{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"ds-1000","formal_name":"DS-1000","introduction":"DS-1000 builds 1,000 data-science problems from real StackOverflow questions across seven libraries including NumPy, Pandas and Matplotlib. The problems are perturbed so that recalling the original answer does not solve them.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://ds1000-code-gen.github.io/","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"a312465b-a617-5a82-a193-68de0ede7262","task_key":"default--test--926","task_revision_id":"1","upstream_id":"926","short_description":"Here is my code:","config":"default","split":"test","body":"{\"library\":\"Sklearn\",\"prompt\":\"Problem:\\n\\nHere is my code:\\n\\ncount = CountVectorizer(lowercase = False)\\n\\nvocabulary = count.fit_transform([words])\\nprint(count.get_feature_names())\\nFor example if:\\n\\n words = \\\"Hello @friend, this is a good day. #good.\\\"\\nI want it to be separated into this:\\n\\n['Hello', '@friend', 'this', 'is', 'a', 'good', 'day', '#good']\\nCurrently, this is what it is separated into:\\n\\n['Hello', 'friend', 'this', 'is', 'a', 'good', 'day']\\n\\nA:\\n\\nrunnable code\\n<code>\\nimport numpy as np\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\nwords = load_data()\\n</code>\\nfeature_names = ... # put solution in this variable\\nBEGIN SOLUTION\\n<code>\\n\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://ds1000-code-gen.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}