bryanyang0528

import tensorflow as tf
import numpy as np
import time

N=10000
K=4
MAX_ITERS = 1000

start = time.time()

bryanyang0528

__reference__ = 'http://stackoverflow.com/questions/16852655/convert-a-tsv-file-to-xls-xlsx-using-python'
__author__ = 'jmcnamara'
__contributor__ = 'bryan yang'

import sys
import csv
from xlsxwriter.workbook import Workbook

class Tsvtoxlsx(object):

bryanyang0528

import numpy as np
import operator
point = [0,0]
k = 3
listOfPoint=[(1,1),(1,0),(2,1),(0,-1),(2,2)]


def knn(point, k, lists):
    #create a dic to store distance for each point
    dic={}

bryanyang0528

input = [-3,-1, 0, 1, 2 ,3]
res = []
def sumOfZero(input, target, part=[]):
    s = 0
    if part:
        for i in part:
            s+=i

    if s == target:
        res.append(part)

bryanyang0528

import numpy as np
def roc(actual, pred):
    fpr=np.array([1.0])
    tpr=np.array([1.0])
    n=float(len(actual)-sum(actual))
    p=float(sum(actual))
    for i in np.arange(min(pred), max(pred), 1.0/len(pred)):
        TP=0.0
        FP=0.0
        for j in range(len(pred)):

bryanyang0528

def roc(pred, actual):
    roc=[]
    p=float(len(actual)-sum(actual))
    n=float(sum(actual))
    for i in range(0,100,1) :
        TP=0
        FP=0
        i = float(i)/100
        for j in range(len(pred)):
            if (pred[j] > i) & (actual[j]==0):

bryanyang0528

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

bryanyang0528

http://d.stavrovski.net/blog/post/how-to-install-and-setup-oracle-java-jdk-in-centos-6

# rpm
wget --no-cookies \
--no-check-certificate \
--header "Cookie: oraclelicense=accept-securebackup-cookie" \
"http://download.oracle.com/otn-pub/java/jdk/7u55-b13/jdk-7u55-linux-x64.rpm" \
-O jdk-7-linux-x64.rpm

# ubuntu

bryanyang0528

core-site.xml
=================================
<property>
  <name>fs.defaultFS</name>
  <value>hdfs://ec2-54-148-213-237.us-west-2.compute.amazonaws.com</value>
</property>
<property>
  <name>hadoop.tmp.dir</name>
  <value>/home/hadoop/local/var/hadoop/tmp/hadoop-${user.name}</value>
</property>

bryanyang0528

# coding=utf-8
# Goal: parse house information for each district from websites
# for each district, get 「土地區段位置或建物區門牌」,「建物型態」,「建物現況格局」,「坪數」,「屋齡」,「總價元」,「資料來源」into csv file

# Procedure:
# 1. get the number of page for each district by parsing first html content
# 2. for each district put all html page together, use htmlparser to parse content and save data into file

import sys
import math