Kaggle API Guide

# The kaggle.json file should be at ~/.kaggle/kaggle.json
# It contains your username and key from your Kaggle account settings
mkdir -p ~/.kaggle
# Move your downloaded kaggle.json to ~/.kaggle/kaggle.json
chmod 600 ~/.kaggle/kaggle.json

export KAGGLE_USERNAME=$KAGGLE_USERNAME
export KAGGLE_KEY=$KAGGLE_KEY

pip install kaggle

# Search for datasets
kaggle datasets list -s "climate change" --sort-by votes

# Search with specific criteria
kaggle datasets list -s "medical imaging" --file-type csv --max-size 1000000

# Download and unzip a dataset
kaggle datasets download -d "heptapod/titanic" --unzip -p ./data/titanic/

# Download a specific file from a dataset
kaggle datasets download -d "yelp-dataset/yelp-dataset" -f "yelp_academic_dataset_review.json" -p ./data/

# List active competitions
kaggle competitions list

# Download competition data (must accept rules on kaggle.com first)
kaggle competitions download -c "house-prices-advanced-regression-techniques" -p ./data/house-prices/

# Submit predictions
kaggle competitions submit -c "house-prices-advanced-regression-techniques" \
  -f ./submission.csv -m "Random forest baseline v1"

# Check submission status
kaggle competitions submissions -c "house-prices-advanced-regression-techniques"

# Search for notebooks
kaggle kernels list -s "transformer nlp" --sort-by voteCount

# Pull a notebook to local
kaggle kernels pull "username/notebook-name" -p ./notebooks/

# Push a notebook to Kaggle
kaggle kernels push -p ./my-notebook/

import subprocess
import json
import os

def search_kaggle_datasets(query, sort_by="votes", max_results=10):
    """Search Kaggle datasets and return structured results."""
    cmd = [
        "kaggle", "datasets", "list",
        "-s", query,
        "--sort-by", sort_by,
        "--max-size", "50000000",
        "--csv"
    ]
    result = subprocess.run(cmd, capture_output=True, text=True)
    lines = result.stdout.strip().split("\n")
    if len(lines) < 2:
        return []

    headers = lines[0].split(",")
    datasets = []
    for line in lines[1:max_results + 1]:
        values = line.split(",")
        dataset = dict(zip(headers, values))
        datasets.append(dataset)
    return datasets

def download_dataset(dataset_ref, output_dir="./data"):
    """Download a Kaggle dataset by reference."""
    os.makedirs(output_dir, exist_ok=True)
    cmd = [
        "kaggle", "datasets", "download",
        "-d", dataset_ref,
        "--unzip",
        "-p", output_dir
    ]
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode == 0:
        print(f"Downloaded {dataset_ref} to {output_dir}")
    else:
        print(f"Error: {result.stderr}")

# Search for NLP benchmark datasets
datasets = search_kaggle_datasets("nlp text classification benchmark")
for ds in datasets[:5]:
    print(f"  {ds.get('ref', 'N/A')}")
    print(f"    Size: {ds.get('totalBytes', 'N/A')} bytes")
    print(f"    Votes: {ds.get('voteCount', 'N/A')}")
    print()

from kaggle.api.kaggle_api_extended import KaggleApi

api = KaggleApi()
api.authenticate()

# Search datasets
datasets = api.dataset_list(search="genomics", sort_by="updated")
for ds in datasets[:5]:
    print(f"{ds.ref}: {ds.title} ({ds.size})")

# Get dataset metadata
metadata = api.dataset_view("nih-chest-xrays/data")
print(f"Title: {metadata.title}")
print(f"Size: {metadata.totalBytes}")
print(f"Description: {metadata.description[:200]}")

# Download dataset files
api.dataset_download_files(
    "nih-chest-xrays/sample",
    path="./data/chest-xrays/",
    unzip=True
)