An improvement over the CompressedFeatures class introduced at http://derandomized.com/post/51709771229/compressed-features-for-machine-learning#disqus_thread by not requiring the key->component mapping to be stored.

DeterministicCompressedFeatures.py

class DeterministicCompressedFeatures(CompressedFeatures):
    """Generates random components after seeding with the component_key.

    By using a known seed to generate the random components, we do not need to
    store or manage them. We can just recompute them whenever we need.
    """

    def __init__(self, num_features=RANDOM_FEATURE_LENGTH):
        super(DeterministicallyRandomFeatures, self).__init__(num_features)

        # We can't use a defaultdict, because we must pass a parameter to
        # _generate_component()
        self.random_components = {}

    def _generate_component(self, component_key):
        # We must use hashlib, because hash() is unreliable
        # http://stackoverflow.com/questions/793761/built-in-python-hash-function
        big_hash = int(hashlib.md5(repr(component_key)).hexdigest(), 16)

        # Shrink the 39-digit hash to something seed() will accept
        lil_hash = int(big_hash % ((1 << 31) - 1))
        np.random.seed(lil_hash)

        # Deterministically compute the feature vector, based on the key
        rv = np.random.randn(self.num_features, 1)
        rv /= np.sqrt(np.dot(rv.T, rv))  # normalize to unit length
        return rv

    def increment_component(self, component_key, scale=1.0):
        """Increments feature_vector by the specified component.

        Arguments:
            component_key - The component to increment by. If this key has
                never been seen before, the component values are generated.
            scale - The multiplicative factor to apply against the
                component values.
        """
        if not self.contains_component(component_key):
            if self.dynamic_mode:
                self.random_components[component_key] = (
                    self._generate_component(component_key))
            else:
                return False

        self.feature_vector += scale * self.random_components[component_key]
        return True