marcelcaraciolo

# BM25F Model

def bm25(idf, tf, fl, avgfl, B, K1):
    # idf - inverse document frequency
    # tf - term frequency in the current document
    # fl - field length in the current document
    # avgfl - average field length across documents in collection
    # B, K1 - free paramters

    return idf * ((tf * (K1 + 1)) / (tf + K1 * (1 - B + B * (fl / avgfl))))

marcelcaraciolo

#-*- coding:utf-8 - *-


def load_dataset():
    "Load the sample dataset."
    return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]


def createC1(dataset):
    "Create a list of candidate item sets of size one."

marcelcaraciolo

import json
import re
import grequests
import pandas as pd
import requests
from bs4 import BeautifulSoup
from bs4.diagnose import profile

marcelcaraciolo

marcelcaraciolo

def map_feature(x1, x2):
    '''
    Maps the two input features to quadratic features.

    Returns a new feature array with more features, comprising of
    X1, X2, X1 ** 2, X2 ** 2, X1*X2, X1*X2 ** 2, etc...

    Inputs X1, X2 must be the same size
    '''
    x1.shape = (x1.size, 1)

marcelcaraciolo

import subprocess



def check_dependencies():
    """Ensure required tools for installation are present.
    """
    print("Checking required dependencies")
    for cmd, param, url in [("git", '--version', "http://git-scm.com/"),

marcelcaraciolo

<?xml version='1.0' encoding='UTF-8'?>
<TrainingCenterDatabase xmlns:ext="http://www.garmin.com/xmlschemas/ActivityExtension/v2" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.garmin.com/xmlschemas/TrainingCenterDatabase/v2">
  <Activities>
    <Activity Sport="Running">
      <Id>2012-12-26T21:29:53Z</Id>
      <Notes>Aerobics</Notes>
      <Lap StartTime="2012-12-26T21:29:53Z">
        <TotalTimeSeconds>608.47</TotalTimeSeconds>
        <DistanceMeters>1609.34399414</DistanceMeters>
        <MaximumSpeed>4.55431461334</MaximumSpeed>

marcelcaraciolo

import requests
from BeautifulSoup import BeautifulSoup

def megasena_api():
  URL_ULTIMOS_RESULTADOS = 'http://www1.caixa.gov.br/loterias/loterias/megasena/megasena_pesquisa_new.asp'
	page = requests.get(URL_ULTIMOS_RESULTADOS)
	bs = BeautifulSoup(page.content)
	numeros_sena =  [ n.contents[0] for n in bs.findAll('li')[:6]]
	
	results = page.content.split('|')

marcelcaraciolo

from numpy import loadtxt, zeros, ones, array, linspace, logspace
from pylab import scatter, show, title, xlabel, ylabel, plot, contour


#Evaluate the linear regression
def compute_cost(X, y, theta):
    '''
    Comput cost for linear regression
    '''
    #Number of training samples

marcelcaraciolo

version: "2"

services:
  web:
    build: .
    #command: python3 manage.py runserver 0.0.0.0:8000
    command: bash -c "pip install -r requirements.txt && gunicorn geninfo.wsgi:application --bind 0.0.0.0:8000"
    volumes:
      - .:/usr/src/
    expose: