{"id":47388,"date":"2023-06-11T21:07:44","date_gmt":"2024-01-11T14:13:14","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/"},"modified":"2024-04-30T08:26:47","modified_gmt":"2024-04-30T00:26:47","slug":"%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/","title":{"rendered":"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09"},"content":{"rendered":"<p>\u8fd9\u662f\u4e00\u7bc7\u9006\u5411PySpark\u7cfb\u5217\u7684\u5b57\u7b26\u4e32\u7248\u672c\uff0c\u603b\u7ed3\u4e86\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\u5e94\u8be5\u600e\u4e48\u505a\u3002<br \/>\n\uff08\u5c06\u4e0d\u65ad\u8fdb\u884c\u66f4\u65b0\u3002\uff09<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u539f\u5247\u3068\u3057\u3066Apache Spark 3.3\u306ePySpark\u306eAPI\u306b\u6e96\u62e0\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u4e00\u90e8\u3001\u4fbf\u5229\u306aDatabricks\u9650\u5b9a\u306e\u6a5f\u80fd\u3082\u5229\u7528\u3057\u3066\u3044\u307e\u3059\uff08\u5229\u7528\u3057\u3066\u3044\u308b\u3068\u3053\u308d\u306f\u305d\u306e\u65e8\u8a18\u8f09\u3057\u3066\u3044\u307e\u3059\uff09\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Databricks Runtime 11.3 \u4e0a\u3067\u52d5\u4f5c\u3059\u308b\u3053\u3068\u3092\u78ba\u8a8d\u3057\u3066\u3044\u307e\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30ce\u30fc\u30c8\u30d6\u30c3\u30af\u3092\u3053\u3061\u3089\u306e\u30ea\u30dd\u30b8\u30c8\u30ea \u304b\u3089Repos\u306b\u3066\u3054\u4f7f\u7528\u306eDatabricks\u306e\u74b0\u5883\u306b\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3067\u304d\u307e\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u9006\u5f15\u304dPySpark\u306e\u4ed6\u306e\u7ae0\u306b\u3064\u3044\u3066\u306f\u3001\u3053\u3061\u3089\u306e\u8a18\u4e8b\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002<\/ul>\n<h2>\u4f8b\u53e5\u7684\u524d\u63d0\u6761\u4ef6<\/h2>\n<ul class=\"post-ul\">SparkSession\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u304cspark\u3068\u3044\u3046\u5909\u6570\u540d\u3067\u5229\u7528\u53ef\u80fd\u306a\u3053\u3068<\/ul>\n<h1>\u6574\u5f62\u624b\u672f\u7684\u610f\u601d\u662f\u901a\u8fc7\u5916\u79d1\u624b\u672f\u6765\u6539\u53d8\u6216\u4fee\u590d\u4eba\u4f53\u5916\u8c8c\u6216\u8eab\u4f53\u7ed3\u6784\u3002<\/h1>\n<h2>\u5c063-1-1\u53d8\u6210\u5927\u5199\u5b57\u6bcd\u3002<\/h2>\n<p>\u4f7f\u7528upper()\u51fd\u6570\u5c06\u5b57\u7b26\u4e32\u8f6c\u6362\u4e3a\u5927\u5199\u5b57\u6bcd\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">upper<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u306e\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name_upper<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">upper<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">last_name_upper<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">upper<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">last_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u662f\u5de5\u4f5c\u65f6\u6240\u6295\u5165\u7684\u80fd\u91cf\u548c\u52aa\u529b\u3002<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namefirst_name_upperlast_name_upper110LionelMessiLIONELMESSI29JulianAlvarezJULIANALVAREZ322LautaroMartinezLAUTAROMARTINEZ<\/div>\n<\/div>\n<h2>3-1-2 \u6539\u6210\u5c0f\u5b57<\/h2>\n<p>\u4f7f\u7528lower()\u51fd\u6570\u5c06\u5b57\u7b26\u4e32\u8f6c\u6362\u4e3a\u5c0f\u5199\u5b57\u6bcd\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lower<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u306e\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name_lower<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lower<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">last_name_lower<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lower<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">last_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u6765\u8bf4\u660e<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namefirst_name_lowerlast_name_lower110JulianAlvarezlionelmessi29LautaroMartinezjulianalvarez322LionelMessilautaromartinez<\/div>\n<\/div>\n<h2>\u5c063-1-3\u4e2d\u7684\u6bcf\u4e2a\u5355\u8bcd\u7684\u9996\u5b57\u6bcd\u6539\u4e3a\u5927\u5199<\/h2>\n<p>\u4f7f\u7528initcap()\u51fd\u6570\uff0c\u5c06\u5355\u8bcd\u7684\u9996\u5b57\u6bcd\u53d8\u4e3a\u5927\u5199\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">initcap<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u306e\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name_initcap<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">initcap<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">last_name_initcap<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">initcap<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">last_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51fa\u529b\u4f8b\u7684\u7ffb\u8bd1\u5982\u4e0b\uff1a\u4f8b\u5b50\u7684\u4ea7\u51fa\u3002<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namefirst_name_initcaplast_name_initcap110LIONELMESSILionelMessi29JULIANALVAREZJulianAlvarez322LAUTAROMARTINEZLautaroMartinez<\/div>\n<\/div>\n<h2>\u6574\u7406\u6570\u5b57\u4e3a 3-1-4.<\/h2>\n<p>\u4f7f\u7528format_number()\u51fd\u6570\uff0c\u5bf9\u6570\u503c\u8fdb\u884c\u683c\u5f0f\u5316\u5904\u7406\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">format_number<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6570\u5024\u578b\u306e\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u5c0f\u6570\u70b9\u4ee5\u4e0b\u306e\u6841\u6570<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">salary_formatted<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">format_number<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">salary<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namesalarysalary_formatted110LionelMessi4100000041,000,000.0029JulianAlvarez31300003,130,000.00322LautaroMartinez63750006,375,000.00<\/div>\n<\/div>\n<h2>\u4ee5\u5e26\u6709\u683c\u5f0f\u7684\u65b9\u5f0f\u8f93\u51fa\u5b57\u7b26\u4e323-1-5\u3002<\/h2>\n<p>\u4f7f\u7528format_string()\u51fd\u6570\uff0c\u4ee5printf\u683c\u5f0f\u8f93\u51fa\u5b57\u7b26\u4e32\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">format_string<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u66f8\u5f0f<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">...])