aboutsummaryrefslogtreecommitdiff
path: root/backend/microservice/api
diff options
context:
space:
mode:
Diffstat (limited to 'backend/microservice/api')
-rw-r--r--backend/microservice/api/config.py2
-rw-r--r--backend/microservice/api/controller.py19
-rw-r--r--backend/microservice/api/ml_service.py2
-rw-r--r--backend/microservice/api/ml_socket.py30
-rw-r--r--backend/microservice/api/newmlservice.py28
5 files changed, 30 insertions, 51 deletions
diff --git a/backend/microservice/api/config.py b/backend/microservice/api/config.py
new file mode 100644
index 00000000..2b6fbe89
--- /dev/null
+++ b/backend/microservice/api/config.py
@@ -0,0 +1,2 @@
+api_url = "http://localhost:5283/api"
+
diff --git a/backend/microservice/api/controller.py b/backend/microservice/api/controller.py
index 4d9f8f2a..08f953a6 100644
--- a/backend/microservice/api/controller.py
+++ b/backend/microservice/api/controller.py
@@ -1,10 +1,11 @@
import flask
from flask import request, jsonify
-import ml_socket
import newmlservice
import tensorflow as tf
import pandas as pd
import json
+import requests
+import config
app = flask.Flask(__name__)
app.config["DEBUG"] = True
@@ -17,16 +18,22 @@ class train_callback(tf.keras.callbacks.Callback):
#
def on_epoch_end(self, epoch, logs=None):
print(epoch)
- ml_socket.send(epoch)
+ #ml_socket.send(epoch)
+ #file = request.files.get("file")
+ url = config.api_url + "/Model/epoch"
+ requests.post(url, epoch).text
#print('Evaluation: ', self.model.evaluate(self.x_test,self.y_test),"\n") #broj parametara zavisi od izabranih metrika loss je default
@app.route('/train', methods = ['POST'])
def train():
print("******************************TRAIN*************************************************")
- f = request.json["dataset"]
- dataset = pd.read_csv(f)
- #
- result = newmlservice.train(dataset, request.json["model"], train_callback)
+ f = request.files.get("file")
+ data = pd.read_csv(f)
+ paramsModel = json.loads(request.form["model"])
+ paramsExperiment = json.loads(request.form["experiment"])
+ paramsDataset = json.loads(request.form["dataset"])
+ #dataset, paramsModel, paramsExperiment, callback)
+ result = newmlservice.train(data, paramsModel, paramsExperiment,paramsDataset, train_callback)
print(result)
return jsonify(result)
diff --git a/backend/microservice/api/ml_service.py b/backend/microservice/api/ml_service.py
index 4d2212f7..16ee7cc6 100644
--- a/backend/microservice/api/ml_service.py
+++ b/backend/microservice/api/ml_service.py
@@ -101,7 +101,7 @@ class TrainingResultRegression:
class TrainingResult:
metrics: dict
'''
-def train(dataset, paramsModel, paramsExperiment, callback):
+def train(dataset, paramsModel, paramsExperiment, paramsDataset, callback):
problem_type = paramsModel["type"]
dataModel = pd.DataFrame()
dataExperiment = pd.DataFrame()
diff --git a/backend/microservice/api/ml_socket.py b/backend/microservice/api/ml_socket.py
deleted file mode 100644
index cab157eb..00000000
--- a/backend/microservice/api/ml_socket.py
+++ /dev/null
@@ -1,30 +0,0 @@
-import asyncio
-import websockets
-import json
-
-def get_or_create_eventloop():
- try:
- return asyncio.get_event_loop()
- except RuntimeError as ex:
- if "There is no current event loop in thread" in str(ex):
- loop = asyncio.new_event_loop()
- asyncio.set_event_loop(loop)
- return asyncio.get_event_loop()
-
-# create handler for each connection
-async def handler(websocket, path):
- #data = json.loads(await websocket.recv())
- #print(data['test'])
- msg = await websocket.recv()
- print(msg)
-
-async def start():
- start_server = websockets.serve(handler, "localhost", 5027)
- print('Websocket starting...')
