issue_comments: 743701422
This data as json
| html_url | issue_url | id | node_id | user | created_at | updated_at | author_association | body | reactions | issue | performed_via_github_app |
|---|---|---|---|---|---|---|---|---|---|---|---|
| https://github.com/simonw/sqlite-utils/issues/207#issuecomment-743701422 | https://api.github.com/repos/simonw/sqlite-utils/issues/207 | 743701422 | MDEyOklzc3VlQ29tbWVudDc0MzcwMTQyMg== | 9599 | 2020-12-12T04:37:14Z | 2020-12-12T04:38:25Z | OWNER | Prototype: ```python from collections import namedtuple ColumnDetails = namedtuple("ColumnDetails", ("column", "num_null", "num_blank", "num_distinct", "most_common", "least_common")) def analyze_column(db, table, column, values=10): num_null = db.execute("select count(*) from [{}] where [{}] is null".format(table, column)).fetchone()[0] num_blank = db.execute("select count(*) from [{}] where [{}] = ''".format(table, column)).fetchone()[0] num_distinct = db.execute("select count(distinct [{}]) from [{}]".format(column, table)).fetchone()[0] most_common = None least_common = None if num_distinct != 1: most_common = [(r[0], r[1]) for r in db.execute( "select [{}], count(*) from [{}] group by [{}] order by count(*) desc limit ".format(column, table, column, values) ).fetchall()] if num_distinct <= values: # No need to run the query if it will just return the results in revers order least_common = most_common[::-1] else: least_common = [(r[0], r[1]) for r in db.execute( "select [{}], count(*) from [{}] group by [{}] order by count(*) limit {}".format(column, table, column, values) ).fetchall()] return ColumnDetails(column, num_null, num_blank, num_distinct, most_common, least_common) def analyze_table(db, table): for column in db[table].columns: details = analyze_column(db, table, column.name) print(details) ``` | {"total_count": 0, "+1": 0, "-1": 0, "laugh": 0, "hooray": 0, "confused": 0, "heart": 0, "rocket": 0, "eyes": 0} | 763283616 |