correct database attribute names in python script and added seed to dblp random lines

dblp/random_lines.py

@@ -7,6 +7,7 @@ filename = sys.argv[2]
 with open(filename) as f:
     lines = f.readlines()
 
+random.seed("12345678")
 linestoprint = random.sample(range(len(lines)), number)
 
 for ln in linestoprint:

statistics/statistics.py

@@ -88,11 +88,11 @@ with open(args.inputfile) as f:
 dataset_info = "{"
 dataset_info += "\"filename\": \"" + str(filename) + "\""
 dataset_info += ", \"short_description\": \"" + str(short_description) + "\""
-dataset_info += ", \"number_of_trees\": " + str(number_of_trees)
+dataset_info += ", \"number_trees\": " + str(number_of_trees)
 dataset_info += ", \"avg_tree_size\": " + str(sum_of_tree_sizes/number_of_trees)
 dataset_info += ", \"min_tree_size\": " + str(min_tree_size)
 dataset_info += ", \"max_tree_size\": " + str(max_tree_size)
-dataset_info += ", \"different_label\": " + str(len(labels))
+dataset_info += ", \"number_labels\": " + str(len(labels))
 dataset_info += "}"
 
 # print result to stdout
@@ -100,7 +100,7 @@ print(dataset_info)
 
 # store dataset in db
 if args.storeindb:
-  store_result(db_table_name, dataset_info)
+  store_result(db_table_name, json.loads(dataset_info))
 
 # print label distribution
 if args.printlabels: