Skip to content

Instantly share code, notes, and snippets.

View amn41's full-sized avatar

Alan Nichol amn41

View GitHub Profile
@amn41
amn41 / epic-first-attempt
Last active May 10, 2016 16:59
attempt at using epic NER on plaintext file
import epic.models.{NerSelector, ParserSelector}
import epic.parser.ParserAnnotator
import epic.preprocess
import epic.preprocess.{TreebankTokenizer, MLSentenceSegmenter}
import epic.sequences.{SemiCRF, Segmenter}
import epic.slab.{EntityMention, Token, Sentence}
import epic.trees.{AnnotatedLabel, Tree}
import epic.util.SafeLogging

Keybase proof

I hereby claim:

  • I am amn41 on github.
  • I am alanmnichol (https://keybase.io/alanmnichol) on keybase.
  • I have a public key whose fingerprint is E4A6 5E28 9A74 DAE1 B53B BC9C 034A 0F94 FB6F 4774

To claim this, I am signing this object:

%load dependenices
run('~/Software/gpml/gpml-matlab-v3.4-2013-11-11/startup.m');
% params
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
restart=true;
filename='hypers22-Jan-2015.mat';
maxiters=20;
npoints=3500;
nsparse=2000;
from pymongo import MongoClient
"""
quick and dirty
"""
client=MongoClient()
db=client['treevdb']
gdrivecoll=db['googledriveinformation']
cursor=gdrivecoll.find()
@amn41
amn41 / quip_params.xml
Created August 16, 2015 15:42
sample parameters for polarisable models
<Multipoles_Potentials>
<Multipoles_params n_types="0" n_monomer_types="2" cutoff="10.0" method="direct" label="default" damping="erf" polarisation="none" intermolecular_only="T">
<monomer type='1' species='h2o' n_sites='3' signature="8_1_1" monomer_cutoff="2.0" >
<per_site_data monomer="1" site='1' pos_type="atom" atomic_num="8" charge_method="FIXED" charge="-0.7" pol_alpha="0.0" damp_rad="1.0"/>
<per_site_data monomer="1" site='2' pos_type="atom" atomic_num="1" charge_method="FIXED" charge="0.35" pol_alpha="0.0" damp_rad="1.0"/>
Verifying that +alannichol is my blockchain ID. https://onename.com/alannichol
# I like using seaborn, but of course you can also just use this as a set of colours.
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
# from seaborn docs
def sinplot(flip=1):
x = np.linspace(0, 14, 100)
for i in range(1, 7):
while ( not formData.is_complete() ):
questionKey = formData.first_missing_field()
ask(questions[questionKey])
@amn41
amn41 / embedding.py
Last active October 17, 2017 01:19
class Embedding(object):
def __init__(self,vocab_file,vectors_file):
with open(vocab_file, 'r') as f:
words = [x.rstrip().split(' ')[0] for x in f.readlines()]
with open(vectors_file, 'r') as f:
vectors = {}
for line in f:
vals = line.rstrip().split(' ')
vectors[vals[0]] = [float(x) for x in vals[1:]]
def find_similar_words(embed,text,refs,thresh):
C = np.zeros((len(refs),embed.W.shape[1]))
for idx, term in enumerate(refs):
if term in embed.vocab:
C[idx,:] = embed.W[embed.vocab[term], :]
tokens = text.split(' ')