bin/test/TrialComparisonFakeDataGen.py

   1
   2
   3
   4
   5 import csv, time,random, sys
   6 cols = ['studyYear', 'studyDbId', 'studyName', 'studyDesign', 'locationDbId', 'locationName', 'germplasmDbId', 'germplasmName', 'germplasmSynonyms', 'observationLevel', 'observationUnitDbId', 'observationUnitName', 'replicate', 'blockNumber', 'plotNumber', 'Variable']
   7 study_count = 5
   8 accession_count = 50
   9 value_range = (0,100)
  10 value_wobble = 30
  11
  12 def make_row(study,accession,base_value):
  13     studyYear = "2038"
  14     studyDbId = str(study)
  15     studyName = str(random.random()*1000000)#"Study"+str(study)
  16     studyDesign = "chaos"
  17     locationDbId = "00800"
  18     locationName = "The Moon"
  19     germplasmDbId = accession
  20     germplasmName = "AN"+str(accession)
  21     germplasmSynonyms = ''
  22     observationLevel = "plot"
  23     observationUnitDbId = "MoonPlanter"+str(accession)
  24     observationUnitName = "MoonPlanter"+str(accession)
  25     replicate = "1"
  26     blockNumber = "1"
  27     plotNumber = str(accession)
  28     variable = str(max(0,base_value + random.randint(-value_wobble,value_wobble)))
  29     return [studyYear,studyDbId,studyName,studyDesign,locationDbId,locationName,germplasmDbId,germplasmName,germplasmSynonyms,observationLevel,observationUnitDbId,observationUnitName,replicate,blockNumber,plotNumber,variable]
  30
  31 # with open("generated.csv","w") as outfile:
  32 writer = csv.writer(sys.stdout,delimiter=',',quotechar='"',quoting=csv.QUOTE_ALL)
  33 writer.writerow(cols)
  34 row_list = []
  35 for accession in range(accession_count):
  36     base_value = random.randint(*value_range)
  37     for study in range(study_count):
  38         row_list.append(make_row(study,accession,base_value))
  39 row_list.sort()
  40 writer.writerows(row_list)