add tensorflow interface

This commit is contained in:
robcaulk 2022-09-26 21:55:23 +02:00
parent 853a4d1014
commit f5870a7540
6 changed files with 249 additions and 15 deletions

View File

@ -48,5 +48,5 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `learning_rate` | Boosting learning rate during regression. <br> **Datatype:** Float. | `learning_rate` | Boosting learning rate during regression. <br> **Datatype:** Float.
| `n_jobs`, `thread_count`, `task_type` | Set the number of threads for parallel processing and the `task_type` (`gpu` or `cpu`). Different model libraries use different parameter names. <br> **Datatype:** Float. | `n_jobs`, `thread_count`, `task_type` | Set the number of threads for parallel processing and the `task_type` (`gpu` or `cpu`). Different model libraries use different parameter names. <br> **Datatype:** Float.
| | **Extraneous parameters** | | **Extraneous parameters**
| `keras` | If the selected model makes use of Keras (typical for Tensorflow-based prediction models), this flag needs to be activated so that the model save/loading follows Keras standards. <br> **Datatype:** Boolean. <br> Default: `False`. | `model_save_type` | Indicate to FreqAI if the model save type needs to be something besides typical `joblib` files. Available (`keras` (hd5) and `stable_baselines` (zip). <br> **Datatype:** str. <br> Default: `joblib`.
| `conv_width` | The width of a convolutional neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. <br> Default: 2. | `conv_width` | The width of a convolutional neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. <br> Default: 2.

View File

@ -3,10 +3,10 @@ from time import time
from typing import Any from typing import Any
from pandas import DataFrame from pandas import DataFrame
import numpy as np
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.freqai_interface import IFreqaiModel from freqtrade.freqai.freqai_interface import IFreqaiModel
import tensorflow as tf
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@ -17,6 +17,13 @@ class BaseTensorFlowModel(IFreqaiModel):
User *must* inherit from this class and set fit() and predict(). User *must* inherit from this class and set fit() and predict().
""" """
def __init__(self, **kwargs):
super().__init__(config=kwargs['config'])
self.keras = True
if self.ft_params.get("DI_threshold", 0):
self.ft_params["DI_threshold"] = 0
logger.warning("DI threshold is not configured for Keras models yet. Deactivating.")
def train( def train(
self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
) -> Any: ) -> Any:
@ -68,3 +75,76 @@ class BaseTensorFlowModel(IFreqaiModel):
f"({end_time - start_time:.2f} secs) --------------------") f"({end_time - start_time:.2f} secs) --------------------")
return model return model
class WindowGenerator:
def __init__(
self,
input_width,
label_width,
shift,
train_df=None,
val_df=None,
test_df=None,
train_labels=None,
val_labels=None,
test_labels=None,
batch_size=None,
):
# Store the raw data.
self.train_df = train_df
self.val_df = val_df
self.test_df = test_df
self.train_labels = train_labels
self.val_labels = val_labels
self.test_labels = test_labels
self.batch_size = batch_size
self.input_width = input_width
self.label_width = label_width
self.shift = shift
self.total_window_size = input_width + shift
self.input_slice = slice(0, input_width)
self.input_indices = np.arange(self.total_window_size)[self.input_slice]
def make_dataset(self, data, labels=None):
data = np.array(data, dtype=np.float32)
if labels is not None:
labels = np.array(labels, dtype=np.float32)
ds = tf.keras.preprocessing.timeseries_dataset_from_array(
data=data,
targets=labels,
sequence_length=self.total_window_size,
sequence_stride=1,
sampling_rate=1,
shuffle=False,
batch_size=self.batch_size,
)
return ds
@property
def train(self):
return self.make_dataset(self.train_df, self.train_labels)
@property
def val(self):
return self.make_dataset(self.val_df, self.val_labels)
@property
def test(self):
return self.make_dataset(self.test_df, self.test_labels)
@property
def inference(self):
return self.make_dataset(self.test_df)
@property
def example(self):
"""Get and cache an example batch of `inputs, labels` for plotting."""
result = getattr(self, "_example", None)
if result is None:
# No example batch was found, so get one from the `.train` dataset
result = next(iter(self.train))
# And cache it for next time
self._example = result
return result

