andreasvc

andreasvc

andreasvc

"""Compute complexity metrics from Universal Dependencies.

Usage: python3 udstyle.py [OPTIONS] FILE...
  --parse=LANG          parse texts with Stanza; provide 2 letter language code
  --output=FILENAME     write result to a tab-separated file.
  --persentence         report per sentence results, not mean per document
Reported metrics:
  - LEN:  mean sentence length in words (excluding punctuation).
  - MDD:  mean dependency distance (Gibson, 1998).
  - NDD:  normalized dependency distance (Lei & Jockers, 2018).

andreasvc

# -*- coding: UTF-8 -*-
"""Preprocessing of text files.
Writes one paragraph per line, and normalizes punctuation & whitespace.
No sentence or word tokenization.

Usage: preprocess.py [FILE]
or: preprocess.py --batch FILES...

By default, produce cleaned version given a single filename to standard output.
Diagnostic information is written to standard error.

andreasvc

DBNLti_id	DBNLpers_id	YearFirstPublished	YearEditionPublished	Edition	Woman	Born	Died	AuthorOrigin	DBNLgeb_land_code	DBNLgenre	DBNLsubgenre	Author	Title	Filename	ti_id_set	WPAuthor	AuthorInCanon2002	TitleInCanon2002	InBasisbibliotheek2008	AuthorDBRDMatches	AuthorNLWikipedia2019Matches	DBNLSecRefsAuthor	DBNLSecRefsTitle	holding	lending	GNTpages
kist001leve01	kist001	1800	1800	1ste druk	0	1758	1841	Woerden		proza	roman	Willem Kist	Het leven, gevoelens en zonderlinge reize van den landjonker Govert Hendrik Godefroi van Blankenheim tot den Stronk (2 delen)	kist001leve01_01.xml	kist001leve01		0	0	0	0	1	19	1	0	0	4
wolf016gesc01	deke001	1802	1802	1ste druk	1	1741	1804	Amstelveen		proza	roman	Aagje Deken	Geschrift eener bejaarde vrouw	wolf016gesc01_01.xml	wolf016gesc01	Aagje Deken	1	0	0	1	21	131	6	0	0	0
stre001char01	stre001	1804	1804	1ste druk	1	1760	1828	Amsterdam		proza	briefroman	Naatje van Streek-Brinkman	Charakters en lotgevallen van Adelson, Héloïse en Elius	stre001char01_01.xml	stre001char01		0	0	0	0	0	13	0	0

andreasvc

"""Apply PCA to a CSV file and plot its datapoints (one per line).

The first column should be a category (determines the color of each datapoint),
the second a label (shown alongside each datapoint)."""
import sys
import pandas
import pylab as pl
from sklearn import preprocessing
from sklearn.decomposition import PCA

andreasvc

andreasvc

# This is a comment
FROM ubuntu:20.04
MAINTAINER Andreas van Cranenburgh <a.w.vancranenburgh@uva.nl>
RUN ln -fs /usr/share/zoneinfo/Europe/Amsterdam /etc/localtime
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y \
        build-essential \
        curl \
        git \
        python3 \

andreasvc

"""A baseline Bag-of-Words text classification.

Usage: python3 classify.py <train.txt> <test.txt> [--svm] [--tfidf] [--bigrams]
train.txt and test.txt should contain one "document" per line,
first token should be the label.
The default is to use regularized Logistic Regression and relative frequencies.
Pass --svm to use Linear SVM instead.
Pass --tfidf to use tf-idf instead of relative frequencies.
Pass --bigrams to use bigrams instead of unigrams.
"""

andreasvc

"""Extract metadata from Project Gutenberg RDF catalog into a Python dict.

Based on https://bitbucket.org/c-w/gutenberg/

>>> md = readmetadata()
>>> md[123]
{'LCC': {'PS'},
 'author': u'Burroughs, Edgar Rice',
 'authoryearofbirth': 1875,
 'authoryearofdeath': 1950,