sminot

#!/usr/bin/env python3

import boto3
import argparse
from datetime import datetime

parser = argparse.ArgumentParser()
parser.add_argument("job_id")

# Add the arguments

a-hisame

#!/usr/bin/python
# -*- coding: utf-8 -*-

'''To use gzip file between python application and S3 directly for Python3.
Python 2 version - https://gist.github.com/a-hisame/f90815f4fae695ad3f16cb48a81ec06e
'''

import io
import gzip
import json

kstohr

import os
import traceback
import logging
import facebook
import requests
import pandas as pd
import json
import time
import numpy as np
from pandas.io.json import json_normalize

nkt1546789

import numpy as np
from numpy import random
from sklearn import base

class PUWrapper(object):
    def __init__(self,trad_clf,n_fold=5):
        self._trad_clf=trad_clf
        self._n_fold=n_fold

    def fit(self,X,s):

benmarwick

# Speed tests of different ways to read in large numbers of CSV files
# specifically read.csv.sql, read.csv (optimised) and fread


library(sqldf)
setwd("~/Downloads/wordcounts")
files <- sample(list.files(".", pattern="*.csv|CSV$"), 10000)

############# read.csv.sql ###################
system.time(