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">string_formatted<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">format_string<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">%s<\/span><span class=\"sh\">'<\/span><span class=\"s\">s number is %d<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">last_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u5b9e\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namestring_formatted110LionelMessiMessi&#8217;s number is 1029JulianAlvarezAlvarez&#8217;s number is 9322LautaroMartinezMartinez&#8217;s number is 22<\/div>\n<\/div>\n<h2>3-1-6 \u5de6\u4fa7\u8fdb\u884c\u586b\u5145\uff08\u9760\u53f3\u5bf9\u9f50\uff09<\/h2>\n<p>\u4f7f\u7528lpad()\u51fd\u6570\uff0c\u5728\u6307\u5b9a\u7684\u5b57\u7b26\u957f\u5ea6\u4e4b\u524d\uff0c\u5728\u5de6\u4fa7\u586b\u5145\u6307\u5b9a\u7684\u5b57\u7b26\u3002\u586b\u5145\u7684\u76ee\u6807\u5217\u53ef\u4ee5\u662f\u5b57\u7b26\u4e32\u7c7b\u578b\u6216\u6570\u503c\u7c7b\u578b\u90fd\u53ef\u4ee5\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lpad<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u9577<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u30d1\u30c7\u30a3\u30f3\u30b0\u306b\u4f7f\u3046\u6587\u5b57<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number_padded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lpad<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">0<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b (ch\u016b l\u00ec l\u00ec)<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namenumber_padded110LionelMessi001029JulianAlvarez0009322LautaroMartinez0022<\/div>\n<\/div>\n<h2>\u5c06 3-1-7 \u53f3\u4fa7\u8fdb\u884c\u586b\u5145\uff08\u5de6\u5bf9\u9f50\uff09<\/h2>\n<p>\u4f7f\u7528rpad()\u51fd\u6570\uff0c\u5728\u6307\u5b9a\u7684\u5b57\u7b26\u4e32\u957f\u5ea6\u4e4b\u524d\uff0c\u5728\u53f3\u4fa7\u586b\u5145\u6307\u5b9a\u7684\u5b57\u7b26\u3002\u8981\u586b\u5145\u7684\u5217\u53ef\u4ee5\u662f\u5b57\u7b26\u4e32\u7c7b\u578b\uff0c\u4e5f\u53ef\u4ee5\u662f\u6570\u5b57\u7c7b\u578b\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">rpad<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u9577<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u30d1\u30c7\u30a3\u30f3\u30b0\u306b\u4f7f\u3046\u6587\u5b57<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number_padded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">rpad<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">0<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u5de5\u4f5c\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namenumber_padded110LionelMessi100029JulianAlvarez9000322LautaroMartinez2200<\/div>\n<\/div>\n<h2>\u5220\u96643-1-8\u5de6\u4fa7\u7684\u7a7a\u767d\u5b57\u7b26<\/h2>\n<p>\u4f7f\u7528ltrim()\u51fd\u6570\uff0c\u5220\u9664\u5b57\u7b26\u4e32\u5de6\u4fa7\u7684\u7a7a\u767d\u5b57\u7b26\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">ltrim<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name_trimmed<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">ltrim<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u5b9e\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namefirst_name_trimmed110LionelMessiLionel29JulianAlvarezJulian322LautaroMartinezLautaro<\/div>\n<\/div>\n<h2>\u5220\u9664\u53f3\u4fa7\u7684\u7a7a\u767d\u5b57\u7b26<\/h2>\n<p>\u4f7f\u7528rtrim()\u51fd\u6570\u6765\u5220\u9664\u5b57\u7b26\u4e32\u53f3\u4fa7\u7684\u7a7a\u767d\u5b57\u7b26\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">rtrim<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name_trimmed<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">rtrim<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namefirst_name_trimmed110LionelMessiLionel29JulianAlvarezJulian322LautaroMartinezLautaro<\/div>\n<\/div>\n<h2>\u5220\u9664\u4e24\u7aef\u7684\u7a7a\u767d\u5b57\u7b26<\/h2>\n<p>\u4f7f\u7528trim()\u51fd\u6570\uff0c\u53ef\u4ee5\u5220\u9664\u5b57\u7b26\u4e32\u5de6\u53f3\u4e24\u7aef\u7684\u7a7a\u767d\u5b57\u7b26\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">trim<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name_trimmed<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">trim<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\uff1a\u5de5\u4f5c\u4ea7\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nnumberfirst_namelast_namefirst_name_trimmed110LionelMessiLionel29JulianAlvarezJulian322LautaroMartinezLautaro<\/div>\n<\/div>\n<h1>3-2 \u641c\u7d22\u3001\u63d0\u53d6<\/h1>\n<h2>\u67e5\u627e\u6307\u5b9a\u5b57\u7b26\u9996\u6b21\u51fa\u73b0\u7684\u4f4d\u7f6e\u4e3a3-2-1\u3002<\/h2>\n<p>\u4f7f\u7528instr()\u51fd\u6570\u53ef\u4ee5\u4ece\u5b57\u7b26\u4e32\u4e2d\u641c\u7d22\u5b50\u5b57\u7b26\u4e32\u7b2c\u4e00\u6b21\u51fa\u73b0\u7684\u4f4d\u7f6e\uff08\u5982\u679c\u662f\u7b2c\u4e00\u6b21\u51fa\u73b0\uff0c\u5219\u8fd4\u56de1\uff09\u3002\u5982\u679c\u672a\u627e\u5230\u5b50\u5b57\u7b26\u4e32\uff0c\u5219\u8fd4\u56de0\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">instr<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u691c\u7d22\u5bfe\u8c61\u306e\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u691c\u7d22\u3059\u308b\u90e8\u5206\u6587\u5b57\u5217<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">instr_position<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">instr<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">what_is<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">open<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50 