lizadaly

rm -rf dist
mkdir dist
cp -r images dist
cp *.css dist/
echo "Writing index..."
pandoc index.md -o dist/index.html --template templates/default.html
for d in pages/*; do
  mkdir -p dist/$d
  for i in $d/*.md; do
    f="${i##*/}"

lizadaly

# Toy example of using a deep neural network to predict average temperature
# by month. Note that this is not any better than just taking the average
# of the dataset; it's just meant as an example of a regression analysis using
# neural networks.

import logging
import datetime

import pandas as pd
import torch

lizadaly

import spacy
nlp = spacy.load('en')
doc = nlp('Do you have a car or truck')
for token in doc:
  print(token, token.pos_)

lizadaly

Keybase proof

I hereby claim:

• I am lizadaly on github.
• I am lizadaly (https://keybase.io/lizadaly) on keybase.
• I have a public key ASBKi45tuqp1aEuDXp8B0EYFUcdlRSGFMlRxb9nNAqm4owo

To claim this, I am signing this object:

lizadaly

/* Version without division */
var findProductsNoDiv = function (arr) {
  let forw = new Array(arr.length)
  let back = new Array(arr.length)
  let res = new Array(arr.length)
  let prod = 1
  /* Go through the array forward and multiply as we go */
  for (var i=0;i<arr.length;i++) {
    forw[i] = prod
    prod *= arr[i]

lizadaly

*/
var sortedArrays = function (arr1, arr2) {
  let ans = new Array(arr1.length + arr2.length)
  let i = 0, j = 0, k = 0
  while (i < arr1.length && j < arr2.length) {
    if (arr1[i] < arr2[j])  {
      ans[k] = arr1[i]
      i++
    }
    else {

lizadaly

import random
from collections import Counter
import nltk

# See https://gist.github.com/lizadaly/7071e0de589883a197433951bc7314c5 for comments on the setup here
word_list = []
[word_list.extend(nltk.corpus.gutenberg.words(f)) for f in nltk.corpus.gutenberg.fileids()]
cleaned_words = [w.lower() for w in word_list if w.isalnum()]
all_bigrams = [b for b in nltk.bigrams(cleaned_words)]

lizadaly

import nltk
from nltk.corpus import stopwords
from collections import Counter

word_list = []

# Set up a quick lookup table for common words like "the" and "an" so they can be excluded
stops = set(stopwords.words('english'))

# For all 18 novels in the public domain book corpus, extract all their words

lizadaly

> db.subjects.getIndexes()
[
	{
		"v" : 1,
		"key" : {
			"_id" : 1
		},
		"name" : "_id_",
		"ns" : "scribe_api_development.subjects"
	},

lizadaly

from sklearn.datasets import load_files
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.pipeline import Pipeline

import numpy as np

# Load the pre-classified training data as "training-fanfic/clean" and "training-fanfic/dirty/"
train = load_files("training-fanfic", encoding="utf-8", load_content=True)