{"blog_title":"IT\u306e\u968a\u9577\u306e\u30d6\u30ed\u30b0","title":"PySpark\u306e\u96d1\u30e1\u30e2","width":"100%","version":"1.0","type":"rich","author_url":"https://blog.hatena.ne.jp/aipacommander/","image_url":null,"provider_name":"Hatena Blog","blog_url":"https://aipacommander.com/","url":"https://aipacommander.com/entry/2020/01/28/063624","categories":["PySpark"],"published":"2020-01-28 06:36:24","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Faipacommander.com%2Fentry%2F2020%2F01%2F28%2F063624\" title=\"PySpark\u306e\u96d1\u30e1\u30e2 - IT\u306e\u968a\u9577\u306e\u30d6\u30ed\u30b0\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","author_name":"aipacommander","description":"PySpark\u3067\u4f7f\u3044\u65b9\u306b\u56f0\u3063\u305f\u3068\u304d\u306e\u30e1\u30e2 \u8907\u6570\u30ab\u30e9\u30e0\u3067\u96c6\u8a08 from pyspark.sql import functions as F a1 = df.groupby('column_1', 'column_2').agg(F.count(F.col('column_3')).alias('count'), F.collect_set('column_4').alias('collect_column_4')) \u8907\u6570\u30ab\u30e9\u30e0\u3067orderby from pyspark.sql import functions as F a1 = df.select('column_1', 'column_2',\u2026","provider_url":"https://hatena.blog","height":"190"}