of output<\/p>\n<div>\n<div class=\"post-table\">\nnamewhat_isposition1MLflowMLflow is an open source platform for managing the end-to-end machine learning lifecycle. It tackles four primary functions142Delta LakeDelta Lake is an open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs for Scala, Java, Rust, Ruby, and Python.183Apache SparkApache Spark\u2122 is a multi-language engine for executing data engineering, data science, and machine learning on single-node machines or clusters.0<\/div>\n<\/div>\n<h2>\u627e\u51fa\u6307\u5b9a\u4f4d\u7f6e\u4ee5\u540e\u51fa\u73b0\u6307\u5b9a\u5b57\u7b26\u7684\u7b2c\u4e00\u4e2a\u4f4d\u7f6e\u3002<\/h2>\n<p>\u4f7f\u7528locate()\u51fd\u6570\uff0c\u5728\u6307\u5b9a\u4f4d\u7f6e\u4e4b\u540e\u7684\u5b57\u7b26\u4e32\u4e2d\u67e5\u627e\u5b50\u5b57\u7b26\u4e32\u9996\u6b21\u51fa\u73b0\u7684\u4f4d\u7f6e\uff08\u5982\u679c\u627e\u5230\u4e86\uff0c\u8fd4\u56de1\uff09\u3002\u5982\u679c\u672a\u627e\u5230\u5b50\u5b57\u7b26\u4e32\uff0c\u5219\u8fd4\u56de0\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">instr<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u691c\u7d22\u3059\u308b\u90e8\u5206\u6587\u5b57\u5217<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u691c\u7d22\u5bfe\u8c61\u306e\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u691c\u7d22\u3059\u308b\u6700\u521d\u306e\u4f4d\u7f6e<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">locate_position<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">locate<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">is<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">proverb<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">10<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51fa\u529b\u4f8b\uff1a<br \/>\n&#8211; \u5b9e\u4f8b\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nproverblocate_position1Time is money02Speech is silver, silence is golden273Art is long, life is short19<\/div>\n<\/div>\n<h2>\u63d0\u53d63-2-3\u90e8\u5206\u7684\u5b50\u5b57\u7b26\u4e32<\/h2>\n<p>\u4f7f\u7528substring()\u51fd\u6570\uff0c\u6839\u636e\u4f4d\u7f6e\u548c\u957f\u5ea6\u4ece\u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u5b50\u5b57\u7b26\u4e32\u3002\u6307\u5b9a\u90e8\u5206\u5b57\u7b26\u4e32\u7684\u8d77\u59cb\u4f4d\u7f6e\u65f6\uff0c\u5c06\u7b2c\u4e00\u4e2a\u5b57\u7b26\u8ba1\u4e3a1\uff0c\u800c\u975e0\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">substring<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u90e8\u5206\u6587\u5b57\u5217\u306e\u958b\u59cb\u4f4d\u7f6e<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u90e8\u5206\u6587\u5b57\u5217\u306e\u9577\u3055<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">substring<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">substring<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">proverb<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">22<\/span><span class=\"p\">,<\/span> <span class=\"mi\">5<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nproverbsubstring1Time is money<br \/>\n2Speech is silver, silence is goldenence3Art is long, life is shortshort<\/div>\n<\/div>\n<h2>\u63d0\u53d6\u4e0e\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u7684\u90e8\u5206\u76843-2-4\u3002<\/h2>\n<p>\u4f7f\u7528regexp_extract()\u51fd\u6570\uff0c\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u4ece\u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u5b50\u5b57\u7b26\u4e32\u3002<\/p>\n<p>\u4f60\u53ef\u4ee5\u53c2\u8003\u4ee5\u4e0b\u9875\u9762\u7684\u76ee\u5f55\u6765\u4e86\u89e3\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u7684\u8bed\u6cd5\uff1a<br \/>\n\u53c2\u8003\uff1a\u3010Java\u3011\u6b63\u5219\u8868\u8fbe\u5f0f\u6c47\u603b<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">regexp_extract<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6b63\u898f\u8868\u73fe\u30d1\u30bf\u30fc\u30f3<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u30de\u30c3\u30c1\u6587\u5b57\u5217\u306e\u4f55\u756a\u76ee\u306e\u8981\u7d20\u3092\u62bd\u51fa\u3059\u308b\u304b<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">hyphon<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">regexp_extract<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">what_is<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sa\">r<\/span><span class=\"sh\">\"<\/span><span class=\"s\">\\w+-\\w+<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">0<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u7684\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nnamewhat_ishyphon_word1MLflowMLflow is an open source platform for managing the end-to-end machine learning lifecycle. It tackles four primary functionsend-to2Delta LakeDelta Lake is an open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs for Scala, Java, Rust, Ruby, and Python.open-source3Apache SparkApache Spark\u2122 is a multi-language engine for executing data engineering, data science, and machine learning on single-node machines or clusters.multi-language<\/div>\n<\/div>\n<h2>\u63d0\u53d6\u5305\u542b\u7279\u5b9a\u5206\u9694\u7b26\u51fa\u73b0\u6307\u5b9a\u6b21\u6570\u7684\u5b50\u5b57\u7b26\u4e32\uff0c\u76f4\u5230\u8fbe\u5230\u6307\u5b9a\u6b21\u6570\u4e3a\u6b62\u3002<\/h2>\n<p>\u4f7f\u7528substring_index()\u51fd\u6570\uff0c\u4ece\u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u51fa\u6307\u5b9a\u5206\u9694\u7b26\u51fa\u73b0\u6307\u5b9a\u6b21\u6570\u4e4b\u524d\u7684\u5b50\u5b57\u7b26\u4e32\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">substring_index<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u533a\u5207\u308a\u6587\u5b57<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u767b\u5834\u56de\u6570<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">subdomain<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">substring_index<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">domain<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">.