aronwc

# cluster users based on feature vectors
import argparse
import io
import numpy as np
import pickle
import re
import string
import sys

from sklearn.cluster import MiniBatchKMeans

aronwc

Here are the steps I took to make Emacs have code-completion and PEP8 checking:

1. Install [Marmalade](http://marmalade-repo.org) by putting this in your .emacs

(require 'package)
(add-to-list 'package-archives 
    '("marmalade" .
      "http://marmalade-repo.org/packages/"))
(package-initialize)

aronwc

''' An example of how to use Celery to manage a mix of serial and parallel
tasks.  This depends on a running instance of a rabbitmq messaging server to
keep track of task statuses. This can be launched on our ec2 instance with:
~/rabbitmq/rabbitmq_server-3.1.3/sbin/rabbitmq-server

For this script to work, you first need to run a celery worker process to
await orders:
$ celery -A tasks worker --loglevel=info

Then, you can call any of the functions below (see main for an example).

aronwc

import numpy as np

from sklearn import linear_model
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer


def print_features(coef, names):
    """ Print sorted list of non-zero features/weights. """
    print "\n".join('%s/%.2f' % (names[j], coef[j]) for j in np.argsort(coef)[::-1] if coef[j] != 0)

aronwc

""" Example using GenSim's LDA and sklearn. """

import numpy as np

from gensim import matutils
from gensim.models.ldamodel import LdaModel
from sklearn import linear_model
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer

aronwc

# show that max_depth affects floating point precision of predict_proba in RandomForest

from collections import Counter
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification

X, y = make_classification(n_samples=1000, n_features=20,
                                    n_informative=5, n_redundant=10,
                                    random_state=42)