def wait_jobdone(self, jobId):
jobStatus = CasJobs.getJobStatus(jobId)['Status']
while jobStatus < 2:
time.sleep(10)
jobStatus = CasJobs.getJobStatus(jobId)['Status']
if jobStatus in [2, 3, 4]:
raise RuntimeError("Job is canceled or failed")
print("Job {} is finished".format(jobId))
return jobStatus
def download_query(self,
query,
table_name,
save_to='data',
context='MyDB'):
"""Perform a query based on the context given"""
if context != 'MyDB':
jobid = cj.submitJob(query, context=context)
cj.waitForJob(jobid, verbose=True)
job_status = cj.getJobStatus(jobid)
if job_status['Success'] != 5:
raise CasJobsError(
'Error Performing the query, {}'.format(job_status))
# Now the results are safely saved in myDB
# You can go ahead and download by using a session
self.download_csv(table_name)
self._download_from_scidrive(table_name, save_to)
def test_CasJobs_getJobStatus(self):
jobId = CasJobs.submitJob(sql=CasJobs_TestQuery,
context=CasJobs_TestDatabase)
jobDescription = CasJobs.getJobStatus(jobId)
self.assertEqual(jobDescription["JobID"], jobId)
# In[ ]: # drop or delete table in MyDB database context df = CasJobs.executeQuery(sql="DROP TABLE " + CasJobs_TestTableName1, context="MyDB", format="pandas") print(df) # In[ ]: #get job status jobId = CasJobs.submitJob(sql=CasJobs_TestQuery, context=CasJobs_TestDatabase) jobDescription = CasJobs.getJobStatus(jobId) print(jobId) print(jobDescription) # In[ ]: #cancel a job jobId = CasJobs.submitJob(sql=CasJobs_TestQuery, context=CasJobs_TestDatabase) jobDescription = CasJobs.cancelJob(jobId=jobId) print(jobId) print(jobDescription) # In[ ]:
verylongquery += 'u, g, r, i, z, err_u, err_g, err_r, err_i, err_z, petror90_r \n'
verylongquery += 'into mydb.' + bigtablename + '\n'
verylongquery += 'from galaxy\n'
verylongquery += 'where clean = 1'
print('Submitting query:\n', verylongquery)
print('\n')
thisjobid = CasJobs.submitJob(sql=verylongquery, context=this_context)
print('Job submitted with jobId = ', thisjobid)
print('\n')
waited = CasJobs.waitForJob(
jobId=thisjobid) # waited is a dummy variable; just print wait msg
jobDescription = CasJobs.getJobStatus(thisjobid)
print('\n')
print('Information about the job:')
#pprint(jobDescription)
jobDescriber(jobDescription)
# ## Thank you!
#
# Thanks for reviewing this SciServer example notebook. You can use this notebook as a template to develop your own notebooks, but please do so in a copy rather than in the original example notebook.
# As you begin to use any of our SciServer modules in your own notebooks, consult the SciServer scripting documentation at http://www.sciserver.org/docs/sciscript-python/SciServer.html (link opens in a new window).
#
# If you have questions, please email the SciServer helpdesk at [email protected].
# In[ ]:
def do(self,
user='******',
password='******',
search=1,
path_to_model='YSE_DNN_photoZ_model_315.hdf5',
debug=True):
"""
Predicts photometric redshifts from RA and DEC points in SDSS
An outline of the algorithem is:
first pull from SDSS u,g,r,i,z magnitudes from SDSS;
should be able to handle a list/array of RA and DEC
place u,g,r,i,z into a vector, append the derived information into the data array
predict the information from the model
return the predictions in the same order to the user
inputs:
Ra: list or array of len N, right ascensions of target galaxies in decimal degrees
Dec: list or array of len N, declination of target galaxies in decimal degrees
search: float, arcmin tolerance to search for the object in SDSS Catalogue
path_to_model: str, filepath to saved model for prediction
Returns:
predictions: array of len N, photometric redshift of input galaxy
"""
try:
nowdate = datetime.datetime.utcnow() - datetime.timedelta(1)
from django.db.models import Q #HAS To Remain Here, I dunno why
print('Entered the photo_z cron')
#save time b/c the other cron jobs print a time for completion
transients = Transient.objects.filter(
Q(host__isnull=False) & Q(host__photo_z__isnull=True))
my_index = np.array(
range(0, len(transients))
) #dummy index used in DF, then used to create a mapping from matched galaxies back to these hosts
transient_dictionary = dict(zip(my_index, transients))
RA = []
DEC = []
for i, T in enumerate(transients): #get rid of fake entries
if T.host.ra and T.host.dec:
RA.append(T.host.ra)
DEC.append(T.host.dec)
else:
transient_dictionary.pop(i)
DF_pre = pd.DataFrame()
DF_pre['myindex'] = list(transient_dictionary.keys())
DF_pre['RA'] = RA
DF_pre['DEC'] = DEC
SciServer.Authentication.login(user, password)
try:
SciServer.SkyQuery.dropTable('SDSSTable1', datasetName='MyDB')
SciServer.SkyQuery.dropTable('SDSSTable2', datasetName='MyDB')
except Exception as e:
print('tables are not in CAS MyDB, continuing')
print(
'if system says table is already in DB, contact Andrew Engel'
)
SciServer.CasJobs.uploadPandasDataFrameToTable(DF_pre,
'SDSSTable1',
context='MyDB')
myquery = 'SELECT s.myindex, p.z, p.zErr, p.nnAvgZ '
myquery += 'INTO MyDB.SDSSTable2 '
myquery += 'FROM MyDB.SDSSTable1 s '
myquery += 'CROSS APPLY dbo.fGetNearestObjEq(s.RA,s.DEC,1.0/60.0) AS nb '
myquery += 'INNER JOIN Photoz p ON p.objID = nb.objID'
jobID = CasJobs.submitJob(sql=myquery, context="DR16")
waited = SciServer.CasJobs.waitForJob(jobId=jobID)
jobDescription = CasJobs.getJobStatus(jobID)
jobDescriber(jobDescription)
PhotoDF = SciServer.SkyQuery.getTable('SDSSTable2',
datasetName='MyDB',
top=10)
#change this
PhotoDF.drop_duplicates(
subset='#myindex',
inplace=True) #neccessary to patch some bugs
PhotoDF.dropna(inplace=True)
whats_left = PhotoDF['#myindex'].values
point_estimates = PhotoDF['z'].values
error = PhotoDF['zErr'].values
other_z = PhotoDF['nnAvgZ']
point_estimates[error < -9998] = other_z[
error <
-9998] #if there is a bad error, then authors write this is more effective
for i, value in enumerate(whats_left):
T = transient_dictionary[value]
T.host.photo_z = point_estimates[i]
T.host.photo_z_err = error[i]
#T.host.photo_z_posterior = posterior[i] #Gautham suggested we add it to the host model
T.host.photo_z_source = 'SDSS'
T.host.save(
) #takes a long time and then my query needs to be reset which is also a long time
print('time taken with upload:',
datetime.datetime.utcnow() - nowdate)
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
print("""Photo-z cron failed with error %s at line number %s""" %
(e, exc_tb.tb_lineno))
#html_msg = """Photo-z cron failed with error %s at line number %s"""%(e,exc_tb.tb_lineno)
#sendemail(from_addr, user.email, subject, html_msg,
# djangoSettings.SMTP_LOGIN, djangoSettings.SMTP_PASSWORD, smtpserver)
#IDK = YSE() #why is this suddenly neccessary???
#IDK.do()
