train_utils.py 22.6 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
# @author lucasmiranda42
# encoding: utf-8
# module deepof

"""

Simple utility functions used in deepof example scripts. These are not part of the main package

"""

lucas_miranda's avatar
lucas_miranda committed
11
12
import json
import os
13
from datetime import date, datetime
lucas_miranda's avatar
lucas_miranda committed
14
15
16
17
from typing import Tuple, Union, Any, List

import numpy as np
import tensorflow as tf
18
from kerastuner import BayesianOptimization, Hyperband
19
from kerastuner_tensorboard_logger import TensorBoardLogger
lucas_miranda's avatar
lucas_miranda committed
20
from sklearn.metrics import roc_auc_score
21
from tensorboard.plugins.hparams import api as hp
lucas_miranda's avatar
lucas_miranda committed
22

23
24
25
import deepof.hypermodels
import deepof.model_utils

26
27
28
29
30
# Ignore warning with no downstream effect
tf.get_logger().setLevel("ERROR")
tf.autograph.set_verbosity(0)


31
class CustomStopper(tf.keras.callbacks.EarlyStopping):
32
    """ Custom early stopping callback. Prevents the model from stopping before warmup is over """
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49

    def __init__(self, start_epoch, *args, **kwargs):
        super(CustomStopper, self).__init__(*args, **kwargs)
        self.start_epoch = start_epoch

    def get_config(self):  # pragma: no cover
        """Updates callback metadata"""

        config = super().get_config().copy()
        config.update({"start_epoch": self.start_epoch})
        return config

    def on_epoch_end(self, epoch, logs=None):
        if epoch > self.start_epoch:
            super().on_epoch_end(epoch, logs)


50
51
52
53
54
def load_treatments(train_path):
    """Loads a dictionary containing the treatments per individual,
    to be loaded as metadata in the coordinates class"""
    try:
        with open(
55
56
57
58
59
            os.path.join(
                train_path,
                [i for i in os.listdir(train_path) if i.endswith(".json")][0],
            ),
            "r",
60
        ) as handle:
61
            treatment_dict = json.load(handle)
62
63
64
65
66
67
68
    except IndexError:
        treatment_dict = None

    return treatment_dict


def get_callbacks(
69
70
71
    X_train: np.array,
    batch_size: int,
    variational: bool,
72
73
74
    phenotype_prediction: float,
    next_sequence_prediction: float,
    rule_based_prediction: float,
75
    loss: str,
76
77
    loss_warmup: int = 0,
    warmup_mode: str = "none",
78
    X_val: np.array = None,
79
    input_type: str = False,
80
81
82
83
84
85
86
    cp: bool = False,
    reg_cat_clusters: bool = False,
    reg_cluster_variance: bool = False,
    entropy_samples: int = 15000,
    entropy_knn: int = 100,
    logparam: dict = None,
    outpath: str = ".",
87
    run: int = False,
88
) -> List[Union[Any]]:
89
    """Generates callbacks for model training, including:
90
91
    - run_ID: run name, with coarse parameter details;
    - tensorboard_callback: for real-time visualization;
92
93
94
95
    - cp_callback: for checkpoint saving;
    - onecycle: for learning rate scheduling;
    - entropy: neighborhood entropy in the latent space;
    """
96

97
98
99
100
101
102
103
104
    latreg = "none"
    if reg_cat_clusters and not reg_cluster_variance:
        latreg = "categorical"
    elif reg_cluster_variance and not reg_cat_clusters:
        latreg = "variance"
    elif reg_cat_clusters and reg_cluster_variance:
        latreg = "categorical+variance"

105
    run_ID = "{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}".format(
106
        ("GMVAE" if variational else "AE"),
107
        ("_input_type={}".format(input_type) if input_type else "coords"),
108
        ("_window_size={}".format(X_train.shape[1])),
109
110
111
        ("_NextSeqPred={}".format(next_sequence_prediction) if variational else ""),
        ("_PhenoPred={}".format(phenotype_prediction) if variational else ""),
        ("_RuleBasedPred={}".format(rule_based_prediction) if variational else ""),
112
        ("_loss={}".format(loss) if variational else ""),
113
114
        ("_loss_warmup={}".format(loss_warmup)),
        ("_warmup_mode={}".format(warmup_mode)),
115
116
        ("_encoding={}".format(logparam["encoding"]) if logparam is not None else ""),
        ("_k={}".format(logparam["k"]) if logparam is not None else ""),
117
        ("_latreg={}".format(latreg)),
118
119
        ("_entknn={}".format(entropy_knn)),
        ("_run={}".format(run) if run else ""),
120
        ("_{}".format(datetime.now().strftime("%Y%m%d-%H%M%S")) if not run else ""),
121
122
    )

