twitter-pagerank controlscript: the pagerank loop

gistfile1.py

iteration = Pig.compileFromFile(self.iteration_script)
for i in range(self.max_num_iterations):
    print "Starting iteration step: %s" % str(i + 1)

    # Append the iteration number to the input/output stems
    iteration_input = self.preprocess_pageranks if i == 0 else (self.iteration_pageranks_prefix + str(i-1))
    iteration_pageranks_output = self.iteration_pageranks_prefix + str(i)
    iteration_rank_changes_output = self.iteration_rank_changes_prefix + str(i)

    iteration_bound = iteration.bind({
        "INPUT_PATH": iteration_input,
        "DAMPING_FACTOR": self.damping_factor,
        "NUM_NODES": num_nodes,
        "PAGERANKS_OUTPUT_PATH": iteration_pageranks_output,
        "AGG_RANK_CHANGE_OUTPUT_PATH": iteration_rank_changes_output
    })
    iteration_stats = iteration_bound.runSingle()

    # If we're below the convergence threshold break out of the loop.
    aggregate_rank_change = long(str(iteration_stats.result("aggregate_rank_change").iterator().next().get(0)))
    if aggregate_rank_change < convergence_threshold:
        print "Sum of ordering-rank changes %d under convergence threshold %d. Stopping." \
               % (aggregate_rank_change, convergence_threshold)
        break
    elif i == self.max_num_iterations-1:
        print ("Sum of ordering-rank changes %d " % aggregate_rank_change) + \
              ("above convergence threshold %d but hit max number of iterations. " % convergence_threshold) + \
               "Stopping."
    else:
        print "Sum of ordering-rank changes %d above convergence threshold %d. Continuing." \
               % (aggregate_rank_change, convergence_threshold)