class RiverML:
# fraud detection model
model = compose.Pipeline(preprocessing.StandardScaler(),
linear_model.LogisticRegression())
# ROCAUC metric to score the model as it trains
metric = metrics.ROCAUC()
def __init__(self,
my_id=1,
bootstrap_servers='',
list_of_partitions=[],
request_topic='',
inference_topic='',
group_id='my_grp'):
""" Constructor
:type interval: int
:param interval: Check interval, in seconds
"""
self.model = compose.Pipeline(
preprocessing.MinMaxScaler(), anomaly.HalfSpaceTrees(
seed=42)) # tree.HoeffdingTreeClassifier(max_depth=10)
self.metric = metrics.ROCAUC() # metrics.Accuracy() #
self.my_id = my_id
self.t = request_topic
self.result_t = inference_topic
self.my_grp_id = group_id
self.result_t_p = 8
self.bootstrap_servers = bootstrap_servers
# self.list_of_partitions = list_of_partitions
self.tls = []
x = 0
for i in list_of_partitions:
self.tls.insert(x, TopicPartition(self.t, i))
x = x + 1
#self.tls=list_of_partitions
print(self.tls)
conf = {
'bootstrap.servers': bootstrap_servers,
'sasl.mechanism': 'PLAIN',
'security.protocol': 'SASL_SSL',
'ssl.ca.location': '/tmp/cacert.pem',
'sasl.username': '******',
'sasl.password':
'******',
# 'sasl.username': '******',
# 'sasl.password': '******',
# 'key.serializer': StringSerializer('utf_8'),
# 'value.serializer': StringSerializer('utf_8'),
'client.id': 'test-sw-1'
}
self.producer = Producer(conf)
conf = {
'bootstrap.servers': bootstrap_servers,
'sasl.mechanism': 'PLAIN',
'security.protocol': 'SASL_SSL',
'sasl.username': '******',
'sasl.password':
'******',
'ssl.ca.location': '/tmp/cacert.pem',
'group.id': group_id,
'auto.offset.reset': 'latest'
}
self.consumer = consumer = Consumer(conf)
self.consumer.assign(self.tls)
from river import compose
from river import preprocessing
from river import linear_model
from river import metrics
from river import datasets
from river import optim
optimizer = optim.SGD(0.1)
model = compose.Pipeline(preprocessing.StandardScaler(),
linear_model.LogisticRegression(optimizer))
metric = metrics.ROCAUC()
precision = metrics.Precision()
for x, y in datasets.Phishing():
y_pred = model.predict_proba_one(x)
model.learn_one(x, y)
metric.update(y, y_pred)
precision.update(y, y_pred)
print(metric)
print(precision)