load ClickBench · 1M, warm.

def load_polars(path, mode, loads, opt=None):
    import polars as pl
    kw = {}
    if opt and "infer" in opt: kw = {"infer_schema_length": opt["infer"]}
    if opt and "overrides" in opt: kw = {"schema_overrides": {c: (pl.Float64 if t == "float" else pl.String) for c, t in opt["overrides"].items()}}
    pl.read_csv(io.BytesIO(b"a,b\n1,x\n2,y\n"))  # untimed: the reader's own start-up (its thread pool), on three lines that are not the file
    out, rows, cols = [], 0, 0
    for _ in range(loads):
        t0 = time.perf_counter()
        df = pl.read_csv(path, infer_schema=False) if mode == "text" else pl.read_csv(path, **kw)
        out.append(ms_since(t0))
        rows, cols = df.height, df.width
        del df
    return pl.__version__, out, rows, cols, pl.thread_pool_size()

def load_arrow(path, mode, loads, opt=None):
    import pyarrow as pa
    import pyarrow.csv as pc
    convert = pc.ConvertOptions(column_types={n: pa.string() for n in header_names(path)}) if mode == "text" else pc.ConvertOptions()
    parse = pc.ParseOptions(newlines_in_values=True) if opt else pc.ParseOptions()
    pc.read_csv(io.BytesIO(b"a,b\n1,x\n2,y\n"))  # untimed: the reader's own start-up (its thread pools), on three lines that are not the file
    out, rows, cols = [], 0, 0
    for _ in range(loads):
        t0 = time.perf_counter()
        t = pc.read_csv(path, convert_options=convert, parse_options=parse)
        out.append(ms_since(t0))
        rows, cols = t.num_rows, t.num_columns
        del t
    return pa.__version__, out, rows, cols, pa.cpu_count()

def load_duckdb(path, mode, loads, opt=None):
    import duckdb
    con = duckdb.connect()
    con.execute("SELECT 42").fetchall()  # untimed: what the binding sets up on its first query (it imports pandas) is not CSV loading
    opts = ", all_varchar=true" if mode == "text" else ""
    out, rows, cols = [], 0, 0
    for _ in range(loads):
        con.execute("DROP TABLE IF EXISTS t")
        t0 = time.perf_counter()
        con.execute(f"CREATE TABLE t AS SELECT * FROM read_csv(?, header=true{opts})", [path])
        out.append(ms_since(t0))
        rows = con.execute("SELECT count(*) FROM t").fetchone()[0]
        cols = len(con.execute("SELECT * FROM t LIMIT 0").description)
    threads = con.execute("SELECT current_setting('threads')").fetchone()[0]
    return duckdb.__version__, out, rows, cols, int(threads)

def load_pandas(path, mode, loads, opt=None):
    import pandas as pd
    pd.read_csv(io.BytesIO(b"a,b\n1,x\n2,y\n"), engine="pyarrow")  # untimed: the reader's own start-up
    out, rows, cols = [], 0, 0
    for _ in range(loads):
        t0 = time.perf_counter()
        # engine="pyarrow": pandas' multithreaded reader, one keyword from the default (its C engine is single-threaded:
        # 1.3-1.7 s on worldcitiespop where this takes tens of ms — bench/results/standards.jsonl, the records of 09:02-09:22)
        eng = (opt or {}).get("engine", "pyarrow")
        df = pd.read_csv(path, dtype=str, keep_default_na=False, engine=eng) if mode == "text" else pd.read_csv(path, engine=eng)
        out.append(ms_since(t0))
        rows, cols = df.shape
        del df
    import pyarrow as pa
    return pd.__version__, out, rows, cols, (pa.cpu_count() if (opt or {}).get("engine", "pyarrow") == "pyarrow" else 1)