#!/usr/bin/env python
#
# file: $ISIP_EXP/tuh_dpath/exp_0074/scripts/model.py
#
# revision history:
#  20190925 (TE): first version
#
# usage:
#
# This script hold the model architecture
#------------------------------------------------------------------------------

# import tensorflow modules
#
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras import Sequential
from tensorflow.keras.initializers import GlorotUniform

# import modules
#
import os
import random
import numpy as np

# define global values
#
SEED = 1337
DEF_NUM_FEATS = 2
NUM_NODES = 26
NUM_CLASSES = 2
NEW_LINE = "\n"

#-----------------------------------------------------------------------------
#
# helper functions are listed here
#
#-----------------------------------------------------------------------------

# function: set_seed
#
# arguments: seed - the seed for all the rng
#
# returns: none
#
# this method seeds all the random number generators and makes
# the results deterministic
#
def set_seed(seed):
    random.seed(seed)
    os.environ['PYTHONHASHSEED'] = str(seed)
    tf.random.set_seed(seed)
    np.random.seed(seed)
#
# end of method


# function: get_data
#
# arguments: fp - file pointer
#            num_feats - the number of features in a sample
#
# returns: data - the signals/features
#          labels - the correct labels for them
#
# this method takes in a fp and returns the data and labels
#
def get_data(fp, num_feats):

    # initialize the data and labels
    #
    data = []
    labels = []

    # for each line of the file
    #
    for line in fp.read().split(NEW_LINE):

        # split the string by white space
        #
        temp = line.split()

        # if we dont have feats + 1 label
        #
        if not (len(temp) > 1):
            continue

        # append the labels and data
        #
        labels.append(int(temp[0]))
        data.append([float(sample) for sample in temp[1:]])

    # exit gracefully
    #
    return data, labels
#
# end of function


#------------------------------------------------------------------------------
#
# the model is defined here
#
#------------------------------------------------------------------------------


# function: Model
#
# arguments: input_size - int representing size of input
#            hidden_size - number of nodes in the hidden layer
#            num_classes - number of classes to classify
#            seed - the number to seed the layers' random weights
#
# return: model - the entire MLP model
#
# This method returns an MLP model
#
def Model(input_size, hidden_size, num_classes, seed):

    # define the model
    #
    model = Sequential()    
    model.add(layers.Dense(hidden_size, activation='relu',
        input_shape=(input_size, ), kernel_initializer=GlorotUniform(seed=seed)))
    model.add(layers.Dense(num_classes, activation='softmax',
        input_shape=(hidden_size,), kernel_initializer=GlorotUniform(seed=seed)))

    # exit gracefully
    #
    return model
#
# end of function

#
# end of file