コード例 #1
0
ファイル: prep.py プロジェクト: yerbby/dask-tutorial
def accounts_csvs(num_files, n, k):
    from accounts import account_entries, account_params
    fn = os.path.join(data_dir, 'accounts.%d.csv' % (num_files - 1))

    if os.path.exists(fn):
        return

    print("Create CSV accounts for dataframe exercise")

    args = account_params(k)

    for i in range(num_files):
        df = account_entries(n, *args)
        df.to_csv(os.path.join(data_dir, 'accounts.%d.csv' % i), index=False)
コード例 #2
0
ファイル: prep.py プロジェクト: deepakprakash37/dask-tutorial
def accounts_csvs(num_files, n, k):
    from accounts import account_entries, account_params
    fn = os.path.join(data_dir, 'accounts.%d.csv' % (num_files - 1))

    if os.path.exists(fn):
        return

    print("Create CSV accounts for dataframe exercise")

    args = account_params(k)

    for i in range(num_files):
        df = account_entries(n, *args)
        df.to_csv(os.path.join(data_dir, 'accounts.%d.csv' % i),
                  index=False)
コード例 #3
0
ファイル: prep.py プロジェクト: yerbby/dask-tutorial
def accounts_json(num_files, n, k):
    from accounts import account_params, json_entries
    import json
    import gzip
    fn = os.path.join(data_dir, 'accounts.%02d.json.gz' % (num_files - 1))
    if os.path.exists(fn):
        return

    print("Create JSON accounts for bag exercise")

    args = account_params(k)

    for i in range(num_files):
        seq = json_entries(n, *args)
        fn = os.path.join(data_dir, 'accounts.%02d.json.gz' % i)
        with gzip.open(fn, 'wb') as f:
            f.write(os.linesep.join(map(json.dumps, seq)).encode())
コード例 #4
0
ファイル: prep.py プロジェクト: deepakprakash37/dask-tutorial
def accounts_json(num_files, n, k):
    from accounts import account_params, json_entries
    import json
    import gzip
    fn = os.path.join(data_dir, 'accounts.%02d.json.gz' % (num_files - 1))
    if os.path.exists(fn):
        return

    print("Create JSON accounts for bag exercise")

    args = account_params(k)

    for i in range(num_files):
        seq = json_entries(n, *args)
        fn = os.path.join(data_dir, 'accounts.%02d.json.gz' % i)
        with gzip.open(fn, 'wb') as f:
            f.write(os.linesep.join(map(json.dumps, seq)).encode())
コード例 #5
0
def accounts_json(small=False):
    t0 = time.time()
    if small:
        num_files, n, k = 50, 10000, 250
    else:
        num_files, n, k = 50, 100000, 500
    fn = os.path.join(data_dir, 'accounts.%02d.json.gz' % (num_files - 1))
    if os.path.exists(fn):
        return

    args = account_params(k)

    for i in range(num_files):
        seq = json_entries(n, *args)
        fn = os.path.join(data_dir, 'accounts.%02d.json.gz' % i)
        with gzip.open(fn, 'wb') as f:
            f.write(os.linesep.join(map(json.dumps, seq)).encode())

    t1 = time.time()
    print("Created CSV acccouts in {:0.2f}s".format(t1 - t0))
コード例 #6
0
def accounts_csvs(small=False):
    t0 = time.time()
    if small:
        num_files, n, k = 3, 10000, 100
    else:
        num_files, n, k = 3, 1000000, 500

    fn = os.path.join(data_dir, 'accounts.%d.csv' % (num_files - 1))

    if os.path.exists(fn):
        return

    args = account_params(k)

    for i in range(num_files):
        df = account_entries(n, *args)
        df.to_csv(os.path.join(data_dir, 'accounts.%d.csv' % i), index=False)

    t1 = time.time()
    print("Created CSV acccouts in {:0.2f}s".format(t1 - t0))