import tensorflow as tf
from tensorflow.python.ops import array_ops
from keras import backend as K

def multi_category_focal_loss2(gamma=2., alpha=1):
    epsilon = 1.e-7
    gamma = float(gamma)
    alpha = tf.constant(alpha, dtype=tf.float32)

    def multi_category_focal_loss2_fixed(y_true, y_pred):
        y_true = tf.cast(y_true, tf.float32)
        y_pred = tf.clip_by_value(y_pred, epsilon, 1. - epsilon)

        alpha_t = y_true * alpha + (tf.ones_like(y_true) - y_true) * (1 - alpha)
        y_t = tf.multiply(y_true, y_pred) + tf.multiply(1 - y_true, 1 - y_pred)
        ce = -tf.log(y_t)
        weight = tf.pow(tf.subtract(1., y_t), gamma)
        fl = tf.multiply(tf.multiply(weight, ce), alpha_t)
        loss = tf.reduce_mean(fl)
        return loss

    return multi_category_focal_loss2_fixed

def multi_category_focal_loss1(alpha, gamma=2.0):
    epsilon = 1.e-7
    alpha = tf.constant(alpha, dtype=tf.float32)
    gamma = float(gamma)
    def multi_category_focal_loss1_fixed(y_true, y_pred):
        y_true = tf.cast(y_true, tf.float32)
        y_pred = tf.clip_by_value(y_pred, epsilon, 1. - epsilon)
        y_t = tf.multiply(y_true, y_pred) + tf.multiply(1-y_true, 1-y_pred)
        ce = -tf.log(y_t)
        weight = tf.pow(tf.subtract(1., y_t), gamma)
        fl = tf.matmul(tf.multiply(weight, ce), alpha)
        loss = tf.reduce_mean(fl)
        return loss
    return multi_category_focal_loss1_fixed


def Cross_entropy_loss(y_true, y_pred):
    y_pred = K.clip(y_pred, K.epsilon(), 1.0 - K.epsilon())
    crossEntropyLoss = -y_true * tf.log(y_pred)

    return tf.reduce_sum(crossEntropyLoss, -1)

def focal_loss(classes_num, gamma=2., alpha=.25, e=0.1):
    def focal_loss_fixed(target_tensor, prediction_tensor):
        zeros = array_ops.zeros_like(prediction_tensor, dtype=prediction_tensor.dtype)
        one_minus_p = array_ops.where(tf.greater(target_tensor,zeros), target_tensor - prediction_tensor, zeros)
        FT = -1 * (one_minus_p ** gamma) * tf.log(tf.clip_by_value(prediction_tensor, 1e-8, 1.0))

        classes_weight = array_ops.zeros_like(prediction_tensor, dtype=prediction_tensor.dtype)

        total_num = float(sum(classes_num))
        classes_w_t1 = [ total_num / ff for ff in classes_num ]
        sum_ = sum(classes_w_t1)
        classes_w_t2 = [ ff/sum_ for ff in classes_w_t1 ]   #scale
        classes_w_tensor = tf.convert_to_tensor(classes_w_t2, dtype=prediction_tensor.dtype)
        classes_weight += classes_w_tensor

        alpha = array_ops.where(tf.greater(target_tensor, zeros), classes_weight, zeros)

        balanced_fl = alpha * FT
        balanced_fl = tf.reduce_mean(balanced_fl)

        nb_classes = len(classes_num)
        fianal_loss = (1-e) * balanced_fl + e * K.categorical_crossentropy(K.ones_like(prediction_tensor)/nb_classes, prediction_tensor)

        return fianal_loss
    return focal_loss_fixed