nnetsauce

 21class AdaBoostClassifier(Boosting, ClassifierMixin):
 22    """AdaBoost Classification (SAMME) model class derived from class Boosting
 23
 24    Parameters:
 25
 26        obj: object
 27            any object containing a method fit (obj.fit()) and a method predict
 28            (obj.predict())
 29
 30        n_estimators: int
 31            number of boosting iterations
 32
 33        learning_rate: float
 34            learning rate of the boosting procedure
 35
 36        n_hidden_features: int
 37            number of nodes in the hidden layer
 38
 39        reg_lambda: float
 40            regularization parameter for weights
 41
 42        reg_alpha: float
 43            controls compromize between l1 and l2 norm of weights
 44
 45        activation_name: str
 46            activation function: 'relu', 'tanh', 'sigmoid', 'prelu' or 'elu'
 47
 48        a: float
 49            hyperparameter for 'prelu' or 'elu' activation function
 50
 51        nodes_sim: str
 52            type of simulation for the nodes: 'sobol', 'hammersley', 'halton',
 53            'uniform'
 54
 55        bias: boolean
 56            indicates if the hidden layer contains a bias term (True) or not
 57            (False)
 58
 59        dropout: float
 60            regularization parameter; (random) percentage of nodes dropped out
 61            of the training
 62
 63        direct_link: boolean
 64            indicates if the original predictors are included (True) in model's
 65            fitting or not (False)
 66
 67        n_clusters: int
 68            number of clusters for 'kmeans' or 'gmm' clustering (could be 0:
 69                no clustering)
 70
 71        cluster_encode: bool
 72            defines how the variable containing clusters is treated (default is one-hot)
 73            if `False`, then labels are used, without one-hot encoding
 74
 75        type_clust: str
 76            type of clustering method: currently k-means ('kmeans') or Gaussian
 77            Mixture Model ('gmm')
 78
 79        type_scaling: a tuple of 3 strings
 80            scaling methods for inputs, hidden layer, and clustering respectively
 81            (and when relevant).
 82            Currently available: standardization ('std') or MinMax scaling ('minmax')
 83
 84        col_sample: float
 85            percentage of covariates randomly chosen for training
 86
 87        row_sample: float
 88            percentage of rows chosen for training, by stratified bootstrapping
 89
 90        seed: int
 91            reproducibility seed for nodes_sim=='uniform'
 92
 93        verbose: int
 94            0 for no output, 1 for a progress bar (default is 1)
 95
 96        method: str
 97            type of Adaboost method, 'SAMME' (discrete) or 'SAMME.R' (real)
 98
 99        backend: str
100            "cpu" or "gpu" or "tpu"
101
102    Attributes:
103
104        alpha_: list
105            AdaBoost coefficients alpha_m
106
107        base_learners_: dict
108            a dictionary containing the base learners
109
110    Examples:
111
112    See also [https://github.com/Techtonique/nnetsauce/blob/master/examples/adaboost_classification.py](https://github.com/Techtonique/nnetsauce/blob/master/examples/adaboost_classification.py)
113
114    ```python
115    import nnetsauce as ns
116    import numpy as np
117    from sklearn.datasets import load_breast_cancer
118    from sklearn.linear_model import LogisticRegression
119    from sklearn.model_selection import train_test_split
120    from sklearn import metrics
121    from time import time
122
123    breast_cancer = load_breast_cancer()
124    Z = breast_cancer.data
125    t = breast_cancer.target
126    np.random.seed(123)
127    X_train, X_test, y_train, y_test = train_test_split(Z, t, test_size=0.2)
128
129    # SAMME.R
130    clf = LogisticRegression(solver='liblinear', multi_class = 'ovr',
131                            random_state=123)
132    fit_obj = ns.AdaBoostClassifier(clf,
133                                    n_hidden_features=int(11.22338867),
134                                    direct_link=True,
135                                    n_estimators=250, learning_rate=0.01126343,
136                                    col_sample=0.72684326, row_sample=0.86429443,
137                                    dropout=0.63078613, n_clusters=2,
138                                    type_clust="gmm",
139                                    verbose=1, seed = 123,
140                                    method="SAMME.R")
141
142    start = time()
143    fit_obj.fit(X_train, y_train)
144    print(f"Elapsed {time() - start}")
145
146    start = time()
147    print(fit_obj.score(X_test, y_test))
148    print(f"Elapsed {time() - start}")
149
150    preds = fit_obj.predict(X_test)
151
152    print(metrics.classification_report(preds, y_test))
153
154    ```
155
156    """
157
158    # construct the object -----
159
160    def __init__(
161        self,
162        obj,
163        n_estimators=10,
164        learning_rate=0.1,
165        n_hidden_features=1,
166        reg_lambda=0,
167        reg_alpha=0.5,
168        activation_name="relu",
169        a=0.01,
170        nodes_sim="sobol",
171        bias=True,
172        dropout=0,
173        direct_link=False,
174        n_clusters=2,
175        cluster_encode=True,
176        type_clust="kmeans",
177        type_scaling=("std", "std", "std"),
178        col_sample=1,
179        row_sample=1,
180        seed=123,
181        verbose=1,
182        method="SAMME",
183        backend="cpu",
184    ):
185        self.type_fit = "classification"
186        self.verbose = verbose
187        self.method = method
188        self.reg_lambda = reg_lambda
189        self.reg_alpha = reg_alpha
190
191        super().__init__(
192            obj=obj,
193            n_estimators=n_estimators,
194            learning_rate=learning_rate,
195            n_hidden_features=n_hidden_features,
196            activation_name=activation_name,
197            a=a,
198            nodes_sim=nodes_sim,
199            bias=bias,
200            dropout=dropout,
201            direct_link=direct_link,
202            n_clusters=n_clusters,
203            cluster_encode=cluster_encode,
204            type_clust=type_clust,
205            type_scaling=type_scaling,
206            col_sample=col_sample,
207            row_sample=row_sample,
208            seed=seed,
209            backend=backend,
210        )
211
212        self.alpha_ = []
213        self.base_learners_ = dict.fromkeys(range(n_estimators))
214
215    def fit(self, X, y, sample_weight=None, **kwargs):
216        """Fit Boosting model to training data (X, y).
