turian

def first_by_column(df, colname):
    """
    Pandas function to take to the first value for each of a column value.
    Useful if the table if sorted in descending order and you want to group over
    a particular column, to find the max for each value of that field.
    """
    newdf = []
    #print(colname)
    #print(df)
    colvals = pd.unique(df.loc[:, [colname]].squeeze())

turian

# Number of inputs
NIN = 1000
NHID = 10
# Number of examples
EXAMPLES = 100000

import timeit
import logging
from collections import OrderedDict

turian

turian

"""
Tune search_k for annoy library.

This is for people who want their nearest-neighbors to be above a
certain threshold of precision, but otherwise want it as fast as
possible.

AUTHOR: Joseph Turian
LICENSE: Apache License 2.0
"""

turian

Keybase proof

I hereby claim:

• I am turian on github.
• I am turian (https://keybase.io/turian) on keybase.
• I have a public key whose fingerprint is B8C4 F42B D493 3F85 FA4E 2E94 7384 B7F2 7748 51AB

To claim this, I am signing this object:

turian

"""
Modified from: https://gist.github.com/1142142
to include the text of the link.
"""

import re

from scrapy.link import Link
from urlparse import urljoin
from BeautifulSoup import BeautifulSoup