diff --git a/distance_batsim_output.py b/distance_batsim_output.py
index b8938a8bb8f3c2c4b64a82139c6d71d166b50414..8b8e0865fe26cb492f1f0121c670183112d37b17 100755
--- a/distance_batsim_output.py
+++ b/distance_batsim_output.py
@@ -49,8 +49,20 @@ def open_and_compare(file1, file2):
out1 = out1[out1.success == 1]
out2 = out2[out2.success == 1]
+ runtimes1 = out1.finish_time - out1.starting_time
+ runtimes2 = out2.finish_time - out2.starting_time
+
+ if not np.allclose(runtimes1, runtimes2, atol=1):
+ warnings.warn(f"Some jobs in {file1} and {file2} don't have the same runtime (+/- 1sec). It is unusual, as runtime are normally an input of the simulation.")
+
return out1, out2
+def sum_execution_times(out):
+ """Returns the sum of all job execution times from a clean batsim output"""
+
+ runtimes = out.finish_time - out.starting_time
+ return runtimes.sum()
+
def euclidean_distance(s1, s2):
"""Returns the Euclidean distance between two series s1 and s2"""
@@ -64,15 +76,6 @@ def lateness_distance(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,
- or None if one of the vectors is the null vector (undefined)"""
-
- n1, n2 = l2_norm(s1), l2_norm(s2)
- if n1==0 or n2==0:
- return None
- eucl_dist = euclidean_distance(s1, s2)
- return float( eucl_dist**2 / (n1 * n2) )
def l2_norm(s):
"""Return the l2 norm of the series s"""
@@ -87,13 +90,20 @@ def distances(file1, file2, euclidean=True, lateness=False, norm_eucl=False,
out1, out2 = open_and_compare(file1, file2)
+ sum_runtimes1 = sum_execution_times(out1)
+ sum_runtimes2 = sum_execution_times(out2)
+
dist = {}
for f in field:
dist[f] = {}
+ eucl = euclidean_distance(out1[f], out2[f])
if euclidean:
- dist[f]["euclidean"] = euclidean_distance(out1[f], out2[f])
+ dist[f]["euclidean"] = eucl
if norm_eucl:
- dist[f]["normalized_euclidean"] = normalized_euclidian_distance(out1[f], out2[f])
+ if sum_runtimes1 == 0 or sum_runtimes2 == 0:
+ dist[f]["normalized_euclidean"] = None
+ else:
+ dist[f]["normalized_euclidean"] = eucl / np.sqrt(sum_runtimes1 * sum_runtimes2)
if lateness:
dist[f]["lateness"] = lateness_distance(out1[f], out2[f])
diff --git a/example_distance.ipynb b/example_distance.ipynb
index a4984069c80bf726c1c2f50979f67a965d88cdfd..6a64b40379374a0e315bcbe2b455f829e073f2fc 100644
--- a/example_distance.ipynb
+++ b/example_distance.ipynb
@@ -37,7 +37,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
@@ -179,7 +179,7 @@
"[324 rows x 5 columns]"
]
},
- "execution_count": 3,
+ "execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
@@ -250,13 +250,15 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
+ "/home/mael/ownCloud/workspace/batmen-tools/distance_batsim_output.py:56: UserWarning: Some jobs in test/input/3jobs.csv and test/input/3jobs_w_sessions.csv don't have the same runtime (+/- 1sec). It is unusual, as runtime are normally an input of the simulation.\n",
+ " warnings.warn(f\"Some jobs in {file1} and {file2} don't have the same runtime (+/- 1sec). It is unusual, as runtime are normally an input of the simulation.\")\n",
"{\n",
" \"submission_time\": {\n",
" \"euclidean\": 0.0,\n",
@@ -270,7 +272,7 @@
" },\n",
" \"finish_time\": {\n",
" \"euclidean\": 28.284271247461902,\n",
- " \"normalized_euclidean\": 0.08000000000000002,\n",
+ " \"normalized_euclidean\": 0.4040610178208843,\n",
" \"lateness\": 0.0\n",
" }\n",
"}\n"
@@ -283,27 +285,31 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
+ "/home/mael/ownCloud/workspace/batmen-tools/distance_batsim_output.py:56: UserWarning: Some jobs in test/input/3jobs.csv and test/input/3jobs_zeros.csv don't have the same runtime (+/- 1sec). It is unusual, as runtime are normally an input of the simulation.\n",
+ " warnings.warn(f\"Some jobs in {file1} and {file2} don't have the same runtime (+/- 1sec). It is unusual, as runtime are normally an input of the simulation.\")\n",
+ "/home/mael/ownCloud/workspace/batmen-tools/distance_batsim_output.py:114: RuntimeWarning: divide by zero encountered in double_scalars\n",
+ " dist[f][\"normalized_euclidean\"] = eucl / np.sqrt(sum_runtimes1 * sum_runtimes2)\n",
"{\n",
" \"submission_time\": {\n",
" \"euclidean\": 50.0,\n",
- " \"normalized_euclidean\": null,\n",
+ " \"normalized_euclidean\": Infinity,\n",
" \"lateness\": -70.0\n",
" },\n",
" \"starting_time\": {\n",
" \"euclidean\": 50.0,\n",
- " \"normalized_euclidean\": null,\n",
+ " \"normalized_euclidean\": Infinity,\n",
" \"lateness\": -70.0\n",
" },\n",
" \"finish_time\": {\n",
" \"euclidean\": 100.0,\n",
- " \"normalized_euclidean\": null,\n",
+ " \"normalized_euclidean\": Infinity,\n",
" \"lateness\": -140.0\n",
" }\n",
"}\n"
@@ -316,7 +322,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
@@ -326,17 +332,17 @@
"{\n",
" \"submission_time\": {\n",
" \"euclidean\": 172.1394783308001,\n",
- " \"normalized_euclidean\": 2.739806304756353e-10,\n",
+ " \"normalized_euclidean\": 1.2942984329407551e-05,\n",
" \"lateness\": 2254.0\n",
" },\n",
" \"starting_time\": {\n",
" \"euclidean\": 172.1394783308001,\n",
- " \"normalized_euclidean\": 2.739806304756353e-10,\n",
+ " \"normalized_euclidean\": 1.2942984329407551e-05,\n",
" \"lateness\": 2254.0\n",
" },\n",
" \"finish_time\": {\n",
" \"euclidean\": 172.1394783308001,\n",
- " \"normalized_euclidean\": 2.3852456580198333e-10,\n",
+ " \"normalized_euclidean\": 1.2942984329407551e-05,\n",
" \"lateness\": 2254.0\n",
" }\n",
"}\n"
@@ -349,7 +355,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -359,17 +365,17 @@
"{\n",
" \"submission_time\": {\n",
" \"euclidean\": 241.15762480170517,\n",
- " \"normalized_euclidean\": 5.377222025784075e-10,\n",
+ " \"normalized_euclidean\": 1.813216587526566e-05,\n",
" \"lateness\": 3311.0\n",
" },\n",
" \"starting_time\": {\n",
" \"euclidean\": 241.15762480170517,\n",
- " \"normalized_euclidean\": 5.377222025784075e-10,\n",
+ " \"normalized_euclidean\": 1.813216587526566e-05,\n",
" \"lateness\": 3311.0\n",
" },\n",
" \"finish_time\": {\n",
" \"euclidean\": 255.14897609044016,\n",
- " \"normalized_euclidean\": 5.240304046302593e-10,\n",
+ " \"normalized_euclidean\": 1.91841479662116e-05,\n",
" \"lateness\": 3633.0\n",
" }\n",
"}\n"