TensorFlow Arrow Blog Part 3 - ArrowFeatherDataset

tf_arrow_blog_pt3.py

import tensorflow_io.arrow as arrow_io
from pyarrow.feather import write_feather

# Write the Pandas DataFrame to a Feather file
write_feather(df, '/path/to/df.feather')

# Create the dataset with one or more filenames
ds = arrow_io.ArrowFeatherDataset(
    ['/path/to/df.feather'],
    columns=(0, 1, 2),
    output_types=(tf.int64, tf.float64, tf.float64),
    output_shapes=([], [], []))

# Iterate over each row of each file
for record in ds:
   label, x0, x1 = record
   # use label and feature tensors