ottokart

# coding: utf-8

from __future__ import division
from nltk.tokenize import word_tokenize

import models
import data

import theano
import tornado.ioloop

ottokart

# coding: utf-8
from __future__ import division

import struct
import sys
import gzip

FILE_NAME = "GoogleNews-vectors-negative300.bin.gz" # outputs GoogleNews-vectors-negative300.bin.gz.txt
MAX_VECTORS = 100000 # Top words to take
FLOAT_SIZE = 4 # 32bit float

ottokart

from __future__ import division

import numpy as np
import matplotlib.pyplot as plt

np.random.seed(1)

# Replace X with your own data if you wish
##########################################
N = 300 # num samples

ottokart

# coding: utf-8

# A little demo illustrating the effect of momentum in neural network training.
# Try using different values for MOMENTUM constant below (e.g. compare 0.0 with 0.9).
# This neural network is actually more like logistic regression, but I have used
# squared error to make the error surface more interesting.

import numpy as np
import pylab

ottokart

# Tiny example of 3-layer nerual network with dropout in 2nd hidden layer
# Output layer is linear with L2 cost (regression model)
# Hidden layer activation is tanh

import numpy as np

n_epochs = 100
n_samples = 100
n_in = 10
n_hidden = 5

ottokart

# coding: utf-8
from __future__ import division

import struct
import sys

FILE_NAME = "GoogleNews-vectors-negative300.bin"
MAX_VECTORS = 200000 # This script takes a lot of RAM (>2GB for 200K vectors), if you want to use the full 3M embeddings then you probably need to insert the vectors into some kind of database
FLOAT_SIZE = 4 # 32bit float