securetorobert’s gists

securetorobert / constants_transfer_learning_tf_20.py

Created September 28, 2019 17:11

Constants for transfer learning in TF 2.0

securetorobert / install_tf_20.py

Created September 28, 2019 17:08

Install TF 2.0 and import libraries

	!pip install tensorflow-gpu==2.0.0-beta0

	import tensorflow as tf
	from tensorflow.keras import layers, models, optimizers

securetorobert / Dockerfile

Created August 15, 2019 12:07

A Dockerfile Sample

	# Use an official Python runtime as a parent image
	FROM python:2.7-slim

	# Set the working directory to /app
	WORKDIR /app

	# Copy the current directory contents into the container at /app
	COPY . /app

	# Install any needed packages specified in requirements.txt

securetorobert / bqml_model_predict.sql

Created May 20, 2019 02:15

Get prediction with BQML

	#standardSQL
	SELECT
	*
	FROM
	ML.PREDICT(MODEL `bqml_tutorial.sample_model`, (
	SELECT
	IFNULL(device.operatingSystem, "") AS os,
	device.isMobile AS is_mobile,
	IFNULL(totals.pageviews, 0) AS pageviews,
	IFNULL(geoNetwork.country, "") AS country

securetorobert / bqml_confusion_matrix.sql

Created May 20, 2019 02:06

Confusion Matrix in BQML

	SELECT
	*
	FROM
	ML.CONFUSION_MATRIX(MODEL `bqml_tutorial.sample_model`,
	(
	SELECT
	IF(totals.transactions IS NULL, 0, 1) AS label,
	IFNULL(device.operatingSystem, "") AS os,
	device.isMobile AS is_mobile,
	IFNULL(geoNetwork.country, "") AS country,

securetorobert / bqml_roc_curve.sql

Created May 20, 2019 02:00

Generate ROC curve in BQML

	SELECT
	*
	FROM
	ML.ROC_CURVE(MODEL `bqml_tutorial.sample_model`,
	(
	SELECT
	IF(totals.transactions IS NULL, 0, 1) AS label,
	IFNULL(device.operatingSystem, "") AS os,
	device.isMobile AS is_mobile,
	IFNULL(geoNetwork.country, "") AS country,

securetorobert / bqml_evaluate_model.sql

Last active May 20, 2019 01:57

Evaluate a model with BQML

	SELECT
	*
	FROM
	ML.EVALUATE(MODEL `bqml_tutorial.sample_model`,
	(
	SELECT
	IF(totals.transactions IS NULL, 0, 1) AS label,
	IFNULL(device.operatingSystem, "") AS os,
	device.isMobile AS is_mobile,
	IFNULL(geoNetwork.country, "") AS country,

securetorobert / bqml_create_model.sql

Created May 19, 2019 16:53

Create a Logistic Regression model with BQML

	#standardSQL
	CREATE MODEL `bqml_tutorial.sample_model`
	OPTIONS(model_type='logistic_reg') AS
	SELECT
	IF(totals.transactions IS NULL, 0, 1) AS label,
	IFNULL(device.operatingSystem, "") AS os,
	device.isMobile AS is_mobile,
	IFNULL(geoNetwork.country, "") AS country,
	IFNULL(totals.pageviews, 0) AS pageviews
	FROM

securetorobert / tf_2_image_dataset.py

Created May 11, 2019 19:44

A gist showing code for preprocessing images for tf.keras

	AUTOTUNE = tf.data.experimental.AUTOTUNE

	path_ds = tf.data.Dataset.from_tensor_slices(train_file_list)
	image_ds = path_ds.map(load_and_preprocess_image, num_parallel_calls=AUTOTUNE)
	label_ds = tf.data.Dataset.from_tensor_slices(tf.cast(train_label_list, tf.int64))
	image_label_ds = tf.data.Dataset.zip((image_ds, label_ds))

	ds = image_label_ds.shuffle(buffer_size=1000 * BATCH_SIZE)
	ds = ds.repeat()
	ds = ds.batch(BATCH_SIZE)

securetorobert / tf_keras_sequential_l1_l2.py

Created January 14, 2019 07:10

Simple Keras Model with l1_l2 regularization

	import tensorflow as tf
	from tensorflow import keras

	model = keras.models.Sequential([
	keras.layers.Dense(4, activation=tf.nn.relu, input_shape=(4,), kernel_regularizer=keras.regularizers.l1_l2(l1=0.1, l2=0.01)),
	keras.layers.Dense(4, activation=tf.nn.relu, kernel_regularizer=keras.regularizers.l1_l2(l1=0.1, l2=0.01)),
	keras.layers.Dense(1, activation=tf.nn.sigmoid)
	])

	model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

Robert John securetorobert