samukweku

# data is from DuckDB's github repo
# https://github.com/duckdb/duckdb/tree/master/benchmark/micro/join

import pandas as pd; import numpy as np; import janitor as jn; import duckdb
query = """SELECT SETSEED(0.8675309);
CREATE TABLE events AS (
	SELECT *,
		 "start" + INTERVAL (CASE WHEN random() < 0.1 THEN 120 ELSE (5 + round(random() * 50, 0)::BIGINT) END) MINUTE
		 	AS "end"
	FROM (

samukweku

from datatable import dt, f
from typing import Pattern, NamedTuple, Union
from collections import Counter, defaultdict
from itertools import compress, chain
import re
import numpy as np

class measure(NamedTuple):
    """reshape either with a separator or a regular expression."""
    column_names:Union[str, list]

samukweku

link to source blog post

import pandas as pd
import numpy as np
import janitor

samukweku

link

import pandas as pd

df = pd.DataFrame({'x': [1, 1, 1, 2, 2, 3],