DerekChia

aaa
aarp
abb
abbott
abogado
ac
academy
accenture
accountant
accountants

DerekChia

### Locating UI elements ###

# By ID
<div id="coolestWidgetEvah">...</div>
element = driver.find_element_by_id("coolestWidgetEvah")
or
from selenium.webdriver.common.by import By
element = driver.find_element(by=By.ID, value="coolestWidgetEvah")

# By class name:

DerekChia

text = "natural language processing and machine learning is fun and exciting"

# Note the .lower() as upper and lowercase does not matter in our implementation
# [['natural', 'language', 'processing', 'and', 'machine', 'learning', 'is', 'fun', 'and', 'exciting']]
corpus = [[word.lower() for word in text.split()]]

DerekChia

# Initialise object
w2v = word2vec()
# Numpy ndarray with one-hot representation for [target_word, context_words]
training_data = w2v.generate_training_data(settings, corpus)

DerekChia

class word2vec():
  def __init__(self):
    self.n = settings['n']
    self.lr = settings['learning_rate']
    self.epochs = settings['epochs']
    self.window = settings['window_size']

  def generate_training_data(self, settings, corpus):
    # Find unique word counts using dictonary
    word_counts = defaultdict(int)

DerekChia

# Training
w2v.train(training_data)

class word2vec():
  def train(self, training_data):
  # Initialising weight matrices
  # Both s1 and s2 should be randomly initialised but for this demo, we pre-determine the arrays (getW1 and getW2)
  # getW1 - shape (9x10) and getW2 - shape (10x9)
  self.w1 = np.array(getW1)
  self.w2 = np.array(getW2)

DerekChia

# Training
w2v.train(training_data)

class word2vec():
  def train(self, training_data):
    # Initialising weight matrices
    # Both s1 and s2 should be randomly initialised but for this demo, we pre-determine the arrays (getW1 and getW2)
    # getW1 - shape (9x10) and getW2 - shape (10x9)
    self.w1 = np.array(getW1)
    self.w2 = np.array(getW2)

DerekChia

class word2vec():
  ##Removed##
  
  for i in range(self.epochs):
    self.loss = 0
    for w_t, w_c in training_data:
    ##Removed##
      
      # Calculate error
      # 1. For a target word, calculate difference between y_pred and each of the context words

DerekChia

# Get vector for word
vec = w2v.word_vec("machine")

class word2vec():
  ## Removed ##
  
  # Get vector from word
  def word_vec(self, word):
    w_index = self.word_index[word]
    v_w = self.w1[w_index]

DerekChia

# Find similar words
w2v.vec_sim("machine", 3)

class word2vec():
  ## Removed##
  
  # Input vector, returns nearest word(s)
  def vec_sim(self, word, top_n):
    v_w1 = self.word_vec(word)
    word_sim = {}