[TensorFlow 2.x]Easy-peasy importing dataset on new TensorFlow

Photo by Kelly Sikkema on Unsplash

Code shortlist for importing dataset in TensorFlow based on its official tutorial

https://www.tensorflow.org/tutorials

1. Using keras datasets by ‘keras.datasests’

Train your first neural network: basic classification

import tensorflow as tf
from tensorflow import keras
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

2. Using ‘tensorflow_datasets(a.k.a. tfds)’ to import data

Text classification of movie reviews with Keras and TensorFlow Hub

import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_datasets as tfds
# comments start
# Split the training set into 60% and 40%, so we'll end up with 15,000 examples
# for training, 10,000 examples for validation and 25,000 examples for testing.
# comments end
train_validation_split = tfds.Split.TRAIN.subsplit([6, 4])
(train_data, validation_data), test_data = tfds.load(
    name="imdb_reviews", 
    split=(train_validation_split, tfds.Split.TEST),
    as_supervised=True)

3. Reading csv data from its URL using pandas

Classify structured data | TensorFlow Core

URL = 'https://storage.googleapis.com/applied-dl/heart.csv'
dataframe = pd.read_csv(URL)
dataframe.head()