Comment by eesmith

Wee! Pointless optimization Saturday!

Looks like my gen_stats_eesmith is even faster. Radim's is about 400x faster, iClaudiusX is 450x faster, and eesmith is 580x faster.

Under pypy2-v5.8.0 those are 65x, 16x, and 91x, respectively. The original algorithm is 10x faster under pypy.

    def gen_stats_python(dataset_python):
        start = time.time()
        product_stats = []
        unique_products = set([x[0] for x in dataset_python])
        for product_id in unique_products:
            product_items = [x for x in dataset_python if x[0]==product_id ]
            num_orders = len(product_items)
            total_quantity = 0
            total_price = 0
            for row in product_items:
                total_quantity += row[2]
                total_price += row[3]
            avg_price = float(total_price/num_orders)
            product_stats.append([int(product_id),int(num_orders),int(total_quantity),round(avg_price,2)])
        end = time.time()
        working_time = end-start
        return product_stats,working_time

    def gen_stats_radim(dataset_python):
      start = time.time()
      aggr = {}
      for product_id, product_order_num, quantity, price in dataset_python:
          item = aggr.get(product_id, [0, []])
          item[0] += quantity
          item[1].append(price)
          aggr[product_id] = item
      return [
          [int(product_id), len(prices), int(quantity), round(float(sum(prices)) / len(prices), 2)]
          for product_id, (quantity, prices) in aggr.items()
      ], time.time()-start

    def gen_stats_iclaudiusx(data):
        start = time.time()
        stats = []
        data.sort(key=itemgetter(0))
        for p_id, p_items in itertools.groupby(data, key=itemgetter(0)):
          num_orders, _, total_quantity, total_price = map(sum, zip(*p_items))
          p_id, num_orders, total_quantity = map(int, [p_id, num_orders/p_id, total_quantity])
          stats.append([p_id, num_orders, total_quantity, round(float(total_price/num_orders),2)])
        end = time.time()
        working_time = end-start
        return stats, working_time

    def gen_stats_eesmith(dataset_python):
        start = time.time()
        product_stats = []
        total_num_orders = defaultdict(int)
        total_quantity_by_product_id = defaultdict(int)
        total_price_by_product_id = defaultdict(float)

        for product_id, order_id, quantity, price in dataset_python:
            total_num_orders[product_id] += 1
            total_quantity_by_product_id[product_id] += quantity
            total_price_by_product_id[product_id] += price

        for product_id in total_price_by_product_id:
            num_orders = total_num_orders[product_id]
            total_quantity = total_quantity_by_product_id[product_id]
            total_price = total_price_by_product_id[product_id]

            avg_price = float(total_price)/num_orders
            product_stats.append([int(product_id),int(num_orders),int(total_quantity),round(avg_price,2)])
        end = time.time()
        working_time = end-start
        return product_stats,working_time

    reference_result = reference_dt = None
    gen_stats_functions = (gen_stats_python, gen_stats_radim,
        gen_stats_iclaudiusx, gen_stats_eesmith)
    for gen_stats_function in gen_stats_functions:
        result, dt = gen_stats_function(dataset_python)
        if reference_result is None:
            reference_result = result
            reference_dt = dt
        assert result == reference_result, (gen_stats_function.__name__,
                 result[:2], reference_result[:2])
        print(gen_stats_function.__name__, dt, reference_dt/dt)