thomasaarholt

import ipywidgets as widgets

import os
from pathlib import Path
cwd = Path(os.getcwd())

FOLDERLABEL = '-------FOLDERS-------'
FILESLABEL = '-------FILES-------'

def get_folder_contents(folder):

ihnorton

#!/bin/sh

# pull the listing
wget http://mirror.centos.org/centos/6/sclo/x86_64/rh/devtoolset-3/

# yank the hrefs
egrep -o 'href=\"(.*\.rpm)"' index.html | cut -d \" -f2 > rpm.list

# download them
for f in `cat rpm.list`;

tsu-nera

from sklearn.datasets import load_boston
import pandas as pd

import xgboost as xgb
from tensorboard_logger import configure, log_value
from sklearn.cross_validation import train_test_split


def logspy(env):
    log_value("train", env.evaluation_result_list[0][1], step=env.iteration)

colbyford

########################################
## Title: Spark MLlib Classification Data Prep Script
## Language: PySpark
## Author: Colby T. Ford, Ph.D.
########################################

from pyspark.ml import Pipeline
from pyspark.ml.feature import OneHotEncoder, OneHotEncoderEstimator, StringIndexer, VectorAssembler

label = "dependentvar"

goraj

import numpy as np
from sklearn.datasets import load_digits
from sklearn.metrics import roc_auc_score
import lightgbm as lgbm


if __name__ == '__main__':
    np.random.seed(4242)
    d = load_digits()

Rustem

"""
1. Store the image and create an instance of ImagefileProcessHistory with status NOT_STARTED

    ImageFileProcessHistory
        - local_path
        - file_name
        - status # enum: NOT_STARTED, STARTED, SUCCEEDED, FAILED
        - bytes_processed
        - bytes_total
"""

stefansundin

# http://docs.python-requests.org/en/master/api/
import requests

class RequestsApi:
    def __init__(self, base_url, **kwargs):
        self.base_url = base_url
        self.session = requests.Session()
        for arg in kwargs:
            if isinstance(kwargs[arg], dict):
                kwargs[arg] = self.__deep_merge(getattr(self.session, arg), kwargs[arg])

rnowling

"""
Script for comparing Logistic Regression and associated evaluation metrics on the imbalanced Media 6 Degrees dataset from the Doing Data Science book.  You'll need to download a copy of the dataset from the GitHub repo: https://github.com/oreillymedia/doing_data_science .

Copyright 2016 Ronald J. Nowling

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

eddies

Standalone Spark 2.0.0 with s3

###Tested with:

• Spark 2.0.0 pre-built for Hadoop 2.7
• Mac OS X 10.11
• Python 3.5.2

Goal

Use s3 within pyspark with minimal hassle.

ispmarin

rdd = sc.parallelize(
    [
        (0., 1.), 
        (0., 0.), 
        (0., 0.), 
        (1., 1.), 
        (1.,0.), 
        (1.,0.),
        (1.,1.),
        (1.,1.)