<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4ea7\u51fa\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnamedomainsubdomain1Apache Sparkspark.apache.orgspark2Apache Kafkakafka.apache.orgkafka3Apache Parquetparquet.apache.orgparquet<\/div>\n<\/div>\n<h2>\u63d0\u53d6\u4ee5\u6307\u5b9a\u7684\u5b57\u7b26\u4e32\u5f00\u5934\u7684\u5b57\u7b26\u4e32\uff1a3-2-6.<\/h2>\n<p>\u60a8\u53ef\u4ee5\u4f7f\u7528startswith()\u51fd\u6570\u6765\u786e\u5b9a\u67d0\u5217\u662f\u5426\u4ee5\u7279\u5b9a\u5b57\u7b26\u4e32\u5f00\u5934\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">filter<\/span><span class=\"p\">(<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">col<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">).<\/span><span class=\"nf\">startswith<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u958b\u59cb\u6587\u5b57\u5217<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">filter<\/span><span class=\"p\">(<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">col<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">name<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">).<\/span><span class=\"nf\">startswith<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">Apache<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u5de5\u4f5c\u8303\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnamewhat_is1Apache SparkApache Spark\u2122 is a multi-language engine for executing data engineering, data science, and machine learning on single-node machines or clusters.2Apache ParquetApache Parquet is an open source, column-oriented data file format designed for efficient data storage and retrieval.3Apache AirflowAirflow is a platform created by the community to programmatically author, schedule and monitor workflows.<\/div>\n<\/div>\n<h2>\u62bd\u53d6\u4ee5\u6307\u5b9a\u5b57\u7b26\u4e32\u7ed3\u5c3e\u7684\u5b57\u7b26\u4e32\u662f3-2-7. y\u01d0 de sh\u00ec 3-2-7.)<\/h2>\n<p>\u4f7f\u7528Column\u7684endswith()\u51fd\u6570\uff0c\u53ef\u4ee5\u5224\u65ad\u4e00\u4e2a\u5b57\u7b26\u4e32\u662f\u5426\u4ee5\u7279\u5b9a\u7684\u5b57\u7b26\u4e32\u7ed3\u5c3e\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">filter<\/span><span class=\"p\">(<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">col<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">).<\/span><span class=\"nf\">endswith<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u7d42\u4e86\u6587\u5b57\u5217<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">filter<\/span><span class=\"p\">(<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">col<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">name<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">).<\/span><span class=\"nf\">endswith<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">flow<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u4e2d\u7684\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nnamewhat_is1MLflowMLflow is an open source platform for managing the end-to-end machine learning lifecycle. It tackles four primary functions.2Apache ParquetAirflow is a platform created by the community to programmatically author, schedule and monitor workflows.<\/div>\n<\/div>\n<h1>3-3\u4ea4\u6362<\/h1>\n<h2>\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u5e76\u66ff\u63623-3-1\u7684\u90e8\u5206\u3002<\/h2>\n<p>\u4f7f\u7528regexp_replace()\u51fd\u6570\uff0c\u5bf9\u5b57\u7b26\u4e32\u8fdb\u884c\u64cd\u4f5c\uff0c\u5c06\u7b26\u5408\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u90e8\u5206\u66ff\u6362\u4e3a\u53e6\u4e00\u4e2a\u5b57\u7b26\u4e32\u3002<\/p>\n<p>\u60a8\u53ef\u4ee5\u53c2\u8003\u4ee5\u4e0b\u9875\u9762\u7684\u5217\u8868\u6765\u4e86\u89e3\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u7684\u8bed\u6cd5\u3002<br \/>\n\u53c2\u8003\uff1a\u3010Java\u3011\u6b63\u5219\u8868\u8fbe\u5f0f\u603b\u7ed3<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">regexp_replace<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6b63\u898f\u8868\u73fe\u30d1\u30bf\u30fc\u30f3<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u7f6e\u63db\u306b\u4f7f\u3046\u6587\u5b57\u5217<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">note_wo_phone<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">regexp_replace<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">note<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sa\">r<\/span><span class=\"sh\">\"<\/span><span class=\"s\">\\d{3}-\\d{4}-\\d{4}<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">&lt;redacted&gt;<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4ea7\u91cf\u7684\u4f8b\u5b50<\/p>\n<div>\n<div class=\"post-table\">\nnote_takernotenote_wo_phone1YamadaMy phone is 090-0012-3456. please call me backMy phone is &lt;redacted&gt;. please call me back2Tanaka\u96fb\u8a71\u756a\u53f7\u306f090-0123-4567\u3067\u3059\u96fb\u8a71\u756a\u53f7\u306f&lt;redacted&gt;\u3067\u30593Suzuki070-0012-3456\u306b\u9023\u7d61\u6b32\u3057\u3044\u3068\u306e\u3053\u3068\u3067\u3059&lt;redacted&gt;\u306b\u9023\u7d61\u6b32\u3057\u3044\u3068\u306e\u3053\u3068\u3067\u3059<\/div>\n<\/div>\n<h2>\u5728\u6307\u5b9a\u7684\u4f4d\u7f6e\u8986\u76d6\uff08\u63d2\u5165\uff09\u5b57\u7b26\u4e32<\/h2>\n<p>\u4f7f\u7528overlay()\u51fd\u6570\u53ef\u4ee5\u5728\u5b57\u7b26\u4e32\u4e0a\u8986\u76d6\u6216\u63d2\u5165\u6307\u5b9a\u4f4d\u7f6e\u7684\u5b57\u7b26\u4e32\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">overlay<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u4e0a\u66f8\u304d\u3059\u308b\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u4e0a\u66f8\u304d\u3059\u308b\u4f4d\u7f6e<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u4e0a\u66f8\u304d\u3059\u308b\u9577\u3055<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">overlayed<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">overlay<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">original<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">phrase<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">pos<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">len<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u529b\u91cf\u5c55\u793a<\/p>\n<div>\n<div