Artifact reorganization and new results captured on the Chameleon tes…

…tbed
llpilla · Mar 2, 2023 · 2289c44 · 2289c44
1 parent 5238eea
commit 2289c44
Show file tree

Hide file tree

Showing 32 changed files with 6,177 additions and 67 deletions.
diff --git a/README.md b/README.md
diff --git a/chameleon_requirements.txt b/chameleon_requirements.txt
@@ -0,0 +1,5 @@
+numpy>=1.19.5
+matplotlib>=3.3.4
+pandas>=1.1.5
+seaborn>=0.11.2
+scipy>=1.5.4
diff --git a/...results/Analysis of execution times.ipynb → ...results/Analysis of execution times.ipynb b/...results/Analysis of execution times.ipynb → ...results/Analysis of execution times.ipynb
@@ -59,7 +59,8 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_of_timing_with_fixed_resources.csv', comment='#')\n",
-    "print('- Results with increasing numbers of tasks')\n",
+    "print('Execution time analysis')\n",
+    "print('- Results with increasing numbers of tasks (fixed resources)')\n",
     "results.head(9)"
    ]
   },
@@ -93,7 +94,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figure fig-time-fixed-resources.pdf for the results with a fixed number of resources')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -140,14 +141,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('- Result description')\n",
+    "print('- Result description: data distribution for 200 and 2000 tasks with different schedulers')\n",
     "for sched in schedulers:\n",
     "    for tasks in (200, 2000):\n",
     "        res = results[(results['Scheduler'] == sched) &\n",
     "                      (results['Tasks'] == tasks)].avg\n",
     "        print(f'Scheduler {sched} with {tasks} tasks')\n",
     "        print(res.describe())\n",
-    "        print('\\n')"
+    "        print(' ')"
    ]
   },
   {
@@ -164,6 +165,7 @@
    "outputs": [],
    "source": [
     "print('-- Checking the distribution of origin for different results')\n",
+    "print('   Kolmogorov-Smirnov test results with p-values < 0.05 mean that the results do not follow normal distributions')\n",
     "# Checking all schedulers\n",
     "np.random.seed(2022)\n",
     "for sched in schedulers:\n",
@@ -183,6 +185,8 @@
    "source": [
     "# Statistical comparison between MarCo and MarDecUn\n",
     "# Using Mann-Whitney U test as results do not follow normal distributions some times (p-values < 0.05)\n",
+    "print(' ')\n",
+    "print('-- Comparing MarCo and MarDecUn. p-values < 0.05 indicate that the algorithms perform differently')\n",
     "for tasks in range(200,2001,200):\n",
     "    marco = list(results[(results['Scheduler'] == 'MarCo') &\n",
     "                         (results['Tasks'] == tasks)].avg)\n",
@@ -214,7 +218,7 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_of_timing_with_fixed_tasks.csv', comment='#')\n",
-    "print('- Results with increasing numbers of resources')\n",
+    "print('\\n- Results with increasing numbers of resources (fixed tasks)')\n",
     "results.head(9)"
    ]
   },
@@ -248,7 +252,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figure fig-time-fixed-tasks.pdf for the results with a fixed number of tasks')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -295,14 +299,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('- Result description')\n",
+    "print('- Result description: data distribution for 20 and 80 resources with different schedulers')\n",
     "for sched in schedulers:\n",
     "    for resources in (20, 80):\n",
     "        res = results[(results['Scheduler'] == sched) &\n",
     "                      (results['Resources'] == resources)].avg\n",
     "        print(f'Scheduler {sched} with {resources} resources')\n",
     "        print(res.describe())\n",
-    "        print('\\n')"
+    "        print(' ')"
    ]
   },
   {
@@ -319,6 +323,7 @@
    "outputs": [],
    "source": [
     "print('-- Checking the distribution of origin for different results')\n",
+    "print('   Kolmogorov-Smirnov test results with p-values < 0.05 mean that the results do not follow normal distributions')\n",
     "# Checking all schedulers\n",
     "np.random.seed(2022)\n",
     "for sched in schedulers:\n",
@@ -338,13 +343,16 @@
    "source": [
     "# Statistical comparison between MarCo and MarDecUn\n",
     "# Using Mann-Whitney U test as results do not follow normal distributions some times (p-values < 0.05)\n",
+    "print(' ')\n",
+    "print('-- Comparing MarCo and MarDecUn. p-values < 0.05 indicate that the algorithms perform differently')\n",
     "for resources in range(20,81,20):\n",
     "    marco = list(results[(results['Scheduler'] == 'MarCo') &\n",
     "                         (results['Resources'] == resources)].avg)\n",
     "    mardec = list(results[(results['Scheduler'] == 'MarDec') &\n",
     "                         (results['Resources'] == resources)].avg)\n",
     "    print(f'Mann-Whitney U test - ({resources} resources).')\n",
-    "    print(stats.mannwhitneyu(marco, mardec, alternative='two-sided'))"
+    "    print(stats.mannwhitneyu(marco, mardec, alternative='two-sided'))\n",
+    "print('\\n')    "
    ]
   },
   {

diff --git a/...ed_results/Analysis of execution times.py → ...on_results/Analysis of execution times.py b/...ed_results/Analysis of execution times.py → ...on_results/Analysis of execution times.py
@@ -41,7 +41,8 @@
 
