gistfile1.txt

require 'matrix'
require 'ruby_linear_regression'

ROWS_PER_OPTION = 1_000

POSITION_VALUES_MAPPING = {
  top_left: { value: [1, 1], consent_rate: 60 },
  bottom_left: { value: [1000, 1], consent_rate: 30 },
  top_right: { value: [1, 1000], consent_rate: 45 },
  bottom_right: { value: [1000, 1000], consent_rate: 20 },
}

generated_array = []

POSITION_VALUES_MAPPING.each do |position, values_map|
  consent_rate = values_map[:consent_rate]
  lower_bound = consent_rate - 0.1 * consent_rate
  upper_bound = consent_rate + 0.1 * consent_rate

  ROWS_PER_OPTION.times do
    random_consent_rate = rand(lower_bound..upper_bound)

    generated_array << [values_map[:value], random_consent_rate]
  end
end

generated_array.shuffle!

x_data = []
y_data = []

POSITION_MAPPING = {
  top_left: [1, 1],
  bottom_left: [1000, 1],
  top_right: [1, 1000],
  bottom_right: [1000, 1000],
}

# Load data from CSV file into two arrays - one for independent variables X (x_data) and one for the dependent variable y (y_data)
generated_array.each do |row|
  # Each row contains option value and expected consent rate
  x_data.push( [row[0][0].to_i, row[0][1].to_i])
  y_data.push( row[1].to_i )
end

# Create regression model
linear_regression = RubyLinearRegression.new

# Load training data
linear_regression.load_training_data(x_data, y_data)

# Train the model using gradient descent
# p linear_regression.train_gradient_descent(0.0001, 1000, false)
# Train using least squares
linear_regression.train_normal_equation

# Output the cost
puts "Trained model with the following cost fit #{linear_regression.compute_cost}"

# Predictions
POSITION_MAPPING.each do |key, value|
  predicted_consent_rate = linear_regression.predict([value[0], value[1]])

  puts "Prediction for #{key} position is #{predicted_consent_rate}"
end

#Trained model with the following cost fit 3.6977304062500846
#
# Prediction for top_left position is 58.2812499999997
# Prediction for bottom_left position is 30.821750000000435
# Prediction for top_right position is 45.663750000000164
# Prediction for bottom_right position is 18.204250000000897