diff options
Diffstat (limited to 'simulation/active_blocks.py')
| -rw-r--r-- | simulation/active_blocks.py | 38 |
1 files changed, 19 insertions, 19 deletions
diff --git a/simulation/active_blocks.py b/simulation/active_blocks.py index e3924c6..7aa1afb 100644 --- a/simulation/active_blocks.py +++ b/simulation/active_blocks.py @@ -33,7 +33,7 @@ class LearnedDataset(fuel.datasets.Dataset): i = 0 while i < request: x_tmp, s_tmp = mn.build_cascade_list( - mn.simulate_cascades(self.n_cascades, graph, self.source), + mn.simulate_cascades(self.n_cascades, self.graph, self.source), collapse=True ) x_obs[i:i + len(x_tmp)] = x_tmp[:request - i] @@ -60,11 +60,9 @@ class ActiveLearning(blocks.extensions.SimpleExtension): class ShuffledBatchesScheme(fuel.schemes.ShuffledScheme): - """ - Iteration scheme over finite dataset: + """Iteration scheme over finite dataset: -shuffles batches but not within batch - -arguments: dataset_size (int) ; batch_size (int) - """ + -arguments: dataset_size (int) ; batch_size (int)""" def get_request_iterator(self): indices = list(self.indices) # self.indices = xrange(dataset_size) start = np.random.randint(self.batch_size) @@ -80,12 +78,8 @@ class ShuffledBatchesScheme(fuel.schemes.ShuffledScheme): def create_mle_model(graph): - """ - return cascade likelihood theano computation graph - """ + """return cascade likelihood theano computation graph""" n_nodes = len(graph) - g_shared = theano.shared(value=graph, name='graph') - x = tsr.matrix(name='x', dtype='int8') s = tsr.matrix(name='s', dtype='int8') params = theano.shared( @@ -100,12 +94,19 @@ def create_mle_model(graph): lkl_mle = lkl_pos + lkl_neg lkl_mle.name = 'cost' + return x, s, params, lkl_mle + + +def rmse_error(graph, params): + n_nodes = len(graph) + g_shared = theano.shared(value=graph, name='graph') diff = (g_shared - params) ** 2 subarray = tsr.arange(g_shared.shape[0]) tsr.set_subtensor(diff[subarray, subarray], 0) rmse = tsr.sum(diff) / (n_nodes ** 2) rmse.name = 'rmse' - return x, s, params, lkl_mle, rmse + g_shared.name = 'graph' + return rmse, g_shared def create_fixed_data_stream(n_cascades, graph, batch_size, shuffle=True): @@ -137,27 +138,26 @@ def create_learned_data_stream(graph, batch_size): if __name__ == "__main__": batch_size = 1000 - #graph = mn.create_random_graph(n_nodes=1000) graph = mn.create_star(1000) print('GRAPH:\n', graph, '\n-------------\n') - x, s, params, cost, rmse = create_mle_model(graph) + x, s, params, cost = create_mle_model(graph) + rmse, g_shared = rmse_error(graph, params) alg = blocks.algorithms.GradientDescent( cost=-cost, parameters=[params], step_rule=blocks.algorithms.AdaDelta() ) data_stream = create_learned_data_stream(graph, batch_size) - #n_cascades = 10000 - #data_stream = create_fixed_data_stream(n_cascades, graph, batch_size, - # shuffle=False) loop = blocks.main_loop.MainLoop( alg, data_stream, extensions=[ blocks.extensions.FinishAfter(after_n_batches = 10**4), blocks.extensions.monitoring.TrainingDataMonitoring([cost, params, - rmse], after_batch=True), - blocks.extensions.Printing(every_n_batches = 10)#, - #ActiveLearning(data_stream.dataset) + rmse, g_shared], after_batch=True), + blocks.extensions.Printing(every_n_batches = 10), + ActiveLearning(data_stream.dataset), + blocks.extras.extensions.Plot('graph rmse', channels=[], + every_n_batches = 10) ] ) loop.run() |