How Gousto is building an algorithm to offer personalised menus to their customers using python<\/p>\n
This talk will describe how Gousto, a leading recipe box service based in the UK, is using python to build a personalisation ecosystem. Our menu planning optimisation algorithm allows us to create the perfect \u2026<\/p>","content":"
How Gousto is building an algorithm to offer personalised menus to their customers using python<\/p>\n
This talk will describe how Gousto, a leading recipe box service based in the UK, is using python to build a personalisation ecosystem. Our menu planning optimisation algorithm allows us to create the perfect mix of recipes, ensuring a variety of dish types, cuisines and ingredients. Our recommendation engine sitting on top of this can then offer each customer a personally curated menu, making sure that users have meaningful choice. All this while ensuring that we are also optimising for maximum performance from the operations point of view!<\/p>\n
To build this, we have used a range of Python packages, such as DEAP for implementing genetic algorithms, and integrations, such as the one for graph database neo4j.<\/p>\n
The talk will give an overview of our methods, our infrastructure, our results and everything that we have learnt along the way!<\/p>\n","category":[{"@attributes":{"term":"EuroPython 2020"}},{"@attributes":{"term":"europython"}},{"@attributes":{"term":"europython-2020"}},{"@attributes":{"term":"europython-online"}},{"@attributes":{"term":"Algorithms"}},{"@attributes":{"term":"Case Study"}},{"@attributes":{"term":"Data Science"}},{"@attributes":{"term":"E-Commerce"}},{"@attributes":{"term":"Machine-Learning"}}]},{"title":"LFS - Ein Online-Shop basierend auf Django","link":{"@attributes":{"href":"https:\/\/pyvideo.org\/pycon-de-2012\/lfs-ein-online-shop-basierend-auf-django.html","rel":"alternate"}},"published":"2012-10-31T00:00:00+00:00","updated":"2012-10-31T00:00:00+00:00","author":{"name":"Kai Diefenbach"},"id":"tag:pyvideo.org,2012-10-31:\/pycon-de-2012\/lfs-ein-online-shop-basierend-auf-django.html","summary":"
LFS ist ein Online-Shop basieren auf Python, Django und jQuery. Er\nerfreut sich zunehmender Aufmerksamkeit, sowohl bei Entwicklern als auch\nbei Anwendern. Laut djangopackages.com<\/a>\nist LFS der am h\u00e4ufigsten heruntergeladene Shop f\u00fcr Django. \u00c4nderungen\nam Source Code verfolgen \u00fcber 200 Entwickler und die Google-Gruppe hat\nzur Zeit \u00fcber \u2026<\/p>","content":" LFS ist ein Online-Shop basieren auf Python, Django und jQuery. Er\nerfreut sich zunehmender Aufmerksamkeit, sowohl bei Entwicklern als auch\nbei Anwendern. Laut djangopackages.com<\/a>\nist LFS der am h\u00e4ufigsten heruntergeladene Shop f\u00fcr Django. \u00c4nderungen\nam Source Code verfolgen \u00fcber 200 Entwickler und die Google-Gruppe hat\nzur Zeit \u00fcber 170 Mitglieder.<\/p>\n LFS ist praxiserprobt. Beispiele f\u00fcr gro\u00dfe und erfolgreiche Shops sind:<\/p>\n Kai Diefenbach, Gr\u00fcnder und einer der Kern-Entwickler, gibt in diesem\nVortrag ein \u00dcberblick zu folgenden Themen:<\/p>\n Carsten Pohl<\/strong> (@carstenpohl)<\/p>\n Before joining REWE digital I worked for Zalando, Fraunhofer IML. My first computer was a VIC-20. I develop professionally software since the 90ies. I am one of the main developers of the new Big data platform of REWE digital, and have deep knowledge about all aspects \u2026<\/p>","content":" Carsten Pohl<\/strong> (@carstenpohl)<\/p>\n Before joining REWE digital I worked for Zalando, Fraunhofer IML. My first computer was a VIC-20. I develop professionally software since the 90ies. I am one of the main developers of the new Big data platform of REWE digital, and have deep knowledge about all aspects of the platform. And I have no favorite member of One Direction.<\/p>\n Abstract<\/strong><\/p>\n shop.rewe.de is not only visited by human customers, but also by machines. We have built a deep learning platform using python with Keras, Tensorflow, on the Google infrastructure. In this talk we would like to show you how python is used in practice, supporting 2,5 million visitors each day.