Function parallelize

process.py:36–42

(data, func, num_of_processes=2)

import matplotlib.dates as mdates

def parallelize(data, func, num_of_processes=2):
    data_split = np.array_split(data, num_of_processes)
    pool = Pool(num_of_processes)
    data = pd.concat(pool.map(func, data_split))
    pool.close()
    pool.join()
    return data

def run_on_subset(func, data_subset):
    return data_subset.apply(func, axis=1)