Plot the 100 jobs.

scripts/plot-single-job.py

@@ -6,12 +6,13 @@ from pandas import DataFrame
 from pandas import Grouper
 from matplotlib import pyplot
 
-jobs = sys.argv[1:]
+jobs = [sys.argv[1]]
+prefix = sys.argv[2]
 
-print("Analyzing the jobs: " + str(jobs))
+print("Plotting the job: " + str(jobs))
 
 # Plot the timeseries
-def plot(header, row):
+def plot(prefix, header, row):
   x = { h : d for (h, d) in zip(header, row)}
   jobid = x["jobid"]
   del x["jobid"]
@@ -40,7 +41,7 @@ def plot(header, row):
     ax[i].set_ylabel(l)
 
   pyplot.xlabel("Segment number")
-  pyplot.savefig("timeseries" + jobid + ".png")
+  pyplot.savefig(prefix + "timeseries" + jobid + ".png")
 
   # Plot first 30 minutes
 
@@ -49,8 +50,9 @@ def plot(header, row):
     ax[i].set_ylabel(l)
 
   pyplot.xlabel("Segment number")
-  pyplot.savefig("timeseries" + jobid + "-30.png")
+  pyplot.savefig(prefix + "timeseries" + jobid + "-30.png")
 
+### end plotting function
 
 
 
@@ -66,4 +68,4 @@ with open('job-io-datasets/datasets/job_codings.csv') as csv_file:
       if not row[0].strip() in jobs:
         continue
       else:
-        plot(header, row)
+        plot(prefix, header, row)

scripts/plot.R

@@ -50,6 +50,14 @@ plotJobs = function(jobs){
     #print(tbl)
     md = metadata[metadata$jobid %in% jobs,]
     print(summary(md))
+
+    # print the job timeline
+    r = e[ordered, ]
+    for (row in 1:length(jobs)) {
+      prefix = sprintf("%s-%f-%.0f", level, r[row, "similarity"], row)
+      job = r[row, "jobid"]
+      system(sprintf("scripts/plot-single-job.py %s %s", job, prefix))
+    }
   }
 
 # Store the job ids in a table, each column is one algorithm