eisenjulian

import pdfminer.high_level
import datetime
import requests
import sys
import os
import re
import unidecode
import collections

def split(delimiters, string, maxsplit=0):

eisenjulian

def text_to_index(sentence):
    # Remove punctuation characters except for the apostrophe
    translator = str.maketrans('', '', string.punctuation.replace("'", ''))
    tokens = sentence.translate(translator).lower().split()
    return np.array([1] + [word_index[t] if t in word_index else 2 for t in tokens])

def print_predictions(sentences, classifier):
    indexes = [text_to_index(sentence) for sentence in sentences]
    x = sequence.pad_sequences(indexes, 
                               maxlen=sentence_size, 

eisenjulian

def my_initializer(shape=None, dtype=tf.float32, partition_info=None):
    assert dtype is tf.float32
    return embedding_matrix
params = {'embedding_initializer': my_initializer}
cnn_pretrained_classifier = tf.estimator.Estimator(
    model_fn=cnn_model_fn,
    model_dir=os.path.join(model_dir, 'cnn_pretrained'),
    params=params)
train_and_evaluate(cnn_pretrained_classifier)

eisenjulian

embedding_matrix = np.random.uniform(-1, 1, size=(vocab_size, embedding_size))
for w, i in word_index.items():
    v = embeddings.get(w)
    if v is not None and i < vocab_size:
        embedding_matrix[i] = v

eisenjulian

embeddings = {}
with open('glove.6B.50d.txt', 'r', encoding='utf-8') as f:
    for line in f:
        values = line.strip().split()
        w = values[0]
        vectors = np.asarray(values[1:], dtype='float32')
        embeddings[w] = vectors

eisenjulian

lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(100)
_, final_states = tf.nn.dynamic_rnn(
        lstm_cell, inputs, sequence_length=features['len'], dtype=tf.float32)
logits = tf.layers.dense(inputs=final_states.h, units=1)

eisenjulian

initializer = tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0))
params = {'embedding_initializer': initializer}
cnn_classifier = tf.estimator.Estimator(model_fn=model_fn,
                                        model_dir=os.path.join(model_dir, 'cnn'),
                                        params=params)
train_and_evaluate(cnn_classifier)

eisenjulian

head = tf.contrib.estimator.binary_classification_head()
optimizer = tf.train.AdamOptimizer()    
def _train_op_fn(loss):
    tf.summary.scalar('loss', loss)
    return optimizer.minimize(
        loss=loss,
        global_step=tf.train.get_global_step())

return head.create_estimator_spec(
    features=features,

eisenjulian

training = (mode == tf.estimator.ModeKeys.TRAIN)
dropout_emb = tf.layers.dropout(inputs=input_layer, 
                                rate=0.2, 
                                training=training)
conv = tf.layers.conv1d(
    inputs=dropout_emb,
    filters=32,
    kernel_size=3,
    padding="same",
    activation=tf.nn.relu)

eisenjulian

input_layer = tf.contrib.layers.embed_sequence(
    features['x'], 
    vocab_size, 
    embedding_size,
    initializer=params['embedding_initializer'])