- get_or_create_eventloop().run_until_complete(start_server)
- get_or_create_eventloop().run_forever()
-
-async def send(msg):
- print("WS sending message:")
- print(msg)
- await websocket.send(msg) \ No newline at end of file
diff --git a/backend/microservice/api/newmlservice.py b/backend/microservice/api/newmlservice.py
index 02ce2250..d19a4e44 100644
--- a/backend/microservice/api/newmlservice.py
+++ b/backend/microservice/api/newmlservice.py
@@ -225,28 +225,28 @@ def train(dataset, params, callback):
#
###OPTIMIZATORI
- if(params['optimizer']=='Adam'):
+ if(params['optimizer']=='adam'):
opt=tf.keras.optimizers.Adam(learning_rate=params['learningRate'])
- elif(params['optimizer']=='Adadelta'):
+ elif(params['optimizer']=='adadelta'):
opt=tf.keras.optimizers.Adadelta(learning_rate=params['learningRate'])
- elif(params['optimizer']=='Adagrad'):
+ elif(params['optimizer']=='adagrad'):
opt=tf.keras.optimizers.Adagrad(learning_rate=params['learningRate'])
- elif(params['optimizer']=='Adamax'):
+ elif(params['optimizer']=='adamax'):
opt=tf.keras.optimizers.Adamax(learning_rate=params['learningRate'])
- elif(params['optimizer']=='Nadam'):
+ elif(params['optimizer']=='nadam'):
opt=tf.keras.optimizers.Nadam(learning_rate=params['learningRate'])
- elif(params['optimizer']=='SGD'):
+ elif(params['optimizer']=='sgd'):
opt=tf.keras.optimizers.SGD(learning_rate=params['learningRate'])
- elif(params['optimizer']=='Ftrl'):
+ elif(params['optimizer']=='ftrl'):
opt=tf.keras.optimizers.Ftrl(learning_rate=params['learningRate'])
- elif(params['optimizer']=='RMSprop'):
+ elif(params['optimizer']=='rmsprop'):
opt=tf.keras.optimizers.RMSprop(learning_rate=params['learningRate'])
###REGULARIZACIJA
@@ -282,10 +282,10 @@ def train(dataset, params, callback):
#print('multi')
classifier=tf.keras.Sequential()
- classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][0],input_dim=x_train.shape[1]),kernel_regularizer=kernelreg,bias_regularizer=biasreg,activity_regularizer=activityreg)#prvi skriveni + definisanje prethodnog-ulaznog
+ classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][0],input_dim=x_train.shape[1]))#prvi skriveni + definisanje prethodnog-ulaznog
for i in range(params['hiddenLayers']-1):#ako postoji vise od jednog skrivenog sloja
#print(i)
- classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][i+1],kernel_regularizer=kernelreg,bias_regularizer=biasreg,activity_regularizer=activityreg))#i-ti skriveni sloj
+ classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][i+1]))#i-ti skriveni sloj
classifier.add(tf.keras.layers.Dense(units=5, activation=params['outputLayerActivationFunction']))#izlazni sloj
@@ -309,10 +309,10 @@ def train(dataset, params, callback):
#print('*************************************************************************binarni')
classifier=tf.keras.Sequential()
- classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][0],input_dim=x_train.shape[1],kernel_regularizer=kernelreg,bias_regularizer=biasreg,activity_regularizer=activityreg))#prvi skriveni + definisanje prethodnog-ulaznog
+ classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][0],input_dim=x_train.shape[1]))#prvi skriveni + definisanje prethodnog-ulaznog
for i in range(params['hiddenLayers']-1):#ako postoji vise od jednog skrivenog sloja
#print(i)
- classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][i+1],kernel_regularizer=kernelreg,bias_regularizer=biasreg,activity_regularizer=activityreg))#i-ti skriveni sloj
+ classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][i+1]))#i-ti skriveni sloj
classifier.add(tf.keras.layers.Dense(units=1, activation=params['outputLayerActivationFunction']))#izlazni sloj
classifier.compile(loss =params["lossFunction"] , optimizer = params['optimizer'] , metrics =params['metrics'])
@@ -334,10 +334,10 @@ def train(dataset, params, callback):
elif(problem_type=='regresioni'):
classifier=tf.keras.Sequential()
- classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][0],input_dim=x_train.shape[1],kernel_regularizer=kernelreg,bias_regularizer=biasreg,activity_regularizer=activityreg))#prvi skriveni + definisanje prethodnog-ulaznog
+ classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][0],input_dim=x_train.shape[1]))#prvi skriveni + definisanje prethodnog-ulaznog
for i in range(params['hiddenLayers']-1):#ako postoji vise od jednog skrivenog sloja
#print(i)
- classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][i+1],kernel_regularizer=kernelreg,bias_regularizer=biasreg,activity_regularizer=activityreg))#i-ti skriveni sloj
+ classifier.add(tf.keras.layers.Dense(units=params['hiddenLayerNeurons'], activation=params['hiddenLayerActivationFunctions'][i+1]))#i-ti skriveni sloj
classifier.add(tf.keras.layers.Dense(units=1))
classifier.compile(loss =params["lossFunction"] , optimizer = params['optimizer'] , metrics =params['metrics'])
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-20 09:46:07 +0000