 # reads the result file
 results = pd.read_csv('results_of_timing_with_fixed_resources.csv', comment='#')
-print('- Results with increasing numbers of tasks')
+print('Execution time analysis')
+print('- Results with increasing numbers of tasks (fixed resources)')
 results.head(9)
 
 
@@ -66,7 +67,7 @@
 # In[ ]:
 
 
-print('-- Generating figures')
+print('-- Generating figure fig-time-fixed-resources.pdf for the results with a fixed number of resources')
 
 # Sets figure parameters
 plt.figure(figsize=(6,5))
@@ -105,14 +106,14 @@
 # In[ ]:
 
 
-print('- Result description')
+print('- Result description: data distribution for 200 and 2000 tasks with different schedulers')
 for sched in schedulers:
     for tasks in (200, 2000):
         res = results[(results['Scheduler'] == sched) &
                       (results['Tasks'] == tasks)].avg
         print(f'Scheduler {sched} with {tasks} tasks')
         print(res.describe())
-        print('\n')
+        print(' ')
 
 
 # ### Distributions of the results
@@ -121,6 +122,7 @@
 
 
 print('-- Checking the distribution of origin for different results')
+print('   Kolmogorov-Smirnov test results with p-values < 0.05 mean that the results do not follow normal distributions')
 # Checking all schedulers
 np.random.seed(2022)
 for sched in schedulers:
@@ -137,6 +139,8 @@
 
 # Statistical comparison between MarCo and MarDecUn
 # Using Mann-Whitney U test as results do not follow normal distributions some times (p-values < 0.05)
+print(' ')
+print('-- Comparing MarCo and MarDecUn. p-values < 0.05 indicate that the algorithms perform differently')
 for tasks in range(200,2001,200):
     marco = list(results[(results['Scheduler'] == 'MarCo') &
                          (results['Tasks'] == tasks)].avg)
@@ -155,7 +159,7 @@
 
 # reads the result file
 results = pd.read_csv('results_of_timing_with_fixed_tasks.csv', comment='#')
-print('- Results with increasing numbers of resources')
+print('\n- Results with increasing numbers of resources (fixed tasks)')
 results.head(9)
 
 
@@ -180,7 +184,7 @@
 # In[ ]:
 
 
-print('-- Generating figures')
+print('-- Generating figure fig-time-fixed-tasks.pdf for the results with a fixed number of tasks')
 
 # Sets figure parameters
 plt.figure(figsize=(6,5))
@@ -219,14 +223,14 @@
 # In[ ]:
 
 
-print('- Result description')
+print('- Result description: data distribution for 20 and 80 resources with different schedulers')
 for sched in schedulers:
     for resources in (20, 80):
         res = results[(results['Scheduler'] == sched) &
                       (results['Resources'] == resources)].avg
         print(f'Scheduler {sched} with {resources} resources')
         print(res.describe())
-        print('\n')
+        print(' ')
 
 
 # ### Distributions of the results
@@ -235,6 +239,7 @@
 
 
 print('-- Checking the distribution of origin for different results')
+print('   Kolmogorov-Smirnov test results with p-values < 0.05 mean that the results do not follow normal distributions')
 # Checking all schedulers
 np.random.seed(2022)
 for sched in schedulers:
@@ -251,13 +256,16 @@
 
 # Statistical comparison between MarCo and MarDecUn
 # Using Mann-Whitney U test as results do not follow normal distributions some times (p-values < 0.05)
+print(' ')
+print('-- Comparing MarCo and MarDecUn. p-values < 0.05 indicate that the algorithms perform differently')
 for resources in range(20,81,20):
     marco = list(results[(results['Scheduler'] == 'MarCo') &
                          (results['Resources'] == resources)].avg)
     mardec = list(results[(results['Scheduler'] == 'MarDec') &
                          (results['Resources'] == resources)].avg)
     print(f'Mann-Whitney U test - ({resources} resources).')
     print(stats.mannwhitneyu(marco, mardec, alternative='two-sided'))
+print('\n')    
 
