def __init__(self, kernel, verbose=False):
self.K, self.parameters_search_space = kernel()
self.model = gp.GaussianProcessRegressor(kernel=self.K)
self.verbose = verbose
self.logger = config.getlogger("GP")
self.best_param = None
self.trained = False
import requests
from config import getlogger
logger = getlogger()
class Gsearch:
"""Abstraction over Google Custom Search API"""
base_url = 'https://www.googleapis.com/customsearch/v1'
api_key = None
cse_id = None
def __init__(self, api_key, cse_id, **kwargs):
if not api_key or not cse_id:
raise ValueError('An api_key and cse_id is required.')
self.api_key = api_key
self.cse_id = cse_id
if hasattr(kwargs, 'url'):
self.base_url = kwargs['url']
def query(self, phrase, start_idx):
"""Exectute a query for the given search phrase"""
payload = {
'key': self.api_key,
'cx': self.cse_id,
'q': phrase,
'start': start_idx
import numpy as np
import pandas as pd
import pprint
import config
from stats import permutation_test
from sklearn.metrics import mean_squared_error
from GP import gaussian_process
from kernels import *
import data_generator
import data_loader
import vis
pp = pprint.PrettyPrinter(indent=4)
logger = config.getlogger("main")
flatten = lambda l: [item for sublist in l for item in sublist]
def NN_fit(train_set, val_set, nn=5, epochs=10, width=10, layers=2):
from NN import NeuralNetwork
last_error = 100
last_predicated = None
fnn = None
for x in range(nn):
nn = NeuralNetwork()
nn.train(
train_set,
val_set,
def __init__(self, *args, **kwargs):
self.logger = config.getlogger("NN")
self.loss_func = torch.nn.MSELoss()
self.model = None
return super().__init__(*args, **kwargs)
from lxml import html, etree
from config import getlogger
from collections import deque
from datetime import datetime
from urlparse import urlparse, urljoin
from models.page import Page
import requests
logger = getlogger()
class PageScraper:
depth = 0
def run(self, page):
"""
Get all the links from `page['link']`
"""
logger.info('getting contents of %s', page['link'])
try:
res = requests.get(page['link'])
except requests.exceptions.RequestException as e:
logger.error(e)
tree = etree.Element('root')
try:
tree = html.fromstring(res.text)
except ValueError:
logger.error('failed to parse html for %s', page['link'])