66 "source" : [
77 " ## <span style=\" color:#ff5f27\" >👩🏻🔬 Feature Engineering </span>\n "
88 " \n "
9+ " **Note**: This tutorial does not support Google Colab.\n "
10+ " \n "
911 " **Your Python Jupyter notebook should be configured for >8GB of memory.**\n "
1012 " \n "
1113 " In this series of tutorials, we will build a recommender system for fashion items. It will consist of two models: a *retrieval model* and a *ranking model*. The idea is that the retrieval model should be able to quickly generate a small subset of candidate items from a large collection of items. This comes at the cost of granularity, which is why we also train a ranking model that can afford to use more features than the retrieval model.\n "
3133 " ## <span style=\" color:#ff5f27\" >📝 Imports </span>"
3234 ]
3335 },
34- {
35- "cell_type" : " code"
36- "execution_count" : null ,
37- "metadata" : {},
38- "outputs" : [],
39- "source" : [
40- " # Hosted notebook environments may not have the local features package\n "
41- " import os\n "
42- " \n "
43- " def need_download_modules():\n "
44- " if 'google.colab' in str(get_ipython()):\n "
45- " return True\n "
46- " if 'HOPSWORKS_PROJECT_ID' in os.environ:\n "
47- " return True\n "
48- " return False\n "
49- " \n "
50- " if need_download_modules():\n "
51- " print(\" ⚙️ Downloading modules...\" )\n "
52- " os.system('mkdir -p features')\n "
53- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/articles.py')\n "
54- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/customers.py')\n "
55- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/transactions.py')\n "
56- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/ranking.py') \n "
57- " print('✅ Done!')\n "
58- " else:\n "
59- " print(\" Local environment\" )"
60- ]
61- },
62- {
63- "cell_type" : " code"
64- "execution_count" : null ,
65- "metadata" : {},
66- "outputs" : [],
67- "source" : [
68- " try:\n "
69- " from features.articles import prepare_articles\n "
70- " from features.customers import prepare_customers\n "
71- " from features.transactions import prepare_transactions\n "
72- " from features.ranking import compute_ranking_dataset\n "
73- " except ImportError:\n "
74- " print(\" ⚙️ Downloading modules...\" )\n "
75- " os.system('mkdir -p features')\n "
76- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/articles.py')\n "
77- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/customers.py')\n "
78- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/transactions.py')\n "
79- " os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/ranking.py') \n "
80- " print('✅ Done!')\n "
81- " from features.articles import prepare_articles\n "
82- " from features.customers import prepare_customers\n "
83- " from features.transactions import prepare_transactions\n "
84- " from features.ranking import compute_ranking_dataset "
85- ]
86- },
8736 {
8837 "cell_type" : " code"
8938 "execution_count" : null ,
9443 " import numpy as np\n "
9544 " \n "
9645 " import great_expectations as ge\n "
97- " from great_expectations.core import ExpectationSuite, ExpectationConfiguration"
46+ " from great_expectations.core import ExpectationSuite, ExpectationConfiguration\n "
47+ " \n "
48+ " from features.articles import prepare_articles\n "
49+ " from features.customers import prepare_customers\n "
50+ " from features.transactions import prepare_transactions\n "
51+ " from features.ranking import compute_ranking_dataset "
9852 ]
9953 },
10054 {
613567 "metadata" : {},
614568 "outputs" : [],
615569 "source" : [
616- " ranking_df = compute_ranking_dataset(trans_fg, articles_fg, customers_fg)"
570+ " ranking_df = compute_ranking_dataset(\n "
571+ " trans_fg, \n "
572+ " articles_fg, \n "
573+ " customers_fg,\n "
574+ " )"
617575 ]
618576 },
619577 {
687645 "hash" : " 31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
688646 },
689647 "kernelspec" : {
690- "display_name" : " Python"
648+ "display_name" : " Python 3 (ipykernel) "
691649 "language" : " python"
692650 "name" : " python3"
693651 },
701659 "name" : " python"
702660 "nbconvert_exporter" : " python"
703661 "pygments_lexer" : " ipython3"
704- "version" : " 3.10.11 "
662+ "version" : " 3.9.18 "
705663 }
706664 },
707665 "nbformat" : 4 ,
708666 "nbformat_minor" : 4
709- }
667+ }
0 commit comments