Make Pandas DataFrame apply() use all cores?

Question

As of August 2017, Pandas DataFame.apply() is unfortunately still limited to working with a single core, meaning that a multi-core machine will waste the majority of its com

Answer 1

Here is an example of sklearn base transformer, in which pandas apply is parallelized

import multiprocessing as mp
from sklearn.base import TransformerMixin, BaseEstimator

class ParllelTransformer(BaseEstimator, TransformerMixin):
    def __init__(self,
                 n_jobs=1):
        """
        n_jobs - parallel jobs to run
        """
        self.variety = variety
        self.user_abbrevs = user_abbrevs
        self.n_jobs = n_jobs
    def fit(self, X, y=None):
        return self
    def transform(self, X, *_):
        X_copy = X.copy()
        cores = mp.cpu_count()
        partitions = 1

        if self.n_jobs <= -1:
            partitions = cores
        elif self.n_jobs <= 0:
            partitions = 1
        else:
            partitions = min(self.n_jobs, cores)

        if partitions == 1:
            # transform sequentially
            return X_copy.apply(self._transform_one)

        # splitting data into batches
        data_split = np.array_split(X_copy, partitions)

        pool = mp.Pool(cores)

        # Here reduce function - concationation of transformed batches
        data = pd.concat(
            pool.map(self._preprocess_part, data_split)
        )

        pool.close()
        pool.join()
        return data
    def _transform_part(self, df_part):
        return df_part.apply(self._transform_one)
    def _transform_one(self, line):
        # some kind of transformations here
        return line

for more info see https://towardsdatascience.com/4-easy-steps-to-improve-your-machine-learning-code-performance-88a0b0eeffa8