123
    log_dir = os.path.abspath(os.path.join(outpath, "fit", run_ID))
124
    tensorboard_callback = tf.keras.callbacks.TensorBoard(
125
126
127
        log_dir=log_dir,
        histogram_freq=1,
        profile_batch=2,
128
129
    )

130
    entropy = deepof.model_utils.neighbor_latent_entropy(
131
        encoding_dim=logparam["encoding"],
132
        k=entropy_knn,
133
        samples=entropy_samples,
lucas_miranda's avatar
lucas_miranda committed
134
        validation_data=X_val,
135
        log_dir=os.path.join(outpath, "metrics", run_ID),
136
        variational=variational,
lucas_miranda's avatar
lucas_miranda committed
137
138
    )

139
    onecycle = deepof.model_utils.one_cycle_scheduler(
140
141
        X_train.shape[0] // batch_size * 250,
        max_rate=0.005,
142
        log_dir=os.path.join(outpath, "metrics", run_ID),
143
144
    )

145
    callbacks = [run_ID, tensorboard_callback, entropy, onecycle]
146
147
148

    if cp:
        cp_callback = tf.keras.callbacks.ModelCheckpoint(
149
            os.path.join(outpath, "checkpoints", run_ID + "/cp-{epoch:04d}.ckpt"),
150
151
152
153
154
155
156
157
            verbose=1,
            save_best_only=False,
            save_weights_only=True,
            save_freq="epoch",
        )
        callbacks.append(cp_callback)

    return callbacks
158
159


lucas_miranda's avatar
lucas_miranda committed
160
def log_hyperparameters(phenotype_class: float, rec: str):
lucas_miranda's avatar
lucas_miranda committed
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
    """Blueprint for hyperparameter and metric logging in tensorboard during hyperparameter tuning"""

    logparams = [
        hp.HParam(
            "encoding",
            hp.Discrete([2, 4, 6, 8, 12, 16]),
            display_name="encoding",
            description="encoding size dimensionality",
        ),
        hp.HParam(
            "k",
            hp.IntInterval(min_value=1, max_value=25),
            display_name="k",
            description="cluster_number",
        ),
        hp.HParam(
            "loss",
            hp.Discrete(["ELBO", "MMD", "ELBO+MMD"]),
            display_name="loss function",
            description="loss function",
        ),
    ]

    metrics = [
        hp.Metric("val_{}mae".format(rec), display_name="val_{}mae".format(rec)),
        hp.Metric("val_{}mse".format(rec), display_name="val_{}mse".format(rec)),
    ]
    if phenotype_class:
        logparams.append(
            hp.HParam(
                "pheno_weight",
                hp.RealInterval(min_value=0.0, max_value=1000.0),
                display_name="pheno weight",
                description="weight applied to phenotypic classifier from the latent space",
            )
        )
        metrics += [
            hp.Metric(
                "phenotype_prediction_accuracy",
                display_name="phenotype_prediction_accuracy",
            ),
            hp.Metric(
                "phenotype_prediction_auc",
                display_name="phenotype_prediction_auc",
            ),
        ]

    return logparams, metrics


# noinspection PyUnboundLocalVariable
lucas_miranda's avatar
lucas_miranda committed
212
def tensorboard_metric_logging(
213
214
215
216
217
    run_dir: str,
    hpms: Any,
    ae: Any,
    X_val: np.ndarray,
    y_val: np.ndarray,
218
219
220
    next_sequence_prediction: float,
    phenotype_prediction: float,
    rule_based_prediction: float,
221
    rec: str,
lucas_miranda's avatar
lucas_miranda committed
222
):
lucas_miranda's avatar
lucas_miranda committed
223
224
    """Autoencoder metric logging in tensorboard"""

