persiyanov

import torch
import torch.autograd


class MaskedSpMatmul(torch.autograd.Function):
	CHUNK_SIZE = 10000

	@staticmethod
	def forward(ctx, a, b, mask):
		"""

persiyanov

----- MODEL "cython-linesentence-word2vec-window-05-workers-01-size-300" RESULTS -----
       * Vocab time: 126.159779072 sec.
       * Total epoch time: 1181.82512498 sec.
       * Processing speed: 144372.118509 words/sec
       * Avg CPU loads: 0.14, 0.35, 5.27, 94.53, 0.09, 0.23, 0.01, 0.02, 0.02, 0.02, 0.02, 0.01, 0.02, 0.02, 0.33, 0.02
       * Sum CPU load: 101.11282
----- MODEL "cython-linesentence-word2vec-window-05-workers-04-size-300" RESULTS -----
       * Vocab time: 126.206352949 sec.
       * Total epoch time: 305.442888975 sec.

persiyanov

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (C) 2010 Radim Rehurek <[email protected]>
# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html


"""Corpus in the Matrix Market format.

This code uses python's struct library to read/write binary data

persiyanov

persiyanov

persiyanov

# Optionally, you could now dump the network weights to a file like this:
np.savez('model.npz', *lasagne.layers.get_all_param_values(network))
#
# And load them again later on like this:
with np.load('model.npz') as f:
    param_values = [f['arr_%d' % i] for i in range(len(f.files))]
lasagne.layers.set_all_param_values(network, param_values)

persiyanov

import gym
import numpy as np

DISCOUNT = 1.0
STEP_REWARD = 0.0
LOSE_REWARD = 0.0
WIN_REWARD = 1.0

def avg_reward(env, s, a):
    avg_reward = 0

persiyanov

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
import logging


class BagOfWordsModel(object):
    OUT_FOLDER = 'out'

    def __init__(self, id_document_dict, max_features=None, max_df=1.0):
        """Builds bow model.

persiyanov

persiyanov

Goal

Want to move computation on machine with much power. We will set up Anaconda 4.0.0 and XGBoost 0.4 (it is tricky installable).

Preliminaries

• Amazon AWS Educate gives 100$ for MIPT students.
• GitHub Students Pack additionaly gives 15$.

Let's start

AWS Console and launching EC2 Instance.