ashunigion

def get_target(words, idx, window_size=5):
    ''' Get a list of words in a window around an index. 
        words -- list of words in text
        idx -- index of the center word
        window_size -- the window size to define context
    '''
    
    # implement this function
    R = np.random.randint(1, window_size+1)
    start = idx - R if (idx - R) > 0 else 0

ashunigion

# we create a list of the indices of words in vocabulary as the input to network
training_reviews = []
for review in training_reviews_raw:
    indices = set()
    for word in review.split(" "):
        if word in word2index.keys():
            indices.add(self.word2index[word])
    training_reviews.append(list(indices))
# forward pass for each data point in the batch(index i)
self.layer_1 *= 0

ashunigion

for word in review.split(' '):
    if word in self.word2index.keys():
        self.layer_0[0,self.word2index[word]] = 1 # changed "+= 1" to "= 1"

ashunigion

[('.', 27),    # noise with a large weight
 ('', 18),     # noise...
 ('the', 9),
 ('to', 6),
 ('high', 5),
 ('i', 5),
 ('bromwell', 4),
 ('is', 4),
 ('a', 4),
 ('teachers', 4),

ashunigion

# forward-pass
h_1 = np.dot(self.layer_0,self.weights_0_1)
output = self.sigmoid(np.dot(h_1,self.weights_1_2))
# back propagation  
output_error = label - output
output_error_term = output_error*output*(1-output)
        
hidden_error = np.dot(output_error_term,(self.weights_1_2).T)
hidden_error_term = hidden_error
#weight update           

ashunigion

# sentences (list of list of str): A list of sentences to be parsed
# model (ParserModel): The model that makes parsing decisions. It is assumed to have a function
#                      model.predict(partial_parses) that takes in a list of PartialParses as input and
#                              returns a list of transitions predicted for each parse. 
# batch_size (int): The number of PartialParses to include in each minibatch
# dependencies (list of dependency lists): A list where each element is the dependencies
#                                          list for a parsed sentence.
partial_parsers = []
for sentence in sentences:
    partial_parsers.append(PartialParse(sentence))

ashunigion

 # sentence :The sentence to be parsed as a list of words.
 self.stack = ["ROOT"] # corresponds to first column in above image 
 self.buffer = (self.sentence).copy() # corresponds to second column in above image
 self.dependencies = [] # corresponds to the third column in above image
 
 # transition (str): A string that equals "S", "LA", or "RA" representing the shift,
 #                   left-arc, and right-arc transitions. You can assume the provided
 #                   transition is a legal transition.
 #                   corresponds to the last column in above image
 if transition == "S":

ashunigion

def get_target_for_label(label):
    """Convert a label to `0` or `1`.
    Args:
        label(string) - Either "POSITIVE" or "NEGATIVE".
    Returns:
        `0` or `1`.
    """
    if label == "POSITIVE":
        return 1
    else:

ashunigion

def update_input_layer(review):
    """ Modify the global layer_0 to represent the vector form of review.
    The element at a given index of layer_0 should represent
    how many times the given word occurs in the review.
    Args:
        review(string) - the string of the review
    Returns:
        None
    """
    global layer_0

ashunigion

# Create a dictionary of words in the vocabulary mapped to index positions
# (to be used in layer_0)
word2index = {}
for i,word in enumerate(vocab):
    word2index[word] = i