erickpeirson

# Usage:
#  $ python process_workspace [path to workspace] [path to output directory]

import sys
import os
import pandas as pd
import re

md = sys.argv[1]        # Path to directory containing Hydrus output directories.
outpath = sys.argv[2]   # Path to directory where processed data will be stored.

erickpeirson

# Usage:
#  python change_nodes.py [path to workspace]

import sys
import os
import subprocess
import re

hpath = os.path.join(sys.argv[1], 'PROFILE.DAT')

erickpeirson

# Usage:
#  $ python process_tlevel.py [path to data] [path to output]
#
# [path to data] should point to a directory containing Hydrus workspaces (subdirectories)
#  each of which contains a file called "T_Level.out". If such a file is not encountered
#  in a subdirectory, that subdirectory will be ignored quietly.
#

import sys
import os

erickpeirson

import websocket
import re
import socket

class OpenIEExtractor(object):
    endtoken = ''
    greeting = '* * * * * * * * * * * * *'
    
    def __init__(self, hostname, port, verbose=False):
        url = 'ws://{hostname}:{port}'.format(hostname=hostname, port=port)

erickpeirson

import nltk

class AuthoritativeText(object):
    original = ""
    T = []    # Tokens.
    P = []    # Paragraph start indices (in T).
    S = []    # Sentence start indices (in T).
    I = []    # Token start,end character position indices.
    
    def __init__(self, text): 

erickpeirson

# I found this package called "reshape", and it looks useful:
#  http://svitsrv25.epfl.ch/R-doc/library/reshape/html/00Index.html
library("reshape")

# Here are some jagged data with a shared column.
d1<-data.frame(primary=c(1, 2, 3, 4), foo='bar')
d2<-data.frame(primary=c(1,3,5), secret=42)
d3<-data.frame(primary=c(5, 3, 1, 20, 4), scout="scout")
d4<-data.frame(primary=c(6, 7, 20, 4), bat='baz')
d5<-data.frame(primary=c(1, 2, 3, 4, 5, 6, 7), pi=3.141592764)

erickpeirson

erickpeirson

<OAI-PMH xmlns:bib="http://purl.org/net/biblio#" xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dcterms="http://purl.org/dc/terms/" xmlns:foaf="http://xmlns.com/foaf/0.1/"
xmlns:prsmstndrd="http://prismstandard.org/namespaces/1.2/basic#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns"
xmlns:ztr="http://www.zotero.org/namespaces/export#" xmlns="http://www.openarchives.org/OAI/2.0/"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
    <responseDate>2016-09-09T19:41:07Z</responseDate>
    <request verb="ListRecords" set="1" metadataPrefix="oai_dc">/oaipmh/</request>
    <ListRecords>
        <record>
            <header>

erickpeirson

from django.contrib.contenttypes.models import ContentType
from collections import Counter
import networkx as nx

def generate_collection_coauthor_graph(collection, 
                                       author_predicate_uri="http://purl.org/net/biblio#authors"):
    """
    Create a graph describing co-occurrences of :class:`.ConceptEntity` instances
    linked to individual :class:`.Resource` instances via an authorship 
    :class:`.Relation` instance. 

erickpeirson

<VirtualHost *:80>
    WSGIDaemonProcess references user=apache group=apache threads=5 python-path=/opt/reflink/arxiv-reflink:/opt/reflink/venv/lib/python3.5/site-packages:/opt/reflink/venv/lib64/python3.5/site-packages home=/opt/reflink/arxiv-reflink
    WSGIScriptAlias / /opt/reflink/arxiv-reflink/reflink.wsgi process-group=references

    <Directory /opt/reflink/arxiv-reflink>
        WSGIProcessGroup references
        WSGIApplicationGroup %{GLOBAL}
        WSGIScriptReloading On
        Require all granted
    </Directory>