Eligijus112

import numpy as np


class Embeddings():
    """
    A class to read the word embedding file and to create the word embedding matrix
    """

    def __init__(self, path, vector_dimension):
        self.path = path 

Eligijus112

mport numpy as np
from keras.preprocessing.sequence import pad_sequences
     

class TextToTensor():

    def __init__(self, tokenizer, max_len):
        self.tokenizer = tokenizer
        self.max_len = max_len

Eligijus112

# Deep learning: 
from keras.models import Input, Model
from keras.layers import LSTM, Dense, Embedding, concatenate, Dropout, concatenate
from keras.layers import Bidirectional

class RnnModel():
    """
    A recurrent neural network for semantic analysis
    """

Eligijus112

import numpy as np

# The main model class
from RNN_model import RnnModel

# Importing the word preprocesing class
from text_preprocessing import TextToTensor, clean_text

# Importing the word embedding class
from embeddings import Embeddings

Eligijus112

# Importing the packages
import tensorflow as tf

# Downloading data
# The default split is 60k images in the training set and 10k in the test set
mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()

# Normalizing the pixel values
training_images  = training_images / 255.0

Eligijus112

import tensorflow as tf

# Initiating the class
mnist = tf.keras.datasets.fashion_mnist

# Downloading the data
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()

# Reshaping the images for the convolutional input
training_images=training_images.reshape(60000, 28, 28, 1)

Eligijus112

# Extracting the trained layers from the model 
successive_outputs = [layer.output for layer in model.layers[1:]]
visualization_model = tf.keras.models.Model(inputs = model.input, outputs = successive_outputs)

# Getting an image from the training set
image = training_images[1]

# Intermediate representations for this image
successive_feature_maps = visualization_model.predict(image.reshape(1, 28, 28, 1))

Eligijus112

import cv2
import numpy as np
from scipy import misc
import matplotlib.pyplot as plt

# Getting the image of ascent
i = misc.ascent()

# Ploting the original image
plt.grid(False)

Eligijus112

def create_X_Y(ts: np.array, lag=1, n_ahead=1, target_index=0) -> tuple:
    """
    A method to create X and Y matrix from a time series array for the training of 
    deep learning models 
    """
    # Extracting the number of features that are passed from the array 
    n_features = ts.shape[1]
    
    # Creating placeholder lists
    X, Y = [], []

Eligijus112

class NNMultistepModel():
    
    def __init__(
        self, 
        X, 
        Y, 
        n_outputs,
        n_lag,
        n_ft,
        n_layer,