martindurant

martindurant

127.0.0.1	sb.freeskreen.com
127.0.0.1	adfarm.mediaplex.com
127.0.0.1       adclick.g.doubleclick.net
127.0.0.1       secure.insightexpressai.com
127.0.0.1       pagead2.googlesyndication.com
127.0.0.1       js.moatads.com
127.0.0.1       cdn.teads.tv
127.0.0.1       s0.2mdn.net
127.0.0.1       ad.doubleclick.net
127.0.0.1       pixel.adsafeprotected.com

martindurant

from __future__ import unicode_literals
import json

MAGIC = b'Obj\x01'
SYNC_SIZE = 16


def read_long(fo):
    """variable-length, zig-zag coding."""
    c = fo.read(1)

martindurant

{"time": 1501196547.959372, "log": "start"}
{"finish": "waiting", "log": "transition", "start": "released", "args": [], "time": 1501196559.388243, "key": "<lambda>-c9f069025429b973b33b0f27c23e2347", "kwargs": {}}
{"finish": "processing", "log": "transition", "start": "waiting", "args": [], "time": 1501196559.388446, "key": "<lambda>-c9f069025429b973b33b0f27c23e2347", "kwargs": {}}
{"kwargs": {"client": "Client-a785c5f0-731f-11e7-a5aa-acbc32a9ff1d", "loose_restrictions": [], "dependencies": {"<lambda>-c9f069025429b973b33b0f27c23e2347": []}}, "dsk": null, "keys": ["<lambda>-c9f069025429b973b33b0f27c23e2347"], "log": "update_graph", "restrictions": {}, "time": 1501196559.388531}
{"finish": "memory", "log": "transition", "start": "processing", "args": [], "time": 1501196559.390576, "key": "<lambda>-c9f069025429b973b33b0f27c23e2347", "kwargs": {"startstops": [["compute", 1501196559.391431, 1501196559.3914502]], "thread": 123145409626112, "nbytes": 28, "worker": "tcp://192.168.0.11:58953", "status": "OK"}}
{"finish

martindurant

martindurant

import dask
import dask.dataframe as dd
import numpy as np
import numba
import time


@numba.njit
def calc_hist(X, Y, xrange, yrange, out, w, h):
    x0, x1 = xrange

martindurant

import requests


class GiTea(object):
    base_url = 'http://127.0.0.1:3000'

    def __init__(self, user, pword, base_url=None):
        if base_url is not None:
            self.base_url = base_url

martindurant

import dask.dataframe as dd
import gcsfs  # registers with dask filesystems

# Initial authentication
# gcs = gcsfs.core.GCSFileSystem(project='continuum-compute',
# token='/Users/mdurant/.config/gcloud/application_default_credentials.json')

# Tiny block-size to ensure more than one block
df = da.read_csv('s3://blaze-data/iris/*', blocksize=2500,
                 names=['petal_length', 'sepal_length', 'petal_width',

martindurant

import collections
import dask.array as da
from dask.utils import infer_storage_options
import numpy as np
import pickle
import xarray as xr
import zarr

martindurant