class=\"post-table\">\noriginalphraseposlenoverlayed1SPARK_SQLCORE7-1SPARK_CORE2SPARK_SQLSTREAMING72SPARK_STREAMINGL3SPARK_SQLPY10PYSPARK_SQL<\/div>\n<\/div>\n<h2>\u5c063-3-3\u4e2d\u7684\u6bcf\u4e2a\u6570\u5b57\u66ff\u6362\u4e3a\u4e0d\u540c\u7684\u6587\u5b57\u3002<\/h2>\n<p>\u4f7f\u7528translate()\u51fd\u6570\uff0c\u5728\u5b57\u7b26\u4e32\u4e2d\uff0c\u5982\u679c\u5b58\u5728\u6307\u5b9a\u7684\u5b57\u7b26\uff0c\u5219\u7528\u6307\u5b9a\u7684\u5b57\u7b26\u8fdb\u884c\u66ff\u6362\u3002\u4ee5\u4e0b\uff0c\u5982\u679c\u5b57\u7b26\u4e32\u578b\u5217\u4e2d\u5b58\u5728&lt;\u88ab\u66ff\u6362\u5b57\u7b26&gt;\uff0c\u5219\u5c06\u76f8\u5e94\u4f4d\u7f6e\u4e0a\u7684\u5b57\u7b26\u7528&lt;\u66ff\u6362\u5b57\u7b26&gt;\u8fdb\u884c\u66ff\u6362\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">translate<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u7f6e\u63db\u3055\u308c\u308b\u6587\u5b57<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u7f6e\u63db\u3059\u308b\u6587\u5b57<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">order_corrected<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">translate<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">order<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">olSeg<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">01569<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51fa\u529b\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nitemorderorder_corrected1sofal234S123452chairg9993tableSo0500<\/div>\n<\/div>\n<h1>3-4 \u5206\u5272\u30fb\u7d50\u5408 \u53ef\u4ee5\u7406\u89e3\u4e3a\u5c06\u4e00\u4e2a\u6574\u4f53\u5206\u62103\u52304\u4e2a\u90e8\u5206\uff0c\u6216\u8005\u5c06\u591a\u4e2a\u90e8\u5206\u5408\u5e76\u6210\u4e00\u4e2a\u6574\u4f53\u3002<\/h1>\n<h2>\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5c06\u6307\u5b9a\u4f4d\u7f6e\u8fdb\u884c\u5206\u5272\u76843-4-1\u65b9\u6cd5\u3002<\/h2>\n<p>\u4f7f\u7528split()\u51fd\u6570\uff0c\u901a\u8fc7\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u6765\u5206\u5272\u5b57\u7b26\u4e32\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">&lt;\u6700\u5927\u56de\u6570&gt;\u304c0\u3088\u308a\u5927\u304d\u3044\u6642\uff1a \u6700\u5927\u3067\u3053\u306e\u56de\u6570\u307e\u3067\u5206\u5272\u3055\u308c\u307e\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">&lt;\u6700\u5927\u56de\u6570&gt;\u304c0\u4ee5\u4e0b\u306e\u6642\uff1a\u3000\u56de\u6570\u306b\u5236\u9650\u306a\u304f\u3001\u6b63\u898f\u8868\u73fe\u306e\u30d1\u30bf\u30fc\u30f3\u306b\u5f93\u3063\u3066\u5206\u5272\u3055\u308c\u307e\u3059\u3002<\/ul>\n<p>\u53ef\u4ee5\u53c2\u8003\u4ee5\u4e0b\u9875\u9762\u7684\u5217\u8868\u6765\u4e86\u89e3\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u7684\u8bed\u6cd5\u3002<br \/>\n\u53c2\u8003\u94fe\u63a5\uff1a\u3010Java\u3011\u6b63\u5219\u8868\u8fbe\u5f0f\u6c47\u603b<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">split<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6b63\u898f\u8868\u73fe\u30d1\u30bf\u30fc\u30f3<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6700\u5927\u56de\u6570<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number_split<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">split<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">[()-]<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mi\">1<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\ncompanynumbernumber_split1ABC trading(06)1234-5678[&#8220;&#8221;, &#8220;06&#8221;, &#8220;1234&#8221;, &#8220;5678&#8221;]2XYZ company(03)1234-5678[&#8220;&#8221;, &#8220;03&#8221;, &#8220;1234&#8221;, &#8220;5678&#8221;]3shop123090-0012-3456[&#8220;090&#8221;, &#8220;0012&#8221;, &#8220;3456&#8221;]<\/div>\n<\/div>\n<h2>\u4ee5\u6307\u5b9a\u7684\u8bed\u8a00\u5c063-4-2\u5206\u5272\u6210\u5355\u8bcd\u3002<\/h2>\n<p>\u4f7f\u7528sentences()\u51fd\u6570\uff0c\u6839\u636e\u533a\u57df\u8bbe\u7f6e\u5c06\u5b57\u7b26\u4e32\u5206\u5272\u4e3a\u5355\u8bcd\u3002\u533a\u57df\u8bbe\u7f6e\u6307\u5b9a\u8bed\u8a00\u548c\u56fd\u5bb6\u3002\u5982\u679c\u672a\u6307\u5b9a\u533a\u57df\u8bbe\u7f6e\uff0c\u5219\u4f7f\u7528\u73af\u5883\u7684\u9ed8\u8ba4\u533a\u57df\u8bbe\u7f6e\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">sentences<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8a00\u8a9e\u3092\u6307\u5b9a\u3059\u308b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u56fd\u3092\u6307\u5b9a\u3059\u308b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">example_split<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">sentences<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">example<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">language<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">country<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u7684\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nexamplelanguagecountryexample_split1\u3053\u308c\u306f\u79c1\u306e\u30da\u30f3\u3067\u3059jaJP[[&#8220;\u3053\u308c\u306f&#8221;, &#8220;\u79c1&#8221;, &#8220;\u306e&#8221;, &#8220;\u30da\u30f3&#8221;, &#8220;\u3067\u3059&#8221;]]2This is my penenUS[[&#8220;This&#8221;, &#8220;is&#8221;, &#8220;my&#8221;, &#8220;pen&#8221;]]3PySpark\u306f\u3001Spark SQL\u3092Python\u3067\u6271\u3046\u3053\u3068\u306e\u3067\u304d\u308b\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059jaJP[[&#8220;PySpark&#8221;, &#8220;\u306f&#8221;, &#8220;Spark&#8221;, &#8220;SQL&#8221;, &#8220;\u3092&#8221;, &#8220;Python&#8221;, &#8220;\u3067&#8221;, &#8220;\u6271&#8221;, &#8220;\u3046\u3053\u3068\u306e\u3067\u304d\u308b&#8221;, &#8220;\u30e9\u30a4\u30d6\u30e9\u30ea&#8221;, &#8220;\u3067\u3059&#8221;]]<\/div>\n<\/div>\n<h2>\u5c063-4-3\u7684\u5b57\u7b26\u4e32\u548c\u5176\u4ed6\u6587\u672c\u4e32\u8054\u8d77\u6765\u3002<\/h2>\n<p>\u53ef\u4ee5\u4f7f\u7528concat()\u51fd\u6570\u6765\u8fde\u63a5\u5b57\u7b26\u4e32\u7b49\u3002\u53ef\u4ee5\u8bbe\u7f6e\u591a\u4e2a\u8981\u8fde\u63a5\u7684\u5217\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">concat<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,...