diff --git a/distance_batsim_output.py b/distance_batsim_output.py
index 8b8e0865fe26cb492f1f0121c670183112d37b17..30aaa2b764b84621ab84c5a8489e4adcbcf710a1 100755
--- a/distance_batsim_output.py
+++ b/distance_batsim_output.py
@@ -77,12 +77,6 @@ def lateness_distance(s1, s2):
return float(np.sum([y-x for x, y in zip(s1, s2)]))
-def l2_norm(s):
- """Return the l2 norm of the series s"""
-
- return float( np.sqrt(np.sum([x * x for x in s])) )
-
-
def distances(file1, file2, euclidean=True, lateness=False, norm_eucl=False,
field=["finish_time"]):
"""Computes and returns a set of distances between two batsim outputs, if
diff --git a/example_distance.ipynb b/example_distance.ipynb
index 6a64b40379374a0e315bcbe2b455f829e073f2fc..ed2e2f47dad8e53db95cd4c9a37a4d08a7ce16cc 100644
--- a/example_distance.ipynb
+++ b/example_distance.ipynb
@@ -285,7 +285,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -294,22 +294,20 @@
"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\": Infinity,\n",
+ " \"normalized_euclidean\": null,\n",
" \"lateness\": -70.0\n",
" },\n",
" \"starting_time\": {\n",
" \"euclidean\": 50.0,\n",
- " \"normalized_euclidean\": Infinity,\n",
+ " \"normalized_euclidean\": null,\n",
" \"lateness\": -70.0\n",
" },\n",
" \"finish_time\": {\n",
" \"euclidean\": 100.0,\n",
- " \"normalized_euclidean\": Infinity,\n",
+ " \"normalized_euclidean\": null,\n",
" \"lateness\": -140.0\n",
" }\n",
"}\n"
diff --git a/test/test_distance.py b/test/test_distance.py
index 536faec44abe55a0bbff11e7da32c3acd5e8856c..0be21d0cba34cedd1bbcc4c2a773813c3b32cd0d 100644
--- a/test/test_distance.py
+++ b/test/test_distance.py
@@ -19,17 +19,6 @@ def test_lateness_distance():
assert lateness_distance(s1, s2) == - lateness_distance(s2, s1) == 6
assert lateness_distance(empty, empty) == 0
-def test_l2_norm():
- assert l2_norm(empty) == 0
- assert l2_norm(s1) == np.sqrt(10*10 + 14*14 + 500*500)
- assert l2_norm(u) == 2
- assert l2_norm(v) == 1
-
-def test_normalized_euclidean_distance():
- assert normalized_euclidian_distance(u, v) == .5
-
-
-
####### Integration tests #######
three_jobs = "test/input/3jobs.csv"
@@ -40,7 +29,8 @@ mc_10days_a60 = "test/input/mc_10days_a60_jobs.csv"
def test_cleaning():
# Clean session info:
- distances(three_jobs_w_session, three_jobs_zero)
+ with pytest.warns(UserWarning):
+ distances(three_jobs_w_session, three_jobs_zero)
# Clean unsuccessful jobs:
with pytest.warns(UserWarning):
@@ -63,24 +53,26 @@ def test_some_distances():
euclidean=False, lateness=True, field=fin) == 0
# Eucl distance
- assert distances(three_jobs, three_jobs_zero, field=sub) == 50
- assert distances(three_jobs_zero, three_jobs, field=start) == 50
- assert distances(three_jobs, three_jobs_zero, field=fin) == 100
+ with pytest.warns(UserWarning):
+ assert distances(three_jobs, three_jobs_zero, field=sub) == 50
+ assert distances(three_jobs_zero, three_jobs, field=start) == 50
+ assert distances(three_jobs, three_jobs_zero, field=fin) == 100
- assert distances(three_jobs, three_jobs_w_session, field=sub) == 0
- assert distances(three_jobs, three_jobs_w_session, field=start) == 0
- assert distances(three_jobs, three_jobs_w_session, field=fin) == 20 * np.sqrt(2)
+ assert distances(three_jobs, three_jobs_w_session, field=sub) == 0
+ assert distances(three_jobs, three_jobs_w_session, field=start) == 0
+ assert distances(three_jobs, three_jobs_w_session, field=fin) == 20 * np.sqrt(2)
# Normalized eucl distance
- assert distances(three_jobs, three_jobs_zero,
- euclidean=False, norm_eucl=True, field=sub) == None
- assert distances(three_jobs, three_jobs_w_session,
- euclidean=False, norm_eucl=True, field=sub) == 0
-
- norm_dis_A_B = distances(three_jobs, three_jobs_w_session,
- euclidean=False, norm_eucl=True, field=fin)
- norm_dis_B_A = distances(three_jobs, three_jobs_w_session,
+ with pytest.warns(UserWarning):
+ assert distances(three_jobs, three_jobs_zero,
+ euclidean=False, norm_eucl=True, field=sub) == None
+ assert distances(three_jobs, three_jobs_w_session,
+ euclidean=False, norm_eucl=True, field=sub) == 0
+
+ norm_dis_A_B = distances(three_jobs, three_jobs_w_session,
+ euclidean=False, norm_eucl=True, field=fin)
+ norm_dis_B_A = distances(three_jobs, three_jobs_w_session,
euclidean=False, norm_eucl=True, field=fin)
- expected = 800 / (100*100)
+ expected = 20 * np.sqrt(2) / 70 # eucl / sum_runtime
assert norm_dis_A_B == norm_dis_B_A
assert norm_dis_B_A - expected < 1e-8