225
226
    outputs = ae.predict(X_val)
    idx_generator = (idx for idx in range(len(outputs)))
lucas_miranda's avatar
lucas_miranda committed
227
228
229

    with tf.summary.create_file_writer(run_dir).as_default():
        hp.hparams(hpms)  # record the values used in this trial
230
231
        idx = next(idx_generator)

lucas_miranda's avatar
lucas_miranda committed
232
        val_mae = tf.reduce_mean(
233
            tf.keras.metrics.mean_absolute_error(y_val[idx], outputs[idx])
lucas_miranda's avatar
lucas_miranda committed
234
235
        )
        val_mse = tf.reduce_mean(
236
            tf.keras.metrics.mean_squared_error(y_val[idx], outputs[idx])
lucas_miranda's avatar
lucas_miranda committed
237
238
239
240
        )
        tf.summary.scalar("val_{}mae".format(rec), val_mae, step=1)
        tf.summary.scalar("val_{}mse".format(rec), val_mse, step=1)

241
        if next_sequence_prediction:
242
            idx = next(idx_generator)
lucas_miranda's avatar
lucas_miranda committed
243
            pred_mae = tf.reduce_mean(
244
                tf.keras.metrics.mean_absolute_error(y_val[idx], outputs[idx])
lucas_miranda's avatar
lucas_miranda committed
245
246
            )
            pred_mse = tf.reduce_mean(
247
                tf.keras.metrics.mean_squared_error(y_val[idx], outputs[idx])
248
249
250
251
252
253
            )
            tf.summary.scalar(
                "val_next_sequence_prediction_mae".format(rec), pred_mae, step=1
            )
            tf.summary.scalar(
                "val_next_sequence_prediction_mse".format(rec), pred_mse, step=1
lucas_miranda's avatar
lucas_miranda committed
254
255
            )

256
        if phenotype_prediction:
257
            idx = next(idx_generator)
258
259
260
            pheno_acc = tf.keras.metrics.binary_accuracy(
                y_val[idx], tf.squeeze(outputs[idx])
            )
261
            pheno_auc = tf.keras.metrics.AUC()
262
            pheno_auc.update_state(y_val[idx], outputs[idx])
263
            pheno_auc = pheno_auc.result().numpy()
lucas_miranda's avatar
lucas_miranda committed
264
265
266
267

            tf.summary.scalar("phenotype_prediction_accuracy", pheno_acc, step=1)
            tf.summary.scalar("phenotype_prediction_auc", pheno_auc, step=1)

268
        if rule_based_prediction:
269
            idx = next(idx_generator)
270
            rules_mae = tf.reduce_mean(
271
                tf.keras.metrics.mean_absolute_error(y_val[idx], outputs[idx])
272
273
            )
            rules_mse = tf.reduce_mean(
274
                tf.keras.metrics.mean_squared_error(y_val[idx], outputs[idx])
275
276
277
278
            )
            tf.summary.scalar("val_prediction_mae".format(rec), rules_mae, step=1)
            tf.summary.scalar("val_prediction_mse".format(rec), rules_mse, step=1)

lucas_miranda's avatar
lucas_miranda committed
279

280
def autoencoder_fitting(
281
282
283
284
285
    preprocessed_object: Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray],
    batch_size: int,
    encoding_size: int,
    epochs: int,
    hparams: dict,
286
    kl_annealing_mode: str,
287
288
289
290
    kl_warmup: int,
    log_history: bool,
    log_hparams: bool,
    loss: str,
291
    mmd_annealing_mode: str,
292
293
294
295
    mmd_warmup: int,
    montecarlo_kl: int,
    n_components: int,
    output_path: str,
296
297
298
    next_sequence_prediction: float,
    phenotype_prediction: float,
    rule_based_prediction: float,
299
300
301
302
303
304
305
306
    pretrained: str,
    save_checkpoints: bool,
    save_weights: bool,
    variational: bool,
    reg_cat_clusters: bool,
    reg_cluster_variance: bool,
    entropy_samples: int,
    entropy_knn: int,
307
    input_type: str,
308
    run: int = 0,
309
    strategy: tf.distribute.Strategy = tf.distribute.MirroredStrategy(),
310
):
311
312
    """Implementation function for deepof.data.coordinates.deep_unsupervised_embedding"""

313
    # Load data
314
315
316
317
318
    X_train, y_train, X_val, y_val = preprocessed_object

    # To avoid stability issues
    tf.keras.backend.clear_session()

319
    # Defines what to log on tensorboard (useful for trying out different models)
320
321
    logparam = {
        "encoding": encoding_size,
322
        "k": n_components,
323
324
        "loss": loss,
    }
325
326
    if phenotype_prediction:
        logparam["pheno_weight"] = phenotype_prediction
327