217
218        Parameters:
219
220            X: {array-like}, shape = [n_samples, n_features]
221                Training vectors, where n_samples is the number
222                of samples and n_features is the number of features.
223
224            y: array-like, shape = [n_samples]
225                Target values.
226
227            **kwargs: additional parameters to be passed to
228                    self.cook_training_set or self.obj.fit
229
230        Returns:
231
232             self: object
233        """
234
235        assert mx.is_factor(y), "y must contain only integers"
236
237        assert self.method in (
238            "SAMME",
239            "SAMME.R",
240        ), "`method` must be either 'SAMME' or 'SAMME.R'"
241
242        assert (self.reg_lambda <= 1) & (
243            self.reg_lambda >= 0
244        ), "must have self.reg_lambda <= 1 &  self.reg_lambda >= 0"
245
246        assert (self.reg_alpha <= 1) & (
247            self.reg_alpha >= 0
248        ), "must have self.reg_alpha <= 1 &  self.reg_alpha >= 0"
249
250        # training
251        n, p = X.shape
252        self.n_classes = len(np.unique(y))
253        self.classes_ = np.unique(y)  # for compatibility with sklearn
254        self.n_classes_ = len(self.classes_)  # for compatibility with sklearn
255
256        if sample_weight is None:
257            w_m = np.repeat(1.0 / n, n)
258        else:
259            w_m = np.asarray(sample_weight)
260
261        base_learner = CustomClassifier(
262            self.obj,
263            n_hidden_features=self.n_hidden_features,
264            activation_name=self.activation_name,
265            a=self.a,
266            nodes_sim=self.nodes_sim,
267            bias=self.bias,
268            dropout=self.dropout,
269            direct_link=self.direct_link,
270            n_clusters=self.n_clusters,
271            type_clust=self.type_clust,
272            type_scaling=self.type_scaling,
273            col_sample=self.col_sample,
274            row_sample=self.row_sample,
275            seed=self.seed,
276        )
277
278        if self.verbose == 1:
279            pbar = Progbar(self.n_estimators)
280
281        if self.method == "SAMME":
282            err_m = 1e6
283            err_bound = 1 - 1 / self.n_classes
284            self.alpha_.append(1.0)
285            x_range_n = range(n)
286
287            for m in range(self.n_estimators):
288                preds = base_learner.fit(
289                    X, y, sample_weight=w_m.ravel(), **kwargs
290                ).predict(X)
291
292                self.base_learners_.update({m: deepcopy(base_learner)})
293
294                cond = [y[i] != preds[i] for i in x_range_n]
295
296                err_m = max(
297                    sum([elt[0] * elt[1] for elt in zip(cond, w_m)]),
298                    2.220446049250313e-16,
299                )  # sum(w_m) == 1
300
301                if self.reg_lambda > 0:
302                    err_m += self.reg_lambda * (
303                        (1 - self.reg_alpha) * 0.5 * sum([x**2 for x in w_m])
304                        + self.reg_alpha * sum([abs(x) for x in w_m])
305                    )
306
307                err_m = min(err_m, err_bound)
308
309                alpha_m = self.learning_rate * log(
310                    (self.n_classes - 1) * (1 - err_m) / err_m
311                )
312
313                self.alpha_.append(alpha_m)
314
315                w_m_temp = [exp(alpha_m * cond[i]) for i in x_range_n]
316
317                sum_w_m = sum(w_m_temp)
318
319                w_m = np.asarray([w_m_temp[i] / sum_w_m for i in x_range_n])
320
321                base_learner.set_params(seed=self.seed + (m + 1) * 1000)
322
323                if self.verbose == 1:
324                    pbar.update(m)
325
326            if self.verbose == 1:
327                pbar.update(self.n_estimators)
328
329            self.n_estimators = len(self.base_learners_)
330            self.classes_ = np.unique(y)
331
332            return self
333
334        if self.method == "SAMME.R":
335            Y = mo.one_hot_encode2(y, self.n_classes)
336
337            if sample_weight is None:
338                w_m = np.repeat(1.0 / n, n)  # (N, 1)
339
340            else:
341                w_m = np.asarray(sample_weight)
342
343            for m in range(self.n_estimators):
344                probs = base_learner.fit(
345                    X, y, sample_weight=w_m.ravel(), **kwargs
346                ).predict_proba(X)
347
348                np.clip(a=probs, a_min=2.220446049250313e-16, a_max=1.0, out=probs)
349
350                self.base_learners_.update({m: deepcopy(base_learner)})
351
352                w_m *= np.exp(
353                    -1.0
354                    * self.learning_rate
355                    * (1.0 - 1.0 / self.n_classes)
356                    * xlogy(Y, probs).sum(axis=1)
357                )
358
359                w_m /= np.sum(w_m)
360
361                base_learner.set_params(seed=self.seed + (m + 1) * 1000)
362
363                if self.verbose == 1:
364                    pbar.update(m)
365
366            if self.verbose == 1:
367                pbar.update(self.n_estimators)
368
369            self.n_estimators = len(self.base_learners_)
370            self.classes_ = np.unique(y)
371
372            return self
373
374    def predict(self, X, **kwargs):
375        """Predict test data X.
