def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "income_classifier"
algorithm_object = RandomForestClassifier()
algorithm_name = "random forest"
algorithm_status = "production"
algorithm_version = "v1"
algorithm_description = (
"A random forest is a meta estimator that fits a number of decision tree classifiers "
"on various sub-samples of the dataset and uses averaging to improve the predictive "
"accuracy and control over-fitting. ")
algorithm_code = inspect.getsource(RandomForestClassifier)
# add to registry
registry.add_algorithm(
endpoint_name,
algorithm_object,
algorithm_name,
algorithm_status,
algorithm_version,
algorithm_description,
algorithm_code,
)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "income_classifier"
algorithm_object = RandomForestClassifier()
algorithm_name = "random forest"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = "Piotr"
algorithm_description = "Random Forest with simple pre- and post-processing"
algorithm_code = inspect.getsource(RandomForestClassifier)
# add to registry
registry.add_algorithm(
endpoint_name,
algorithm_object,
algorithm_name,
algorithm_status,
algorithm_version,
algorithm_owner,
algorithm_description,
algorithm_code,
)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self): registry = MLRegistry() self.assertEqual(len(registry.endpoints), 0) endpoint_name = "income_classifier" algorithm_object = RandomForestClassifier() algorithm_name = "random forest" algorithm_status = "production" algorithm_version = "0.0.1" algorithm_owner = "Islambek" algorithm_description = "RF al with pre post proc" algorithm_code = inspect.getsource(RandomForestClassifier) registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name, algorithm_status, algorithm_version, algorithm_owner, algorithm_description, algorithm_code) self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "classifier"
algorithm_object = FasttextClassifier()
algorithm_name = "fasttext"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = ""
algorithm_description = "Fasttext with simple pre-processing"
algorithm_code = inspect.getsource(FasttextClassifier)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.newsite), 0)
newsite_name = "income_classifier"
algorithm_object = RandomForestClassifier()
algorithm_name = "random forest"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = "Piotr"
algorithm_description = "Random Forest with simple pre- and post-processing"
algorithm_code = inspect.getsource(RandomForestClassifier)
registry.add_algorithm(newsite_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
self.assertEqual(len(registry.newsite), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "rate_classifier"
algorithm_object = LstmClassifier()
algorithm_name = "lstm"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = "Ashish"
algorithm_description = "Lstm simple pre-preocessing"
algorithm_code = inspect.getsource(LstmClassifier)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version, algorithm_owner,
algorithm_description, algorithm_code)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "phising_classifier"
algorithm_object = PhisingClassifier()
algorithm_name = "phising svm"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = "gemastik"
algorithm_description = "Phising Detection using SVM Classifier"
algorithm_code = inspect.getsource(PhisingClassifier)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "movie_rec"
algorithm_object = ContentRec()
algorithm_name = "content-based recommendation"
algorithm_status = "production"
algorithm_version = "0.0.2"
algorithm_owner = "James"
algorithm_description = "Content-Based Recommendation based on Movie Genres"
algorithm_code = inspect.getsource(ContentRec)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "nails_segmenter"
algorithm_object = NailsSegmenter()
algorithm_name = "segmentation"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = "xyz"
algorithm_description = "-"
algorithm_code = inspect.getsource(NailsSegmenter)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "Gunosy_classifier"
algorithm_object = NaiveBayes()
algorithm_name = "Naive Bayes"
algorithm_status = "production"
algorithm_version = "1.0"
algorithm_owner = "Tung Dang"
algorithm_description = "Navie Bayes with NLP to classify news article"
algorithm_code = inspect.getsource(NaiveBayes)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "posture_detector"
algorithm_object = DarkflowDetector(
pbpath="D:\code\Yangpyong_Detecting_Model/tiny-yolo-voc-custom.pb",
metapath=
"D:\code\Yangpyong_Detecting_Model/tiny-yolo-voc-custom.meta")
algorithm_name = "darkflow"
algorithm_status = "production"
algorithm_version = "0.0.1"
