internaut

import numpy as np


def word_cooccurrence(dtm):
    """
    Calculate the co-document frequency (aka word co-occurrence) matrix for a document-term matrix `dtm`, i.e. how often
    each pair of tokens occurs together at least once in the same document.

    :param dtm: (sparse) document-term-matrix of size NxM (N docs, M is vocab size) with raw term counts.
    :return: co-document frequency (aka word co-occurrence) matrix with shape MxM

internaut

"""
Sample scripts for blog post "Robust data collection via web scraping and web APIs"
(https://datascience.blog.wzb.eu/2020/12/01/robust-data-collection-via-web-scraping-and-web-apis/).

Script 1. Starting point – baseline (unreliable) web scraping script.

December 2020, Markus Konrad <[email protected]>
"""

from datetime import datetime, timedelta

internaut

"""
Voronoi regions of schools in East Germany.
An example using the geovoronoi package (https://pypi.org/project/geovoronoi/).

Feb. 2021

Markus Konrad <[email protected]>
"""

import os

internaut

"""
Transfer all GitLab projects from the user authenticated with a supplied private access token (PAT) to a new
namespace (i.e. a group with a group ID).

To generate a PAT, log in to your GitLab account and go to "User settings > Access tokens".

To find out the ID of a group to which you want to transfer the projects, go to the group's page. The group ID is shown
under the title of the group.

Requirements: Python 3 with requests package installed (tested with Python 3.8 and requests 2.27.1).

internaut

#!/bin/python3
# Copy contents of a XSFP music playlist to a target folder
#
# required two arguments: path to xspf file, target path
# requires Python >= 3.8
# 
# author: Markus Konrad <[email protected]>

import os.path
import sys