Michele Pasin lambdamusic

## 1-introducing-datasets.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                lambdamusic
                / 1-introducing-datasets.ipynb
            
            
              Created Nov 30, 2020
            
              
                test.ipynb
              
          
      View 1-introducing-datasets.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.
      
    
## python_request_create_gist.py
'''
HTTP Reuests has following parameters:
1)Request URL
2)Header Fields
3)Parameter
4)Request body

PREREQUISITE
* head over to https://github.com/settings/tokens and generate a new token with 'gists' permissions

## load_logs_from_s3.py
#!/usr/bin/python
# -*- coding: utf-8 -*-


"""
iterate a bucket in s3 containing JSON log files
get each file, massage json a little and uploade to elasticsearc
"""

## split_json.sh
#!/bin/bash
FILENAME=records_111901_00000000.jsonl
split -a 5 -l 1 $FILENAME temp
n=1
for f in temp*
do
	cat $f >> Part${n}.json
	rm $f
	((n++))
done

## splitter.sh
#!/bin/bash
FILENAME=filename_here.csv
HDR=$(head -1 $FILENAME)
split -l 100 $FILENAME xyz
n=1
for f in xyz*
do
	if [ $n -gt 1 ]; then
		echo $HDR > Part${n}.csv
	fi

## scigraph_context.json
# source: https://github.com/springernature/scigraph/blob/master/2018Q3/context/scigraph.json

{
    "@context": {
        "@vocab": "http://schema.org/",
        "@base": null,
        "sg": "http://scigraph.springernature.com/id/",
        "sgo": "http://scigraph.springernature.com/ontologies/core/",
        "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
        "rdfs": "http://www.w3.org/2000/01/rdf-schema#",

## grant.jsonld
{
    "@context": {
        "@vocab": "http://schema.org/",
        "@base": null,
        "sg.articles": "http://scigraph.springernature.com/things/articles/",
        "sg.persons": "http://scigraph.springernature.com/things/persons/",
        "sg.grants": "http://scigraph.springernature.com/things/grants/",
        "sg": "http://scigraph.springernature.com/ontologies/core/"
    },
    "@id": "sg.grants:grant.2691278",

## SPARQL queries to obtain statistics.
# Obtain the label of a given class (:class1).
SELECT DISTINCT ?c (STR(?l) AS ?lb)
    WHERE {
      ?c a :class1 ;
        <http://www.w3.org/2000/01/rdf-schema#label> ?l .
    }

# Obtain a list of classes.
SELECT DISTINCT ?c
    WHERE {

## querymanager.py
    def __getitem__(self, key):
        """
        Basic slicing support up to 100 (QueryManager.BATCH_DEFAULT_SIZE)
        https://docs.python.org/3/reference/datamodel.html#object.__getitem__

        This is just quick way to get samples items, as it works only for the initial batch of results.

        Use the next() method to go through all the resultset.
        """
        if isinstance( key, slice ) :

## Django 1.8 static tips

# usual way

```
<link href="{% static 'libs/bootswatch3.2/{{ THEME }}/bootstrap.min.css' %}" rel="stylesheet">
```

# more manual but works if you have variables in it

```
	'''
	HTTP Reuests has following parameters:
	1)Request URL
	2)Header Fields
	3)Parameter
	4)Request body

	PREREQUISITE
	* head over to https://github.com/settings/tokens and generate a new token with 'gists' permissions
	#!/usr/bin/python
	# -- coding: utf-8 --


	"""
	iterate a bucket in s3 containing JSON log files
	get each file, massage json a little and uploade to elasticsearc
	"""
	#!/bin/bash
	FILENAME=records_111901_00000000.jsonl
	split -a 5 -l 1 $FILENAME temp
	n=1
	for f in temp*
	do
	cat $f >> Part${n}.json
	rm $f
	((n++))
	done
	#!/bin/bash
	FILENAME=filename_here.csv
	HDR=$(head -1 $FILENAME)
	split -l 100 $FILENAME xyz
	n=1
	for f in xyz*
	do
	if [ $n -gt 1 ]; then
	echo $HDR > Part${n}.csv
	fi
	# source: https://github.com/springernature/scigraph/blob/master/2018Q3/context/scigraph.json

	{
	"@context": {
	"@vocab": "http://schema.org/",
	"@base": null,
	"sg": "http://scigraph.springernature.com/id/",
	"sgo": "http://scigraph.springernature.com/ontologies/core/",
	"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
	"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
	# Obtain the label of a given class (:class1).
	SELECT DISTINCT ?c (STR(?l) AS ?lb)
	WHERE {
	?c a :class1 ;
	<http://www.w3.org/2000/01/rdf-schema#label> ?l .
	}

	# Obtain a list of classes.
	SELECT DISTINCT ?c
	WHERE {
	def __getitem__(self, key):
	"""
	Basic slicing support up to 100 (QueryManager.BATCH_DEFAULT_SIZE)
	https://docs.python.org/3/reference/datamodel.html#object.__getitem__

	This is just quick way to get samples items, as it works only for the initial batch of results.

	Use the next() method to go through all the resultset.
	"""
	if isinstance( key, slice ) :

	# usual way

	```
	<link href="{% static 'libs/bootswatch3.2/{{ THEME }}/bootstrap.min.css' %}" rel="stylesheet">
	```

	# more manual but works if you have variables in it

	```