pjbull

pjbull

import sys
import types

import dev_package

def reload_package(root_module):
    package_name = root_module.__name__

    # get a reference to each loaded module
    loaded_package_modules = dict([

pjbull

from __future__ import division

# graphics
import matplotlib.pyplot as plt
from matplotlib import rc_params

mpl_default = rc_params()

import seaborn as sns
sns.set(rc=mpl_default)

pjbull

Running RODEO on EC2

1. Make sure instance is allowing HTTP traffic through the SecurityGroup (Type: HTTP, Protocol: TCP, Port Range: 80, Source: 0.0.0.0/0 on EC2. Note: THIS CAN ONLY BE DONE WHEN YOU ARE SETTING UP THE IMAGE
2. SSH into the machine: ssh -i [MYCREDS].pem ubuntu@[public ip]
3. Install whatever packages/Python you need
4. Redirect HTTP traffic from port 80 to another port greater than 1024. 8080 is a common choice:

sudo iptables -t nat -A PREROUTING -p tcp --dport 80 -j REDIRECT --to-port 8080

pjbull

import re
import sys
import unicodedata

import pandas as pd


def clean_string(s):
    if isinstance(s, unicode):
        s = unicodedata.normalize('NFKD', s).encode('ascii', 'ignore')

pjbull

# I keep this in my .bashrc to get to a running EC2 instance if there is only one running with my current creds

export AWS_EC2_PEM=<PATH_TO_PEM>

function ec2me () {
    running=$(ec2-describe-instances | grep running)
    instances=$(wc -l <<< "$running")

    if [ $instances = 1 ]; then
        server=$(cut -f4 <<< "$running" )

pjbull

================================================
Failed to save <type 'numpy.ndarray'> to .npy file:
Traceback (most recent call last):
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/numpy_pickle.py", line 275, in save
    obj, filename = self._write_array(obj, filename)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/numpy_pickle.py", line 236, in _write_array
    self.np.save(filename, array)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/numpy/lib/npyio.py", line 491, in save
    pickle_kwargs=pickle_kwargs)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/numpy/lib/format.py", line 585, in write_array

pjbull

import os
import re

from nbconvert.nbconvertapp import NbConvertApp
from nbconvert.postprocessors.base import PostProcessorBase


class CopyToSubfolderPostProcessor(PostProcessorBase):
    def __init__(self, subfolder=None):
        self.subfolder = subfolder

pjbull

from sklearn.base import BaseEstimator, TransformerMixin
from scipy import sparse
from itertools import combinations


class SparseInteractions(BaseEstimator, TransformerMixin):
    def __init__(self, degree=2, feature_name_separator="_"):
        self.degree = degree
        self.feature_name_separator = feature_name_separator
    

pjbull

import subprocess

path = ROOT_DIR
result = (subprocess.check_output(['tree', '--dirsfirst', path])
                    .decode("utf-8", "strict"))

file_list = result.split('\n')

root = file_list[0]
file_list = file_list[1:-3]