algorithm_owner = "Shawn"
algorithm_description = "Object Detecting and Image Saving by Darkflow"
algorithm_code = inspect.getsource(DarkflowDetector)
# add to registry
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_version,
algorithm_owner, algorithm_description,
algorithm_code)
# there should be one endpoint available
self.assertEqual(len(registry.endpoints), 1)
def test_registry(self):
registry = MLRegistry()
self.assertEqual(len(registry.endpoints), 0)
endpoint_name = "rf-classifier-personal loan"
algorithm_object = RandomForestClassifier()
algorithm_name = "randomforrest"
algorithm_status = "production"
algorithm_code = inspect.getsource(RandomForestClassifier)
algorithm_owner = "starboy"
algorithm_description = "Random Forest with simple pre- and post-processing"
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_owner,
algorithm_description, algorithm_code)
self.assertEqual(len(registry.endpoints), 1)
# input_data={
# "Age" :25,
# "Experience":1,
# "Income":49,
# "Family":4,
# "CCAvg":1.6,
# "Mortgage":0,
# "Securities Account":1,
# "CD Amount":0,
# "Online":0,
# "Credit Card":0,
# "Zips":911,
# "ed1":1,
# "ed2":0,
# "ed3":0
# }
# alg=RandomForestClassifier()
# response=alg.predict(input_data)
# print(response)
https://docs.djangoproject.com/en/3.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.posture_detector.darkflow import DarkflowDetector
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
df = DarkflowDetector(
pbpath="D:\code\Yangpyong_Detecting_Model/tiny-yolo-voc-custom.pb",
metapath="D:\code\Yangpyong_Detecting_Model/tiny-yolo-voc-custom.meta")
# add to ML registry
registry.add_algorithm(
endpoint_name="posture_detector",
algorithm_object=df,
algorithm_name="darkflow",
algorithm_status="production",
algorithm_version="0.0.1",
owner="Shawn",
algorithm_description="Object Detecting and Image Saving by Darkflow",
algorithm_code=inspect.getsource(DarkflowDetector))
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.movie_rec.content_rec import ContentRec
from apps.ml.movie_rec.title_rec import TitleRec
try:
# create ML registry
registry = MLRegistry()
# content based recommendation
cr = ContentRec()
# add to ML registry
registry.add_algorithm(endpoint_name="movie_rec",
algorithm_object=cr,
algorithm_name="content-based recommendation",
algorithm_status="production",
algorithm_version="0.0.2",
owner="James",
algorithm_description="Content-Based Recommendation based on Movie Genres",
algorithm_code=inspect.getsource(ContentRec))
# title based recommendation
tr = TitleRec()
# add to ML registry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
from apps.ml.registry import MLRegistry
import inspect
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
try:
# create ML registry
registry = MLRegistry()
# random forest classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(
endpoint_name="income_classifier",
algorithm_object=rf,
algorithm_name="random forest",
algorithm_status="production",
algorithm_version="0.0.1a",
owner="Daycu_",
algorithm_description="description",
algorithm_code=inspect.getsource(RandomForestClassifier))
except Exception as e:
print("Exception while loading the algorithms to the registry,", str(e))
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
from apps.ml.playstyle_classifier.nnclassifier import NNClassifier
try:
registry = MLRegistry() # create ML registry
# # Random Forest classifier
# rf = RandomForestClassifier()
# # add to ML registry
# registry.add_algorithm(endpoint_name="income_classifier",
# algorithm_object=rf,
# algorithm_name="random forest",
# algorithm_status="production",
# algorithm_version="0.0.1",
# owner="Piotr",
# algorithm_description="Random Forest with simple pre- and post-processing",
# algorithm_code=inspect.getsource(RandomForestClassifier))
nn = NNClassifier()
# add to ML registry
registry.add_algorithm(
endpoint_name="chess_playstyle_classifier",
For more information on this file, see
https://docs.djangoproject.com/en/3.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifer_example.random_forest import RandomForestClassifier
try:
registry = MLRegistry() # create ML Registry
# Random FOrest Classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(
endpoint_name='income_classifier',
algorithm_object=rf,
algorithm_name='random forest',
algorithm_status='production',
algorithm_version='0.0.1',
owner='JR',
algorithm_code=inspect.getsource(RandomForestClassifier),
algorithm_description=
'Random Forest with simple pre- and post-processing')
except Exception as e:
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'ml_service.settings')
application = get_wsgi_application()
import json
import joblib
