eileen-code4fun

from dgl.nn.tensorflow import GATConv

class GAT(tf.keras.Model):
    def __init__(self, feat_dim, hidden_dim, class_num):
        super(GAT, self).__init__()
        self.num_heads = 8
        self.h1 = GATConv(in_feats=feat_dim, out_feats=hidden_dim, feat_drop=0.5, num_heads=self.num_heads, allow_zero_in_degree=True)
        self.h2 = GATConv(in_feats=hidden_dim*self.num_heads, out_feats=class_num, feat_drop=0.5, num_heads=1, allow_zero_in_degree=True)
    
    def call(self, g, features):

eileen-code4fun

import gensim
import gensim.downloader
model = gensim.downloader.load('glove-twitter-50')

eileen-code4fun

def nn_sentence_aug(sentence, factor=2, model):
   sentences = []
   words = sentence.split()
   for i in range(len(words)):
       ps = model.most_similar(words[i], topn=factor)
       for p in ps:
           new_words = words[0:i] + [p[0]] + words[i+1:]
           sentences.append(' '.join(new_words))
   return sentences

eileen-code4fun

def ngram_paraphrase(words, phrases, ngram, factor=2):
   sentences = []
   for i in range(0, len(words)-ngram):
       phrase = ''
       for j in range(0, ngram):
           phrase += words[i+j] + ' '
       phrase = phrase.strip()
       if not phrase in phrases:
           continue
       for p in list(phrases[phrase])[0:factor]:

eileen-code4fun

from sklearn.decomposition import PCA

def project(words, phrases, model):
    embeddings = []
    associated_words = []
    pca = PCA(n_components=2)
    for word in words:
        associated_words.append(word)
        embeddings.append(model[word])
        for pphrase in phrases[word]:

eileen-code4fun

import tensorflow_datasets as tfds
import tensorflow as tf

dataset, info = tfds.load('imdb_reviews', with_info=True,
                          as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']

def experiment(train, test):
    VOCAB_SIZE = 1000
    encoder = tf.keras.layers.experimental.preprocessing.TextVectorization(max_tokens=VOCAB_SIZE, standardize=None)

eileen-code4fun

def preprocess(dataset, fn):
    features = []
    labels = []
    for example, label in dataset:
        features.append(fn(example.numpy().decode('utf-8')))
        labels.append(label.numpy())
    features_dataset = tf.data.Dataset.from_tensor_slices(features)
    labels_dataset = tf.data.Dataset.from_tensor_slices(labels)
    return tf.data.Dataset.zip((features_dataset, labels_dataset))
  

eileen-code4fun

def lower(txt):
    return txt.lower()
 
train = preprocess(train_dataset, lower)
test = preprocess(test_dataset, lower)

eileen-code4fun

import re
def lower_remove_punctuation(txt):
    txt = txt.lower()
    return re.sub(r'[^\w\s]','',txt)

train = preprocess(train_dataset, lower_remove_punctuation)
test = preprocess(test_dataset, lower_remove_punctuation)

eileen-code4fun

from nltk.stem import PorterStemmer
from nltk.stem import WordNetLemmatizer

def lower_remove_punctuation_stem(txt):
    txt = lower_remove_punctuation(txt)
    ps = PorterStemmer()
    words = [ps.stem(w) for w in txt.split()]
    return ' '.join(words)

def lower_remove_punctuation_lemmatize(txt):