Douglas Hindson curiousest

Hi, I'm Douglas from Babylon Health!

curiousest / compare_pandas_dataframes.py

Created November 25, 2021 17:12

Compare pandas dataframes

	# Because I couldn't get this to do what I wanted:
	# https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.compare.html

	import pandas as pd
	from typing import Optional, List

	def compare_dataframes(df1, df2, drop_indexes=False, ignore_columns: Optional[List]=None):
	'''Returns two dataframes: the rows that only show up in each dataframe'''
	if drop_indexes:
	df1 = df1.reset_index(drop=True)

curiousest / reducefieldsmixin.py

Created June 3, 2017 11:24

DRF reduce serializer fields mixin

	class ReduceFieldsMixin:
	def get_fields(self, args, *kwargs):
	fields = super().get_fields(args, *kwargs)
	query_params = getattr(self.context.get('request', {}), 'query_params', {})
	requested_fields = query_params.get('fields', None)

	if requested_fields:
	requested_fields = requested_fields.split(',')
	fields = {key: value for key, value in fields.items() if key in requested_fields}
	return fields

curiousest / postgres_autonumbering.py

Created May 24, 2017 11:17

Postgres table id prefix

	def set_up_autonumbering(engine, table, prefix):
	conn = engine.connect()
	try:
	logging.info("Creating autonumber sequence for {}".format(table))
	conn.execute("CREATE SEQUENCE {}_ids".format(table))
	except:
	logging.info("Autonumber sequence already created".format(table))

	try:

curiousest / django_per_request_fields

Created November 28, 2016 13:54

	class PerRequestFieldsSerializerMixin():
	def get_field_names(self, args, *kwargs):
	field_names = super().get_field_names(args, *kwargs)
	request_field_names = getattr(
	getattr(kwargs.get('context', {}).get('view', None), 'request', None),
	'query_params', {}
	).get('fields', None)
	if request_field_names is not None:
	request_field_names = request_field_names.split(',')
	return list(set(field_names) ^ set(request_field_names))

curiousest / read_postgres_sqlalchemy.py

Created November 23, 2016 15:20

Use automap_base to use an existing db with sqlalchemy

	from sqlalchemy import MetaData, create_engine
	from sqlalchemy.orm import sessionmaker
	from sqlalchemy.ext.automap import automap_base
	from sqlalchemy.sql import select
	from sqlalchemy import func

	engine = create_engine('postgres://db_user@db_host:5432/db_name', client_encoding='utf8')
	Session = sessionmaker(bind=engine)
	session = Session()

curiousest / gist:ed3e595148f48ca427e3

Created October 15, 2015 11:28

Memory efficient Django Queryset Iterator

	import gc


	# inspiration: https://djangosnippets.org/snippets/1949/
	def queryset_memreduce_iterator(queryset, field='pk', queryset_filter='pk__gt',
	ordering_function=lambda x, y: x < y,
	chunksize=1000):
	'''''
	Iterate over a Django Queryset ordered by field (kwarg)

curiousest / gist:5386350

Created April 15, 2013 07:28

	jitsu deploy
	info: Welcome to Nodejitsu curiousest
	info: jitsu v0.12.10-1, node v0.8.21
	info: It worked if it ends with Nodejitsu ok
	info: Executing command deploy
	warn:
	warn: The package.json file is missing required fields:
	warn:
	warn: Subdomain name
	warn: