Skip to content

Instantly share code, notes, and snippets.

View gdsaxton's full-sized avatar

Gregory Saxton gdsaxton

View GitHub Profile
import pandas as pd ; import numpy as np; import dask.dataframe as dd; from sklearn.datasets import load_boston
df = dd.from_pandas(pd.DataFrame(load_boston().data),npartitions=10)
def operation(df):
df['new'] = df[0]
return df[['new']]
df.pipe(operation).to_csv('boston*.csv')