Shawn Graham shawngraham

## demo.R
# demo for sharing a script
# in scripts, a hashtag (pound sign) = a comment (in markdown, it means a header)

# we create a variable called y, and give it a _string_ of text; in this case, the direct URL to a csv file
y <- "https://raw.githubusercontent.com/shawngraham/exercise/gh-pages/CND.csv"

# now we use the read.csv command to read the file address stored in 'y'; the results go into a dataframe called 'documents2'
documents2 <- read.csv(y)

## retrieve-theses-metadata.R
library(rvest)
library(dplyr)
library(xml2)
library(stringr)
library(purrr)

base_url <- "https://curve.carleton.ca"

theses = data.frame()

## test-neo4j.csv

          
            Artifact
            Position_X
            Position_Y
            chip name

            
              242
              1110.973076
              480.0500947
              /Users/shawngraham/Documents/chips2/object1/0000000001.png

            
              252
              772.6520572
              434.331038
              /Users/shawngraham/Documents/chips2/object2/0000000001.png

            
              1231
              626.3510759
              672.0701326
              /Users/shawngraham/Documents/chips2/object3/0000000001.png

            
              35
              2059.369176
              1630.107527
              /Users/shawngraham/Documents/chips2/object4/0000000001.png

            
              35
              594.3477363
              1275.56168
              /Users/shawngraham/Documents/chips2/object4/0000000002.png

## simple-scraper.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                shawngraham
                / simple-scraper.ipynb
            
            
              Created Dec 1, 2020
            
          
      View simple-scraper.ipynb
  
    
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## bib.xsl
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:output method="text"/>

<xsl:template match="/">

<xsl:for-each select="article/front">
"<xsl:value-of select="article-meta/contrib-group/contrib/string-name/surname" />, <xsl:value-of select="article-meta/contrib-group/contrib/string-name/given-names" />" <xsl:text>&#9;</xsl:text><xsl:value-of select="article-meta/pub-date/year" /> <xsl:text>&#9;</xsl:text> "<xsl:value-of select="article-meta/title-group/article-title" />" <xsl:text>&#9;"</xsl:text><xsl:value-of select="journal-meta/journal-title-group/journal-title"/>"<xsl:text>&#9;</xsl:text> "<xsl:value-of select="article-meta/volume" />(<xsl:value-of select="article-meta/issue" />)" <xsl:text>&#9;</xsl:text> "<xsl:value-of select="article-meta/page-range" />" <xsl:text>&#9;</xsl:text>"<xsl:value-of select="article-meta/article-id" />" <xsl:text>&#9;</xsl:text><xsl:value-of select="article-meta/self-uri" /><xsl:text>&#xA;</xsl:text>
</xsl:for-each>


## entities.csv

          
            doc
            entity
            entityType
            count

            
              104184105
              ABERDEEN
              organization
              1

            
              104184105
              Navy
              organization
              1

            
              104184105
              Sceptre
              organization
              1

            
              104184105
              1
              person
              1

            
              104184105
              Brodie
              person
              2

            
              104184105
              Cromar
              person
              2

            
              104184105
              Earl
              person
              1

            
              104184105
              Fife
              person
              3

            
              104184105
              Glen
              person
              1

## splitAudio.py

#!/usr/bin/python
## Split audio files into chunks
## Daniel Pett 1/5/2020
__author__ = 'portableant'
## Tested on Python 2.7.13

import argparse
import os
import speech_recognition as sr

## getNotes.scpt
(* Inspired and modified based on http://drosophiliac.com/2012/09/an-academic-notetaking-workflow.html and https://gist.github.com/smargh/6068104 *)

(* PROPERTIES *)
property LF : (ASCII character 10)
property tid : AppleScript's text item delimiters

(* THE SCRIPT *)
tell application "Skim"
	set the clipboard to ""
	activate

## now, extract the lat,long
import json
with open('ottawadata.json') as f:
    data = json.load(f)

....now, what cunning piece of code would do the trick? with jqplay I can get eg latitude with

.content.indexedStructured.geoLocation[]|.points[].latitude.content

anyway... off to read some basic python stuff I guess.

