MarketStudy/marketstudy/Equity Prediction/CNNtextual.py

import tensorflow as tf
import numpy as np

class CNNtextual(object):

    def __init__(self, embedding_matrix, sequence_length, vocab_size, embedding_size, filter_sizes, num_filters):

        # Placeholders for input, dropout
        self.input_text = tf.placeholder(tf.int32, [None, sequence_length], name="input_text")
        self.keep_prob = tf.placeholder(tf.float32, name="keep_prob")
        with tf.name_scope("embedding"):
            self.embed_input = tf.nn.embedding_lookup(embedding_matrix, self.input_x)
            self.embed_input_expanded = tf.expand_dims(self.embed_input, -1)

        # conv and maxpool layer for each size
        pooled_ouputs = []
        for i, filter_size in enumerate(filter_sizes):
            with tf.name_scope("conv-maxpool-{}".format(str(filter_size))):
                # Conv layer
                filter_shape = [filter_size, embedding_size, 1, num_filters]
                W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
                b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
                conv = tf.nn.conv2d(self.embed_input_expanded, W, strides=[1,1,1,1], padding="VALID", name="conv")
                # relu
                h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")

                # max-pooling over outputs
                pooled = tf.nn.max_pool(h, ksize=[1, sequence_length-filter_size + 1, 1, 1], padding="VALID", name="pool")
                pooled_outputs.append(pooled)

        # Combine all pooled features
        num_filters_total = num_filters*len(filter_sizes)
        self.hpool = tf.concat(3, pooled_outputs)
        self.hpool_flat = tf.reshape(self.hpool, [-1, num_filters_total])

        # dropout
        with tf.name_scope("dropout"):
            self.h_drop = tf.nn.dropout(self.h_pool_flat, self.keep_prob)
        
        # TODO Recurrent layer