yhfyhf

import threading


class Queue(object):
    def __init__(self, max_size):
        self.max_size = max_size
        self.mutex = threading.Lock()
        self.is_full = threading.Condition(self.mutex)
        self.is_empty = threading.Condition(self.mutex)
        self._queue = []

yhfyhf

class ThreadUrl(threading.Thread):

    def __init__(self, queue, visited, lock):
        super(ThreadUrl, self).__init__()
        self.queue = queue
        self.visited = visited
        self.lock = lock

    def run(self):
        while True:

yhfyhf

# coding: utf-8

# version 1.0.3
# #![Spark Logo](http://spark-mooc.github.io/web-assets/images/ta_Spark-logo-small.png) + ![Python Logo](http://spark-mooc.github.io/web-assets/images/python-logo-master-v3-TM-flattened_small.png)
# # **Text Analysis and Entity Resolution**
# ####Entity resolution is a common, yet difficult problem in data cleaning and integration. This lab will demonstrate how we can use Apache Spark to apply powerful and scalable text analysis techniques and perform entity resolution across two datasets of commercial products.

# #### Entity Resolution, or "[Record linkage][wiki]" is the term used by statisticians, epidemiologists, and historians, among others, to describe the process of joining records from one data source with another that describe the same entity. Our terms with the same meaning include, "entity disambiguation/linking", duplicate detection", "deduplication", "record matching", "(reference) reconciliation", "object identification", "data/information integration", and "conf

yhfyhf

#!/usr/bin/env python


def curry(func):
    """
    Decorator to curry a function, typical usage:

    >>> @curry
    ... def foo(a, b, c):
    ...    return a + b + c

yhfyhf

"""
# generate ListNode from unpacking list
>>> l = l = ListNode(*range(10))

>>> l
<ListNode [0]>

>>> print l
<ListNode [0]>: 0 -> 1 -> 2 -> 3 -> 4 -> 5 -> 6 -> 7 -> 8 -> 9

yhfyhf

# encoding: utf-8
'''
>>> l = fn_list([3, 2, 1])

>>> l.len()
3

>>> l.map(lambda x: x + 1).map(lambda x: x * 2)
[8, 6, 4]

yhfyhf

# encoding: utf-8

"""
    Use kNN algorithm to recognize digits.

    Download files here: http://download.csdn.net/detail/zouxy09/6610571

    ├── digits
    │   ├── testDigits
    │   └── trainingDigits

yhfyhf

import random
import numpy as np


def distance(v1, v2):
    """
    euclidean metric of v1, v2. 
    v1 and v2 are both n-dimensions vectors
    """
    return np.sqrt(sum(np.power(v1 - v2, 2)))

yhfyhf

#include <iostream>
#include <ext/hash_map>
using namespace std;
using namespace __gnu_cxx;

template <class K, class T>
struct Node{
    K key;
    T data;
    Node *prev, *next;