def __init__(self, query):
#Importing all dicts from conf file
conf = shelve.open('conf')
self.relations = conf['relations']
self.attr_relations = conf['attr_relations']
self.replace_attr = conf['replace_attr']
self.syn_attr = conf['syn_attr']
self.syn_common = conf['syn_common']
self.common_attr = conf['common_attr']
self.relations_attr = conf['relations_attr']
self.replace_contractions = conf['replace_contractions']
self.replace_operators = conf['replace_operators']
self.operator_list = conf['operator_list']
self.ant_operators = conf['ant_operators']
self.syn_aggregate = conf['syn_aggregate']
self.aggregate_list = conf['aggregate_list']
self.proper_nouns = conf['proper_nouns']
#Original Query
self.original_query = query
self.lowercase_query = self.original_query.lower()
#Stop words list
init = Initialization()
self.stop_words = init.initializeStopWords()
def __init__ (self, query):
#Importing all dicts from conf file
conf = shelve.open('conf')
self.relations = conf['relations']
self.attr_relations = conf['attr_relations']
self.replace_attr = conf['replace_attr']
self.syn_attr = conf['syn_attr']
self.syn_common = conf['syn_common']
self.common_attr = conf['common_attr']
self.relations_attr = conf['relations_attr']
self.replace_contractions = conf['replace_contractions']
self.replace_operators = conf['replace_operators']
self.operator_list = conf['operator_list']
self.ant_operators = conf['ant_operators']
self.syn_aggregate = conf['syn_aggregate']
self.aggregate_list = conf['aggregate_list']
self.proper_nouns = conf['proper_nouns']
#Original Query
self.original_query = query
self.lowercase_query = self.original_query.lower()
#Stop words list
init = Initialization()
self.stop_words = init.initializeStopWords()
def configure(self):
with open('Configurations/config.json') as base_json_file:
base_data = json.load(base_json_file)
config_file = base_data['default']
for elem in base_data['aircraft']:
aircraft_contains = elem['aircraft_contains']
file = elem['file']
if aircraft_contains in str(self._aircraft):
config_file = file
self._configure_additional_simvars(base_data)
if 'automatic_layer_revert' in base_data:
GlobalStorage().active_layer_changer.enable_layer_revert_timer(
base_data['automatic_layer_revert'])
config_file = 'Configurations/' + config_file # Add folder prefix
print("Loading config file:", config_file)
with open(config_file) as json_file:
data = json.load(json_file)
self._configure_encoders(data['encoders'])
self._configure_buttons(data['buttons'])
self._configure_faders(data['faders'])
self._configure_triggers(data['triggers'])
Initialization(data.get('initialization', None))
from flask import Flask, request, abort
import requests
import re
import random
import configparser
import urllib3
from bs4 import BeautifulSoup
from initialization import Initialization
'''import linebot sdk'''
from linebot import (LineBotApi, WebhookHandler)
from linebot.exceptions import (InvalidSignatureError)
from linebot.models import *
urllib3.disable_warnings()
# initial Line Api Handler and Webhook.
_initialization = Initialization()
handler = _initialization.handler
line_bot_api = _initialization.line_bot_api
website_config = configparser.ConfigParser()
website_config.read("CrawlingSites.ini")
websites = website_config['TARGET_URL']
ReStart_Counter = 0
app = Flask(__name__)
"""
Define Fixed Reply
"""
REPLY_OK = "OK"
REPLY_FAIL = "SYSTEM_FAIL"
def __init__(self, layers, actvtn_types,
initn_weight_type, initn_bias_type,
cost_type,
reg_type, reg_lambda,
traing_type, epochs, batch_size, learng_eta,
groups,
traing_x_list, traing_y_list, evaltn_x_list, evaltn_y_list,
input_log,
traing_qtts_log,
traing_acts_log, traing_cost_log, evaltn_cost_log):
''' NN features '''
self.layers = layers
self.actvtn_types = actvtn_types
self.initn_weight_type = initn_weight_type
self.initn_bias_type = initn_bias_type
self.cost_type = cost_type
self.reg_type = reg_type
self.reg_lambda = reg_lambda
''' groups '''
self.groups = groups
''' training features '''
self.traing_type = traing_type
self.epochs = epochs
self.batch_size = batch_size
self.learng_eta = learng_eta
''' training data '''
self.traing_x = np.array(traing_x_list)
self.traing_y = np.array(traing_y_list)
''' evaluation data '''
self.evaltn_x = np.array(evaltn_x_list)
self.evaltn_y = np.array(evaltn_y_list)
''' model : list of arrays '''
self.l_number = len(self.layers)
self.l_sizes = []
self.l_weights = []
self.l_biases = []
self.l_actvtns = []
for l_ix in range(0, self.l_number):
self.l_sizes.append(len(self.layers[l_ix]))
self.l_weights.append(np.array([]))
self.l_biases.append(np.array([]))
self.l_actvtns.append(np.array([]))
# weights and biases initialization
for l_ix in range(1, self.l_number):
w_size = (self.l_sizes[l_ix-1], self.l_sizes[l_ix])
b_size = (self.l_sizes[l_ix])
self.l_weights[l_ix] = ii.set_weights(self.initn_weight_type,
w_size) / len(self.traing_x) # scaling
self.l_biases[l_ix] = ii.set_biases(self.initn_bias_type,
b_size)
''' monitor features '''
self.input_log = input_log
self.traing_qtts_log = traing_qtts_log
self.traing_acts_log = traing_acts_log
self.traing_cost_log = traing_cost_log
self.evaltn_cost_log = evaltn_cost_log
self.monitor = mm(self)
''' show input '''
if self.input_log:
if self.traing_x[0].shape == (2,):
self.monitor.show_2d_input_map()
def tokenize(self):
self.words = WordPunctTokenizer().tokenize(self.lowercase_query)
init = Initialization()
self.punct_list = init.initializePunctList()
self.alpha_list = list(string.ascii_lowercase)
def tokenize(self): self.words = WordPunctTokenizer().tokenize(self.lowercase_query) init = Initialization() self.punct_list = init.initializePunctList() self.alpha_list = list(string.ascii_lowercase)