organisciak

// Solarized for Mosh Chrome
// Mosh does not seem to save profiles, so this sets the default 'mosh' profile.
// To reset, evaluate term_.prefs_.resetAll()

// Run in the JavaScript console of mosh_browser.html, which can be opened
// as explained here: 
// https://github.com/rpwoodbu/mosh-chrome/wiki/FAQ#how-can-i-change-the-way-the-terminal-looks-font-color-etc
 
var htermProfiles = {
    // Solarized Dark

organisciak

{
"origin": ["I accuse #suspect# of committing the crime in the #room# with the #weapon#!"],
"suspect": ["Miss Scarlett", "Colonel Mustard", "Mrs. White", "Reverend Green", "Mrs. Peacock", "Professor Plum", "Miss Peach", "Monsieur Brunette", "Madame Rose", " Sergeant Gray"],
"room": ["kitchen", "ballroom", "conservatory", "dining room", "billiard room", "library", "study", "hall", "lounge"],
"weapon": ["candlestick", "knife", "lead pipe", "dagger", "revolver", "rope", "wrench"]
}

organisciak

READPY=$(git log --name-only HEAD^.. | grep "^README.ipynb$")
READMD=$(git log --name-only HEAD^.. | grep "^README.md$")

if [ -n "$READPY" ] && [ -z "$READMD" ]; then
    echo "It looks like a new README was committed, appending a Markdown version"
    ipython nbconvert --to markdown README.ipynb

    # Adding this file doesn't work in pre-commit hooks, which is
    # why we're appending post-commit
    git add README.md

organisciak

'''
Author: Peter Organisciak

Convert Day of DH (or other Wordpress) export to Mallet import format.
[url] [user] [post text]

Use in the following way:
>> python process.py input-file output-file --split [post|author]

For the split argument, choose either post (a document representation is the words of a post) or author (a document representation is the words that an author has written).

organisciak

from htrc_features import FeatureReader
import argparse
import pandas as pd
import numpy as np
import random
import string


def main():
    parser = argparse.ArgumentParser(description='Calculate Collection '

organisciak

organisciak

tl = vol.tokenlist(pages=False)
just_nouns = tl.loc[(slice(None), slice(None), ["NN", "NNS"]),]
top_nouns = just_nouns.sort_values('count', ascending=False)
top_nouns.head(5)

# OUTPUT:
#                     count
# section token  pos       
# body    doctor NN      83
#         time   NN      80

organisciak

Field Coverage  Description
035	  100%      SYSTEM CONTROL NUMBER (R)
245	  100%      TITLE STATEMENT (NR)
538	  100%      SYSTEM DETAILS NOTE (R)
974	  100%      NA
260	  99.7%     PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) (R)
300	  99.0%     PHYSICAL DESCRIPTION (R)
040	  95.8%     CATALOGING SOURCE (NR)
100	  73.9%     MAIN ENTRY--PERSONAL NAME (NR)
650	  64.9%     SUBJECT ADDED ENTRY--TOPICAL TERM (R)

organisciak

def calculate_tfidf(tokencounts, idf_df, df='PF', case=True, log_tf=True):
  '''Takes a 'token, count' DF and returns TF*IDF weights '''
  if not case:
    tc['token'] = tc['token'].str.lower()
    tc = tc.groupby('token', as_index=False).sum()
  tfidf = pd.merge(tc.set_index('token'), idf_df, left_index=True, right_index=True)
  if log_tf:
    tfidf['TF'] = tfidf['count'].add(1).apply(np.log10)
  else:
    tfidf['TF'] = tfidf['count']

organisciak

Quick declination of the head.
Free from weeds.
Thoroughfare: way.
Raw, unprepared.
Enclosed place.
Railway station.

Effect of commutation.
Small bit of bread.
Machine-made net or lace.