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
from apps.ml.income_classifier.etclassifier import ExtraTreeClassifier
try:
registry = MLRegistry()
rf = RandomForestClassifier()
registry.add_algorithm(endpoint_name='income_classifier',
algorithm_object=rf,
algorithm_name='random forest',
algorithm_status='production',
algorithm_version='1.0.0',
owner='admin',
description='Random Forest Income Classifier',
algorithm_code=inspect.getsource(RandomForestClassifier)
)
et = ExtraTreeClassifier()
registry.add_algorithm(endpoint_name='income_classifier',
algorithm_object= et,
algorithm_name='extratreeclassifier',
algorithm_status='production',
# file backend/server/server/wsgi.py
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(
endpoint_name="income_classifier",
algorithm_object=rf,
algorithm_name="random forest",
algorithm_status="production",
algorithm_version="0.0.1",
owner="Mohammed Samir Mahmoud",
algorithm_description=
"Random Forest with simple pre- and post-processing",
algorithm_code=inspect.getsource(RandomForestClassifier))
except Exception as e:
print("Exception while loading the algorithms to the registry,", str(e))
For more information on this file, see
https://docs.djangoproject.com/en/3.1/howto/deployment/wsgi/
"""
from apps.ml.income_classifier.random_forest import RandomForestClassifier
from apps.ml.income_classifier.extra_trees import ExtraTreesClassifier
from apps.ml.registry import MLRegistry
import inspect
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
try:
registry = MLRegistry()
rf = RandomForestClassifier()
et = ExtraTreesClassifier()
registry.add_algorithm(endpoint_name="income_classifier",
algorithm_object=rf,
algorithm_name="random forest",
algorithm_status="production",
algorithm_version="0.0.1",
owner="Josh",
algorithm_description="Random forest with simple pre- and post processing",
algorithm_code=inspect.getsource(RandomForestClassifier))
registry.add_algorithm(endpoint_name="income_classifier",
algorithm_object=et,
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
#ML Registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
try:
registry = MLRegistry()
#Random Forest classifier
rf = RandomForestClassifier()
#add to ML registry
registry.add_algorithm(
endpoint_name='income_classifier',
algorithm_object=rf,
algorithm_name='random forest',
algorithm_status='production',
algorithm_version='0.0.1',
owner='edgarbasto',
algorithm_description='Random forest income classifier.',
algorithm_code=inspect.getsource(RandomForestClassifier))
except Exception as e:
print('Exception while loading the algorithms to the registry', str(e))
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.Gunosy_classifier.NaiveBayes import NaiveBayes
try:
registry = MLRegistry()
nb = NaiveBayes()
# add to ML registry
registry.add_algorithm(
endpoint_name="Gunosy_classifier",
algorithm_object=nb,
algorithm_name="Naive Bayes",
algorithm_status="production",
algorithm_version="1.0",
owner="Tung Dang",
algorithm_description="Navie Bayes with NLP to classify news article",
algorithm_code=inspect.getsource(NaiveBayes))
except Exception as e:
print("Exception while loading the algorithm to the registry", str(e))
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
#Ml Registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.recommendation_model.rec_model import RandomForestClassifier
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(
endpoint_name="recommend_sci",
algorithm_object=rf,
algorithm_name="science_concierge",
algorithm_status="production",
algorithm_version="0.0.1",
owner="Aditya",
algorithm_description="Recommendation based on likes",
algorithm_code=inspect.getsource(RandomForestClassifier))
except Exception as e:
print("Exception while loading the algorithms to the registry,", str(e))
For more information on this file, see
https://docs.djangoproject.com/en/2.2/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.crime_classifier.random_forest import RandomForestClassifier
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(endpoint_name="crime_classifier",
algorithm_object=rf,
algorithm_name="random forest",
algorithm_status="production",
algorithm_version="0.2",
owner="dataDetective",
algorithm_description="Crime Prediction model using Boston Dataset with Accuracy 50%",
algorithm_code=inspect.getsource(RandomForestClassifier))
except Exception as e:
print("Exception while loading the algorithms to the registry,", str(e))
For more information on this file, see
https://docs.djangoproject.com/en/3.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.classifier.rf import RandomForestClassifier
registry = MLRegistry()
try:
endpoint_name = "rf-PL-hardpunish"
