def __cinit__()

in hype/graph_dataset.pyx [0:0]

• 32 lines of code
• 1 McCabe index (conditional complexity)

    def __cinit__(self, idx, objects, weights, nnegs, batch_size, num_workers,
                  burnin=False, sample_dampening=0.75):
        '''
        Create a dataset for training Hyperbolic embeddings.  Rather than
        allocating many tensors for individual dataset items, we instead
        produce a single batch in each iteration.  This allows us to do a single
        Tensor allocation for the entire batch and filling it out in place.

        Args:
            idx (ndarray[ndims=2]):  Indexes of objects corresponding to co-occurrence.
                I.E. if `idx[0, :] == [4, 19]`, then item 4 co-occurs with item 19
            weights (ndarray[ndims=1]): Weights for each co-occurence.  Corresponds
                to the number of times a pair co-occurred.  (Equal length to `idx`)
            nnegs (int): Number of negative samples to produce with each positive
            objects (list[str]): Mapping from integer ID to hashtag string
            nnegs (int): Number of negatives to produce with each positive
            batch_size (int): Size of each minibatch
            num_workers (int): Number of threads to use to produce each batch
            burnin (bool): ???
        '''
        self.idx = idx
        self.objects = objects
        self.nnegs = nnegs
        self.burnin = burnin
        self.N = len(objects)
        self.counts = np.zeros((self.N), dtype=np.double)
        self.num_workers = num_workers
        self.batch_size = batch_size
        self.sample_dampening = sample_dampening
        self._mk_weights(idx, weights)
        self.max_tries = 10 * nnegs
        self.neg_multiplier = 1
        self.queue = queue.Queue(maxsize=num_workers)