train_utils.py 21.8 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
):
310
311
    """Implementation function for deepof.data.coordinates.deep_unsupervised_embedding"""

312
    # Load data
313
314
315
316
317
    X_train, y_train, X_val, y_val = preprocessed_object

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

318
    # Defines what to log on tensorboard (useful for trying out different models)
319
320
    logparam = {
        "encoding": encoding_size,
321
        "k": n_components,
322
323
        "loss": loss,
    }
324
325
    if phenotype_prediction:
        logparam["pheno_weight"] = phenotype_prediction
326

327
    # Load callbacks
328
    run_ID, *cbacks = get_callbacks(
329
330
331
        X_train=X_train,
        batch_size=batch_size,
        variational=variational,
332
        phenotype_prediction=phenotype_prediction,
333
        next_sequence_prediction=next_sequence_prediction,
334
        rule_based_prediction=rule_based_prediction,
335
        loss=loss,
336
337
338
        input_type=input_type,
        X_val=(X_val if X_val.shape != (0,) else None),
        cp=save_checkpoints,
339
        reg_cat_clusters=reg_cat_clusters,
340
        reg_cluster_variance=reg_cluster_variance,
341
342
        entropy_samples=entropy_samples,
        entropy_knn=entropy_knn,
343
344
        logparam=logparam,
        outpath=output_path,
345
        run=run,
346
    )
347
348
    if not log_history:
        cbacks = cbacks[1:]
349

350
    # Logs hyperparameters to tensorboard
351
    rec = "reconstruction_" if phenotype_prediction else ""
352
    if log_hparams:
353
        logparams, metrics = log_hyperparameters(phenotype_prediction, rec)
354
355

        with tf.summary.create_file_writer(
356
            os.path.join(output_path, "hparams", run_ID)
357
358
359
360
361
        ).as_default():
            hp.hparams_config(
                hparams=logparams,
                metrics=metrics,
            )
362

363
364
365
366
367
368
369
370
    # 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

371
    # Build models
372
373
374
375
376
377
378
    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:
379
380
381
382
383
384
385
386
        (
            encoder,
            generator,
            grouper,
            ae,
            prior,
            posterior,
        ) = deepof.models.SEQ_2_SEQ_GMVAE(
387
388
389
390
            architecture_hparams=({} if hparams is None else hparams),
            batch_size=batch_size,
            compile_model=True,
            encoding=encoding_size,
391
            kl_annealing_mode=kl_annealing_mode,
392
393
            kl_warmup_epochs=kl_warmup,
            loss=loss,
394
            mmd_annealing_mode=mmd_annealing_mode,
395
396
397
398
399
            mmd_warmup_epochs=mmd_warmup,
            montecarlo_kl=montecarlo_kl,
            neuron_control=False,
            number_of_components=n_components,
            overlap_loss=False,
400
401
402
            next_sequence_prediction=next_sequence_prediction,
            phenotype_prediction=phenotype_prediction,
            rule_based_prediction=rule_based_prediction,
403
            rule_based_features=rule_based_features,
404
405
            reg_cat_clusters=reg_cat_clusters,
            reg_cluster_variance=reg_cluster_variance,
406
407
408
        ).build(
            X_train.shape
        )
409
410
411
        return_list = (encoder, generator, grouper, ae)

    if pretrained:
412
        # If pretrained models are specified, load weights and return
413
414
415
416
417
418
419
420
421
        ae.load_weights(pretrained)
        return return_list

    else:
        if not variational:

            ae.fit(
                x=X_train,
                y=X_train,
422
                epochs=epochs,
423
424
425
                batch_size=batch_size,
                verbose=1,
                validation_data=(X_val, X_val),
426
                callbacks=cbacks
427
428
429
430
431
432
433
434
                + [
                    CustomStopper(
                        monitor="val_loss",
                        patience=5,
                        restore_best_weights=True,
                        start_epoch=max(kl_warmup, mmd_warmup),
                    ),
                ],
435
436
            )

437
438
439
            if not os.path.exists(os.path.join(output_path, "trained_weights")):
                os.makedirs(os.path.join(output_path, "trained_weights"))

440
            if save_weights:
441
442
443
444
445
446
447
                ae.save_weights(
                    os.path.join(
                        "{}".format(output_path),
                        "trained_weights",
                        "{}_final_weights.h5".format(run_ID),
                    )
                )
448

449
450
        else:

451
            callbacks_ = cbacks + [
452
453
454
455
                CustomStopper(
                    monitor="val_loss",
                    patience=5,
                    restore_best_weights=True,
456
                    start_epoch=max(kl_warmup, mmd_warmup),
457
458
459
                ),
            ]

460
461
            Xs, ys = X_train, [X_train]
            Xvals, yvals = X_val, [X_val]
462

463
            if next_sequence_prediction > 0.0:
464
465
466
                Xs, ys = X_train[:-1], [X_train[:-1], X_train[1:]]
                Xvals, yvals = X_val[:-1], [X_val[:-1], X_val[1:]]

467
            if phenotype_prediction > 0.0:
468
                ys += [y_train[-Xs.shape[0] :, 0]]
469
                yvals += [y_val[-Xvals.shape[0] :, 0]]
470
471
472
473
474
475

                # 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:
476
                ys += [y_train[-Xs.shape[0] :]]
477
                yvals += [y_val[-Xvals.shape[0] :]]
478

