### Creating Sample Data for Testing

https://pythonprogramming.net/sample-data-testing-machine-learning-tutorial/

Generating and using sample data to test the functions and equations – similar to unit testing.

Key Points:-

- When starting to define a function build out the inputs and then focus on what it needs to return – and then connect the two with the various steps
- Once the test data is calculated we can then change the variance and correlation in the equation and test that the R^2 value changes as expected
- create_dataset(40,10,2,correlation=’pos’) – gives a higher R^2
- create_dataset(40,80,2,correlation=’pos’) – gives a lower R^2
- create_dataset(40,10,2,correlation=’neg’) – draws the line the other way around
- create_dataset(40,10,2,correlation=False) – gives a very low R^2 (no correlation)

# Import Libs from statistics import mean import numpy as np import matplotlib.pyplot as plt import random #psudo random :) # To set charts to save as images we need to change the default behaviour from matplotlib import style # inport style to change default behaviour of plot style.use('ggplot') # use ggplot # Define values #xs = np.array([1,2,3,4,5], dtype=np.float64) # dtype lets you set the data type. Not needed for this example but useful in future #ys = np.array([5,4,6,5,6], dtype=np.float64) def create_dataset(how_many, variance, step=2, correlation=False): # step and correlation have default values set that can be overwritten when the function is called #set up starting values val=1 ys=[] #empty array # for loop cycling through how_many to give ys for i in range(how_many): y = val + random.randrange(-variance, variance) ys.append(y) # also need to increase/decrease value of val depending on correlation if correlation and correlation =='pos': val += step # add the value of step to Val and store as val elif correlation and correlation =='neg': val -= step # minus the value of step from Val and store as val # now define xs xs = [i for i in range(len(ys))] # one line for loop to generate an array of ittrative xs; could have used How_Many return np.array(xs, dtype=np.float64), np.array(ys, dtype=np.float64) # Define best fit function def best_fit_slope_and_intercept(xs, ys): # defining function to calculate slope (m) - passing values of xs and ys m = ( ((mean(xs)*mean(ys)) - mean(xs * ys)) / # bracket space at the start and space slash at the end allows for a carridge return in the code ((mean(xs)**2)-mean(xs**2))) ## **2 raises to the power of 2 b = mean(ys) - m*mean(xs) return m, b # define new xs and ys xs, ys = create_dataset(40,40,2,'pos') m, b = best_fit_slope_and_intercept(xs,ys) # Define function to square error def squared_error(ys_orig,ys_line): return sum((ys_line - ys_orig) * (ys_line - ys_orig)) # return used with calc rather than seperately first def coefficient_of_determination(ys_orig,ys_line): y_mean_line = [mean(ys_orig) for y in ys_orig] # one line for loop squared_error_regr = squared_error(ys_orig, ys_line) squared_error_y_mean = squared_error(ys_orig, y_mean_line) return 1 - (squared_error_regr/squared_error_y_mean) m, b = best_fit_slope_and_intercept(xs,ys) regression_line = [(m*x)+b for x in xs] r_squared = coefficient_of_determination(ys,regression_line) print(r_squared) plt.scatter(xs,ys,color='#003F72', label = 'data') plt.plot(xs, regression_line, label = 'regression line') plt.legend(loc=4) plt.savefig('ML_Tutorial12.png', bbox_inches='tight') #Sets the output to save an image plt.show() # exports the image