<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">concatenated<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">concat<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">title<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lit<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">. <\/span><span class=\"sh\">\"<\/span><span class=\"p\">),<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">first_name<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">lit<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span> <span class=\"sh\">\"<\/span><span class=\"p\">),<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">last_name<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>Some possible paraphrases in Chinese for &#8220;\u51fa\u529b\u4f8b&#8221; could be:<br \/>\n&#8211; \u793a\u4f8b\u8f93\u51fa<br \/>\n&#8211; \u8f93\u51fa\u6848\u4f8b<br \/>\n&#8211; \u4e3e\u4f8b\u8f93\u51fa<br \/>\n&#8211; \u8303\u4f8b\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\ntitlefirst_namelast_nameconcatenated1MsHanakoYamadaMs. Hanako Yamada2MrIchiroTanakaMr. Ichiro Tanaka3DrNatsukoSuzukiDr. Natsuko Suzuki<\/div>\n<\/div>\n<h2>\u4f7f\u75283-4-4\u7684\u5206\u9694\u7b26\u53f7\u5c06\u5b57\u7b26\u4e32\u8fde\u63a5\u8d77\u6765\u3002<\/h2>\n<p>\u4f7f\u7528concat_ws()\u51fd\u6570\uff0c\u53ef\u4ee5\u4f7f\u7528\u7279\u5b9a\u7684\u5206\u9694\u7b26\u5c06\u5b57\u7b26\u4e32\u7b49\u8fde\u63a5\u8d77\u6765\u3002\u53ef\u4ee5\u8bbe\u7f6e\u591a\u4e2a\u8981\u8fde\u63a5\u7684\u5217\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">concat_ws<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u533a\u5207\u308a\u6587\u5b57<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">[,...<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">])<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">concatenated<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">concat_ws<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">-<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">code<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number_1<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">number_2<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\ncodenumber_1number_2concatenated1A012345678A-0123-456782B002033445B-0020-334453C110009876C-1100-09876<\/div>\n<\/div>\n<h2>\u5c063-4-5\u4e2a\u5b57\u7b26\u4e32\u91cd\u590d\u62fc\u63a5\u5728\u4e00\u8d77<\/h2>\n<p>\u4f7f\u7528repeat()\u51fd\u6570\uff0c\u5c06\u6307\u5b9a\u6b21\u6570\u7684\u5b57\u7b26\u4e32\u91cd\u590d\u8fde\u63a5\u5728\u4e00\u8d77\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">repeat<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u7e70\u308a\u8fd4\u3057\u56de\u6570<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">code_repeated<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">repeat<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">code<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u672c\u5730\u5316\u7684\u6c49\u8bed\u91ca\u4e49\uff1a\u52aa\u529b\u7684\u4f8b\u5b50<\/p>\n<div>\n<div class=\"post-table\">\nnumbercodecode_repeated11abcabcabc22xyzxyzxyz33123123123<\/div>\n<\/div>\n<h1>3-5 \u8f6c\u6362<\/h1>\n<h2>\u83b7\u5f973-5-1\u7684\u7b2c\u4e00\u4e2a\u5b57\u7b26\u7684ASCII\u7801\u3002<\/h2>\n<p>\u4f7f\u7528ascii()\u51fd\u6570\uff0c\u83b7\u53d6\u5b57\u7b26\u4e32\u7684\u7b2c\u4e00\u4e2a\u5b57\u7b26\u7684ASCII\u4ee3\u7801\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">ascii<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">ascii_code<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">ascii<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">code<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u5de5\u4f5c\u793a\u8303<\/p>\n<div>\n<div class=\"post-table\">\nnumbercodeascii_code11abc9722xyz1203312349<\/div>\n<\/div>\n<h2>\u5c063-5-2\u6587\u5b57\u4e32\u4f7f\u7528BASE64\u8fdb\u884c\u7f16\u7801\u3002<\/h2>\n<p>\u4f7f\u7528base64()\u51fd\u6570\uff0c\u5c06\u5b57\u7b26\u4e32\u8fdb\u884cBASE64\u7f16\u7801\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">base64<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">base64_encoded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">base64<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">code<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51fa\u529b\u4f8b\uff1a\u5de5\u4f5c\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumbercodebase64_encoded11abcYWJj22xyzeHl633123MTIz<\/div>\n<\/div>\n<h2>\u89e3\u78013-5-3 BASE64\u7f16\u7801\u5b57\u7b26\u4e32<\/h2>\n<p>\u4f7f\u7528unbase64()\u51fd\u6570\uff0c\u5c06\u88abBASE64\u7f16\u7801\u7684\u5b57\u7b26\u4e32\u89e3\u7801\u4e3a\u4e8c\u8fdb\u5236\u7c7b\u578b\u7684\u5217\uff0c\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\u7c7b\u578b\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">unbase64<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">original_code<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">unbase64<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">base64_encoded<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">).