def get_sample_detail(db, feature_type,data):
collection = db[feature_type]
query = {'_id':data['id']}
sample = collection.find_one(query)
if not sample:
return my_classifier.error_json("No samples are hit")
result = my_classifier.success_json()
result['sample'] =sample
result['event'] = {'_id': generate_event_id('get_sample_detail',feature_type, query)}
return result
def add(db, feature_type, sample):
print "function: add"
collection = db[feature_type]
if collection.find({'_id':sample._id}).count()>0:
return my_classifier.error_json("sample " + sample._id + " already exists.")
print collection.find({}).count()
print sample.__dict__
try:
collection.insert(sample.__dict__)
except:
return my_classifier.error_json(str(sys.exc_info()))
return my_classifier.success_json()
def get_samples(db, feature_type, data):
collection = db[feature_type]
query = data['selector']
samples = collection.find(query)
if samples.count() == 0:
return my_classifier.error_json("No samples are hit")
result = my_classifier.success_json()
result['samples'] = []
for s in samples:
result['samples'].append(s['_id'])
result['event'] = {'_id': generate_event_id('get_samples',feature_type, query)}
return result
def clear_samples(db,feature_type,data):
print "in clear_samples"
#query = {}
query = data['selector']
collection = db[feature_type]
data_count = collection.find(query).count()
if data_count==0:
return my_classifier.error_json("No samples are hit.")
try:
collection.remove(query)
except:
return my_classifier.error_json(sys.exc_info()[1])
result = my_classifier.success_json()
result['event'] = {'_id': generate_event_id('clear_samples',feature_type,json.dumps(query))}
return result
def disband(db,feature_type,data):
print "function: disband"
if not data.has_key('group'):
return my_classifier.error_json("'group' must be set.")
group_name = data['group']
collections = db[feature_type]
samples = collections.find({'group':{'$all':[group_name]}})
if samples.count() == 0:
return my_classifier.error_json("ERROR: no samples are hit.")
for s in samples:
groups = s['group']
while group_name in groups:
groups.remove(group_name)
_id = s['_id']
collections.update({"_id":_id},{"$set":{'group':groups}})
result = my_classifier.success_json()
result['event'] = {'_id':generate_event_id('disband',feature_type,group_name)}
return result
def clear_classifier(db, feature_type, data, algorithm):
print "function: " + __name__
if algorithm==None:
return my_classifier.error_json('algorithm must be designated')
clf_id = my_classifier.generate_clf_id(algorithm,feature_type,data)
query = {'_id':clf_id}
collection = db['classifiers']
data_count = collection.find(query).count()
if data_count==0:
return my_classifier.error_json("No classifiers are hit.")
try:
db['classifiers'].remove(query)
except:
return my_classifier.error_json(sys.exc_info()[1])
result = my_classifier.success_json()
result['event'] = {'_id': generate_event_id('clear_classifier', feature_type, clf_id )}
return result
def band(db,feature_type,data):
print "function: band"
if not data.has_key('group'):
return my_classifier.error_json("'group' must be set.")
group_name = data['group']
selector = data['selector']
collections = db[feature_type]
samples = collections.find(selector)
#print samples
if samples.count() == 0:
return my_classifier.error_json("ERROR: no samples are hit.")
for s in samples:
groups = s['group']
if not group_name in groups:
groups = ensure_list(groups)
groups.append(group_name)
_id = s['_id']
collections.update_one({"_id":_id},{"$set":{'group':groups}})
result = my_classifier.success_json()
result['event'] = {'_id':generate_event_id('band',feature_type,[group_name,json.dumps(selector)])}
return result
def test():
print 'test: %s' % __name__
return my_classifier.success_json()
def test():
print 'test: %s' % __name__
return my_classifier.success_json()
def evaluate(db,feature_type, data,algorithm):
#print "function: evaluate"
# class_name2idのために識別器のデータを呼ぶ
clf_id = my_classifier.generate_clf_id(algorithm,feature_type,data)
#print "clf_id: " + clf_id
try:
record = db["classifiers"].find_one({'_id':clf_id})
if record == None:
return my_classifier.error_json("No classifier was found.")
except:
return my_classifier.error_json(sys.exc_info()[1])
#print record
name2id = record['class_name2id']
y = []
y_pred = []
weights = []
selector = data['selector']
selector['likelihood.'+clf_id] = {"$exists":True}
print selector
samples = get_training_samples(db,feature_type,False,selector)
for s in samples:
if not s['likelihood'].has_key(clf_id):
continue
y.append(name2id[s['ground_truth']])
likelihood = dict(s['likelihood'][clf_id])
pred_name = max([(v,k) for k,v in likelihood.items()])[1]
y_pred.append(name2id[pred_name])
if s.has_key('weight'):
weights.append(float(s['weight']))
else:
weights.append(1.0)
if not y:
return my_classifier.error_json("ERROR: samples are not found.")
result = my_classifier.success_json()
result['event'] = {'_id':generate_event_id('evaluate', feature_type, clf_id)}
id2name = record['class_id2name']
result['class_list'] = [id2name[k] for k in sorted(id2name.keys())]
# confution_matrix
cm = confusion_matrix(y, y_pred)
cm_json_searizable = []
for line in cm:
cm_json_searizable.append(line.tolist())
# id2name = record['class_id2name']
result['confusion_matrix'] = json.dumps(cm_json_searizable)
#print precision_score(y,y_pred,sample_weight=weights)
#print precision_score(y,y_pred)
#print weights
result['precision_score'] = precision_score(y,y_pred,average=None).tolist()#,sample_weight=weights)
result['recall_score'] = recall_score(y,y_pred,average=None).tolist()#,sample_weight=weights)
result['f1_score'] = f1_score(y,y_pred,average=None).tolist()#,sample_weight=weights)
return result