View File

@ -413,10 +413,13 @@ class FreqaiDataDrawer:
save_path = Path(dk.data_path) save_path = Path(dk.data_path)
# Save the trained model # Save the trained model
if not dk.keras: model_type = self.freqai_info.get('model_save_type', 'joblib')
if model_type == 'joblib':
dump(model, save_path / f"{dk.model_filename}_model.joblib") dump(model, save_path / f"{dk.model_filename}_model.joblib")
else: elif model_type == 'keras':
model.save(save_path / f"{dk.model_filename}_model.h5") model.save(save_path / f"{dk.model_filename}_model.h5")
elif 'stable_baselines' in model_type:
model.save(save_path / f"{dk.model_filename}_model.zip")
if dk.svm_model is not None: if dk.svm_model is not None:
dump(dk.svm_model, save_path / f"{dk.model_filename}_svm_model.joblib") dump(dk.svm_model, save_path / f"{dk.model_filename}_svm_model.joblib")
@ -492,15 +495,20 @@ class FreqaiDataDrawer:
dk.data_path / f"{dk.model_filename}_trained_df.pkl" dk.data_path / f"{dk.model_filename}_trained_df.pkl"
) )
model_type = self.freqai_info.get('model_save_type', 'joblib')
# try to access model in memory instead of loading object from disk to save time # try to access model in memory instead of loading object from disk to save time
if dk.live and coin in self.model_dictionary: if dk.live and coin in self.model_dictionary:
model = self.model_dictionary[coin] model = self.model_dictionary[coin]
elif not dk.keras: elif model_type == 'joblib':
model = load(dk.data_path / f"{dk.model_filename}_model.joblib") model = load(dk.data_path / f"{dk.model_filename}_model.joblib")
else: elif model_type == 'keras':
from tensorflow import keras from tensorflow import keras
model = keras.models.load_model(dk.data_path / f"{dk.model_filename}_model.h5") model = keras.models.load_model(dk.data_path / f"{dk.model_filename}_model.h5")
elif model_type == 'stable_baselines':
mod = __import__('stable_baselines3', fromlist=[
self.freqai_info['rl_config']['model_type']])
MODELCLASS = getattr(mod, self.freqai_info['rl_config']['model_type'])
model = MODELCLASS.load(dk.data_path / f"{dk.model_filename}_model")
if Path(dk.data_path / f"{dk.model_filename}_svm_model.joblib").is_file(): if Path(dk.data_path / f"{dk.model_filename}_svm_model.joblib").is_file():
dk.svm_model = load(dk.data_path / f"{dk.model_filename}_svm_model.joblib") dk.svm_model = load(dk.data_path / f"{dk.model_filename}_svm_model.joblib")

View File

@ -76,9 +76,10 @@ class FreqaiDataKitchen:
self.backtest_predictions_folder: str = "backtesting_predictions" self.backtest_predictions_folder: str = "backtesting_predictions"
self.live = live self.live = live
self.pair = pair self.pair = pair
self.model_save_type = self.freqai_config.get('model_save_type', 'joblib')
self.svm_model: linear_model.SGDOneClassSVM = None self.svm_model: linear_model.SGDOneClassSVM = None
self.keras: bool = self.freqai_config.get("keras", False) # self.model_save_type: bool = self.freqai_config.get("keras", False)
self.set_all_pairs() self.set_all_pairs()
if not self.live: if not self.live:
if not self.config["timerange"]: if not self.config["timerange"]:
@ -571,7 +572,7 @@ class FreqaiDataKitchen:
predict: bool = If true, inference an existing SVM model, else construct one predict: bool = If true, inference an existing SVM model, else construct one
""" """
if self.keras: if self.model_save_type == 'keras':
logger.warning( logger.warning(
"SVM outlier removal not currently supported for Keras based models. " "SVM outlier removal not currently supported for Keras based models. "
"Skipping user requested function." "Skipping user requested function."

View File

@ -72,10 +72,10 @@ class IFreqaiModel(ABC):
self.identifier: str = self.freqai_info.get("identifier", "no_id_provided") self.identifier: str = self.freqai_info.get("identifier", "no_id_provided")
self.scanning = False self.scanning = False
self.ft_params = self.freqai_info["feature_parameters"] self.ft_params = self.freqai_info["feature_parameters"]
self.keras: bool = self.freqai_info.get("keras", False) # self.keras: bool = self.freqai_info.get("keras", False)
if self.keras and self.ft_params.get("DI_threshold", 0): # if self.keras and self.ft_params.get("DI_threshold", 0):
self.ft_params["DI_threshold"] = 0 # self.ft_params["DI_threshold"] = 0
logger.warning("DI threshold is not configured for Keras models yet. Deactivating.") # logger.warning("DI threshold is not configured for Keras models yet. Deactivating.")
self.CONV_WIDTH = self.freqai_info.get("conv_width", 2) self.CONV_WIDTH = self.freqai_info.get("conv_width", 2)
if self.ft_params.get("inlier_metric_window", 0): if self.ft_params.get("inlier_metric_window", 0):
self.CONV_WIDTH = self.ft_params.get("inlier_metric_window", 0) * 2 self.CONV_WIDTH = self.ft_params.get("inlier_metric_window", 0) * 2
@ -627,7 +627,8 @@ class IFreqaiModel(ABC):
# # for keras type models, the conv_window needs to be prepended so # # for keras type models, the conv_window needs to be prepended so
# # viewing is correct in frequi # # viewing is correct in frequi
if self.freqai_info.get('keras', False) or self.ft_params.get('inlier_metric_window', 0): if (not self.freqai_info.get('model_save_type', 'joblib') or
self.ft_params.get('inlier_metric_window', 0)):
n_lost_points = self.freqai_info.get('conv_width', 2) n_lost_points = self.freqai_info.get('conv_width', 2)
zeros_df = DataFrame(np.zeros((n_lost_points, len(hist_preds_df.columns))), zeros_df = DataFrame(np.zeros((n_lost_points, len(hist_preds_df.columns))),
columns=hist_preds_df.columns) columns=hist_preds_df.columns)

