Context Navigation

Changeset 38791

Timestamp:

2024-02-26T00:44:26+13:00 (3 months ago)

Author:

jc550

Message:

add comments adding context to functions that require it

Location:

other-projects/metadata-encoding/py

Files:

r38442	r38791
1	1	#!/usr/bin/env PYTHONIOENCODING=utf-8 python
2	2	# encoding: utf-8
	3
	4	# Created by Chris Adams, source (https://gist.github.com/acdha/49a610089c2798db6fe2)
3	5
4	6	from __future__ import absolute_import, print_function, unicode_literals

r38442	r38791
	1	# Created by Chris Adams, source (https://gist.github.com/acdha/49a610089c2798db6fe2)
	2
1	3	import icu
2	4

r38473	r38791
	1	# unfinished experimental function that was supposed to be a part of the equivalence "comparison" test between different academic databases
	2	# for cleaning titles with obviously stupid things in them to test if they WOULD be the same without them
	3
1	4	import re, sys, argparse
2	5

r38771	r38791
	1	# Function to take a sample of articles from CrossRef and display information about the percentage of "Pure Latin" in the titles
	2
1	3	from habanero import Crossref
2	4	import get_unicode_blocks

r38772	r38791
1		#compare titles of openalex and xref, checking to see if the subtitle matters
	1	# compare titles of openalex and xref, checking to see if the subtitle matters
	2	# would probably work a lot better if openalex was in a database. major bottleneck on api wait times
2	3
3	4	import sys, pymongo, json

-              r38773
+              r38791
 # Program to get data from CrossRef, and OpenAlex formatted in a nice JSON file.
+# Was supposed to be a replacement for another function pre-mongo.
 # Crossref API library
 …
+# Unfinished and not worth continuing
 if __name__ == "__main__":

r38772	r38791
2	2	# encoding: utf-8
3	3
4		# This is code from ~~(somewhere) github~~
	4	# This is code from Chris Adams, source https://gist.github.com/acdha/49a610089c2798db6fe2
5	5
6	6	from __future__ import absolute_import, print_function, unicode_literals

r38773	r38791
	1	# slight messing around with plotting library to test suitablility
	2
1	3	import matplotlib as mpl
2	4	import matplotlib.pyplot as plt

r38773	r38791
	1	# Created by Chris Adams, source (https://gist.github.com/acdha/49a610089c2798db6fe2)
	2
1	3	import icu
2	4

r38773	r38791
	1	# test to retrieve subtitles
	2
1	3	from habanero import Crossref
2	4	from diophila import OpenAlex

r38773	r38791
1	1	#!/usr/bin/env python3
	2
	3	# Script to generate a time series graph of percentage of & errors in CrossRef titles
	4	# Does not generate a data file! Graphing is handled by matplotlib.
2	5
3	6	import pymongo

-              r38773
+              r38791
 # function to display cool(?) statistics about the subtitle
 import datetime
 from dateutil.relativedelta import relativedelta
 …
 def main():
+    # Connect to database
     mClient = MongoClient("mongodb://localhost:27017/")
     mDatabase = mClient["test"]
     mCollection = mDatabase["crossref"]
+    getMinDateQuery = "asdas"
+    # Get minimum date
     minimumDateQuery = mCollection.find().sort("dateCreated").limit(1)
+    # Get documents sorted by date
     sortedCollectionQuery = mCollection.find().sort("dateCreated")
+    # And the count
     countQuery = mCollection.estimated_document_count()
 …
                 #increase currentdate by a month
+        # currently unfinished. Need to finish the statistics insertion part of the method, and actually do something with that data.
 main()

Note: See TracChangeset for help on using the changeset viewer.