def get_all_predicts(request,rid, perm,disabled4reader,count):
print "in _predict.get_all_predicts, rid=",rid," user="******"error":"data not found"},status=404)
#use "like" _icontains to get predict and ensemble_predict
if count is None or int(count) <=0:
predictions = Document.objects.all().filter(Q(file_type__icontains="predict"), train_id=rid).order_by('-id')
else:
predictions = Document.objects.all().filter(Q(file_type__icontains="predict"), train_id=rid).order_by('-id')[:int(count)]
#serializer = PredictSerializer(predictions, many=True)
#return Response(serializer.data)
return Response(ml_serializers.pred2json(predictions))
def get_pred(rid, perm,disabled4reader):
print 'in get_pred, rid=', rid
predictions = Document.objects.all().filter(file_type__icontains="predict", id=rid)
#print "t=",type(predictions),",predictions=",predictions
# check if dataset doc accessible
train_id=predictions[0].train_id
ds_doc =_list.get_ds_doc(train_id, perm)
if not ds_doc:
return Response({"error":"data not found"},status=404)
#serializer = PredictSerializer(predictions, many=True)
#return Response(serializer.data)
return Response(ml_serializers.pred2json(predictions))
def get_predict(request, rid, hash, document, perm, disabled4reader):
print "in _predict.get_predict, hash=", hash, " user="******"predict",
train_id=rid,
filename=hash)
#slz = PredictSerializer(doc, many=True)
#return Response(slz.data)
return Response(ml_serializers.pred2json(doc))
if request.method == 'POST':
print "in POST, list=", request.POST.get('list')
hash_list = []
if hash == 'list':
hash_str = request.POST.get('list')
if hash_str:
hash_str = hash_str.lower()
hash_list = hash_str.split(',')
# get unique items
hash_list = set(hash_list)
else:
hash_list.append(hash)
host = request.POST.get('host')
host = "" if host is None else host
port = request.POST.get('port')
port = "" if port is None else port
db = request.POST.get('db')
db = "" if db is None else db
tbl = request.POST.get('tbl')
tbl = "" if tbl is None else tbl
usr = request.POST.get('usr')
usr = "" if usr is None else usr
pwd = request.POST.get('pwd')
pwd = "" if pwd is None else pwd
pred_doc = []
# forloop to predict each item
for a_hash in hash_list:
# create newdoc
newdoc = Document()
newdoc.filename = a_hash
newdoc.submitted_by = request.user.username
newdoc.acl_list = perm
newdoc.train_id = str(rid)
newdoc.file_type = "predict"
newdoc.db_host = host
newdoc.db_db = db
newdoc.db_port = port
newdoc.db_tbl = tbl
newdoc.save()
cid = newdoc.id
upload_fname = a_hash
print "before predict_hash *************** "
#ret=_result.predict_hash(document, newdoc, a_hash, tlabel="", action_type='hash_predict'
ret = predict_hash(document,
newdoc,
a_hash,
tlabel="",
action_type='hash_predict',
host=host,
port=port,
db=db,
tbl=tbl,
usr=usr,
pwd=pwd)
#ret={'rid':rid,"the_post":request.POST.get('the_post'),"username":request.user.username}
print 'in POST: ret=', ret
retdoc = Document.objects.get(id=cid)
pred_doc.append(retdoc)
return Response(ml_serializers.pred2json(pred_doc))
else:
ret = {"error": "no support"}
return Response(json.dumps(ret), status=404)
def get_post_predict(request, rid, hash, perm, disabled4reader):
print "in get_post_predict, hash=", hash, " user="******"not found!"