376
377        Parameters:
378
379            X: {array-like}, shape = [n_samples, n_features]
380                Training vectors, where n_samples is the number
381                of samples and n_features is the number of features.
382
383            **kwargs: additional parameters to be passed to
384                  self.cook_test_set
385
386        Returns:
387
388            model predictions: {array-like}
389        """
390        return self.predict_proba(X, **kwargs).argmax(axis=1)
391
392    def predict_proba(self, X, **kwargs):
393        """Predict probabilities for test data X.
394
395        Parameters:
396
397            X: {array-like}, shape = [n_samples, n_features]
398                Training vectors, where n_samples is the number
399                of samples and n_features is the number of features.
400
401            **kwargs: additional parameters to be passed to
402                  self.cook_test_set
403
404        Returns:
405
406            probability estimates for test data: {array-like}
407
408        """
409
410        n_iter = len(self.base_learners_)
411
412        if self.method == "SAMME":
413            ensemble_learner = np.zeros((X.shape[0], self.n_classes))
414
415            # if self.verbose == 1:
416            #    pbar = Progbar(n_iter)
417
418            for idx, base_learner in self.base_learners_.items():
419                preds = base_learner.predict(X, **kwargs)
420
421                ensemble_learner += self.alpha_[idx] * mo.one_hot_encode2(
422                    preds, self.n_classes
423                )
424
425                # if self.verbose == 1:
426                #    pbar.update(idx)
427
428            # if self.verbose == 1:
429            #    pbar.update(n_iter)
430
431            expit_ensemble_learner = expit(ensemble_learner)
432
433            sum_ensemble = expit_ensemble_learner.sum(axis=1)
434
435            return expit_ensemble_learner / sum_ensemble[:, None]
436
437        # if self.method == "SAMME.R":
438        ensemble_learner = 0
439
440        # if self.verbose == 1:
441        #    pbar = Progbar(n_iter)
442
443        for idx, base_learner in self.base_learners_.items():
444            probs = base_learner.predict_proba(X, **kwargs)
445
446            np.clip(a=probs, a_min=2.220446049250313e-16, a_max=1.0, out=probs)
447
448            log_preds_proba = np.log(probs)
449
450            ensemble_learner += log_preds_proba - log_preds_proba.mean(axis=1)[:, None]
451
452            # if self.verbose == 1:
453            #    pbar.update(idx)
454
455        ensemble_learner *= self.n_classes - 1
456
457        # if self.verbose == 1:
458        #    pbar.update(n_iter)
459
460        expit_ensemble_learner = expit(ensemble_learner)
461
462        sum_ensemble = expit_ensemble_learner.sum(axis=1)
463
464        return expit_ensemble_learner / sum_ensemble[:, None]

 46class Base(BaseEstimator):
 47    """Base model from which all the other classes inherit.