<\/span><span class=\"nf\">cast<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">string<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u5c55\u793a\u4e86\u4ea7\u51fa\u7684\u5b9e\u4f8b\u3002<\/p>\n<div>\n<div class=\"post-table\">\nnumberbase64_encodedoriginal_code11YWJjabc22eHl6xyz33MTIz123<\/div>\n<\/div>\n<h2>\u5c06\u8f93\u5165\u7684\u5b57\u7b26\u96c6\u8f6c\u6362\u4e3a\u4e8c\u8fdb\u5236\u3002<\/h2>\n<p>\u4f7f\u7528encode()\u51fd\u6570\uff0c\u5c06\u5b57\u7b26\u4e32\u8f6c\u6362\u4e3a\u6307\u5b9a\u5b57\u7b26\u96c6\u7684\u4e8c\u8fdb\u5236\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">encode<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"err\">\u3001<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u30ad\u30e3\u30e9\u30af\u30bf\u30fc\u30bb\u30c3\u30c8<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">encoded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">encode<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">nihongo<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">UTF-8<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">).<\/span><span class=\"nf\">printSchema<\/span><span class=\"p\">()<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b<br \/>\n\u6839<br \/>\n|&#8211; number\uff1a\u957f\u6574\u578b\uff08\u53ef\u4e3a\u7a7a\uff09<br \/>\n|&#8211; \u65e5\u672c\u8bed\uff1a\u5b57\u7b26\u4e32\uff08\u53ef\u4e3a\u7a7a\uff09<br \/>\n|&#8211; \u7f16\u7801\uff1a\u4e8c\u8fdb\u5236\uff08\u53ef\u4e3a\u7a7a\uff09<\/p>\n<h2>\u89e3\u7801\u5c06\u6307\u5b9a\u5b57\u7b26\u96c6\u76843-5-5\u4e8c\u8fdb\u5236\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\u3002<\/h2>\n<p>\u4f7f\u7528decode()\u51fd\u6570\uff0c\u5c06\u4ee5\u7279\u5b9a\u5b57\u7b26\u96c6\u7f16\u7801\u7684\u4e8c\u8fdb\u5236\u6570\u636e\u89e3\u7801\u5e76\u63d0\u53d6\u4e3a\u5b57\u7b26\u4e32\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">decode<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u30d0\u30a4\u30ca\u30ea\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u30ad\u30e3\u30e9\u30af\u30bf\u30fc\u30bb\u30c3\u30c8<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">encoded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">encode<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">nihongo<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">UTF-8<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n           <span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">decoded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">decode<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">encoded<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">UTF-8<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u793a\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnihongoencodeddecoded1\u3042\u3044\u3046\u3048\u304a44GC44GE44GG44GI44GK\u3042\u3044\u3046\u3048\u304a2\u304b\u304d\u304f\u3051\u305344GL44GN44GP44GR44GT\u304b\u304d\u304f\u3051\u30533\u3055\u3057\u3059\u305b\u305d44GV44GX44GZ44Gb44Gd\u3055\u3057\u3059\u305b\u305d<\/div>\n<\/div>\n<h2>\u5c06&#8221;3-5-6&#8243;\u7f16\u7801\u4e3aSoundEx\u3002<\/h2>\n<p>\u4f7f\u7528soundex()\u51fd\u6570\u5c06\u5b57\u7b26\u4e32\u7f16\u7801\u4e3aSoundEx\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">soundex<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">soundex<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">soundex<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">fruit<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4f8b\u5b50\u5982\u4e0b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfruitsoundex11appleA14022orangeO65233strawberryS361<\/div>\n<\/div>\n<h1>3-6 \u5176\u4ed6<\/h1>\n<h2>\u83b7\u53d6\u6587\u672c\u957f\u5ea6<\/h2>\n<p>\u4f7f\u7528length()\u51fd\u6570\u6765\u83b7\u53d6\u5b57\u7b26\u4e32\u7684\u957f\u5ea6\u3002\u5305\u62ec\u524d\u540e\u7a7a\u767d\u4e5f\u4f1a\u8ba1\u7b97\u5728\u5185\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">length<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">length<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">length<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">fruit<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u53d1\u6325\u5b9e\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nnumberfruitlength11apple522orange633\u3044\u3061\u30543<\/div>\n<\/div>\n<h2>\u83b7\u53d6 3-6-2 \u4f4d\u7684\u6bd4\u7279\u957f\u5ea6\u3002<\/h2>\n<p>\u4f7f\u7528bit_length()\u51fd\u6570\u83b7\u53d6\u5b57\u7b26\u4e32\u7684\u4f4d\u957f\u5ea6\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">bit_length<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">bit_length<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">bit_length<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">fruit<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51fa\u529b\u4f8b\u7684\u6c49\u8bed\u8868\u8fbe\u53ef\u4ee5\u662f\uff1a\u793a\u4f8b\u8f93\u51fa<\/p>\n<div>\n<div class=\"post-table\">\nnumberfruitbit_length11apple4022orange4833\u3044\u3061\u305472<\/div>\n<\/div>\n<h2>\u83b7\u53d63-6-3\u516b\u4f4d\u5143\u957f\u5ea6<\/h2>\n<p>\u4f7f\u7528octet_length()\u51fd\u6570\u6765\u83b7\u53d6\u5b57\u7b26\u4e32\u7684\u516b\u4f4d\u5b57\u8282\u957f\u5ea6\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">octet_length<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">octet_length<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">octet_length<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">fruit<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51fa\u529b\u4f8b\u7684\u4e2d\u6587\u610f\u601d\u662f\u300c\u8f93\u51fa\u4f8b\u5b50\u300d\u3002<\/p>\n<div>\n<div