# -*- coding: utf-8 -*-
"""Using Auto Encoder with Outlier Detection
"""
# Author: Yue Zhao <zhaoy@cmu.edu>
# License: BSD 2 clause

from __future__ import division
from __future__ import print_function

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.regularizers import l2
from keras.losses import mean_squared_error
from sklearn.preprocessing import StandardScaler
from sklearn.utils import check_array
from sklearn.utils.validation import check_is_fitted

from ..utils.utility import check_parameter
from ..utils.stat_models import pairwise_distances_no_broadcast

from .base import BaseDetector


# noinspection PyUnresolvedReferences,PyPep8Naming,PyTypeChecker
class AutoEncoder(BaseDetector):
    """Auto Encoder (AE) is a type of neural networks for learning useful data
    representations unsupervisedly. Similar to PCA, AE could be used to
    detect outlying objects in the data by calculating the reconstruction
    errors. See :cite:`aggarwal2015outlier` Chapter 3 for details.

    Parameters
    ----------
    hidden_neurons : list, optional (default=[64, 32, 32, 64])
        The number of neurons per hidden layers.

    hidden_activation : str, optional (default='relu')
        Activation function to use for hidden layers.
        All hidden layers are forced to use the same type of activation.
        See https://keras.io/activations/

    output_activation : str, optional (default='sigmoid')
        Activation function to use for output layer.
        See https://keras.io/activations/

    loss : str or obj, optional (default=keras.losses.mean_squared_error)
        String (name of objective function) or objective function.
        See https://keras.io/losses/

    optimizer : str, optional (default='adam')
        String (name of optimizer) or optimizer instance.
        See https://keras.io/optimizers/

    epochs : int, optional (default=100)
        Number of epochs to train the model.

    batch_size : int, optional (default=32)
        Number of samples per gradient update.

    dropout_rate : float in (0., 1), optional (default=0.2)
        The dropout to be used across all layers.

    l2_regularizer : float in (0., 1), optional (default=0.1)
        The regularization strength of activity_regularizer
        applied on each layer. By default, l2 regularizer is used. See
        https://keras.io/regularizers/

    validation_size : float in (0., 1), optional (default=0.1)
        The percentage of data to be used for validation.

    preprocessing : bool, optional (default=True)
        If True, apply standardization on the data.

    verbose : int, optional (default=1)
        Verbosity mode.

        - 0 = silent
        - 1 = progress bar
        - 2 = one line per epoch.

        For verbosity >= 1, model summary may be printed.

    random_state : random_state: int, RandomState instance or None, optional
        (default=None)
        If int, random_state is the seed used by the random
        number generator; If RandomState instance, random_state is the random
        number generator; If None, the random number generator is the
        RandomState instance used by `np.random`.

    contamination : float in (0., 0.5), optional (default=0.1)
        The amount of contamination of the data set, i.e.
        the proportion of outliers in the data set. When fitting this is used
        to define the threshold on the decision function.

    Attributes
    ----------
    encoding_dim_ : int
        The number of neurons in the encoding layer.

    compression_rate_ : float
        The ratio between the original feature and
        the number of neurons in the encoding layer.

    model_ : Keras Object
        The underlying AutoEncoder in Keras.

    history_: Keras Object
        The AutoEncoder training history.

    decision_scores_ : numpy array of shape (n_samples,)
        The outlier scores of the training data.
        The higher, the more abnormal. Outliers tend to have higher
        scores. This value is available once the detector is
        fitted.

    threshold_ : float
        The threshold is based on ``contamination``. It is the
        ``n_samples * contamination`` most abnormal samples in
        ``decision_scores_``. The threshold is calculated for generating
        binary outlier labels.

    labels_ : int, either 0 or 1
        The binary labels of the training data. 0 stands for inliers
        and 1 for outliers/anomalies. It is generated by applying
        ``threshold_`` on ``decision_scores_``.
    """

    def __init__(self, hidden_neurons=None,
                 hidden_activation='relu', output_activation='sigmoid',
                 loss=mean_squared_error, optimizer='adam',
                 epochs=100, batch_size=32, dropout_rate=0.2,
                 l2_regularizer=0.1, validation_size=0.1, preprocessing=True,
                 verbose=1, random_state=None, contamination=0.1):
        super(AutoEncoder, self).__init__(contamination=contamination)
        self.hidden_neurons = hidden_neurons
        self.hidden_activation = hidden_activation
        self.output_activation = output_activation
        self.loss = loss
        self.optimizer = optimizer
        self.epochs = epochs
        self.batch_size = batch_size
        self.dropout_rate = dropout_rate
        self.l2_regularizer = l2_regularizer
        self.validation_size = validation_size
        self.preprocessing = preprocessing
        self.verbose = verbose
        self.random_state = random_state

