Quickstart

import csv
import hashlib
import io
import json
import urllib.request
import zipfile
from collections import Counter
from pathlib import Path

url = (
    "https://www.kaggle.com/api/v1/datasets/download/colacloud/"
    "whiskey-beer-and-california-wine-label-metadata"
)
expected_sha256 = "d54398f6c022eee8c49107ec7f05e2bc0fe9df5f778e0cd1d0819b43b4b4772b"
cohort = "whisky_class_100_199"
# Other choices: "domestic_malt_beverage", "california_origin_wine"

with urllib.request.urlopen(url, timeout=30) as response:
    archive = response.read(1_000_001)
if len(archive) > 1_000_000:
    raise ValueError("Unexpected archive size; review the download before loading")
with zipfile.ZipFile(io.BytesIO(archive)) as bundle:
    csv_bytes = bundle.read("cola_sample.csv")
if hashlib.sha256(csv_bytes).hexdigest() != expected_sha256:
    raise ValueError("Sample changed; review its version and license before loading")

rows = list(csv.DictReader(io.StringIO(csv_bytes.decode("utf-8-sig"))))
counts = Counter(row["SAMPLE_COHORT"] for row in rows)
expected_counts = {
    "whisky_class_100_199": 50,
    "domestic_malt_beverage": 50,
    "california_origin_wine": 50,
}
if counts != expected_counts or any(len(row) != 28 for row in rows):
    raise ValueError("Unexpected sample shape")
if cohort not in expected_counts:
    raise ValueError("Choose one of the three sample cohorts")
seed = [row for row in rows if row["SAMPLE_COHORT"] == cohort]
Path("seed-records.json").write_text(json.dumps(seed, indent=2), encoding="utf-8")
print(f"Loaded {len(rows)} approval records; saved {len(seed)} {cohort} records")

curl -H "X-API-Key: your_api_key" \
  "https://app.colacloud.us/api/v1/usage"

{
  "defaults_applied": {
    "date_range": true,
    "date_from": "2025-03-01"
  }
}

curl -H "X-API-Key: your_api_key" \
  "https://app.colacloud.us/api/v1/colas?category=Beer&derived_subcategory=Beer%20%3E%20Ale&container_type=can&volume_unit=fluid%20ounces&volume_min=12&volume_max=16"