dry_run_buy_12345', 'close_date': None, @@ -1817,9 +1817,9 @@ def test_to_json(fee): 'pair': 'XRP/BTC', 'base_currency': 'XRP', 'quote_currency': 'BTC', - 'open_date': trade.open_date.strftime("%Y-%m-%d %H:%M:%S"), + 'open_date': trade.open_date.strftime(DATETIME_PRINT_FORMAT), 'open_timestamp': int(trade.open_date.timestamp() * 1000), - 'close_date': trade.close_date.strftime("%Y-%m-%d %H:%M:%S"), + 'close_date': trade.close_date.strftime(DATETIME_PRINT_FORMAT), 'close_timestamp': int(trade.close_date.timestamp() * 1000), 'open_rate': 0.123, 'close_rate': 0.125,