## topic-model-john-adams-diaries.r
# Topic Modeling John Adams' Diaries
# slightly modified version of
# https://tm4ss.github.io/docs/Tutorial_6_Topic_Models.html
# by Andreas Niekler, Gregor Wiedemann

library(tidyverse)
library(tidytext)

# go get the diaries
# these were scraped from
	# demo for sharing a script
	# in scripts, a hashtag (pound sign) = a comment (in markdown, it means a header)

	# we create a variable called y, and give it a _string_ of text; in this case, the direct URL to a csv file
	y <- "https://raw.githubusercontent.com/shawngraham/exercise/gh-pages/CND.csv"

	# now we use the read.csv command to read the file address stored in 'y'; the results go into a dataframe called 'documents2'
	documents2 <- read.csv(y)
	library(rvest)
	library(dplyr)
	library(xml2)
	library(stringr)
	library(purrr)

	base_url <- "https://curve.carleton.ca"

	theses = data.frame()
Artifact	Position_X	Position_Y	chip name
242	1110.973076	480.0500947	/Users/shawngraham/Documents/chips2/object1/0000000001.png
252	772.6520572	434.331038	/Users/shawngraham/Documents/chips2/object2/0000000001.png
1231	626.3510759	672.0701326	/Users/shawngraham/Documents/chips2/object3/0000000001.png
35	2059.369176	1630.107527	/Users/shawngraham/Documents/chips2/object4/0000000001.png
35	594.3477363	1275.56168	/Users/shawngraham/Documents/chips2/object4/0000000002.png
	<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
	<xsl:output method="text"/>

	<xsl:template match="/">

	<xsl:for-each select="article/front">
	"<xsl:value-of select="article-meta/contrib-group/contrib/string-name/surname" />, <xsl:value-of select="article-meta/contrib-group/contrib/string-name/given-names" />" <xsl:text> </xsl:text><xsl:value-of select="article-meta/pub-date/year" /> <xsl:text> </xsl:text> "<xsl:value-of select="article-meta/title-group/article-title" />" <xsl:text> "</xsl:text><xsl:value-of select="journal-meta/journal-title-group/journal-title"/>"<xsl:text> </xsl:text> "<xsl:value-of select="article-meta/volume" />(<xsl:value-of select="article-meta/issue" />)" <xsl:text> </xsl:text> "<xsl:value-of select="article-meta/page-range" />" <xsl:text> </xsl:text>"<xsl:value-of select="article-meta/article-id" />" <xsl:text> </xsl:text><xsl:value-of select="article-meta/self-uri" /><xsl:text> </xsl:text>
	</xsl:for-each>
doc	entity	entityType	count
104184105	ABERDEEN	organization	1
104184105	Navy	organization	1
104184105	Sceptre	organization	1
104184105	1	person	1
104184105	Brodie	person	2
104184105	Cromar	person	2
104184105	Earl	person	1
104184105	Fife	person	3
104184105	Glen	person	1

	#!/usr/bin/python
	## Split audio files into chunks
	## Daniel Pett 1/5/2020
	__author__ = 'portableant'
	## Tested on Python 2.7.13

	import argparse
	import os
	import speech_recognition as sr
	(* Inspired and modified based on http://drosophiliac.com/2012/09/an-academic-notetaking-workflow.html and https://gist.github.com/smargh/6068104 *)

	(* PROPERTIES *)
	property LF : (ASCII character 10)
	property tid : AppleScript's text item delimiters

	(* THE SCRIPT *)
	tell application "Skim"
	set the clipboard to ""
	activate
	import json
	with open('ottawadata.json') as f:
	data = json.load(f)

	....now, what cunning piece of code would do the trick? with jqplay I can get eg latitude with

	.content.indexedStructured.geoLocation[]\|.points[].latitude.content

	anyway... off to read some basic python stuff I guess.
	# Topic Modeling John Adams' Diaries
	# slightly modified version of
	# https://tm4ss.github.io/docs/Tutorial_6_Topic_Models.html
	# by Andreas Niekler, Gregor Wiedemann

	library(tidyverse)
	library(tidytext)

	# go get the diaries
	# these were scraped from