class=\"post-table\">\nnumberfruitoctet_length11apple522orange633\u3044\u3061\u30549<\/div>\n<\/div>\n<h2>\u83b7\u53d63-6-4\u7684\u83b1\u6587\u65af\u5766\u8ddd\u79bb<\/h2>\n<p>\u4f7f\u7528levenshtein()\u51fd\u6570\uff0c\u83b7\u5f97\u5b57\u7b26\u4e32\u4e4b\u95f4\u7684\u83b1\u6587\u65af\u5766\u8ddd\u79bb\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># \u69cb\u6587\r\n<\/span><span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u8ffd\u52a0\u3059\u308b\u30ab\u30e9\u30e0\u540d<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">levenshtein<\/span><span class=\"p\">(<\/span><span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">,<\/span> <span class=\"o\">&lt;<\/span><span class=\"n\">\u6587\u5b57\u5217\u578b\u30ab\u30e9\u30e0<\/span><span class=\"o\">&gt;<\/span><span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u4f8b\u6587\r\n<\/span><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">functions<\/span> <span class=\"k\">as<\/span> <span class=\"n\">F<\/span>\r\n\r\n<span class=\"nf\">display<\/span><span class=\"p\">(<\/span> <span class=\"n\">df<\/span><span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">levenshtein_distance<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">F<\/span><span class=\"p\">.<\/span><span class=\"nf\">levenshtein<\/span><span class=\"p\">(<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">left<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">right<\/span><span class=\"sh\">\"<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span> <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u4ea7\u91cf\u5b9e\u4f8b<\/p>\n<div>\n<div class=\"post-table\">\nleftrightoctet_length1tupleapple22rangeorange13\u3044\u306a\u3054\u3044\u3061\u30541<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u8fd9\u662f\u4e00\u7bc7\u9006\u5411PySpark\u7cfb\u5217\u7684\u5b57\u7b26\u4e32\u7248\u672c\uff0c\u603b\u7ed3\u4e86\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\u5e94\u8be5\u600e\u4e48\u505a\u3002 \uff08\u5c06\u4e0d\u65ad\u8fdb\u884c\u66f4\u65b0\u3002\uff09 \u539f\u5247\u3068\u3057\u3066A [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-47388","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09 - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u9006\u5411\u5f15\u7528pyspark\uff08\u4e09-\u5b57\u7b26\u4e32\u7bc7\uff09\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09\" \/>\n<meta property=\"og:description\" content=\"\u8fd9\u662f\u4e00\u7bc7\u9006\u5411PySpark\u7cfb\u5217\u7684\u5b57\u7b26\u4e32\u7248\u672c\uff0c\u603b\u7ed3\u4e86\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\u5e94\u8be5\u600e\u4e48\u505a\u3002 \uff08\u5c06\u4e0d\u65ad\u8fdb\u884c\u66f4\u65b0\u3002\uff09 \u539f\u5247\u3068\u3057\u3066A [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u9006\u5411\u5f15\u7528pyspark\uff08\u4e09-\u5b57\u7b26\u4e32\u7bc7\uff09\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-11T14:13:14+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-30T00:26:47+00:00\" \/>\n<meta name=\"author\" content=\"\u5b87, \u534e\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u5b87, \u534e\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/\",\"name\":\"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2024-01-11T14:13:14+00:00\",\"dateModified\":\"2024-04-30T00:26:47+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458\",\"name\":\"\u5b87, \u534e\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g\",\"caption\":\"\u5b87, \u534e\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yuhua\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09 - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u9006\u5411\u5f15\u7528pyspark\uff08\u4e09-\u5b57\u7b26\u4e32\u7bc7\uff09\/","og_locale":"zh_CN","og_type":"article","og_title":"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09","og_description":"\u8fd9\u662f\u4e00\u7bc7\u9006\u5411PySpark\u7cfb\u5217\u7684\u5b57\u7b26\u4e32\u7248\u672c\uff0c\u603b\u7ed3\u4e86\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\u5e94\u8be5\u600e\u4e48\u505a\u3002 \uff08\u5c06\u4e0d\u65ad\u8fdb\u884c\u66f4\u65b0\u3002\uff09 \u539f\u5247\u3068\u3057\u3066A [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u9006\u5411\u5f15\u7528pyspark\uff08\u4e09-\u5b57\u7b26\u4e32\u7bc7\uff09\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-01-11T14:13:14+00:00","article_modified_time":"2024-04-30T00:26:47+00:00","author":"\u5b87, \u534e","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u5b87, \u534e","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"8 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/","name":"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2024-01-11T14:13:14+00:00","dateModified":"2024-04-30T00:26:47+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u9006\u5411\u5f15\u7528PySpark\uff08\u4e09. \u5b57\u7b26\u4e32\u7bc7\uff09"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458","name":"\u5b87, \u534e","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g","caption":"\u5b87, \u534e"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yuhua\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e9%80%86%e5%90%91%e5%bc%95%e7%94%a8pyspark%ef%bc%88%e4%b8%89-%e5%ad%97%e7%ac%a6%e4%b8%b2%e7%af%87%ef%bc%89\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47388","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=47388"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47388\/revisions"}],"predecessor-version":[{"id":90802,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47388\/revisions\/90802"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=47388"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=47388"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=47388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}