 48
 49    This class contains the most important data preprocessing/feature engineering methods.
 50
 51    Parameters:
 52
 53        n_hidden_features: int
 54            number of nodes in the hidden layer
 55
 56        activation_name: str
 57            activation function: 'relu', 'tanh', 'sigmoid', 'prelu' or 'elu'
 58
 59        a: float
 60            hyperparameter for 'prelu' or 'elu' activation function
 61
 62        nodes_sim: str
 63            type of simulation for hidden layer nodes: 'sobol', 'hammersley', 'halton',
 64            'uniform'
 65
 66        bias: boolean
 67            indicates if the hidden layer contains a bias term (True) or
 68            not (False)
 69
 70        dropout: float
 71            regularization parameter; (random) percentage of nodes dropped out
 72            of the training
 73
 74        direct_link: boolean
 75            indicates if the original features are included (True) in model's
 76            fitting or not (False)
 77
 78        n_clusters: int
 79            number of clusters for type_clust='kmeans' or type_clust='gmm'
 80            clustering (could be 0: no clustering)
 81
 82        cluster_encode: bool
 83            defines how the variable containing clusters is treated (default is one-hot);
 84            if `False`, then labels are used, without one-hot encoding
 85
 86        type_clust: str
 87            type of clustering method: currently k-means ('kmeans') or Gaussian
 88            Mixture Model ('gmm')
 89
 90        type_scaling: a tuple of 3 strings
 91            scaling methods for inputs, hidden layer, and clustering respectively
 92            (and when relevant).
 93            Currently available: standardization ('std') or MinMax scaling ('minmax') or robust scaling ('robust') or  max absolute scaling ('maxabs')
 94
 95        col_sample: float
 96            percentage of features randomly chosen for training
 97
 98        row_sample: float
 99            percentage of rows chosen for training, by stratified bootstrapping
100
101        seed: int
102            reproducibility seed for nodes_sim=='uniform', clustering and dropout
103
104        backend: str
105            "cpu" or "gpu" or "tpu"
106
107    """
108
109    # construct the object -----
110
111    def __init__(
112        self,
113        n_hidden_features=5,
114        activation_name="relu",
115        a=0.01,
116        nodes_sim="sobol",
117        bias=True,
118        dropout=0,
119        direct_link=True,
120        n_clusters=2,
121        cluster_encode=True,
122        type_clust="kmeans",
123        type_scaling=("std", "std", "std"),
124        col_sample=1,
125        row_sample=1,
126        seed=123,
127        backend="cpu",
128    ):
129        # input checks -----
130
131        sys_platform = platform.system()
132
133        if (sys_platform == "Windows") and (backend in ("gpu", "tpu")):
134            warnings.warn("No GPU/TPU computing on Windows yet, backend set to 'cpu'")
135            backend = "cpu"
136
137        assert activation_name in (
138            "relu",
139            "tanh",
140            "sigmoid",
141            "prelu",
142            "elu",
143        ), "'activation_name' must be in ('relu', 'tanh', 'sigmoid','prelu', 'elu')"
144
145        assert nodes_sim in (
146            "sobol",
147            "hammersley",
148            "uniform",
149            "halton",
150        ), "'nodes_sim' must be in ('sobol', 'hammersley', 'uniform', 'halton')"
151
152        assert type_clust in (
153            "kmeans",
154            "gmm",
155        ), "'type_clust' must be in ('kmeans', 'gmm')"
156
157        assert (len(type_scaling) == 3) & all(
158            type_scaling[i] in ("minmax", "std", "robust", "maxabs")
159            for i in range(len(type_scaling))
160        ), "'type_scaling' must have length 3, and available scaling methods are 'minmax' scaling, standardization ('std'), robust scaling ('robust') and max absolute ('maxabs')"
161
162        assert (col_sample >= 0) & (
163            col_sample <= 1
164        ), "'col_sample' must be comprised between 0 and 1 (both included)"
165
166        assert backend in (
167            "cpu",
168            "gpu",
169            "tpu",
170        ), "must have 'backend' in ('cpu', 'gpu', 'tpu')"
171
172        self.n_hidden_features = n_hidden_features
173        self.activation_name = activation_name
174        self.a = a
175        self.nodes_sim = nodes_sim
176        self.bias = bias
177        self.seed = seed
178        self.backend = backend
179        self.dropout = dropout
180        self.direct_link = direct_link
181        self.cluster_encode = cluster_encode
182        self.type_clust = type_clust
183        self.type_scaling = type_scaling
184        self.col_sample = col_sample
185        self.row_sample = row_sample
186        self.n_clusters = n_clusters
187        if isinstance(self, RegressorMixin):
188            self.type_fit = "regression"
189        elif isinstance(self, ClassifierMixin):
190            self.type_fit = "classification"
191        self.subsampler_ = None
192        self.index_col_ = None
193        self.index_row_ = True
194        self.clustering_obj_ = None
195        self.clustering_scaler_ = None
196        self.nn_scaler_ = None
197        self.scaler_ = None
198        self.encoder_ = None
199        self.W_ = None
200        self.X_ = None
201        self.y_ = None
202        self.y_mean_ = None
203        self.beta_ = None
204
205        # activation function -----
206        if sys_platform in ("Linux", "Darwin"):
207            activation_options = {
208                "relu": ac.relu if (self.backend == "cpu") else jnn.relu,
209                "tanh": np.tanh if (self.backend == "cpu") else jnp.tanh,
210                "sigmoid": (ac.sigmoid if (self.backend == "cpu") else jnn.sigmoid),
211                "prelu": partial(ac.prelu, a=a),
212                "elu": (
213                    partial(ac.elu, a=a)
214                    if (self.backend == "cpu")
215                    else partial(jnn.elu, a=a)
216                ),
217            }
218        else:  # on Windows currently, no JAX
219            activation_options = {
220                "relu": (ac.relu if (self.backend == "cpu") else NotImplementedError),
221                "tanh": (np.tanh if (self.backend == "cpu") else NotImplementedError),
222                "sigmoid": (
223                    ac.sigmoid if (self.backend == "cpu") else NotImplementedError
224                ),
225                "prelu": partial(ac.prelu, a=a),
226                "elu": (
227                    partial(ac.elu, a=a)
228                    if (self.backend == "cpu")
229                    else NotImplementedError
230                ),
231            }
232        self.activation_func = activation_options[activation_name]
233
234    # "preprocessing" methods to be inherited -----
235
236    def encode_clusters(self, X=None, predict=False, scaler=None, **kwargs):  #
237        """Create new covariates with kmeans or GMM clustering
238
239        Parameters:
240
241            X: {array-like}, shape = [n_samples, n_features]
242                Training vectors, where n_samples is the number
243                of samples and n_features is the number of features.
