machine_learning.py 文件源码

def lasso_regr(wine_set):

    pred = wine_set[["density", 'alcohol', 'sulphates', 'pH', 'volatile_acidity', 'chlorides', 'fixed_acidity',
                    'citric_acid', 'residual_sugar', 'free_sulfur_dioxide', 'total_sulfur_dioxide']]
    predictors = pred.copy()
    targets = wine_set.quality

    # standardize predictors to have mean=0 and sd=1
    predictors = pd.DataFrame(preprocessing.scale(predictors))
    predictors.columns = pred.columns
    # print(predictors.head())

    # split into training and testing sets
    pred_train, pred_test, tar_train, tar_test = train_test_split(predictors, targets, test_size=.3, random_state=123)

    # specify the lasso regression model
    model = LassoLarsCV(cv=10, precompute=False).fit(pred_train, tar_train)

    print('Predictors and their regression coefficients:')
    d = dict(zip(predictors.columns, model.coef_))
    for k in d:
        print(k, ':', d[k])

    # plot coefficient progression
    m_log_alphas = -np.log10(model.alphas_)
    # ax = plt.gca()
    plt.plot(m_log_alphas, model.coef_path_.T)
    print('\nAlpha:', model.alpha_)
    plt.axvline(-np.log10(model.alpha_), linestyle="dashed", color='k', label='alpha CV')
    plt.ylabel("Regression coefficients")
    plt.xlabel("-log(alpha)")
    plt.title('Regression coefficients progression for Lasso paths')
    plt.show()

    # plot mean squared error for each fold
    m_log_alphascv = -np.log10(model.cv_alphas_)
    plt.plot(m_log_alphascv, model.cv_mse_path_, ':')
    plt.plot(m_log_alphascv, model.cv_mse_path_.mean(axis=-1), 'k', label='Average across the folds', linewidth=2)
    plt.legend()
    plt.xlabel('-log(alpha)')
    plt.ylabel('Mean squared error')
    plt.title('Mean squared error on each fold')
    plt.show()

    # Mean squared error from training and test data
    train_error = mean_squared_error(tar_train, model.predict(pred_train))
    test_error = mean_squared_error(tar_test, model.predict(pred_test))
    print('\nMean squared error for training data:', train_error)
    print('Mean squared error for test data:', test_error)

    rsquared_train = model.score(pred_train, tar_train)
    rsquared_test = model.score(pred_test, tar_test)
    print('\nR-square for training data:', rsquared_train)
    print('R-square for test data:', rsquared_test)
#
# print('----------------Lasso Regression------------------------')
# call(lasso_regr)


# ______________________________K-Means Cluster Analysis_________________