Machine learning WEKA-神经网络-MLP-数据模型
我的目标是利用X站、Y站和Z站的数据预测天气参数（气温、湿度）。其中X站是官方数据，Y站和Z站是观测数据。所有这些台站（观测点）地理位置接近。 这是CSV格式的示例数据文件， X为测试数据，Y和Z为训练数据Machine learning WEKA-神经网络-MLP-数据模型,machine-learning,neural-network,weka,prediction,Machine Learning,Neural Network,Weka,Prediction,我的目标是利用X站、Y站和Z站的数据预测天气参数（气温、湿度）。其中X站是官方数据，Y站和Z站是观测数据。所有这些台站（观测点）地理位置接近。 这是CSV格式的示例数据文件， X为测试数据，Y和Z为训练数据 date_time,StationName,air_temp,dewpoint,humidity,windspeed,windchill,pressure 2014-07-01,X,11,8.74811,86,0,11,1017.22 2014-07-02,X,16.2222,12.7651
date_time,StationName,air_temp,dewpoint,humidity,windspeed,windchill,pressure
2014-07-01,X,11,8.74811,86,0,11,1017.22
2014-07-02,X,16.2222,12.7651,80,1,16.2222,1019.02
2014-07-03,X,21.3889,13.039,59,0,21.3889,1020.37
2014-07-04,X,21.4444,12.8294,58,3,21.4444,1020.74
2014-07-05,X,21.4444,12.8294,58,3,21.33,1020.71
2014-07-06,X,21.4444,12.8294,58,9,21.4444,1020.74
2014-07-07,X,21.3889,12.5119,57,9,21.3889,1020.74
2014-07-08,X,21.3889,12.2423,56,9,21.3889,1020.74
2014-07-09,X,21.3889,12.2423,56,11,21.3889,1020.74
2014-07-01,Y,13.7,9.4,75,1,13.9,1020.3
2014-07-02,Y,13.7,9.4,75,2,13.9,1020.3
2014-07-03,Y,13.7,9.4,76,2,13.9,1020.3
2014-07-04,Y,13.6,9.4,76,3,13.9,1020.4
2014-07-05,Y,13.6,9.4,76,3,13.9,1020.3
2014-07-06,Y,13.6,9.4,76,2,13.3,1020.3
2014-07-07,Y,13.6,9.4,76,2,13.3,1020.4
2014-07-08,Y,13.5,9.4,76,1,13.3,1020.4
2014-07-09,Y,13.5,9.4,76,2,13.3,1020.4
2014-07-01,Z,13.2,10,82,0,13.3,1016.3
2014-07-02,Z,13.2,10,82,0,13.3,1016.3
2014-07-03,Z,13.1,10,82,0,13.3,1016.3
2014-07-04,Z,13.1,10,82,0,13.3,1016.3
2014-07-05,Z,13.1,10,82,0,13.3,1016.3
2014-07-06,Z,13.1,10,82,0,13.3,1016.3
2014-07-07,Z,13.1,10,82,0,13.3,1016.3
2014-07-08,Z,13,10,82,0,12.8,1016.3
2014-07-09,Z,12.9,10,82,0,12.8,1016.2