Mem_usage.log

Line #    Mem usage    Increment   Line Contents
================================================
   320     37.2 MiB      0.0 MiB   @profile
   321                             def func():
   322     37.2 MiB      0.0 MiB       n_products = input("Enter the number of products (that is add +1 to the actual number) : ")
   323     37.2 MiB      0.0 MiB       time_steps = input("Enter the number of time steps (should be equal to the above number of products) : ")
   324     37.2 MiB      0.0 MiB       demand_mat = input("Enter the demand matrix with time instance as columns and products as rows : ")
   325     37.2 MiB      0.0 MiB       max_price = input("Enter the maximum price for each product as an array : ")
   326     37.2 MiB      0.0 MiB       min_price = input("Enter the minimum price for each product as an array : ")
   327     37.2 MiB      0.0 MiB       print "Creating the pricing object "
   328                             
   329     37.2 MiB      0.0 MiB       pricing_obj = Pricing(time_steps, n_products, demand_mat, max_price, min_price)
   330                             
   331     37.2 MiB      0.0 MiB       print "Generating the independent vectors once for all the cases to follow"
   332     37.2 MiB      0.0 MiB       pv = pricing_obj.independent_price_vectors()
   333                             
   334                                 # generating the respective beta matrix
   335     37.2 MiB      0.0 MiB       distribution = raw_input("Enter the distribution, the supported distributions are :\n1. Normal (N) \n2. Poisson (P)\n ")
   336     37.2 MiB      0.0 MiB       print "Generating the beta matrix for the above independent vectors using the above distribution :",distribution
   337     37.2 MiB      0.0 MiB       if distribution == "N":
   338     37.2 MiB      0.0 MiB           print "Choosen distribution is Normal"
   339     37.4 MiB      0.2 MiB           beta_matrix = pricing_obj.beta_mat_normal(pv)
   340                                 elif distribution == "P":
   341                                     print "Choosen distribution is Poisson"
   342                                     beta_matrix = pricing_obj.beta_mat_poisson(pv)
   343                                 else:
   344                                     print "Error : choose N for Normal, P for Poisson"
   345                             
   346     37.4 MiB      0.0 MiB       bound_tuple =  tuple((pricing_obj._pl[i], pricing_obj._ph[i]) for i in range(len(pricing_obj._ph)))
   347                             
   348     37.4 MiB      0.0 MiB       initial_guess =  input("Enter an initial guess for the optimal solution generation : ")
   349                             
   350                                 # generating different optimal solutions depending on various conditions
   351                                 # TODO : this is to be automated to generate the final solution, as the bounds are unknown this
   352                                 #        that is a partial blocker or may be a full blocker.
   353                                 # y = optimal_solution(x, optimal_function, optimal_func_der, optimal_func_hess, [23, 15.5, 36.4, 22.3], beta_matrix, bound_tuple)
   354     37.4 MiB      0.0 MiB       print "Generating the optimal solution to be compared with the bound in order to predict the pricing at future times ..."
   355     37.4 MiB      0.0 MiB       warnings.filterwarnings("ignore")
   356     37.4 MiB      0.0 MiB       if distribution == "N":
   357     37.4 MiB      0.0 MiB           optimal_set = []
   358     37.4 MiB      0.0 MiB           t_end = time.time() + 60 * 1
   359     38.2 MiB      0.8 MiB           while time.time() < t_end:
   360     38.2 MiB      0.0 MiB               y = optimal_solution_normal(pricing_obj, optimal_function_normal, optimal_func_der_normal, optimal_func_hess_normal, initial_guess, beta_matrix, bound_tuple)
   361     38.2 MiB      0.0 MiB               optimal_set.append(y)
   362     38.2 MiB      0.0 MiB           least = np.argsort([opt[0] for opt in optimal_set])
   363     38.2 MiB      0.0 MiB           opt = []
   364     38.2 MiB      0.0 MiB           for ind in least:
   365     38.2 MiB      0.0 MiB               opt.append(optimal_set[ind])
   366     38.2 MiB      0.0 MiB           for i in range(len(opt)):
   367     38.2 MiB      0.0 MiB               if np.array_equal(opt[i], np.array(initial_guess)):
   368                                             continue
   369                                         else:
   370     38.2 MiB      0.0 MiB                   print " optimal solution for normal distribution: ", opt[i]
   371     38.2 MiB      0.0 MiB                   break
   372                                     else:
   373                                         print " optimal solution for normal distribution: ", opt[0]
   374