adding an notebook for example distances

distance_batsim_output.py

@@ -57,13 +57,13 @@ def euclidean_distance(s1, s2):
     """Returns the Euclidean distance between two series s1 and s2"""
 
     dist = np.sqrt(np.sum([(x-y) * (x-y) for x, y in zip(s1, s2)]))
-    return dist
+    return float(dist)
 
 
 def lateness_distance(s1, s2):
     """Returns the 'lateness' of s2 compared to s1"""
 
-    return np.sum([y-x for x, y in zip(s1, s2)])
+    return float(np.sum([y-x for x, y in zip(s1, s2)]))
 
 def normalized_euclidian_distance(s1, s2):
     """Return the euclidien distance normalized by the l2 norm of the vectors, 
@@ -73,12 +73,12 @@ def normalized_euclidian_distance(s1, s2):
     if n1==0 or n2==0:
         return None
     eucl_dist = euclidean_distance(s1, s2)
-    return eucl_dist**2 / (n1 * n2)
+    return float( eucl_dist**2 / (n1 * n2) )
 
 def l2_norm(s):
     """Return the l2 norm of the series s"""
 
-    return np.sqrt(np.sum([x * x for x in s]))
+    return float( np.sqrt(np.sum([x * x for x in s])) )
 
 
 def distances(file1, file2, euclidean=True, lateness=False, norm_eucl=False,
@@ -111,7 +111,7 @@ def distances(file1, file2, euclidean=True, lateness=False, norm_eucl=False,
 def pretty_print(dist):
     """Nice printing of the dictionnary dist"""
     
-    if type(dist) is dict:
+    if isinstance(dist, dict):
         pretty = json.dumps(dist, indent=4)
         print(pretty)
     else:

test/input/3jobs.csv

 job_id,workload_name,profile,submission_time,requested_number_of_resources,requested_time,success,final_state,starting_time,execution_time,finish_time,waiting_time,turnaround_time,stretch,allocated_resources,consumed_energy,metadata
-1216,user11,362,30,1,86400.000000,1,COMPLETED_SUCCESSFULLY,30,362.000000,80,0.000000,362.000000,1.000000,2,62671.250000,
-247,user5,57102,0,8,432000.000000,1,COMPLETED_SUCCESSFULLY,0,57102.000000,0,0.000000,57102.000000,1.000000,0,12391134.000000,
-1242,user11,9620,40,1,86400.000000,1,COMPLETED_SUCCESSFULLY,40,9620.000000,60,0.000000,9620.000000,1.000000,2,1665462.500000,
\ No newline at end of file
+1216,user11,362,30,1,86400.000000,1,COMPLETED_SUCCESSFULLY,30,50,80,0.000000,362.000000,1.000000,2,62671.250000,
+247,user5,57102,0,8,432000.000000,1,COMPLETED_SUCCESSFULLY,0,0,0,0.000000,57102.000000,1.000000,0,12391134.000000,
+1242,user11,9620,40,1,86400.000000,1,COMPLETED_SUCCESSFULLY,40,20,60,0.000000,9620.000000,1.000000,1,1665462.500000,
\ No newline at end of file

test/input/3jobs_w_sessions.csv

 job_id,workload_name,profile,submission_time,requested_number_of_resources,requested_time,success,final_state,starting_time,execution_time,finish_time,waiting_time,turnaround_time,stretch,allocated_resources,consumed_energy,metadata
-1216:s1,user11,362,30,1,86400.000000,1,COMPLETED_SUCCESSFULLY,30,362.000000,60,0.000000,362.000000,1.000000,2,62671.250000,
-247:s1,user5,57102,0,8,432000.000000,1,COMPLETED_SUCCESSFULLY,0,57102.000000,0,0.000000,57102.000000,1.000000,0,12391134.000000,
-1242:s1,user11,9620,40,1,86400.000000,1,COMPLETED_SUCCESSFULLY,40,9620.000000,80,0.000000,9620.000000,1.000000,2,1665462.500000,
\ No newline at end of file
+1216:s1,user11,362,30,1,86400.000000,1,COMPLETED_SUCCESSFULLY,30,30,60,0.000000,362.000000,1.000000,2,62671.250000,
+247:s1,user5,57102,0,8,432000.000000,1,COMPLETED_SUCCESSFULLY,0,0,0,0.000000,57102.000000,1.000000,0,12391134.000000,
+1242:s1,user11,9620,40,1,86400.000000,1,COMPLETED_SUCCESSFULLY,40,40,80,0.000000,9620.000000,1.000000,1,1665462.500000,
\ No newline at end of file