def route(db, json_data_s, operation, feature_type, algorithm=None):
print("function: route")
print("operation => " + operation)
print(json_data_s)
data = json.loads(json_data_s)
init_data(data)
# train, predict, testではalgorithmに対応するモジュールをimportする
if operation in {'train','predict','test'}:
mod = __import__(algorithm+'.classifier', fromlist=['.'])
# train
if operation=='train':
return mod.__dict__[operation](db,feature_type,data)
# clear_classifier
elif operation=='clear_classifier':
return mongointerface.clear_classifier(db, feature_type, data, algorithm)
# clear_samples
elif operation=='clear_samples':
return mongointerface.clear_samples(db, feature_type, data)
# get samples / sample detail
elif operation=='get_samples':
return mongointerface.get_samples(db,feature_type,data)
elif operation=='get_sample_detail':
return mongointerface.get_sample_detail(db,feature_type,data)
# band
elif operation=='band':
return mongointerface.band(db, feature_type, data)
# disband
elif operation=='disband':
return mongointerface.disband(db, feature_type, data)
# evaluate
elif operation=='evaluate':
return mongointerface.evaluate(db, feature_type, data, algorithm)
# operations using sample
else:
if data.has_key('id'):
if (operation != "add"):
sample = db[feature_type].find_one({'_id':data['id']})
if sample:
for k,v in sample.items():
data[k] = v
# generate sample ID automatically (can be collapse if several samples add at once)
else:
data['id'] = "sample_" + "%012d" % db[feature_type].find().count()
sample = Sample(data)
if not sample.ft:
return error_json("sample must contain 'feature'")
# add
if operation == 'add':
return mongointerface.add(db,feature_type,sample)
# predict
elif operation == 'predict':
return mod.__dict__[operation](db, feature_type, sample, data)
# unknown operations (error)
return error_json('Error: unknown operation %s.' % operation)
def wrapper(db,feature_type, sample, data):
# サンプルのグループを取ってくるだけ
# Sample … (ft,_id,type,cls,group,likelihood,weight)
#print "function: predict"
clf_id = generate_clf_id(algorithm,feature_type,data)
# 予測部
collection = db["classifiers"]
try:
record = collection.find_one({'_id':clf_id})
if record == None:
return error_json("No classifier was found.")
print "load %s..."%record['clf']
clf = load_model(record['clf'])
print "done"
except:
print sys.exc_info()[0]
return error_json(sys.exc_info()[1])
if record.has_key('pca'):
print "load %s..."%record['pca']
pca = load_model(record['pca'])
print "done"
feature = sample.ft
sample.ft = pca.transform(sample.ft)
# sparseな学習をしても通常のベクトルを入力として良い
# (逆にsparseなベクトルを入れると出力のlikelihoodもsparseになる)
#if record.has_key('sparse'):
# sample.ft = lil_matrix(sample.ft).tocsr()
# algorithmに応じた処理(func)を行う
likelihood_list = func(clf,sample)
if record.has_key('pca'):
sample.ft = feature
likelihood_dict = {}
for i,l in enumerate(likelihood_list):
if not record['class_id2name'].has_key(str(i)):
# 本来，ここは通らないはず．稀にclass_id2nameに登録されていないクラスID (カテゴリ数と一致を返す．scikit-learnの仕様??要調査
continue
key = record['class_id2name'][str(i)]
likelihood_dict[key] = l
# 予測結果をデータベースへ追加
sample.likelihood[clf_id] = likelihood_dict
collections = db[feature_type]
if collections.find_one(sample._id):
collections.update_one({"_id":sample._id},{"$set":{'likelihood':sample.likelihood}})
sub_result = {'update::%s'%sample._id}
else:
sub_result = mongointerface.add(db,feature_type,sample)
result = success_json()
result['event'] = {'_id':"predict::"+clf_id+"::"+str(sample._id), 'sub_event':sub_result}
result['result'] = {'id':sample._id, 'likelihood':likelihood_dict}
if sample.ground_truth:
result['result']['ground_truth'] = sample.ground_truth
return result