#!/usr/bin/python
"""
    An autoassociator for sparse inputs, using Ronan Collobert + Jason
    Weston's sampling trick (2008).

    The learned model is::
       h   = sigmoid(dot(x, w1) + b1)
       y   = sigmoid(dot(h, w2) + b2)

    We assume that most of the inputs are zero, and hence that we can
    separate x into xnonzero, x's nonzero components, and a xzero,
    a sample of the zeros. (We randomly without replacement choose
    ZERO_SAMPLE_SIZE zero columns.)

    The desideratum is that every nonzero entry is separated from every
    zero entry by margin at least MARGIN.
    For each ynonzero, we want it to exceed max(yzero) by at least MARGIN.
    For each yzero, we want it to be exceed by min(ynonzero) by at least MARGIN.
    The loss is a hinge loss (linear). The loss is irrespective of the
    xnonzero magnitude (this may be a limitation). Hence, all nonzeroes
    are equally important to exceed the maximum yzero.

    LIMITATIONS:
       - Only does pure stochastic gradient (batchsize = 1).
       - Loss is irrespective of the xnonzero magnitude.
       - We will always use all nonzero entries, even if the training
       instance is very non-sparse.
       
    @bug: If there are not ZERO_SAMPLE_SIZE zeroes, we will enter an
    endless loop.
"""


import numpy, random
import globals
random.seed(globals.SEED)

nonzero_instances = []
nonzero_instances.append({1: 0.1, 5: 0.5, 9: 1})
nonzero_instances.append({2: 0.3, 5: 0.5, 8: 0.8})
nonzero_instances.append({1: 0.2, 2: 0.3, 5: 0.5})

import model
model = model.Model()

for i in xrange(100000):
    # Select an instance
    instance = nonzero_instances[i % len(nonzero_instances)]

    # Get the nonzero indices
    nonzero_indexes = instance.keys()
    nonzero_indexes.sort()

    # Get the zero indices
    # @bug: If there are not ZERO_SAMPLE_SIZE zeroes, we will enter an endless loop.
    zero_indexes = []
    while len(zero_indexes) < globals.ZERO_SAMPLE_SIZE:
        idx = random.randint(0, globals.INPUT_DIMENSION - 1)
        if idx in nonzero_indexes or idx in zero_indexes: continue
        zero_indexes.append(idx)
    zero_indexes.sort()

    # SGD update over instance
    model.update(instance, nonzero_indexes, zero_indexes)