minor improvements

dios/profiling/memory.py

 import gc
-from dios.profiling.generate_testsets import _gen_testset
+from dios.profiling.generate_testsets import get_testset, _gen_testset
 
 
 def calc_mem(rows, cols, shifted=False, dtypesz=(64 / 8)):
@@ -39,20 +39,20 @@ if __name__ == '__main__':
     # dos      - linear in rows and colums, same size for r=10,c=100 or r=100,c=10
     do_real_check = True
     cols = 10
-    rows = 1000
+    rows = 100000
     # rows = rows_by_time(nsec=600, mdays=365*2)
 
     mem = calc_mem(rows, cols, shifted=False)
     memsh = calc_mem(rows, cols, shifted=True)
 
-    df, dos = _gen_testset(rows, cols, disalign=False, randstart=True)
+    df, _, _, dos = get_testset(rows, cols, disalign=False, randstart=True)
     dos_mem = dos.memory_usage()
     print(f"dos:\n-----------")
     print("mem: ", *bytes2hread(dos_mem))
     print("entries:", sum([len(dos[e]) for e in dos]))
     print()
 
-    ratio = round(dos_mem / mem, 2), round(dos_mem / memsh, 2)
+    ratio = (1 / (memsh - mem) ) * dos_mem
 
     mem = bytes2hread(mem)
     memsh = bytes2hread(memsh)
@@ -66,8 +66,7 @@ if __name__ == '__main__':
     print("entries:", rows * cols)
 
     print()
-    print(f"dos/(df best case)  :{ratio[0]}")
-    print(f"dos/(df worst case) :{ratio[1]}")
+    print(f"dfbest, dos, dfworst: 0%, {round(ratio, 4)*100}%, 100% ")
 
     if not do_real_check:
         exit(0)
@@ -88,7 +87,7 @@ if __name__ == '__main__':
 
     print()
     print('rand start, rand freq')
-    df, _ = _gen_testset(rows, cols, disalign='random', randstart=True)
+    df, _ = get_testset(rows, cols, disalign='random', randstart=True)
     df.info(memory_usage='deep', verbose=False)
     print("entries:", sum([len(df[e]) for e in df]))
 

dios/profiling/performance.py

@@ -107,9 +107,9 @@ if __name__ == '__main__':
 
     # max increase of of rows
     # 1 = 10 # 2 = 100 # .... # 5 = 100'000
-    iterations = 4
+    iterations = 5
     runs = 10
-    cols = 20
+    cols = 70
 
     profile_assignment = True
 
@@ -117,7 +117,7 @@ if __name__ == '__main__':
     use_df = True
     use_a = False
     use_b = False
-    use_dos = False
+    use_dos = True
 
     # plot options
     normalize_to_df = False