A "Best of the Best Practices" (BOBP) guide to developing in Python.
- "Build tools for others that you want to be built for you." - Kenneth Reitz
- "Simplicity is alway better than functionality." - Pieter Hintjens
# encoding=utf-8 | |
# Obtener el dígito verificador del RUT en Python. | |
# | |
# La función recibe el RUT como un entero, | |
# y entrega el dígito verificador como un entero. | |
# Si el resultado es 10, el RUT es "raya k". | |
from itertools import cycle |
# This is a really old post, in the comments (and stackoverflow too) you'll find better solutions. | |
def find(key, dictionary): | |
for k, v in dictionary.iteritems(): | |
if k == key: | |
yield v | |
elif isinstance(v, dict): | |
for result in find(key, v): | |
yield result | |
elif isinstance(v, list): |
# Logging settings for django projects, works with django 1.5+ | |
# If DEBUG=True, all logs (including django logs) will be | |
# written to console and to debug_file. | |
# If DEBUG=False, logs with level INFO or higher will be | |
# saved to production_file. | |
# Logging usage: | |
# import logging | |
# logger = logging.getLogger(__name__) | |
# logger.info("Log this message") |
# install missing libraries (if any) | |
cd ~ | |
sudo yum update | |
yum install java-1.7.0-openjdk.x86_64 | |
yum install unzip | |
yum install mc | |
yum install wget | |
yum install curl | |
# get and unpack elasticsearch zip file |
import os | |
import sys | |
# constants, configure to match your environment | |
HOST = 'http://localhost:9200' | |
INDEX = 'test' | |
TYPE = 'attachment' | |
TMP_FILE_NAME = 'tmp.json' |
import os | |
import sys | |
# constants, configure to match your environment | |
HOST = 'http://localhost:9200' | |
INDEX = 'test' | |
TYPE = 'attachment' | |
TMP_FILE_NAME = 'tmp.json' | |
# for supported formats, see apache tika - http://tika.apache.org/1.4/formats.html | |
INDEX_FILE_TYPES = ['html','pdf', 'doc', 'docx', 'xls', 'xlsx', 'xml'] |
""" Example using GenSim's LDA and sklearn. """ | |
import numpy as np | |
from gensim import matutils | |
from gensim.models.ldamodel import LdaModel | |
from sklearn import linear_model | |
from sklearn.datasets import fetch_20newsgroups | |
from sklearn.feature_extraction.text import CountVectorizer |
I have moved this over to the Tech Interview Cheat Sheet Repo and has been expanded and even has code challenges you can run and practice against!
\