def test_cluster_points_two_cluster(self):
test_vector = self.create_test_data_vector()
kmeans = KMeans(test_vector, 2)
test_point0 = datapoint.DataPoint()
test_point0.add_dimension(1.1)
test_point0.add_dimension(2.1)
test_point0.add_dimension(3.1)
test_point1 = datapoint.DataPoint()
test_point1.add_dimension(3.1)
test_point1.add_dimension(1.1)
test_point1.add_dimension(2.1)
test_cluster = datapoint.DataVector()
test_cluster.add_point(test_point0)
test_cluster.add_point(test_point1)
self.assertEqual(
[1.0, 2.0, 3.0],
kmeans.cluster_points(test_cluster)[0].data_points[0].coordinates)
self.assertEqual(
[2.0, 3.0, 1.0],
kmeans.cluster_points(test_cluster)[0].data_points[1].coordinates)
self.assertEqual(
[3.0, 1.0, 2.0],
kmeans.cluster_points(test_cluster)[1].data_points[0].coordinates)
def read_data(self, filename, p, train):
positive_temp = list()
negative_temp = list()
all_temp = list()
with open(filename) as File:
reader = csv.reader(File, delimiter=',')
for row in reader:
if row[3] == '1':
point = datapoint.DataPoint(float(row[1]), float(row[2]),
int(row[3]))
positive_temp.append(point)
all_temp.append(point)
else:
if p is True:
row[3] = -1
point = datapoint.DataPoint(float(row[1]), float(row[2]),
int(row[3]))
negative_temp.append(point)
all_temp.append(point)
shuffle(all_temp)
train_temp = all_temp[:train]
test_temp = all_temp[train:]
self.positive = list(set(positive_temp) & set(train_temp))
self.positive_test = list(set(positive_temp) & set(test_temp))
self.negative = list(set(negative_temp) & set(train_temp))
self.negative_test = list(set(negative_temp) & set(test_temp))
def get_rds_metric(self, starttime, endtime, metricname, namespace,
dbclusterid, statistic, period):
datapoints = self.cloudwatch.get_metric_statistics(
Period=period,
StartTime=datetime.datetime.strptime(starttime,
"%Y-%m-%dT%H:%M:%S"),
EndTime=datetime.datetime.strptime(endtime, "%Y-%m-%dT%H:%M:%S"),
MetricName=metricname,
Namespace=namespace,
Dimensions=[{
'Name': 'DBClusterIdentifier',
'Value': dbclusterid
}],
Statistics=[statistic])['Datapoints']
datapoint_list = []
for i in datapoints:
datapoint_list.append(
dp.DataPoint(i["Timestamp"].strftime("%Y-%m-%dT%H:%M:%S"),
float(i["Average"])))
datapoint_list.sort(key=operator.attrgetter('timestamp'))
timestamp = []
value = []
for i in datapoint_list:
timestamp.append(i.timestamp)
value.append(i.value)
return timestamp, value
def create_test_data_vector():
data_vector = datapoint.DataVector()
values_list = [[1.0, 2.0, 3.0], [3.0, 1.0, 2.0], [2.0, 3.0, 1.0]]
for values in values_list:
point = datapoint.DataPoint()
for dimension_value in values:
point.add_dimension(dimension_value)
data_vector.add_point(point)
return data_vector
def test_closest_cluster_index(self):
test_vector = self.create_test_data_vector()
kmeans = KMeans(test_vector, 2)
test_point = datapoint.DataPoint()
test_point.add_dimension(1.1)
test_point.add_dimension(2.1)
test_point.add_dimension(3.1)
self.assertEqual(0,
kmeans.closest_cluster_index(test_vector, test_point))
def read_file_to_data_points(self) -> list():
with open(self.file_path, mode='r') as open_file:
csv_reader = csv.reader(open_file, delimiter=self.delimiter)
data_vector = datapoint.DataVector()
line_count = 0
for row in csv_reader:
point = datapoint.DataPoint()
for item in row:
point.coordinates.append(float(item))
data_vector.add_point(point)
line_count += 1
print(f'Processed {line_count} lines.')
return data_vector