#ret={"error":"data model not found!"}
return Response({"error": "dataset not found"}, status=404)
if hash:
hash = hash.lower()
if request.method == 'GET':
print "In GET: rid=", rid, ",hash=", hash
# by prediction
if hash.isdigit():
doc = Document.objects.all().filter(file_type="predict",
train_id=rid,
id=hash)
else:
doc = Document.objects.all().filter(file_type="predict",
train_id=rid,
filename=hash)
print "doc=", doc
# get by md5/filename
if len(doc) > 0:
#slz = PredictSerializer(doc, many=True)
#return Response(slz.data)
return Response(ml_serializers.pred2json(doc))
return Response({"error": "prediction not found"}, status=404)
action_type = 'hash_predict'
if request.method == 'POST':
print "in POST, list=", request.POST.get('list')
verbose = request.POST.get('verbose')
verbose = "0" if verbose is None else verbose
print "verbose=", verbose
host = request.POST.get('host')
host = "" if host is None else host
port = request.POST.get('port')
port = "" if port is None else port
db = request.POST.get('db')
db = "" if db is None else db
tbl = request.POST.get('tbl')
tbl = "" if tbl is None else tbl
usr = request.POST.get('usr')
usr = "" if usr is None else usr
pwd = request.POST.get('pwd')
pwd = "" if pwd is None else pwd
model_filename = request.POST.get('model_filename')
model_filename = "" if model_filename is None else model_filename
keep_flag = request.POST.get('keep_flag')
keep_flag = "0" if keep_flag is None else keep_flag
predict_list = []
pred_doc = []
# for offline massive prediction
if hash == 'list_offline':
hash_list = request.POST.get('list')
feat_threshold = request.POST.get('feat_threshold')
pred_doc = _predict.predict_massive(document,
hash_list,
host=host,
port=port,
db=db,
tbl=tbl,
usr=usr,
pwd=pwd,
model_filename=model_filename,
keep_flag=keep_flag,
feat_threshold=feat_threshold)
return Response(pred_doc)
# for ONE hash list
elif 'list' in hash:
hash_str = request.POST.get('list')
if hash_str:
hash_str = hash_str.lower()
predict_list = hash_str.split(',')
# get unique items
predict_list = set(predict_list)
# upload raw data for prediction
elif 'raw' in hash:
form = DocumentForm(request.POST, request.FILES)
if form.is_valid():
print "in API upload predict"
newdoc = Document(docfile=request.FILES['docfile'])
newdoc.filename = request.FILES['docfile']
if document.file_type == 'ensemble': # upload binary for ensemble predict
action_type = 'ensemble_predict'
print "for ensemble predict..."
else:
action_type = 'upload_predict'
predict_list.append(newdoc.filename)
print "newdoc.filename=", newdoc.filename
else:
print "Form is invalid!"
return Response({"Error": "invalid form"}, status=404)
# upload binary for sandbox execution & predict
elif hash == 'exec':
form = DocumentForm(request.POST, request.FILES)
if form.is_valid():
print "in API upload for execution & wait:"
exe_type = request.POST.get('_file_type')
# handle by _predict; key field is "_file_type"
if exe_type is None:
print "required field not found!"
return Response({"Error": "required field not found."},
status=404)
else:
return _predict.predict(request,
rid,
cid=None,
msg_id=None,
perm=perm,
disabled4reader=disabled4reader)
else:
print "Form is wrong!!"
return Response({"Error": "invalid form"}, status=404)
else:
predict_list.append(hash)
# TBD need to check upload count here?
for p_item in predict_list:
# create newdoc
if action_type == "hash_predict":
newdoc = Document()
newdoc.filename = p_item
newdoc.submitted_by = request.user.username
newdoc.acl_list = perm
newdoc.train_id = str(rid)
if action_type == "ensemble":
newdoc.file_type = "ensemble_predict"
else:
newdoc.file_type = "predict"
newdoc.ml_n_gram = document.ml_n_gram
newdoc.ml_opts = document.ml_opts
newdoc.ml_lib = document.ml_lib
newdoc.db_host = host
newdoc.db_db = db
newdoc.db_port = port
newdoc.db_tbl = tbl
newdoc.save()
cid = newdoc.id
#upload_fname=p_item
#print "before predict_hash *************** "
ret = _predict.predict_hash(document,
newdoc,
p_item,
tlabel="",
action_type=action_type,
host=host,
port=port,
db=db,
tbl=tbl,
usr=usr,
pwd=pwd,
verbose=verbose)
#print 'in POST: ret=', ret
pred_doc.append(ret)
return Response(pred_doc)
else:
return Response({"error": "data not found"}, status=404)