def z_score(data): u = population_mean(data) new_data = [float(x) for x in data] x = new_data[1] pop_sd = pop_stand_dev(new_data) y = subtraction(x, u) z = division(pop_sd, y) return z
def pop_correlation_coefficient(data): x_data = CsvReader('Tests/Data/female_height.csv').data y_data = CsvReader('Tests/Data/male_height.csv').data x = pop_stand_dev(x_data) y = pop_stand_dev(y_data) divisor = multiplication(x, y) z = len(data) # Covariance calculation: a = subtraction(data, sampleMean) b = subtraction(data, population_mean) c = multiplication(a, b) covariance = division(z, (sum(c))) # Population Correlation Coefficient calculation: d = division(divisor, covariance) return d
def pop_correlation_coefficient(data_x, data_y): x = pop_stand_dev(data_x) y = pop_stand_dev(data_y) divisor = multiplication(x, y) # Covariance calculation: d = population_mean(data_x) e = population_mean(data_y) a = [(element - d) for element in data_x] b = [(element - e) for element in data_y] size = len(a) product = [a[i] * b[i] for i in range(size)] total = sum(product) covariance = division(size, total) # Population Correlation Coefficient calculation: d = division(divisor, covariance) return d
def confidence_interval(data): # For a Confidence Interval of 95% z_value = 1.960 mean = sampleMean(data) sd = pop_stand_dev(data) x = len(data) y = division(square_root(x), sd) margin_of_error = multiplication(z_value, y) a = subtraction(mean, margin_of_error) b = addition(mean, margin_of_error) return a, b
def pop_correlation_coefficient(data): # x_data = CsvReader('Tests/Data/female_height.csv').data # y_data = CsvReader('Tests/Data/male_height.csv').data x_data = [num for elem in data for num in elem] y_data = [num for elem in data for num in elem] new_x_data = [float(x) for x in x_data] new_y_data = [float(x) for x in y_data] x = pop_stand_dev(new_x_data) y = pop_stand_dev(new_y_data) divisor = multiplication(x, y) z = len(new_x_data) # Covariance calculation: a = subtraction(new_x_data, population_mean(new_x_data)) b = subtraction(new_y_data, population_mean(new_y_data)) c = multiplication(a, b) covariance = division(z, (sum(c))) # Population Correlation Coefficient calculation: d = division(divisor, covariance) return d
def confidence_interval(data): data = [num for elem in data for num in elem] new_data = [float(x) for x in data] # For a Confidence Interval of 95% z_value = 1.960 mean = sampleMean(new_data) sd = pop_stand_dev(new_data) x = len(new_data) y = division(square_root(x), sd) margin_of_error = multiplication(z_value, y) a = subtraction(mean, margin_of_error) b = addition(mean, margin_of_error) return a, b
def confidence_interval(data): # For a Confidence Interval of 95% z_value = 1.960 mean = population_mean(data) sd = pop_stand_dev(data) x = len(data) y = division(square_root(x), sd) margin_of_error = multiplication(z_value, y) a = [subtraction(mean, margin_of_error)] b = [addition(mean, margin_of_error)] size = len(a) # c = [(a[i], b[i]) for i in range(size)] lower = a[0] upper = b[0] # print(lower, upper) return lower, upper
def population_st_dev(self, data): self.result = pop_stand_dev(data) return self.result