 
 # MarCo and MarDec perform differently (p-values < 0.05).
diff --git a/stored_results/Analysis of total costs.ipynb → ...eon_results/Analysis of total costs.ipynb b/stored_results/Analysis of total costs.ipynb → ...eon_results/Analysis of total costs.ipynb
@@ -57,6 +57,7 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_with_random_costs.csv', comment='#')\n",
+    "print('Total cost analysis')\n",
     "print('- Results with random costs')\n",
     "results.head(9)"
    ]
@@ -78,7 +79,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figures fig-random-10.pdf and fig-random-100.pdf')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -145,6 +146,7 @@
    "outputs": [],
    "source": [
     "# Checking how many times other schedulers meet the performance of (MC)^2MKP\n",
+    "print('-- Checking how many times other schedulers meet the performance of (MC)2MKP')\n",
     "mc2mkp_cost = results[results['Scheduler'] == '(MC)2MKP']['Total Cost'].reset_index(drop=True)\n",
     "for scheduler in schedulers[1:]:\n",
     "    other_cost = results[results['Scheduler'] == scheduler]['Total Cost'].reset_index(drop=True)\n",
@@ -171,7 +173,7 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_with_increasing_marginal_costs.csv', comment='#')\n",
-    "print('- Results with increasing marginal costs')\n",
+    "print('\\n- Results with increasing marginal costs')\n",
     "results.head(9)"
    ]
   },
@@ -190,7 +192,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figures fig-increasing-10.pdf and fig-increasing-100.pdf')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -259,6 +261,7 @@
    "outputs": [],
    "source": [
     "# Checking how many times other schedulers meet the performance of (MC)^2MKP\n",
+    "print('-- Checking how many times other schedulers meet the performance of (MC)2MKP')\n",
     "mc2mkp_cost = results[results['Scheduler'] == '(MC)2MKP']['Total Cost'].reset_index(drop=True)\n",
     "for scheduler in schedulers[1:]:\n",
     "    other_cost = results[results['Scheduler'] == scheduler]['Total Cost'].reset_index(drop=True)\n",
@@ -285,7 +288,7 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_with_constant_marginal_costs.csv', comment='#')\n",
-    "print('- Results with constant marginal costs')\n",
+    "print('\\n- Results with constant marginal costs')\n",
     "results.head(9)"
    ]
   },
@@ -304,7 +307,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figures fig-constant-10.pdf and fig-constant-100.pdf')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -373,6 +376,7 @@
    "outputs": [],
    "source": [
     "# Checking how many times other schedulers meet the performance of (MC)^2MKP\n",
+    "print('-- Checking how many times other schedulers meet the performance of (MC)2MKP')\n",
     "mc2mkp_cost = results[results['Scheduler'] == '(MC)2MKP']['Total Cost'].reset_index(drop=True)\n",
     "for scheduler in schedulers[1:]:\n",
     "    other_cost = results[results['Scheduler'] == scheduler]['Total Cost'].reset_index(drop=True)\n",
@@ -399,7 +403,7 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_with_decreasing_marginal_costs.csv', comment='#')\n",
-    "print('- Results with decreasing marginal costs')\n",
+    "print('\\n- Results with decreasing marginal costs')\n",
     "results.head(9)"
    ]
   },
@@ -418,7 +422,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figures fig-decreasing-10.pdf, fig-decreasing-100.pdf, and fig-decreasing-100-zoom.pdf')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -520,6 +524,7 @@
    "outputs": [],
    "source": [
     "# Checking how many times other schedulers meet the performance of (MC)^2MKP\n",
+    "print('-- Checking how many times other schedulers meet the performance of (MC)2MKP')\n",
     "mc2mkp_cost = results[results['Scheduler'] == '(MC)2MKP']['Total Cost'].reset_index(drop=True)\n",
     "for scheduler in schedulers[1:]:\n",
     "    other_cost = results[results['Scheduler'] == scheduler]['Total Cost'].reset_index(drop=True)\n",
@@ -546,7 +551,7 @@
    "source": [
     "# reads the result file\n",
     "results = pd.read_csv('results_with_constant_marginal_costs_no_upper_limit.csv', comment='#')\n",
-    "print('- Results with constant marginal costs and no upper limits')\n",
+    "print('\\n- Results with constant marginal costs and no upper limits')\n",
     "results.head(9)"
    ]
   },
@@ -565,7 +570,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print('-- Generating figures')\n",
+    "print('-- Generating figures fig-constant-10-no-u.pdf and fig-constant-100-no-u.pdf')\n",
     "\n",
     "# Sets figure parameters\n",
     "plt.figure(figsize=(6,5))\n",
@@ -634,6 +639,7 @@
    "outputs": [],
    "source": [
     "# Checking how many times other schedulers meet the performance of (MC)^2MKP\n",
+    "print('-- Checking how many times other schedulers meet the performance of (MC)2MKP')\n",
     "mc2mkp_cost = results[results['Scheduler'] == '(MC)2MKP']['Total Cost'].reset_index(drop=True)\n",
     "for scheduler in ['MarIn', 'MarCo', 'MarDecUn', 'FedAvg']:\n",
     "    other_cost = results[results['Scheduler'] == scheduler]['Total Cost'].reset_index(drop=True)\n",