eileen-code4fun

{
  "displayName": "e2e-tutorial-automl",
  "inputDataConfig": {
    "datasetId": "DATASET_ID",
    "filterSplit": {
      "trainingFilter": "labels.aiplatform.googleapis.com/ml_use=training",
      "validationFilter": "labels.aiplatform.googleapis.com/ml_use=validation",
      "testFilter": "labels.aiplatform.googleapis.com/ml_use=test"
    }
  },

eileen-code4fun

from kfp import dsl
from google_cloud_pipeline_components import aiplatform

@dsl.pipeline(
  name='e2e-tutorial-automl-pipeline',
  description='A simple automl training',
  pipeline_root='GCS_PATH_FOR_PIPELINE'
)
def e2e_tutorial_pipeline():
  job = aiplatform.AutoMLImageTrainingJobRunOp(

eileen-code4fun

from kfp.v2 import compiler
from google.cloud.aiplatform import AIPlatformClient

compiler.Compiler().compile(pipeline_func=e2e_tutorial_pipeline, package_path='e2e-tutorial-automl-pipeline.json')

api_client = AIPlatformClient(project_id='PROJECT_ID', region='us-central1')
api_client.create_run_from_job_spec(
  job_spec_path='e2e-tutorial-automl-pipeline.json'
)

eileen-code4fun

api_client.create_schedule_from_job_spec(
  job_spec_path='e2e-tutorial-automl-pipeline-schedule.json',
  # Start at the first minute of every hour.
  schedule='1 * * * *'
)

eileen-code4fun

import tensorflow as tf
import tensorflow_datasets as tfds

ds = tfds.load('cifar10', as_supervised=True)

def csvfy(dataset, filename):
  with open(filename, 'w') as f:
    for image, label in dataset:
      f.write('{},'.format(label.numpy()))
      f.write(','.join(str(x) for x in list(image.numpy().reshape(-1))))

eileen-code4fun

SELECT * FROM `bqml.train` LIMIT 10;

eileen-code4fun

CREATE MODEL
  # Name of the model.
  `bqml.e2e-tutorial`
OPTIONS
  # BigQuery will detect that it's for multiclass.
  ( MODEL_TYPE='LOGISTIC_REG') AS
SELECT
  # Use the first column as the label.
  int64_field_0 as label,
  # The rest are features.

eileen-code4fun

SELECT
  # Display all metrics.
  *
FROM
ML.EVALUATE(
  MODEL `bqml.e2e-tutorial`,
  (
    SELECT
      int64_field_0 as label,
      * EXCEPT (int64_field_0)

eileen-code4fun

import numpy as np
from sklearn import decomposition

# Reuse the same ds from Tensorflow Dataset
train_data = list(ds['train'].map(lambda x, y: tf.reshape(x, [-1])))
test_data = list(ds['test'].map(lambda x, y: tf.reshape(x, [-1])))
X = tf.concat([train_data, test_data], 0).numpy()
print(np.shape(X))
# Output: (60000, 3072)

eileen-code4fun

import tensorflow as tf

# Load the saved custom model.
model = tf.keras.models.load_model(GCS_PATH_FOR_SAVED_MODEL)
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['accuracy'])

model.summary()
'''