def pop_standard_deviation(number_list): # 1. Calculate the mean of number_list mean = population_mean(number_list) # 2. Subtract mean from each data point and then square each value new_list = [] for x in number_list: new_val = x - mean new_val = math.pow(new_val, 2) new_list.append(new_val) # 3. Calculate the mean of the squared differences, this is the variance new_mean = population_mean(new_list) # 4. pop standard deviation is the square root of the variance result = math.sqrt(new_mean) return result
def pop_stand_dev(data): u = population_mean(data) data = [num for elem in data for num in elem] new_data = [float(x) for x in data] leng = len(new_data) return round( square_root(sum([(element - u)**2 for element in new_data]) / leng), 3)
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 population_variance(data): u = population_mean(data) deviations = subtraction(data, u) sq_deviations = square(deviations) x = len(data) y = sum(sq_deviations) d = division(x, y) return d
def z_score(data): data = [num for elem in data for num in elem] new_data = [float(x) for x in data] x = new_data[1] u = population_mean(new_data) sample_sd = sample_st_dev(new_data) y = subtraction(x, u) return division(sample_sd, y)
def z_score(data): x = 62 u = population_mean(data) sample_sd = sample_st_deviation(data) y = subtraction(x, u) return division(sample_sd, y) #this may not work
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 population_variance(data): data = [num for elem in data for num in elem] new_data = [float(x) for x in data] u = population_mean(new_data) deviations = subtraction(new_data, u) sq_deviations = square(deviations) x = len(new_data) y = sum(sq_deviations) d = division(x, y) return d
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): # 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 zscore(zscore_list): return division((subtraction(zscore_list, population_mean(zscore_list))), population_standard_deviance(zscore_list))
def P_value(P_value_list): return division( subtraction(sample_mean(P_value_list), population_mean(P_value_list)), division(population_standard_deviance(P_value_list), square_root(num_values)))
def z_score(data): x = 64 u = population_mean(data) sample_sd = sample_st_dev(data) y = subtraction(x, u) return division(sample_sd, y)
def sample_mean(sample_mean_list): return population_mean(getSample(sample_mean_list, 5))
def pop_mean(self, data): self.result = population_mean(data) return self.result
def confidence_interval_SUB(confidence_interval_SUB_list): return subtraction( population_mean(confidence_interval_SUB_list), (multiplication(zscore(confidence_interval_SUB_list)), division(population_standard_deviance(confidence_interval_SUB_list), square_root(num_values))))
def population_mean(self): self.result = population_mean(self.mean_list) return self.result
def population_mean(self, number_list): self.result = population_mean(number_list) return self.result
def population_mean(self): self.result = population_mean(self.data) return self.result
def population_variance(data): u = population_mean(data) leng = len(data) return round(division(leng, sum([(element - u)**2 for element in data])), 3)
def variance_population_proportion(variance_population_proportion_list): return square_root(division(multiplication(subtraction(population_mean(variance_population_proportion_list), 1)), population_mean(variance_population_proportion_list), num_values))
def pop_stand_dev(data): u = population_mean(data) leng = len(data) return round(square_root(sum([(element - u) ** 2 for element in data]) / leng), 3)
def pop_standard_dev(data): n = len(data) u = population_mean(data) return squareroot( sum([(element - u)**2 for element in data]) / (len(data) - 1))