algorithm_object = RandomForestClassifier("Web_rf_3.joblib")
algorithm_name = "randomforrest-3"
algorithm_status = "production"
algorithm_code = inspect.getsource(RandomForestClassifier)
algorithm_owner = "starboy"
algorithm_description = "Random Forest with class weight ration 10"
# registry.isbefore(endpoint_name,algorithm_name,algorithm_status,algorithm_owner,algorithm_description)
registry.add_algorithm(endpoint_name, algorithm_object, algorithm_name,
algorithm_status, algorithm_owner,
algorithm_description, algorithm_code)
print("Success 3")
except Exception as e:
For more information on this file, see
https://docs.djangoproject.com/en/3.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.nails_segmentation.nails_seg import NailsSegmenter
try:
registry = MLRegistry() # create ML registry
# Nails Segmentation model
ns = NailsSegmenter()
# add to ML registry
registry.add_algorithm(endpoint_name="nails_segmenter",
algorithm_object=ns,
algorithm_name="segmentation",
algorithm_status="production",
algorithm_version="0.0.1",
owner="xyz",
algorithm_description="--",
algorithm_code=inspect.getsource(NailsSegmenter))
except Exception as e:
print("Exception while loading the algorithms to the registry, oui",
str(e))
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.MLP import MLP
# from apps.ml.income_classifier.extra_trees import ExtraTreesClassifier # import ExtraTrees ML algorithm
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
MLP = MLP()
# add to ML registry
registry.add_algorithm(
endpoint_name="income_classifier",
algorithm_object=MLP,
algorithm_name="Multi Layer Perceptron",
algorithm_status="production",
algorithm_version="0.0.1",
owner="Piotr",
algorithm_description=
"Random Forest with simple pre- and post-processing",
algorithm_code=inspect.getsource(MLP))
# Extra Trees classifier
# et = ExtraTreesClassifier()
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'djangoProject.settings')
application = get_wsgi_application()
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
from apps.ml.income_classifier.extra_trees import ExtraTreesClassifier
from apps.ml.income_classifier.logistic_regression import LogisticRegressionClassifier
from apps.ml.income_classifier.naive_bayes import NaiveBayesClassifier
from apps.ml.income_classifier.voting_classifier import VotingClassifier
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(endpoint_name="income_classifier",
algorithm_object=rf,
algorithm_name="random_forest",
algorithm_status="production",
algorithm_version="v1",
algorithm_description="A random forest is a meta estimator that fits a number of decision tree classifiers " \
"on various sub-samples of the dataset and uses averaging to improve the predictive " \
"accuracy and control over-fitting. ",
algorithm_code=inspect.getsource(RandomForestClassifier))
# Extra Trees classifier
et = ExtraTreesClassifier()
https://docs.djangoproject.com/en/dev/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'mysite.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.income_classifier.random_forest import RandomForestClassifier
from apps.ml.income_classifier.extra_trees import ExtraTreesClassifier # import ExtraTrees ML algorithm
from apps.ml.profile_classifier.random_forestN import RandomForestClassifierN
from apps.ml.profile_classifier.extra_treesN import ExtraTreesClassifierN # import ExtraTrees ML algorithm
try:
registry = MLRegistry() # create ML registry
# Random Forest classifier
rf = RandomForestClassifier()
# add to ML registry
registry.add_algorithm(
endpoint_name="income_classifier",
algorithm_object=rf,
algorithm_name="random forest",
algorithm_status="ab_testing",
algorithm_version="0.0.1",
owner="Bilal Fourka",
algorithm_description=
"Random Forest with simple pre- and post-processing",
algorithm_code=inspect.getsource(RandomForestClassifier))
# Extra Trees classifier
et = ExtraTreesClassifier()
For more information on this file, see
https://docs.djangoproject.com/en/2.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'server.settings')
application = get_wsgi_application()
# ML registry
import inspect
from apps.ml.registry import MLRegistry
from apps.ml.classifier.fasttext import FasttextClassifier
try:
registry = MLRegistry() # create ML registry
ft = FasttextClassifier()
# add to ML registry
registry.add_algorithm(endpoint_name="classifier",
algorithm_object=ft,
algorithm_name="fasttext",
algorithm_status="production",
algorithm_version="0.0.1",
owner="",
algorithm_description="Fasttext with simple pre-processing",
algorithm_code=inspect.getsource(FasttextClassifier))
except Exception as e:
print("Exception while loading the algorithms to the registry,", str(e))