244
245            predict: boolean
246                is False on training set and True on test set
247
248            scaler: {object} of class StandardScaler, MinMaxScaler, RobustScaler or MaxAbsScaler
249                if scaler has already been fitted on training data (online training), it can be passed here
250
251            **kwargs:
252                additional parameters to be passed to the
253                clustering method
254
255        Returns:
256
257            Clusters' matrix, one-hot encoded: {array-like}
258
259        """
260
261        np.random.seed(self.seed)
262
263        if X is None:
264            X = self.X_
265
266        if isinstance(X, pd.DataFrame):
267            X = copy.deepcopy(X.values.astype(float))
268
269        if len(X.shape) == 1:
270            X = X.reshape(1, -1)
271
272        if predict is False:  # encode training set
273
274            # scale input data before clustering
275            self.clustering_scaler_, scaled_X = mo.scale_covariates(
276                X, choice=self.type_scaling[2], scaler=self.clustering_scaler_
277            )
278
279            self.clustering_obj_, X_clustered = mo.cluster_covariates(
280                scaled_X,
281                self.n_clusters,
282                self.seed,
283                type_clust=self.type_clust,
284                **kwargs
285            )
286
287            if self.cluster_encode == True:
288                return mo.one_hot_encode(X_clustered, self.n_clusters).astype(
289                    np.float16
290                )
291
292            return X_clustered.astype(np.float16)
293
294        # if predict == True, encode test set
295        X_clustered = self.clustering_obj_.predict(self.clustering_scaler_.transform(X))
296
297        if self.cluster_encode == True:
298            return mo.one_hot_encode(X_clustered, self.n_clusters).astype(np.float16)
299
300        return X_clustered.astype(np.float16)
301
302    def create_layer(self, scaled_X, W=None):
303        """Create hidden layer.
304
305        Parameters:
306
307            scaled_X: {array-like}, shape = [n_samples, n_features]
308                Training vectors, where n_samples is the number
309                of samples and n_features is the number of features
310
311            W: {array-like}, shape = [n_features, hidden_features]
312                if provided, constructs the hidden layer with W; otherwise computed internally
313
314        Returns:
315
316            Hidden layer matrix: {array-like}
317
318        """
319
320        n_features = scaled_X.shape[1]
321
322        # hash_sim = {
323        #         "sobol": generate_sobol,
324        #         "hammersley": generate_hammersley,
325        #         "uniform": generate_uniform,
326        #         "halton": generate_halton
327        #     }
328
329        if self.bias is False:  # no bias term in the hidden layer
330            if W is None:
331                if self.nodes_sim == "sobol":
332                    self.W_ = generate_sobol(
333                        n_dims=n_features,
334                        n_points=self.n_hidden_features,
335                        seed=self.seed,
336                    )
337                elif self.nodes_sim == "hammersley":
338                    self.W_ = generate_hammersley(
339                        n_dims=n_features,
340                        n_points=self.n_hidden_features,
341                        seed=self.seed,
342                    )
343                elif self.nodes_sim == "uniform":
344                    self.W_ = generate_uniform(
345                        n_dims=n_features,
346                        n_points=self.n_hidden_features,
347                        seed=self.seed,
348                    )
349                else:
350                    self.W_ = generate_halton(
351                        n_dims=n_features,
352                        n_points=self.n_hidden_features,
353                        seed=self.seed,
354                    )
355
356                # self.W_ = hash_sim[self.nodes_sim](
357                #             n_dims=n_features,
358                #             n_points=self.n_hidden_features,
359                #             seed=self.seed,
360                #         )
361
362                assert (
363                    scaled_X.shape[1] == self.W_.shape[0]
364                ), "check dimensions of covariates X and matrix W"
365
366                return mo.dropout(
367                    x=self.activation_func(
368                        mo.safe_sparse_dot(a=scaled_X, b=self.W_, backend=self.backend)
369                    ),
370                    drop_prob=self.dropout,
371                    seed=self.seed,
372                )
373
374            # W is not none
375            assert (
376                scaled_X.shape[1] == W.shape[0]
377            ), "check dimensions of covariates X and matrix W"
378
379            # self.W_ = W
380            return mo.dropout(
381                x=self.activation_func(
