Linear Regression Machine Learning with TensorFlow and Oracle JET UI Explained

linear_regression_v2.py

import numpy as np
import tensorflow as tf
from flask import Flask, jsonify, request
from flask_cors import CORS, cross_origin

app = Flask(__name__)
CORS(app)

@app.route("/redsam/api/v0.1/points", methods=['GET', 'POST'])
def linear_regression_train():
    learning_rate = 0.01
    training_epochs = 100
    
    # reading training parameters from REST request
    if request.method == 'POST':
        learning_rate = request.json['learningrate']
        training_epochs = request.json['trainingepochs']
    
    # training data
    x_train = np.linspace(-1, 1, 101)
    y_train = 2 * x_train + np.random.randn(*x_train.shape) * 0.33
    
    # placeholders, initialized from training data
    X = tf.placeholder("float")
    Y = tf.placeholder("float")
    
    # model function, defined as y = W * x
    def model(X, w):
        return tf.multiply(X, w)
    
    # weights variable for equation
    w = tf.Variable(0.0, name="weights")
    
    # cost function for linear regression, defined as the mean squared error
    y_model = model(X, w)
    cost = tf.reduce_mean(tf.square(Y-y_model))
    
    # This operation will be called on each iteration of the learning algorithm
    # GradientDescentOptimizer - TensorFlow implementation
    # Learn with given rate and try to minimize learning cost
    train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
    
    # TensorFlow initialization
    sess = tf.Session()
    init = tf.global_variables_initializer()
    sess.run(init)
    
    # repeating training multiple times
    for epoch in range(training_epochs):
        # iterating through training data set and calling optimizer, for each training entry
        for (x, y) in zip(x_train, y_train):
            sess.run(train_op, feed_dict={X: x, Y: y})
    
    # calculated weights variable
    w_val = sess.run(w)
    # calculated cost variable
    cost_val = sess.run(cost, feed_dict={X: x_train, Y: y_train})
    
    all_points = [];
    eq_vals = [];
    # populating array of x/y training data for REST response
    for (x, y) in zip(x_train, y_train):
        all_points.append({"x": x, "y": y})
    
    # populating weights and cost variables for REST response
    eq_vals.append({"w": str(w_val), "cost": str(cost_val)})
    
    # constructing JSON response
    response = jsonify(results=[eq_vals, all_points])

    sess.close()
    
    return response

# running REST interface
if __name__ == "__main__":
    app.run(host='0.0.0.0')