View File

@ -0,0 +1,144 @@
import logging
from typing import Any, Dict, Tuple
from pandas import DataFrame
from freqtrade.exceptions import OperationalException
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
import tensorflow as tf
from freqtrade.freqai.base_models.BaseTensorFlowModel import BaseTensorFlowModel, WindowGenerator
from tensorflow.keras.layers import Input, Conv1D, Dense
from tensorflow.keras.models import Model
import numpy as np
logger = logging.getLogger(__name__)
# tf.config.run_functions_eagerly(True)
# tf.data.experimental.enable_debug_mode()
MAX_EPOCHS = 10
class CNNPredictionModel(BaseTensorFlowModel):
"""
User created prediction model. The class needs to override three necessary
functions, predict(), fit().
"""
def fit(self, data_dictionary: Dict[str, Any], dk: FreqaiDataKitchen) -> Any:
"""
User sets up the training and test data to fit their desired model here
:params:
:data_dictionary: the dictionary constructed by DataHandler to hold
all the training and test data/labels.
"""
train_df = data_dictionary["train_features"]
train_labels = data_dictionary["train_labels"]
test_df = data_dictionary["test_features"]
test_labels = data_dictionary["test_labels"]
n_labels = len(train_labels.columns)
if n_labels > 1:
raise OperationalException(
"Neural Net not yet configured for multi-targets. Please "
" reduce number of targets to 1 in strategy."
)
n_features = len(data_dictionary["train_features"].columns)
BATCH_SIZE = self.freqai_info.get("batch_size", 64)
input_dims = [BATCH_SIZE, self.CONV_WIDTH, n_features]
w1 = WindowGenerator(
input_width=self.CONV_WIDTH,
label_width=1,
shift=1,
train_df=train_df,
val_df=test_df,
train_labels=train_labels,
val_labels=test_labels,
batch_size=BATCH_SIZE,
)
model = self.create_model(input_dims, n_labels)
steps_per_epoch = np.ceil(len(test_df) / BATCH_SIZE)
lr_schedule = tf.keras.optimizers.schedules.InverseTimeDecay(
0.001, decay_steps=steps_per_epoch * 1000, decay_rate=1, staircase=False
)
early_stopping = tf.keras.callbacks.EarlyStopping(
monitor="loss", patience=3, mode="min", min_delta=0.0001
)
model.compile(
loss=tf.losses.MeanSquaredError(),
optimizer=tf.optimizers.Adam(lr_schedule),
metrics=[tf.metrics.MeanAbsoluteError()],
)
model.fit(
w1.train,
epochs=MAX_EPOCHS,
shuffle=False,
validation_data=w1.val,
callbacks=[early_stopping],
verbose=1,
)
return model
def predict(
self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first=True
) -> Tuple[DataFrame, DataFrame]:
"""
Filter the prediction features data and predict with it.
:param: unfiltered_dataframe: Full dataframe for the current backtest period.
:return:
:predictions: np.array of 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
)
filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe)
dk.data_dictionary["prediction_features"] = filtered_dataframe
# optional additional data cleaning/analysis
self.data_cleaning_predict(dk, filtered_dataframe)
if first:
full_df = dk.data_dictionary["prediction_features"]
w1 = WindowGenerator(
input_width=self.CONV_WIDTH,
label_width=1,
shift=1,
test_df=full_df,
batch_size=len(full_df),
)
predictions = self.model.predict(w1.inference)
len_diff = len(dk.do_predict) - len(predictions)
if len_diff > 0:
dk.do_predict = dk.do_predict[len_diff:]
else:
data = dk.data_dictionary["prediction_features"]
data = tf.expand_dims(data, axis=0)
predictions = self.model(data, training=False)
predictions = predictions[:, 0, 0]
pred_df = DataFrame(predictions, columns=dk.label_list)
pred_df = dk.denormalize_labels_from_metadata(pred_df)
return (pred_df, np.ones(len(pred_df)))
def create_model(self, input_dims, n_labels) -> Any:
input_layer = Input(shape=(input_dims[1], input_dims[2]))
Layer_1 = Conv1D(filters=32, kernel_size=(self.CONV_WIDTH,), activation="relu")(input_layer)
Layer_3 = Dense(units=32, activation="relu")(Layer_1)
output_layer = Dense(units=n_labels)(Layer_3)
return Model(inputs=input_layer, outputs=output_layer)