import time
import numpy as np
import pandas as pd
import pyarrow as pa

def generate_data(total_size, ncols):
    nrows = total_size / ncols / np.dtype('float64').itemsize
    return pd.DataFrame({
        'c' + str(i): np.random.randn(nrows)
        for i in range(ncols)
    })

KILOBYTE = 1 << 10
MEGABYTE = KILOBYTE * KILOBYTE
DATA_SIZE = 1024 * MEGABYTE
NCOLS = 16

def get_timing(f, niter):
    start = time.clock_gettime(time.CLOCK_REALTIME)
    for i in range(niter):
        f()
    return (time.clock_gettime(time.CLOCK_REALTIME) - start) / NITER

def read_as_dataframe(klass, source):
    reader = klass(source)
    table = reader.read_all()
    return table.to_pandas()
NITER = 5
results = []

CHUNKSIZES = [16 * KILOBYTE, 64 * KILOBYTE, 256 * KILOBYTE, MEGABYTE, 16 * MEGABYTE]

for chunksize in CHUNKSIZES:
    nchunks = DATA_SIZE // chunksize
    batch = pa.RecordBatch.from_pandas(generate_data(chunksize, NCOLS))

    sink = pa.InMemoryOutputStream()
    stream_writer = pa.StreamWriter(sink, batch.schema)

    for i in range(nchunks):
        stream_writer.write_batch(batch)

    source = sink.get_result()

    elapsed = get_timing(lambda: read_as_dataframe(pa.StreamReader, source), NITER)

    result = (chunksize, elapsed)
    print(result)
    results.append(result)