natekupp

class BTreeNode(object):
    """A B-Tree Node.
    
    attributes
    =====================
    leaf : boolean, determines whether this node is a leaf.
    keys : list, a list of keys internal to this node
    c : list, a list of children of this node
    """
    def __init__(self, leaf=False):

natekupp

import datetime
import os

from airflow.contrib.operators import dataproc_operator
from airflow.contrib.operators.bigquery_operator import BigQueryOperator
from airflow.contrib.operators.gcs_to_bq import GoogleCloudStorageToBigQueryOperator
from airflow.models import DAG
from airflow.utils import trigger_rule

PROJECT_ID = os.getenv('GCP_PROJECT_ID')

natekupp

diff --git a/hadoop-tools/hadoop-pipes/pom.xml b/hadoop-tools/hadoop-pipes/pom.xml
index 70f66f973d4..5063da640cc 100644
--- a/hadoop-tools/hadoop-pipes/pom.xml
+++ b/hadoop-tools/hadoop-pipes/pom.xml
@@ -54,6 +54,9 @@
                   <source>${basedir}/src</source>
                   <vars>
                     <JVM_ARCH_DATA_MODEL>${sun.arch.data.model}</JVM_ARCH_DATA_MODEL>
+                    <OPENSSL_INCLUDE_DIR>/usr/local/Cellar/openssl/1.0.2t/include</OPENSSL_INCLUDE_DIR>
+                    <OPENSSL_SSL_LIBRARY>/usr/local/Cellar/openssl/1.0.2t/lib/libssl.dylib</OPENSSL_SSL_LIBRARY>

natekupp

# example_airflow.py
from dagster import lambda_solid, pipeline

@lambda_solid
def hello_world():
    return "hello, world"

@pipeline
def basic_pipeline():
    hello_world()

natekupp

import dask
import dask.distributed

from tornado import gen

PUBSUB_NAME = 'test'


class Task:
    def __init__(self, key, num, upstream_tasks):

natekupp

class DataProcSparkOperator(BaseOperator):
    """
    Start a Cloud DataProc cluster, run a Spark job, then shut down the Spark cluster.
    """
    template_fields = ['arguments']
    ui_color = '#0273d4'

    @apply_defaults
    def __init__(
            self,

natekupp

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Terminal visualization of 2D numpy arrays
# Copyright (c) 2009  Nicolas P. Rougier
#
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free Software
# Foundation, either version 3 of the License, or (at your option) any later
# version.

natekupp

try:
    # start http server
    self.p_http = subprocess.Popen(
        ["python", "-m", "SimpleHTTPServer"],
        preexec_fn = sigint_replace,
        cwd = self.resource_dir
    )
    
    # start node.js server
    self.p_node = subprocess.Popen(

natekupp

python waf clean
export PYTHONPATH=/Library/Frameworks/Python.framework/Versions/2.7/
export LD_LIBRARY_PATH=/Library/Frameworks/Python.framework/Versions/2.7/:$LD_LIBRARY_PATH
export LD_LIBRARY_PATH=/Library/Frameworks/Python.framework/Versions/2.7/lib:$LD_LIBRARY_PATH
export LINKFLAGS='-search_dylibs_first  -L /Library/Frameworks/Python.framework/Versions/2.7/lib/'
export ARCHFLAGS='-arch x86_64'
export CC=/usr/bin/gcc-4.2
export PKG_CONFIG_PATH=/usr/local/Cellar/cairo/1.10.2/lib/pkgconfig/

python waf configure --prefix=$PYTHONPATH

natekupp

def buildmodel():
    EPS = 0.001
    data = pandas.read_csv('iris.csv')
    xtrain = data.ix[:50,0:2]
    xtest  = data.ix[51:100,0:2]
    ytrain = data.ix[:50,2]
    ytest  = data.ix[51:100,2]

    # Use pandas.DataFrame
    models = ffx.run(xtrain, ytrain, xtest, ytest)