<\/p>\n Description<\/strong><\/p>\n shop.rewe.de is visited over 2 million times each day. Every visitor is producing thousands of requests in our micro service architecture. We are trying to give the best shopping experience for our customers, and try to keep our platform safe from bad bots. This is partly done by rule sets, and furthermore done by a platform that uses machine learning to classify bad behaviour. In this talk I would like to present our architecture that is not only able to fulfill this use case, but enables our data scientists in general to use our big data platform. the main scope will be the presentation of the use case. I will cover:<\/p>\n Recorded at<\/strong> PyCon.DE 2017 Karlsruhe: https:\/\/de.pycon.org\/<\/a><\/p>\n Video editing<\/strong>: Sebastian Neubauer & Andrei Dan<\/p>\n Tools<\/strong>: Blender, Avidemux & Sonic Pi<\/p>\n","category":[{"@attributes":{"term":"PyCon DE 2017"}},{"@attributes":{"term":"python"}},{"@attributes":{"term":"use-case"}},{"@attributes":{"term":"deep learning"}},{"@attributes":{"term":"e-commerce"}}]},{"title":"Real world Graphene - lessons learned from building a GraphQL API on top of a large Django project","link":{"@attributes":{"href":"https:\/\/pyvideo.org\/pycon-italia-2019\/real-world-graphene-lessons-learned-from-building-a-graphql-api-on-top-of-a-large-django-project.html","rel":"alternate"}},"published":"2019-05-05T00:00:00+00:00","updated":"2019-05-05T00:00:00+00:00","author":{"name":"Marcin G\u0119bala"},"id":"tag:pyvideo.org,2019-05-05:\/pycon-italia-2019\/real-world-graphene-lessons-learned-from-building-a-graphql-api-on-top-of-a-large-django-project.html","summary":" Graphene is currently the most popular framework for building a GraphQL\nin Python and it\u2019s also an obvious choice for adding a GraphQL layer to\nDjango applications. Over the course of a year, we successfully built an\nAPI with about 50 queries and over 100 mutations on top \u2026<\/p>","content":" Graphene is currently the most popular framework for building a GraphQL\nin Python and it\u2019s also an obvious choice for adding a GraphQL layer to\nDjango applications. Over the course of a year, we successfully built an\nAPI with about 50 queries and over 100 mutations on top of existing\nDjango project (Saleor), but we also learned some hard lessons and had\nto overcome several shortcomings of the framework along the way.<\/p>\n In this talk, I\u2019d like to share some practical tips to overcome the most\ncommon problems that a Django developer might face when building an\noptimized and maintainable API with Graphene, such as: - using useful\nabstractions to build queries and mutations faster - optimizing database\nqueries in a graph - structuring a large Graphene project - unified\nerror handling<\/p>\n I\u2019d also like to bring up a few limitations of the framework that we\ndiscovered as we were working on the project and then end the talk with\nthe most important benefits that adoption of GraphQL brings to modern\nweb applications development - both for the backend and frontend.<\/p>\n Prerequisites: - Intermediate knowledge of Django - Familiarity with API\ndesign and concepts in terms of web development - Basic knowledge of\nGraphQL or interest in it<\/p>\n I think the talk would be of great value to anyone working with a\nGraphene framework and those who want to know more about building\nGraphQL in Python.<\/p>\n All code examples in the presentation would be based on Saleor\n(https:\/\/github.com\/mirumee\/saleor<\/a>).<\/p>\n Feedback form:<\/strong> https:\/\/python.it\/feedback-1644<\/a><\/p>\n in __on Sunday 5 May<\/strong> at 11:45 **See\nschedule**<\/a><\/p>\n","category":[{"@attributes":{"term":"PyCon Italia 2019"}},{"@attributes":{"term":"API Design"}},{"@attributes":{"term":"e-commerce"}},{"@attributes":{"term":"graphql"}},{"@attributes":{"term":"open-source"}},{"@attributes":{"term":"django"}}]}]}Summary<\/h3>
\n
\n
Description<\/h3>
Description<\/h3>
\n
Description<\/h3>
Description<\/h3>