def regression_line_housing_no_libs(): """ Solution for HW1 prob 2 """ print('Homework 1 problem 2 - No Libraries - Regression Line') print('Housing Dataset') test, train = utils.load_and_normalize_housing_set() print str(len(train)) + " # in training set <--> # in test " + str(len(test)) columns = train.columns[:-1] Y_fit = mystats.linear_regression_points(train[columns], train['MEDV']) print 'Y_fit' print Y_fit #for i in range(0, len(Y_fit)): # print str(Y_fit[i]) + ' -- ' + str(train['MEDV'][i]) row_sums = np.zeros(len(Y_fit[0])) for col in Y_fit: for i in range(0, len(col)): row_sums[i] += col[i] print row_sums col_MSE = {} for i, col in enumerate(columns): col_fit = row_sums[i] # Y_fit[i] + Y_fit[-1] col_MSE[col] = mystats.compute_MSE(col_fit, train['MEDV']) print col_MSE RMSE = np.sqrt(col_MSE.values()) average_MSE = utils.average(col_MSE.values()) average_RMSE = utils.average(RMSE) print 'Average MSE: ' + str(average_MSE) print 'Average RMSE: ' + str(average_RMSE)
def test_regression_line_housing_no_libs(): """ Testing 2 variable solution for HW1 prob 2 """ print('Testing linear regression with 2 columns') test, train = utils.load_and_normalize_housing_set() print str(len(train)) + " # in training set <--> # in test " + str(len(test)) columns = train.columns[:-1] Y_fit = mystats.linear_regression_points(train[columns[0]], train['MEDV']) #for i, col in enumerate(columns): print 'Y_fit' print Y_fit for i in range(0, len(Y_fit)): print str(Y_fit[i]) + ' -- ' + str(train['MEDV'][i]) print train[columns[0]] #myplot.points([train[columns[0]], train['MEDV']]) #myplot.points([train[columns[0]], list(Y_fit[0])]) myplot.fit_v_point([train[columns[0]], train['MEDV'], list(Y_fit[0] + Y_fit[-1])]) col_MSE = {} print columns[0] i = 0 col = 'CRIM' col_fit = Y_fit[i] + Y_fit[-1] col_MSE[col] = mystats.compute_MSE_arrays(col_fit, train['MEDV']) print col_MSE
def regression_line_spam_no_libs(): """ Solution for HW1 prob 2 """ print('Homework 1 problem 2 - No Libraries - Regression Line') print('Spam Dataset') spam_data = utils.load_and_normalize_spam_data() test, train = utils.split_test_and_train(spam_data) columns = train.columns[:-1] Y_fit = mystats.linear_regression_points(train[columns], train['is_spam']) #print 'Y_fit' #print Y_fit #for i in range(0, len(Y_fit)): # print str(Y_fit[i]) + ' -- ' + str(train['is_spam'][i]) col_MSE = {} for i, col in enumerate(columns): col_fit = Y_fit[i] + Y_fit[-1] col_MSE[col] = mystats.compute_MSE_arrays(col_fit, train['is_spam']) print col_MSE RMSE = np.sqrt(col_MSE.values()) average_MSE = utils.average(col_MSE.values()) average_RMSE = utils.average(RMSE) print 'Average MSE: ' + str(average_MSE) print 'Average RMSE: ' + str(average_RMSE)