382                    mo.safe_sparse_dot(a=scaled_X, b=W, backend=self.backend)
383                ),
384                drop_prob=self.dropout,
385                seed=self.seed,
386            )
387
388        # with bias term in the hidden layer
389        if W is None:
390            n_features_1 = n_features + 1
391
392            if self.nodes_sim == "sobol":
393                self.W_ = generate_sobol(
394                    n_dims=n_features_1,
395                    n_points=self.n_hidden_features,
396                    seed=self.seed,
397                )
398            elif self.nodes_sim == "hammersley":
399                self.W_ = generate_hammersley(
400                    n_dims=n_features_1,
401                    n_points=self.n_hidden_features,
402                    seed=self.seed,
403                )
404            elif self.nodes_sim == "uniform":
405                self.W_ = generate_uniform(
406                    n_dims=n_features_1,
407                    n_points=self.n_hidden_features,
408                    seed=self.seed,
409                )
410            else:
411                self.W_ = generate_halton(
412                    n_dims=n_features_1,
413                    n_points=self.n_hidden_features,
414                    seed=self.seed,
415                )
416
417            # self.W_ = hash_sim[self.nodes_sim](
418            #         n_dims=n_features_1,
419            #         n_points=self.n_hidden_features,
420            #         seed=self.seed,
421            #     )
422
423            return mo.dropout(
424                x=self.activation_func(
425                    mo.safe_sparse_dot(
426                        a=mo.cbind(
427                            np.ones(scaled_X.shape[0]),
428                            scaled_X,
429                            backend=self.backend,
430                        ),
431                        b=self.W_,
432                        backend=self.backend,
433                    )
434                ),
435                drop_prob=self.dropout,
436                seed=self.seed,
437            )
438
439        # W is not None
440        # self.W_ = W
441        return mo.dropout(
442            x=self.activation_func(
443                mo.safe_sparse_dot(
444                    a=mo.cbind(
445                        np.ones(scaled_X.shape[0]),
446                        scaled_X,
447                        backend=self.backend,
448                    ),
449                    b=W,
450                    backend=self.backend,
451                )
452            ),
453            drop_prob=self.dropout,
454            seed=self.seed,
455        )
456
457    def cook_training_set(self, y=None, X=None, W=None, **kwargs):
458        """Create new hidden features for training set, with hidden layer, center the response.
459
460        Parameters:
461
462            y: array-like, shape = [n_samples]
463                Target values
464
465            X: {array-like}, shape = [n_samples, n_features]
466                Training vectors, where n_samples is the number
467                of samples and n_features is the number of features
468
469            W: {array-like}, shape = [n_features, hidden_features]
470                if provided, constructs the hidden layer via W
471
472        Returns:
473
474            (centered response, direct link + hidden layer matrix): {tuple}
475
476        """
477
478        # either X and y are stored or not
479        # assert ((y is None) & (X is None)) | ((y is not None) & (X is not None))
480        if self.n_hidden_features > 0:  # has a hidden layer
481            assert (
482                len(self.type_scaling) >= 2
483            ), "must have len(self.type_scaling) >= 2 when self.n_hidden_features > 0"
484
485        if X is None:
486
487            if self.col_sample == 1:
488                input_X = self.X_
489            else:
490                n_features = self.X_.shape[1]
491                new_n_features = int(np.ceil(n_features * self.col_sample))
492                assert (
493                    new_n_features >= 1
494                ), "check class attribute 'col_sample' and the number of covariates provided for X"
495                np.random.seed(self.seed)
496                index_col = np.random.choice(
497                    range(n_features), size=new_n_features, replace=False
498                )
499                self.index_col_ = index_col
500                input_X = self.X_[:, self.index_col_]
501
502        else:  # X is not None # keep X vs self.X_
503
504            if isinstance(X, pd.DataFrame):
505                X = copy.deepcopy(X.values.astype(float))
506
507            if self.col_sample == 1:
508                input_X = X
509            else:
510                n_features = X.shape[1]
511                new_n_features = int(np.ceil(n_features * self.col_sample))
512                assert (
513                    new_n_features >= 1
514                ), "check class attribute 'col_sample' and the number of covariates provided for X"
