2020-01-02

3. 修改配置文件$HADOOP_HOME/etc/hadoop/mapred-site.xml

    data.loc[index, 'video_memory_value'] = re.sub('\D', '', data.loc[index, 'video_memory'])
    if data.loc[index, 'video_memory_value'] == '':
        data.loc[index, 'video_memory_value'] = float(0)
    else:
        data.loc[index, 'video_memory_value'] = float(data.loc[index, 'video_memory_value'])
   
   cpu_mapping = {'i3':3, 'i5':5, 'i7':7, 'i9':9, 'AMD':6}
   data['cpu'] = data['cpu'].map(cpu_mapping)
   
   data = data.join(pd.get_dummies(data[['brand', 'video_card']]))
   
   data = data.drop_duplicates()
   data = data.dropna(axis=0, how='any')
   
    screen_pixels = re.findall(r'\d+', data.loc[index, 'screen_pixels'])
    if len(screen_pixels) >= 2:
        data.loc[index, 'screen_pixels_x'] = float(screen_pixels[0])
        data.loc[index, 'screen_pixels_y'] = float(screen_pixels[1])
   
    ssd_value = re.findall('\d+', str(data.loc[index, 'ssd']))
    if len(ssd_value) > 0:
        data.loc[index, 'ssd_value'] = float(ssd_value[0])
    else:
        data.loc[index, 'ssd_value'] = 0
   
    def ridge_model(train_data, test_data, train_target, test_target):
        param_alpha = {'alpha':[1.0, 0.1, 0.01, 0.001]}
        estimator = Ridge()
        estimator = GridSearchCV(estimator, param_grid=param_alpha)
        estimator.fit(train_data, train_target)
        print('RIDGE最佳参数alpha:', estimator.best_params_)
        print('RIDGE最佳得分：', estimator.best_score_)
        estimator = estimator.best_estimator_
        print('RIDGE损失函数值MAE：%.2f' % 
        np.divide(np.sum(np.absolute(estimator.predict(test_data) - test_target)), len(test_target)))
        print('RIDGE预测性能得分：%.2f' % estimator.score(test_data, test_target))
   
   
    RIDGE最佳参数alpha: {'alpha': 0.1}
    RIDGE最佳得分： 0.36026660370026786
    RIDGE损失函数值MAE：27.46
    RIDGE预测性能得分：0.54
   
   
    data_columns = data.columns
    min_max_scaler = MinMaxScaler()
    data = min_max_scaler.fit_transform(data)
    data = pd.DataFrame(data)
    data.columns = data_columns
   
   
    def xgb_model(train_data, test_data, train_target, test_target):
        param_learning_rate = {'learning_rate':[1.0, 0.1, 0.01, 0.001], 'max_depth':[3, 4, 5, 6, 7, 8], 'n_estimators':[10, 20, 30, 50, 70, 90, 100, 120, 140, 160, 200, 230, 260, 300]}
        estimator = xgb.XGBRegressor(silent=False, objective='reg:gamma')
        estimator = GridSearchCV(estimator, param_grid=param_learning_rate)
        estimator.fit(train_data, train_target)
        print('XGB最佳参数learning_rate:', estimator.best_params_)
        print('XGB最佳得分：', estimator.best_score_)
   
        estimator = estimator.best_estimator_
        predict_target = estimator.predict(test_data)
   
        actual_target = []
        for index, row in test_target.iterrows():
            comment_count = row['comment_count']
            actual_target.append(comment_count)
   
        mae_value = np.divide(np.sum(np.absolute(predict_target - actual_target)), len(actual_target))
        print('XGB损失函数值MAE：%.2f' % mae_value )
        print('XGB预测性能得分：%.2f' % estimator.score(test_data, test_target))