328
    # Load callbacks
329
    run_ID, *cbacks = get_callbacks(
330
331
332
        X_train=X_train,
        batch_size=batch_size,
        variational=variational,
333
        phenotype_prediction=phenotype_prediction,
334
        next_sequence_prediction=next_sequence_prediction,
335
        rule_based_prediction=rule_based_prediction,
336
        loss=loss,
337
338
        loss_warmup=kl_warmup,
        warmup_mode=kl_annealing_mode,
339
340
341
        input_type=input_type,
        X_val=(X_val if X_val.shape != (0,) else None),
        cp=save_checkpoints,
342
        reg_cat_clusters=reg_cat_clusters,
343
        reg_cluster_variance=reg_cluster_variance,
344
345
        entropy_samples=entropy_samples,
        entropy_knn=entropy_knn,
346
347
        logparam=logparam,
        outpath=output_path,
348
        run=run,
349
    )
350
351
    if not log_history:
        cbacks = cbacks[1:]
352

353
    # Logs hyperparameters to tensorboard
354
    rec = "reconstruction_" if phenotype_prediction else ""
355
    if log_hparams:
356
        logparams, metrics = log_hyperparameters(phenotype_prediction, rec)
357
358

        with tf.summary.create_file_writer(
359
            os.path.join(output_path, "hparams", run_ID)
360
361
362
363
364
        ).as_default():
            hp.hparams_config(
                hparams=logparams,
                metrics=metrics,
            )
365

366
367
368
369
370
371
372
373
    # Gets the number of rule-based features
    try:
        rule_based_features = (
            y_train.shape[1] if not phenotype_prediction else y_train.shape[1] - 1
        )
    except IndexError:
        rule_based_features = 0

374
    # Build models
375
376
377
378
379
380
381
    if not variational:
        encoder, decoder, ae = deepof.models.SEQ_2_SEQ_AE(
            ({} if hparams is None else hparams)
        ).build(X_train.shape)
        return_list = (encoder, decoder, ae)

    else:
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
        with strategy.scope():
            (
                encoder,
                generator,
                grouper,
                ae,
                prior,
                posterior,
            ) = deepof.models.SEQ_2_SEQ_GMVAE(
                architecture_hparams=({} if hparams is None else hparams),
                batch_size=batch_size * strategy.num_replicas_in_sync,
                compile_model=True,
                encoding=encoding_size,
                kl_annealing_mode=kl_annealing_mode,
                kl_warmup_epochs=kl_warmup,
                loss=loss,
                mmd_annealing_mode=mmd_annealing_mode,
                mmd_warmup_epochs=mmd_warmup,
                montecarlo_kl=montecarlo_kl,
                neuron_control=False,
                number_of_components=n_components,
                overlap_loss=False,
                next_sequence_prediction=next_sequence_prediction,
                phenotype_prediction=phenotype_prediction,
                rule_based_prediction=rule_based_prediction,
                rule_based_features=rule_based_features,
                reg_cat_clusters=reg_cat_clusters,
                reg_cluster_variance=reg_cluster_variance,
            ).build(
                X_train.shape
            )
            return_list = (encoder, generator, grouper, ae)
414
415

    if pretrained:
416
        # If pretrained models are specified, load weights and return
417
418
419
420
421
422
423
424
425
        ae.load_weights(pretrained)
        return return_list

    else:
        if not variational:

            ae.fit(
                x=X_train,
                y=X_train,
426
                epochs=epochs,
427
428
                verbose=1,
                validation_data=(X_val, X_val),
429
                callbacks=cbacks
430
431
432
433
434
435
436
437
                + [
                    CustomStopper(
                        monitor="val_loss",
                        patience=5,
                        restore_best_weights=True,
                        start_epoch=max(kl_warmup, mmd_warmup),
                    ),
                ],
438
439
            )

440
441
442
            if not os.path.exists(os.path.join(output_path, "trained_weights")):
                os.makedirs(os.path.join(output_path, "trained_weights"))

443
            if save_weights:
444
445
446
447
448
449
450
                ae.save_weights(
                    os.path.join(
                        "{}".format(output_path),
                        "trained_weights",
                        "{}_final_weights.h5".format(run_ID),
                    )
                )
451

452
453
        else:

454
            callbacks_ = cbacks + [
455
456
457
458
                CustomStopper(
                    monitor="val_loss",
                    patience=5,
                    restore_best_weights=True,
459
                    start_epoch=max(kl_warmup, mmd_warmup),
460
461
462
                ),
            ]