515                np.random.seed(self.seed)
516                index_col = np.random.choice(
517                    range(n_features), size=new_n_features, replace=False
518                )
519                self.index_col_ = index_col
520                input_X = X[:, self.index_col_]
521
522        if self.n_clusters <= 0:
523            # data without any clustering: self.n_clusters is None -----
524
525            if self.n_hidden_features > 0:  # with hidden layer
526
527                self.nn_scaler_, scaled_X = mo.scale_covariates(
528                    input_X, choice=self.type_scaling[1], scaler=self.nn_scaler_
529                )
530                Phi_X = (
531                    self.create_layer(scaled_X)
532                    if W is None
533                    else self.create_layer(scaled_X, W=W)
534                )
535                Z = (
536                    mo.cbind(input_X, Phi_X, backend=self.backend)
537                    if self.direct_link is True
538                    else Phi_X
539                )
540                self.scaler_, scaled_Z = mo.scale_covariates(
541                    Z, choice=self.type_scaling[0], scaler=self.scaler_
542                )
543            else:  # no hidden layer
544                Z = input_X
545                self.scaler_, scaled_Z = mo.scale_covariates(
546                    Z, choice=self.type_scaling[0], scaler=self.scaler_
547                )
548
549        else:
550
551            # data with clustering: self.n_clusters is not None ----- # keep
552
553            augmented_X = mo.cbind(
554                input_X,
555                self.encode_clusters(input_X, **kwargs),
556                backend=self.backend,
557            )
558
559            if self.n_hidden_features > 0:  # with hidden layer
560
561                self.nn_scaler_, scaled_X = mo.scale_covariates(
562                    augmented_X,
563                    choice=self.type_scaling[1],
564                    scaler=self.nn_scaler_,
565                )
566                Phi_X = (
567                    self.create_layer(scaled_X)
568                    if W is None
569                    else self.create_layer(scaled_X, W=W)
570                )
571                Z = (
572                    mo.cbind(augmented_X, Phi_X, backend=self.backend)
573                    if self.direct_link is True
574                    else Phi_X
575                )
576                self.scaler_, scaled_Z = mo.scale_covariates(
577                    Z, choice=self.type_scaling[0], scaler=self.scaler_
578                )
579            else:  # no hidden layer
580                Z = augmented_X
581                self.scaler_, scaled_Z = mo.scale_covariates(
582                    Z, choice=self.type_scaling[0], scaler=self.scaler_
583                )
584
585        # Returning model inputs -----
586        if mx.is_factor(y) is False:  # regression
587            # center y
588            if y is None:
589                self.y_mean_, centered_y = mo.center_response(self.y_)
590            else:
591                self.y_mean_, centered_y = mo.center_response(y)
592
593            # y is subsampled
594            if self.row_sample < 1:
595                n, p = Z.shape
596
597                self.subsampler_ = (
598                    SubSampler(y=self.y_, row_sample=self.row_sample, seed=self.seed)
599                    if y is None
600                    else SubSampler(y=y, row_sample=self.row_sample, seed=self.seed)
601                )
602
603                self.index_row_ = self.subsampler_.subsample()
604
605                n_row_sample = len(self.index_row_)
606                # regression
607                return (
608                    centered_y[self.index_row_].reshape(n_row_sample),
609                    self.scaler_.transform(
610                        Z[self.index_row_, :].reshape(n_row_sample, p)
611                    ),
612                )
613            # y is not subsampled
614            # regression
615            return (centered_y, self.scaler_.transform(Z))
616
617        # classification
618        # y is subsampled
619        if self.row_sample < 1:
620            n, p = Z.shape
621
622            self.subsampler_ = (
623                SubSampler(y=self.y_, row_sample=self.row_sample, seed=self.seed)
624                if y is None
625                else SubSampler(y=y, row_sample=self.row_sample, seed=self.seed)
626            )
627
628            self.index_row_ = self.subsampler_.subsample()
629
630            n_row_sample = len(self.index_row_)
631            # classification
632            return (
633                y[self.index_row_].reshape(n_row_sample),
634                self.scaler_.transform(Z[self.index_row_, :].reshape(n_row_sample, p)),
635            )
636        # y is not subsampled
637        # classification
638        return (y, self.scaler_.transform(Z))
639
640    def cook_test_set(self, X, **kwargs):
641        """Transform data from test set, with hidden layer.