        # default values
        if self.hidden_neurons is None:
            self.hidden_neurons = [64, 32, 32, 64]

        # Verify the network design is valid
        if not self.hidden_neurons == self.hidden_neurons[::-1]:
            print(self.hidden_neurons)
            raise ValueError("Hidden units should be symmetric")

        self.hidden_neurons_ = self.hidden_neurons

        check_parameter(dropout_rate, 0, 1, param_name='dropout_rate',
                        include_left=True)

    def _build_model(self):
        model = Sequential()
        # Input layer
        model.add(Dense(
            self.hidden_neurons_[0], activation=self.hidden_activation,
            input_shape=(self.n_features_,),
            activity_regularizer=l2(self.l2_regularizer)))
        model.add(Dropout(self.dropout_rate))

        # Additional layers
        for i, hidden_neurons in enumerate(self.hidden_neurons_, 1):
            model.add(Dense(
                hidden_neurons,
                activation=self.hidden_activation,
                activity_regularizer=l2(self.l2_regularizer)))
            model.add(Dropout(self.dropout_rate))

        # Output layers
        model.add(Dense(self.n_features_, activation=self.output_activation,
                        activity_regularizer=l2(self.l2_regularizer)))

        # Compile model
        model.compile(loss=self.loss, optimizer=self.optimizer)
        if self.verbose >= 1:
            print(model.summary())
        return model

    # noinspection PyUnresolvedReferences
    def fit(self, X, y=None):
        """Fit detector. y is ignored in unsupervised methods.

        Parameters
        ----------
        X : numpy array of shape (n_samples, n_features)
            The input samples.

        y : Ignored
            Not used, present for API consistency by convention.

        Returns
        -------
        self : object
            Fitted estimator.
        """
        # validate inputs X and y (optional)
        X = check_array(X)
        self._set_n_classes(y)

        # Verify and construct the hidden units
        self.n_samples_, self.n_features_ = X.shape[0], X.shape[1]

        # Standardize data for better performance
        if self.preprocessing:
            self.scaler_ = StandardScaler()
            X_norm = self.scaler_.fit_transform(X)
        else:
            X_norm = np.copy(X)

        # Shuffle the data for validation as Keras do not shuffling for
        # Validation Split
        np.random.shuffle(X_norm)

        # Validate and complete the number of hidden neurons
        if np.min(self.hidden_neurons) > self.n_features_:
            raise ValueError("The number of neurons should not exceed "
                             "the number of features")
        self.hidden_neurons_.insert(0, self.n_features_)

        # Calculate the dimension of the encoding layer & compression rate
        self.encoding_dim_ = np.median(self.hidden_neurons)
        self.compression_rate_ = self.n_features_ // self.encoding_dim_

        # Build AE model & fit with X
        self.model_ = self._build_model()
        self.history_ = self.model_.fit(X_norm, X_norm,
                                        epochs=self.epochs,
                                        batch_size=self.batch_size,
                                        shuffle=True,
                                        validation_split=self.validation_size,
                                        verbose=self.verbose).history
        # Reverse the operation for consistency
        self.hidden_neurons_.pop(0)
        # Predict on X itself and calculate the reconstruction error as
        # the outlier scores. Noted X_norm was shuffled has to recreate
        if self.preprocessing:
            X_norm = self.scaler_.transform(X)
        else:
            X_norm = np.copy(X)

        pred_scores = self.model_.predict(X_norm)
        self.decision_scores_ = pairwise_distances_no_broadcast(X_norm,
                                                                pred_scores)
        self._process_decision_scores()
        return self

    def decision_function(self, X):
        """Predict raw anomaly score of X using the fitted detector.

        The anomaly score of an input sample is computed based on different
        detector algorithms. For consistency, outliers are assigned with
        larger anomaly scores.

        Parameters
        ----------
        X : numpy array of shape (n_samples, n_features)
            The training input samples. Sparse matrices are accepted only
            if they are supported by the base estimator.

        Returns
        -------
        anomaly_scores : numpy array of shape (n_samples,)
            The anomaly score of the input samples.
        """
        check_is_fitted(self, ['model_', 'history_'])
        X = check_array(X)

        if self.preprocessing:
            X_norm = self.scaler_.transform(X)
        else:
            X_norm = np.copy(X)

        # Predict on X and return the reconstruction errors
        pred_scores = self.model_.predict(X_norm)
        return pairwise_distances_no_broadcast(X_norm, pred_scores)