marcelcaraciolo

def cosine(dot_product, rating_norm_squared, rating2_norm_squared):
    '''
    The cosine between two vectors A, B
       dotProduct(A, B) / (norm(A) * norm(B))
    '''
    numerator = dot_product
    denominator = rating_norm_squared * rating2_norm_squared

    return (numerator / (float(denominator))) if denominator else 0.0

marcelcaraciolo

    def calculate_ranking(self, item_keys, values):
        '''
        Emit items with similarity in key for ranking:

        19,0.4    70,1
        19,0.6    21,2
        21,0.6    19,2
        21,0.9    70,1
        70,0.4    19,1
        70,0.9    21,1

marcelcaraciolo

from math import sqrt


def correlation(size, dot_product, rating_sum, \
            rating2sum, rating_norm_squared, rating2_norm_squared):
    '''
      The correlation between two vectors A, B is
      cov(A, B) / (stdDev(A) * stdDev(B))

    '''

marcelcaraciolo

    def pairwise_items(self, user_id, values):
        '''
        The output drops the user from the key entirely, instead it emits
        the pair of items as the key:

        19,21  2,1
        19,70  2,4
        21,70  1,4
        19,21  1,2

marcelcaraciolo

def group_by_user_rating(self, key, line):
    """
    Emit the user_id and group by their ratings (item and rating)

    17  70,3
    35  21,1
    49  19,2
    49  21,1
    49  70,4
    87  19,1

marcelcaraciolo

$ python moviesSimilarities.py ratings.csv > output.csv

marcelcaraciolo

196|Kolya (1996)|3
186|L.A. Confidential (1997)|3
22|Heavyweights (1994)|1
244|Legends of the Fall (1994)|2
166|Jackie Brown (1997)|1
298|Dr. Strangelove or: How I Learned to Stop Worrying and Love the Bomb (1963)|4
115|Hunt for Red October, The (1990)|2
253|Jungle Book, The (1994)|5
305|Grease (1978)|3

marcelcaraciolo

import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pylab
from matplotlib.ticker import MaxNLocator


def plot_graphs(dataP, id_listP, titleP, labelsP,
    dataR, id_listR, titleR, labelsR,
    dataF, id_listF, titleF, labelsF, filesave=None):

marcelcaraciolo

from flask import jsonify
from flask import Flask
from correios import obter_rastreamento
app = Flask(__name__)

@app.route('/track/<trackid>', methods = ['GET'])
def api_tracking(trackid):
    resp = jsonify(obter_rastreamento(trackid))
    resp.status_code = 200
    return resp

marcelcaraciolo

import urllib
import sys
import re
import json

URL = 'http://websro.correios.com.br/sro_bin/txect01$.QueryList?P_ITEMCODE=&P_LINGUA=001&P_TESTE=&P_TIPO=001&P_COD_UNI=%s'

def captura_html(url):
	html_data = urllib.urlopen(url).read()
	return html_data