google-bigquery - 如何在 Google BigQuery 中执行三元运算？

Question

我确实使用pg_trgmPostgreSQL 中的模块来使用三元组计算两个字符串之间的相似度。特别是我使用：

similarity(text, text)

哪个返回返回一个数字，该数字指示两个参数的相似程度（在 0 和 1 之间）。

如何在 Google BigQuery 上执行相似功能（或等效功能）？

Answer 1

下面试试。至少作为增强的蓝图

SELECT text1, text2, similarity FROM 
JS(
// input table
(
  SELECT * FROM 
  (SELECT 'mikhail' AS text1, 'mikhail' AS text2),
  (SELECT 'mikhail' AS text1, 'mike' AS text2),
  (SELECT 'mikhail' AS text1, 'michael' AS text2),
  (SELECT 'mikhail' AS text1, 'javier' AS text2),
  (SELECT 'mikhail' AS text1, 'thomas' AS text2)
) ,
// input columns
text1, text2,
// output schema
"[{name: 'text1', type:'string'},
  {name: 'text2', type:'string'},
  {name: 'similarity', type:'float'}]
",
// function
"function(r, emit) {

  var _extend = function(dst) {
    var sources = Array.prototype.slice.call(arguments, 1);
    for (var i=0; i<sources.length; ++i) {
      var src = sources[i];
      for (var p in src) {
        if (src.hasOwnProperty(p)) dst[p] = src[p];
      }
    }
    return dst;
  };

  var Levenshtein = {
    /**
     * Calculate levenshtein distance of the two strings.
     *
     * @param str1 String the first string.
     * @param str2 String the second string.
     * @return Integer the levenshtein distance (0 and above).
     */
    get: function(str1, str2) {
      // base cases
      if (str1 === str2) return 0;
      if (str1.length === 0) return str2.length;
      if (str2.length === 0) return str1.length;

      // two rows
      var prevRow  = new Array(str2.length + 1),
          curCol, nextCol, i, j, tmp;

      // initialise previous row
      for (i=0; i<prevRow.length; ++i) {
        prevRow[i] = i;
      }

      // calculate current row distance from previous row
      for (i=0; i<str1.length; ++i) {
        nextCol = i + 1;

        for (j=0; j<str2.length; ++j) {
          curCol = nextCol;

          // substution
          nextCol = prevRow[j] + ( (str1.charAt(i) === str2.charAt(j)) ? 0 : 1 );
          // insertion
          tmp = curCol + 1;
          if (nextCol > tmp) {
            nextCol = tmp;
          }
          // deletion
          tmp = prevRow[j + 1] + 1;
          if (nextCol > tmp) {
            nextCol = tmp;
          }

          // copy current col value into previous (in preparation for next iteration)
          prevRow[j] = curCol;
        }

        // copy last col value into previous (in preparation for next iteration)
        prevRow[j] = nextCol;
      }

      return nextCol;
    }

  };

  var the_text1;

  try {
    the_text1 = decodeURI(r.text1).toLowerCase();
  } catch (ex) {
    the_text1 = r.text1.toLowerCase();
  }

  try {
    the_text2 = decodeURI(r.text2).toLowerCase();
  } catch (ex) {
    the_text2 = r.text2.toLowerCase();
  }

  emit({text1: the_text1, text2: the_text2,
        similarity: 1 - Levenshtein.get(the_text1, the_text2) / the_text1.length});

  }"
)
ORDER BY similarity DESC

这是基于@thomaspark的https://storage.googleapis.com/thomaspark-sandbox/udf-examples/pataky.js的轻微修改

Answer 2

我是这样做的：

CREATE TEMP FUNCTION trigram_similarity(a STRING, b STRING) AS (
  (
    WITH a_trigrams AS (
      SELECT
        DISTINCT tri_a
      FROM
        unnest(ML.NGRAMS(SPLIT(LOWER(a), ''), [3,3])) AS tri_a
    ),
    b_trigrams AS (
      SELECT
        DISTINCT tri_b
      FROM
        unnest(ML.NGRAMS(SPLIT(LOWER(b), ''), [3,3])) AS tri_b
    )
    SELECT
      COUNTIF(tri_b IS NOT NULL) / COUNT(*)
    FROM
      a_trigrams
      LEFT JOIN b_trigrams ON tri_a = tri_b
  )
);

这是与Postgres 的 pg_trgm的比较：

select trigram_similarity('saemus', 'seamus');
-- 0.25 vs. pg_trgm 0.272727

select trigram_similarity('shamus', 'seamus');
-- 0.5 vs. pg_trgm 0.4