642
643        Parameters:
644
645            X: {array-like}, shape = [n_samples, n_features]
646                Training vectors, where n_samples is the number
647                of samples and n_features is the number of features
648
649            **kwargs: additional parameters to be passed to self.encode_cluster
650
651        Returns:
652
653            Transformed test set : {array-like}
654        """
655
656        if isinstance(X, pd.DataFrame):
657            X = copy.deepcopy(X.values.astype(float))
658
659        if len(X.shape) == 1:
660            X = X.reshape(1, -1)
661
662        if (
663            self.n_clusters == 0
664        ):  # data without clustering: self.n_clusters is None -----
665            if self.n_hidden_features > 0:
666                # if hidden layer
667                scaled_X = (
668                    self.nn_scaler_.transform(X)
669                    if (self.col_sample == 1)
670                    else self.nn_scaler_.transform(X[:, self.index_col_])
671                )
672                Phi_X = self.create_layer(scaled_X, self.W_)
673                if self.direct_link == True:
674                    return self.scaler_.transform(
675                        mo.cbind(scaled_X, Phi_X, backend=self.backend)
676                    )
677                # when self.direct_link == False
678                return self.scaler_.transform(Phi_X)
679            # if no hidden layer # self.n_hidden_features == 0
680            return self.scaler_.transform(X)
681
682        # data with clustering: self.n_clusters > 0 -----
683        if self.col_sample == 1:
684            predicted_clusters = self.encode_clusters(X=X, predict=True, **kwargs)
685            augmented_X = mo.cbind(X, predicted_clusters, backend=self.backend)
686        else:
687            predicted_clusters = self.encode_clusters(
688                X=X[:, self.index_col_], predict=True, **kwargs
689            )
690            augmented_X = mo.cbind(
691                X[:, self.index_col_], predicted_clusters, backend=self.backend
692            )
693
694        if self.n_hidden_features > 0:  # if hidden layer
695            scaled_X = self.nn_scaler_.transform(augmented_X)
696            Phi_X = self.create_layer(scaled_X, self.W_)
697            if self.direct_link == True:
698                return self.scaler_.transform(
699                    mo.cbind(augmented_X, Phi_X, backend=self.backend)
700                )
701            return self.scaler_.transform(Phi_X)
702
703        # if no hidden layer
704        return self.scaler_.transform(augmented_X)
705
706    def cross_val_score(
707        self,
708        X,
709        y,
710        cv=5,
711        scoring="accuracy",
712        random_state=42,
713        n_jobs=-1,
714        epsilon=0.5,
715        penalized=True,
716        objective="abs",
717        **kwargs
718    ):
719        """
720        Penalized Cross-validation score for a model.
721
722        Parameters:
723
724            X: {array-like}, shape = [n_samples, n_features]
725                Training vectors, where n_samples is the number
726                of samples and n_features is the number of features
727
728            y: array-like, shape = [n_samples]
729                Target values
730
731            X_test: {array-like}, shape = [n_samples, n_features]
732                Test vectors, where n_samples is the number
733                of samples and n_features is the number of features
734
735            y_test: array-like, shape = [n_samples]
736                Target values
737
738            cv: int
739                Number of folds
740
741            scoring: str
742                Scoring metric
743
744            random_state: int
745                Random state
746
747            n_jobs: int
748                Number of jobs to run in parallel
749
750            epsilon: float
751                Penalty parameter
752
753            penalized: bool
754                Whether to obtain penalized cross-validation score or not
755
756            objective: str
757                'abs': Minimize the absolute difference between cross-validation score and validation score
758                'relative': Minimize the relative difference between cross-validation score and validation score
759        Returns:
760
761            A namedtuple with the following fields:
762                - cv_score: float
763                    cross-validation score
764                - val_score: float
765                    validation score
766                - penalized_score: float
767                    penalized cross-validation score: cv_score / val_score + epsilon*(1/val_score + 1/cv_score)
768                    If higher scoring metric is better, minimize the function result.
769                    If lower scoring metric is better, maximize the function result.
770        """
771        if scoring == "accuracy":
772            scoring_func = accuracy_score
773        elif scoring == "balanced_accuracy":
774            scoring_func = balanced_accuracy_score
775        elif scoring == "f1":
776            scoring_func = f1_score
777        elif scoring == "roc_auc":
778            scoring_func = roc_auc_score
779        elif scoring == "r2":
780            scoring_func = r2_score
781        elif scoring == "mse":
782            scoring_func = mean_squared_error
783        elif scoring == "mae":
784            scoring_func = mean_absolute_error
785        elif scoring == "mape":
786            scoring_func = mean_absolute_percentage_error
787        elif scoring == "rmse":
788
789            def scoring_func(y_true, y_pred):
790                return np.sqrt(mean_squared_error(y_true, y_pred))
791
792        X_train, X_val, y_train, y_val = train_test_split(
793            X, y, test_size=0.2, random_state=random_state
794        )
795
796        res = cross_val_score(
797            self, X_train, y_train, cv=cv, scoring=scoring, n_jobs=n_jobs
798        )  # cross-validation error
799
800        if penalized == False:
801            return res
802
803        DescribeResult = namedtuple(
804            "DescribeResult", ["cv_score", "val_score", "penalized_score"]
805        )
806
807        numerator = res.mean()
808
809        # Evaluate on the (cv+1)-th fold
810        preds_val = self.fit(X_train, y_train).predict(X_val)
811        try:
812            denominator = scoring(y_val, preds_val)  # validation error
813        except Exception as e:
814            denominator = scoring_func(y_val, preds_val)
815
816        # if higher is better
817        if objective == "abs":
818            penalized_score = np.abs(numerator - denominator) + epsilon * (
819                1 / denominator + 1 / numerator
820            )
821        elif objective == "relative":
822            ratio = numerator / denominator
823            penalized_score = np.abs(ratio - 1) + epsilon * (
824                1 / denominator + 1 / numerator
825            )
826
827        return DescribeResult(
828            cv_score=numerator,
829            val_score=denominator,
830            penalized_score=penalized_score,
831        )