463
464
            Xs, ys = X_train, [X_train]
            Xvals, yvals = X_val, [X_val]
465

466
            if next_sequence_prediction > 0.0:
467
468
469
                Xs, ys = X_train[:-1], [X_train[:-1], X_train[1:]]
                Xvals, yvals = X_val[:-1], [X_val[:-1], X_val[1:]]

470
            if phenotype_prediction > 0.0:
471
                ys += [y_train[-Xs.shape[0] :, 0]]
472
                yvals += [y_val[-Xvals.shape[0] :, 0]]
473
474
475
476
477
478

                # Remove the used column (phenotype) from both y arrays
                y_train = y_train[:, 1:]
                y_val = y_val[:, 1:]

            if rule_based_prediction > 0.0:
479
                ys += [y_train[-Xs.shape[0] :]]
480
                yvals += [y_val[-Xvals.shape[0] :]]
481

482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
            # Convert data to tf.data.Dataset objects
            options = tf.data.Options()
            options.experimental_distribute.auto_shard_policy = (
                tf.data.experimental.AutoShardPolicy.DATA
            )

            train_dataset = (
                tf.data.Dataset.from_tensor_slices((Xs, *ys))
                .with_options(options)
                .batch(batch_size)
            )
            val_dataset = (
                tf.data.Dataset.from_tensor_slices((Xvals, *yvals))
                .with_options(options)
                .batch(batch_size)
            )

499
            ae.fit(
500
                x=train_dataset,
501
                epochs=epochs,
502
                batch_size=batch_size * strategy.num_replicas_in_sync,
503
                verbose=1,
504
                validation_data=val_dataset,
505
506
507
                callbacks=callbacks_,
            )

508
            if not os.path.exists(os.path.join(output_path, "trained_weights")):
509
                os.makedirs(os.path.join(output_path, "trained_weights"))
510

511
            if save_weights:
512
513
                ae.save_weights(
                    os.path.join(
514
515
516
                        "{}".format(output_path),
                        "trained_weights",
                        "{}_final_weights.h5".format(run_ID),
517
518
                    )
                )
519

520
521
522
            if log_hparams:
                # Logparams to tensorboard
                tensorboard_metric_logging(
523
524
525
526
527
528
529
530
531
                    run_dir=os.path.join(output_path, "hparams", run_ID),
                    hpms=logparam,
                    ae=ae,
                    X_val=Xvals,
                    y_val=yvals,
                    next_sequence_prediction=next_sequence_prediction,
                    phenotype_prediction=phenotype_prediction,
                    rule_based_prediction=rule_based_prediction,
                    rec=rec,
532
                )
533

534
535
536
    return return_list


537
def tune_search(
538
539
540
541
542
543
544
545
546
547
    data: List[np.array],
    encoding_size: int,
    hypertun_trials: int,
    hpt_type: str,
    hypermodel: str,
    k: int,
    kl_warmup_epochs: int,
    loss: str,
    mmd_warmup_epochs: int,
    overlap_loss: float,
548
549
550
    next_sequence_prediction: float,
    phenotype_prediction: float,
    rule_based_prediction: float,
551
552
553
554
555
    project_name: str,
    callbacks: List,
    n_epochs: int = 30,
    n_replicas: int = 1,
    outpath: str = ".",
556
) -> Union[bool, Tuple[Any, Any]]:
557
558
    """Define the search space using keras-tuner and bayesian optimization

559
560
561
562
563
564
565
566
567
568
569
    Parameters:
        - train (np.array): dataset to train the model on
        - test (np.array): dataset to validate the model on
        - hypertun_trials (int): number of Bayesian optimization iterations to run
        - hpt_type (str): specify one of Bayesian Optimization (bayopt) and Hyperband (hyperband)
        - hypermodel (str): hypermodel to load. Must be one of S2SAE (plain autoencoder)
        or S2SGMVAE (Gaussian Mixture Variational autoencoder).
        - k (int) number of components of the Gaussian Mixture
        - loss (str): one of [ELBO, MMD, ELBO+MMD]
        - overlap_loss (float): assigns as weight to an extra loss term which
        penalizes overlap between GM components
570
        - phenotype_class (float): adds an extra regularizing neural network to the model,
571
572
573
574
575
576
577
578
579
580
581
582
        which tries to predict the phenotype of the animal from which the sequence comes
        - predictor (float): adds an extra regularizing neural network to the model,
        which tries to predict the next frame from the current one
        - project_name (str): ID of the current run
        - callbacks (list): list of callbacks for the training loop
        - n_epochs (int): optional. Number of epochs to train each run for
        - n_replicas (int): optional. Number of replicas per parameter set. Higher values
         will yield more robust results, but will affect performance severely

