tenderlove

require 'fiddle'

module Python
  def __class__= k
    value = _wrap self
    [k.object_id<<1].pack('Q').unpack('C8').each_with_index {|n,i|value[i+8]=n}
  end
  def _wrap klass; Fiddle::Pointer.new Fiddle.dlwrap klass; end
end

mhfs

require 'formula'

# some credit to http://github.com/maddox/magick-installer
# NOTE please be aware that the GraphicsMagick formula derives this formula

def ghostscript_srsly?
  ARGV.include? '--with-ghostscript'
end

def x11?

charanpald

# Run some recommendation experiments using MovieLens 100K
import pandas
import numpy
import scipy.sparse
import scipy.sparse.linalg
import matplotlib.pyplot as plt
from sklearn.metrics import mean_absolute_error

data_dir = "data/ml-100k/"
data_shape = (943, 1682)

astrojuanlu

from functools import reduce
from itertools import groupby


def reduceByKey(func, iterable):
    """Reduce by key.

    Equivalent to the Spark counterpart
    Inspired by http://stackoverflow.com/q/33648581/554319

shagunsodhani

Learning to Generate Reviews and Discovering Sentiment

Summary

The authors train a character-RNN (using mLSTM units) over Amazon Product Reviews (82 million reviews) and use the char-RNN as the feature extractor for sentiment analysis. These unsupervised features beat state of the art results for the dataset while are outperformed by supervised approaches on other datasets. Most important observation is that the authors find a single neuron (called as the sentiment neuron) which alone achieves a test accuracy of 92.3% thus giving the impression that the sentiment concept has been captured in that single neuron. Switching this neuron on (or off) during the generative process produces positive (or negative) reviews.

Notes

• The paper aims to evaluate if the low level features captured by char-RNN can support learning of high-level representations.

sap1ens

var MyModel = Backbone.Model.extend({
    someMethod: function(opts) {
        var url = this.url() + '/someMethod',
            // note that these are just $.ajax() options
            options = {
                url: url,
                type: 'POST'
            };

        // add any additional options, e.g. a "success" callback or data

peter0749

def att_loss(y_true, y_pred):
    def att_(x):
        a = tf.where(x>0, K.exp(x), K.zeros_like(x))
        return a / (K.sum(a, axis=-1, keepdims=True)+K.epsilon())
    y_true_a = att_(y_true)
    y_pred_a = att_(y_pred)
    loss = K.mean(K.binary_crossentropy(y_true_a, y_pred_a), axis=-1)
    return loss

lioutasb

import tensorflow as tf

def mrr_metric(labels, predictions, weights=None,
              metrics_collections=None,
              updates_collections=None,
              name=None):
    
    with tf.name_scope(name, 'mrr_metric', [predictions, labels, weights]) as scope:

    

wrburgess

Grab new backup of database

Command: heroku pgbackups:capture --remote production

Response: >>> HEROKU_POSTGRESQL_COLOR_URL (DATABASE_URL) ----backup---> a712

Get url of backup download

Command: heroku pgbackups:url [db_key] --remote production

codeinthehole

from celery import chain

from django.core.management.base import BaseCommand

from . import tasks


class Command(BaseCommand):

    def handle(self, *args, **kwargs):