fjavieralba

import logging
import logging.handlers
import sys

if len(sys.argv) < 2:
    print "ERROR: usage: syslog_generator.py <NAME>"
    exit(1)

my_logger = logging.getLogger('MyLogger')
my_logger.setLevel(logging.DEBUG)

fjavieralba

Packages

• lxml - Pythonic binding for the C libraries libxml2 and libxslt.
• boto - Python interface to Amazon Web Services
• Django - Django is a high-level Python Web framework that encourages rapid development and clean, pragmatic design.
• Fabric - Library and command-line tool for streamlining the use of SSH for application deployment or systems administration task.
• PyMongo - Tools for working with MongoDB, and is the recommended way to work with MongoDB from Python.
• Celery - Task queue to distribute work across threads or machines.
• pytz - pytz brings the Olson tz database into Python. This library allows accurate and cross platform timezone calculations using Python 2.4 or higher.

Guides

fjavieralba

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

fjavieralba

import java.io.IOException;
import java.util.Properties;
import kafka.server.KafkaConfig;
import kafka.server.KafkaServerStartable;
 
 
public class KafkaLocal {
 
	public KafkaServerStartable kafka;
	public ZooKeeperLocal zookeeper;

fjavieralba

from difflib import SequenceMatcher

def distance(url1, url2):
    ratio = SequenceMatcher(None, url1, url2).ratio()
    return 1.0 - ratio

fjavieralba

def value_of(sentiment):
    if sentiment == 'positive': return 1
    if sentiment == 'negative': return -1
    return 0

def sentiment_score(review):    
    return sum ([value_of(tag) for sentence in dict_tagged_sentences for token in sentence for tag in token[2]])

fjavieralba

class DictionaryTagger(object):
    def __init__(self, dictionary_paths):
        files = [open(path, 'r') for path in dictionary_paths]
        dictionaries = [yaml.load(dict_file) for dict_file in files]
        map(lambda x: x.close(), files)
        self.dictionary = {}
        self.max_key_size = 0
        for curr_dict in dictionaries:
            for key in curr_dict:
                if key in self.dictionary:

fjavieralba

text = """What can I say about this place. The staff of the restaurant is nice and the eggplant is not bad. Apart from that, very uninspired food, lack of atmosphere and too expensive. I am a staunch vegetarian and was sorely dissapointed with the veggie options on the menu. Will be the last time I visit, I recommend others to avoid."""

splitter = Splitter()
postagger = POSTagger()

splitted_sentences = splitter.split(text)

print splitted_sentences
[['What', 'can', 'I', 'say', 'about', 'this', 'place', '.'], ['The', 'staff', 'of', 'the', 'restaurant', 'is', 'nice', 'and', 'eggplant', 'is', 'not', 'bad', '.'], ['apart', 'from', 'that', ',', 'very', 'uninspired', 'food', ',', 'lack', 'of', 'atmosphere', 'and', 'too', 'expensive', '.'], ['I', 'am', 'a', 'staunch', 'vegetarian', 'and', 'was', 'sorely', 'dissapointed', 'with', 'the', 'veggie', 'options', 'on', 'the', 'menu', '.'], ['Will', 'be', 'the', 'last', 'time', 'I', 'visit', ',', 'I', 'recommend', 'others', 'to', 'avoid', '.']]

fjavieralba

import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;

/*
        Result is only one tagging of all the possible ones.
        The resulting tagging is determined by these two priority rules:
            - longest matches have higher priority
            - search is made from left to right
*/

fjavieralba

def non_overlapping_tagging(sentence, dict, max_key_size):
    """
        Result is only one tagging of all the possible ones.
        The resulting tagging is determined by these two priority rules:
            - longest matches have higher priority
            - search is made from left to right
    """        
    tag_sentence = []
    N = len(sentence)
    if max_key_size == -1: