def local_prediction(deepnets, test_reader, output, args, exclude=None):
"""Get local deepnet and issue prediction
"""
kwargs = {"full": True}
if args.operating_point_:
kwargs.update({"operating_point": args.operating_point_})
# Only one deepnet at present
local_deepnet = Deepnet(deepnets[0], api=args.retrieve_api_)
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_deepnet.predict(input_data_dict, **kwargs)
write_prediction(prediction_info, output, args.prediction_info,
input_data, exclude)
def local_prediction(deepnets, test_reader, output, args,
exclude=None):
"""Get local deepnet and issue prediction
"""
# Only one deepnet at present
local_deepnet = Deepnet(deepnets[0],
api=args.retrieve_api_)
test_set_header = test_reader.has_headers()
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_deepnet.predict(
input_data_dict, by_name=test_set_header)
write_prediction(prediction_info, output,
args.prediction_info, input_data, exclude)
def local_prediction(deepnets, test_reader, output, args,
exclude=None):
"""Get local deepnet and issue prediction
"""
kwargs = {"full": True}
if args.operating_point_:
kwargs.update({"operating_point": args.operating_point_})
# Only one deepnet at present
local_deepnet = Deepnet(deepnets[0],
api=args.retrieve_api_)
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_deepnet.predict(
input_data_dict, **kwargs)
write_prediction(prediction_info, output,
args.prediction_info, input_data, exclude)
def createRacingModel(dataset, type=util.ML_BIGML):
if type == util.ML_BIGML:
api = BigML(config.BIGML_USER, config.BIGML_API_KEY)
print("Creating model...")
args = {"name": "Racing Model", "objective_field": "Movement"}
model = api.create_deepnet(dataset, args)
api.ok(model)
resource = model["resource"]
# Saves model id to a file
file = open("saved_models.txt", "a+")
file.write(f"\nracing-{resource}")
file.close()
# Creates LOCAL model
model = Deepnet(resource, api)
return model
def i_create_local_deepnet_from_file(step, export_file):
world.local_deepnet = Deepnet(res_filename(export_file))
def i_create_local_deepnet_from_file(step, export_file):
world.local_deepnet = Deepnet(res_filename(export_file),
api=BigML("wrong-user", "wrong-api-key"))
import os.path
import json
import csv
import urllib.request
from urllib.parse import urlparse
from bs4 import BeautifulSoup
from bs4 import Comment
try:
from urllib.parse import urlparse
except ImportError:
import urlparse
BIGML_USERNAME = '******'
BIGML_API_KEY = 'd0ad30e1fa62ba453db353e2e6680866c0393cfb'
BIGML_STORAGE = 'D://Empty'
api = BigML(BIGML_USERNAME, BIGML_API_KEY, storage=BIGML_STORAGE)
deepnet = Deepnet('deepnet/5b867d8c8bf7d57a4302f787', api=api)
con = MongoClient('localhost', 27017)
db = con['Url_data']
collection=db['getJobs']
flag=0
list_=[]
rep_val=''
store_first_keyword=''
def insert_text_in_textBox():
try:
if(len(browser.find_elements_by_xpath("//input[@type='text']"))>=1):
text_box = browser.find_elements_by_xpath("//input[@type='text']")
text_box[0].send_keys("jobs")
except:
pass
def get_all_jobs(url,original_url,valid_urls):
def i_create_a_local_deepnet(step):
world.local_model = Deepnet(world.deepnet['resource'])
if hasattr(world, "local_ensemble"):
world.local_ensemble = None
# Requires BigML Python bindings
#
# Install via: pip install bigml
#
# or clone it:
# git clone https://github.com/bigmlcom/python.git
from bigml.deepnet import Deepnet
from bigml.api import BigML
# Downloads and generates a local version of the DEEPNET,
# if it hasn't been downloaded previously.
deepnet = Deepnet('deepnet/5c59efee00a1e50a6c0039ba',
api=BigML("rshelton",
"adabd734dd2a2af5cb4e49176f0eb472cfa8ce5a",
domain="bigml.io"))
# To make predictions fill the desired input_data in next line.
input_data = {
"EMERG_VEH": "yes",
"Division": "d42",
"DISABILITY": "yes",
"ACCLASS": "Non-Fatal Injury",
"RDSFCOND": "Dry",
"INVTYPE": "Driver",
"IMPACTYPE": "Turning Movement",
"ACCLOC": "At Intersection",
"LIGHT": "Daylight",
"VISIBILITY": "Clear",
"Ward_Name": "scarborough",
"INJURY": "None",
"INVAGE": "unknown",
"ALCOHOL": "yes",
"REDLIGHT": "yes",
def modelFromID(resource, type=util.ML_BIGML):
# Creates a local model based on a model id
if type == util.ML_BIGML:
api = BigML(config.BIGML_USER, config.BIGML_API_KEY)
model = Deepnet(resource, api)
return model
from flask import Flask, jsonify, request
from flask_cors import CORS
from predictor import Predictor
import numpy as np
from bigml.deepnet import Deepnet
from bigml.api import BigML
# Downloads and generates a local version of the DEEPNET,
# if it hasn't been downloaded previously.
deepnet = Deepnet('deepnet/5dba7bb15a21395ce200035a',
api=BigML("medias",
"1bbcaec3bdce36230a99d91fbf5597d0c5ea4fc4",
domain="bigml.io"))
pp = Predictor()
pp.load_pickle()
app = Flask(__name__)
CORS(app)
@app.route("/",methods=["GET","POST"])
def give():
return jsonify({"status":"OK","message":"Hello"})
@app.route("/api/predict",methods=['POST'])
def predict():
#Get Request Data
content = request.json
age = content['Age'] #numeric
km = content['KM'] #numerci
fueltype = content['FuelType'] #string
if fueltype=='CNG':
fueltype = 0
elif fueltype=='Diesel':
fueltype = 1
