Como consultar o Apache Arrow com chDB

python -m venv .venv
source .venv/bin/activate

pip install "chdb>=2.0.2"

pip install pyarrow pandas ipython

ipython

aws s3 cp \
  --no-sign \
  s3://ookla-open-data/parquet/performance/type=mobile/year=2023/quarter=2/2023-04-01_performance_mobile_tiles.parquet .

import pyarrow.parquet as pq

arrow_table = pq.read_table("./2023-04-01_performance_mobile_tiles.parquet")

arrow_table.schema

quadkey: string
tile: string
tile_x: double
tile_y: double
avg_d_kbps: int64
avg_u_kbps: int64
avg_lat_ms: int64
avg_lat_down_ms: int32
avg_lat_up_ms: int32
tests: int64
devices: int64

arrow_table.shape

(3864546, 11)

import chdb

chdb.query("""
DESCRIBE Python(arrow_table)
SETTINGS describe_compact_output=1
""", "DataFrame")

               name     type
0           quadkey   String
1              tile   String
2            tile_x  Float64
3            tile_y  Float64
4        avg_d_kbps    Int64
5        avg_u_kbps    Int64
6        avg_lat_ms    Int64
7   avg_lat_down_ms    Int32
8     avg_lat_up_ms    Int32
9             tests    Int64
10          devices    Int64

chdb.query("SELECT count() FROM Python(arrow_table)", "DataFrame")

   count()
0  3864546

chdb.query("""
WITH numericColumns AS (
  SELECT * EXCEPT ('tile.*') EXCEPT(quadkey)
  FROM Python(arrow_table)
)
SELECT * APPLY(max), * APPLY(avg) APPLY(x -> round(x, 2))
FROM numericColumns
""", "Vertical")

Linha 1:
──────
max(avg_d_kbps):                4155282
max(avg_u_kbps):                1036628
max(avg_lat_ms):                2911
max(avg_lat_down_ms):           2146959360
max(avg_lat_up_ms):             2146959360
max(tests):                     111266
max(devices):                   1226
round(avg(avg_d_kbps), 2):      84393.52
round(avg(avg_u_kbps), 2):      15540.4
round(avg(avg_lat_ms), 2):      41.25
round(avg(avg_lat_down_ms), 2): 554355225.76
round(avg(avg_lat_up_ms), 2):   552843178.3
round(avg(tests), 2):           6.31
round(avg(devices), 2):         2.88