    Returns:
        - best_hparams (dict): dictionary with the best retrieved hyperparameters
        - best_run (tf.keras.Model): trained instance of the best model found
583
584
585

    """

586
587
    X_train, y_train, X_val, y_val = data

588
589
590
591
    assert hpt_type in ["bayopt", "hyperband"], (
        "Invalid hyperparameter tuning framework. " "Select one of bayopt and hyperband"
    )

lucas_miranda's avatar
lucas_miranda committed
592
    if hypermodel == "S2SAE":  # pragma: no cover
593
        assert (
594
            next_sequence_prediction == 0.0 and phenotype_prediction == 0.0
595
        ), "Prediction branches are only available for variational models. See documentation for more details"
596
        batch_size = 1
597
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
598
599

    elif hypermodel == "S2SGMVAE":
600
        batch_size = 64
601
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
602
            input_shape=X_train.shape,
603
            encoding=encoding_size,
604
            kl_warmup_epochs=kl_warmup_epochs,
605
            loss=loss,
606
            mmd_warmup_epochs=mmd_warmup_epochs,
607
            number_of_components=k,
608
            overlap_loss=overlap_loss,
609
610
611
            next_sequence_prediction=next_sequence_prediction,
            phenotype_prediction=phenotype_prediction,
            rule_based_prediction=rule_based_prediction,
612
613
614
            rule_based_features=(
                y_train.shape[1] if not phenotype_prediction else y_train.shape[1] - 1
            ),
615
        )
lucas_miranda's avatar
lucas_miranda committed
616

617
618
619
    else:
        return False

620
621
622
    hpt_params = {
        "hypermodel": hypermodel,
        "executions_per_trial": n_replicas,
623
624
625
        "logger": TensorBoardLogger(
            metrics=["val_mae"], logdir=os.path.join(outpath, "logged_hparams")
        ),
626
627
628
629
630
631
632
        "objective": "val_mae",
        "project_name": project_name,
        "tune_new_entries": True,
    }

    if hpt_type == "hyperband":
        tuner = Hyperband(
633
634
635
            directory=os.path.join(
                outpath, "HyperBandx_{}_{}".format(loss, str(date.today()))
            ),
636
            max_epochs=30,
637
            hyperband_iterations=hypertun_trials,
638
            factor=3,
639
640
641
642
            **hpt_params
        )
    else:
        tuner = BayesianOptimization(
643
644
645
            directory=os.path.join(
                outpath, "BayOpt_{}_{}".format(loss, str(date.today()))
            ),
646
647
648
            max_trials=hypertun_trials,
            **hpt_params
        )
649
650
651

    print(tuner.search_space_summary())

652
653
654
    Xs, ys = [X_train], [X_train]
    Xvals, yvals = [X_val], [X_val]

655
    if next_sequence_prediction > 0.0:
656
657
658
        Xs, ys = X_train[:-1], [X_train[:-1], X_train[1:]]
        Xvals, yvals = X_val[:-1], [X_val[:-1], X_val[1:]]

659
    if phenotype_prediction > 0.0:
660
661
        ys += [y_train[-Xs.shape[0] :, 0]]
        yvals += [y_val[-Xvals.shape[0] :, 0]]
662
663
664
665
666
667

        # Remove the used column (phenotype) from both y arrays
        y_train = y_train[:, 1:]
        y_val = y_val[:, 1:]

    if rule_based_prediction > 0.0:
668
669
        ys += [y_train[-Xs.shape[0] :]]
        yvals += [y_val[-Xvals.shape[0] :]]
670

671
    tuner.search(
672
673
        Xs,
        ys,
674
        epochs=n_epochs,
675
        validation_data=(Xvals, yvals),
676
        verbose=1,
677
        batch_size=batch_size,
lucas_miranda's avatar
lucas_miranda committed
678
        callbacks=callbacks,
679
680
681
682
683
    )

    best_hparams = tuner.get_best_hyperparameters(num_trials=1)[0]
    best_run = tuner.hypermodel.build(best_hparams)

lucas_miranda's avatar
lucas_miranda committed
684
685
    print(tuner.results_summary())

686
    return best_hparams, best_run