479
            ae.fit(
480
481
                x=Xs,
                y=ys,
482
                epochs=epochs,
483
484
485
486
487
488
489
490
491
                batch_size=batch_size,
                verbose=1,
                validation_data=(
                    Xvals,
                    yvals,
                ),
                callbacks=callbacks_,
            )

492
            if not os.path.exists(os.path.join(output_path, "trained_weights")):
493
                os.makedirs(os.path.join(output_path, "trained_weights"))
494

495
            if save_weights:
496
497
                ae.save_weights(
                    os.path.join(
498
499
500
                        "{}".format(output_path),
                        "trained_weights",
                        "{}_final_weights.h5".format(run_ID),
501
502
                    )
                )
503

504
505
506
            if log_hparams:
                # Logparams to tensorboard
                tensorboard_metric_logging(
507
508
509
510
511
512
513
514
515
                    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,
516
                )
517

518
519
520
    return return_list


521
def tune_search(
522
523
524
525
526
527
528
529
530
531
    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,
532
533
534
    next_sequence_prediction: float,
    phenotype_prediction: float,
    rule_based_prediction: float,
535
536
537
538
539
    project_name: str,
    callbacks: List,
    n_epochs: int = 30,
    n_replicas: int = 1,
    outpath: str = ".",
540
) -> Union[bool, Tuple[Any, Any]]:
541
542
    """Define the search space using keras-tuner and bayesian optimization

543
544
545
546
547
548
549
550
551
552
553
    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
554
        - phenotype_class (float): adds an extra regularizing neural network to the model,
555
556
557
558
559
560
561
562
563
564
565
566
        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
567
568
569

    """

570
571
    X_train, y_train, X_val, y_val = data

572
573
574
575
    assert hpt_type in ["bayopt", "hyperband"], (
        "Invalid hyperparameter tuning framework. " "Select one of bayopt and hyperband"
    )

lucas_miranda's avatar
lucas_miranda committed
576
    if hypermodel == "S2SAE":  # pragma: no cover
577
        assert (
578
            next_sequence_prediction == 0.0 and phenotype_prediction == 0.0
579
        ), "Prediction branches are only available for variational models. See documentation for more details"
580
        batch_size = 1
581
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
582
583

    elif hypermodel == "S2SGMVAE":
584
        batch_size = 64
585
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
586
            input_shape=X_train.shape,
587
            encoding=encoding_size,
588
            kl_warmup_epochs=kl_warmup_epochs,
589
            loss=loss,
590
            mmd_warmup_epochs=mmd_warmup_epochs,
591
            number_of_components=k,
592
            overlap_loss=overlap_loss,
593
594
595
            next_sequence_prediction=next_sequence_prediction,
            phenotype_prediction=phenotype_prediction,
            rule_based_prediction=rule_based_prediction,
596
597
598
            rule_based_features=(
                y_train.shape[1] if not phenotype_prediction else y_train.shape[1] - 1
            ),
599
        )
lucas_miranda's avatar
lucas_miranda committed
600

601
602
603
    else:
        return False

604
605
606
    hpt_params = {
        "hypermodel": hypermodel,
        "executions_per_trial": n_replicas,
607
608
609
        "logger": TensorBoardLogger(
            metrics=["val_mae"], logdir=os.path.join(outpath, "logged_hparams")
        ),
610
611
612
613
614
615
616
        "objective": "val_mae",
        "project_name": project_name,
        "tune_new_entries": True,
    }

    if hpt_type == "hyperband":
        tuner = Hyperband(
617
618
619
            directory=os.path.join(
                outpath, "HyperBandx_{}_{}".format(loss, str(date.today()))
            ),
620
            max_epochs=30,
621
            hyperband_iterations=hypertun_trials,
622
            factor=3,
623
624
625
626
            **hpt_params
        )
    else:
        tuner = BayesianOptimization(
627
628
629
            directory=os.path.join(
                outpath, "BayOpt_{}_{}".format(loss, str(date.today()))
            ),
630
631
632
            max_trials=hypertun_trials,
            **hpt_params
        )
633
634
635

    print(tuner.search_space_summary())

636
637
638
    Xs, ys = [X_train], [X_train]
    Xvals, yvals = [X_val], [X_val]

639
    if next_sequence_prediction > 0.0:
640
641
642
        Xs, ys = X_train[:-1], [X_train[:-1], X_train[1:]]
        Xvals, yvals = X_val[:-1], [X_val[:-1], X_val[1:]]

643
    if phenotype_prediction > 0.0:
644
645
        ys += [y_train[-Xs.shape[0] :, 0]]
        yvals += [y_val[-Xvals.shape[0] :, 0]]
646
647
648
649
650
651

        # 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:
652
653
        ys += [y_train[-Xs.shape[0] :]]
        yvals += [y_val[-Xvals.shape[0] :]]
654

655
    tuner.search(
656
657
        Xs,
        ys,
658
        epochs=n_epochs,
659
        validation_data=(Xvals, yvals),
660
        verbose=1,
661
        batch_size=batch_size,
lucas_miranda's avatar
lucas_miranda committed
662
        callbacks=callbacks,
663
664
665
666
667
    )

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

lucas_miranda's avatar
lucas_miranda committed
668
669
    print(tuner.results_summary())

670
    return best_hparams, best_run