alink使用csv数据源

数据源-波士顿房价

过程：首先定义数据源batch

CsvSourceBatchOp

参数：

filePath：csv文件路径

列名： String[] colNames

列数据类型：TypeInformation<?>[] colTypes

列分隔符：String fieldDelim

行分隔符：String rowDelim

 

最后可以定义一个sinkOP来保存数据

最后通过BatchOperator.execute();

public static void main(String[] args) throws Exception{

        String[] fileds = new String[]{"CRIM", "ZN", "INDUS", "CHAS", "NOX", "RM", "AGE", "DIS", "RAD", "TAX", "PTRATIO", "B", "LSTAT", "convert"};

        TypeInformation[] typeInformations = new TypeInformation[fileds.length];
        for(int i = 0;i<fileds.length;i++){
            typeInformations[i] = TypeInformation.of(Double.class);
        }

        CsvSourceBatchOp csvSourceBatchOp = new CsvSourceBatchOp("./house_price2.csv",fileds,typeInformations,",","\n");

        LinearRegression lr = new LinearRegression();
        lr.setFeatureCols("CRIM", "ZN", "INDUS", "CHAS", "NOX", "RM", "AGE", "DIS", "RAD", "TAX", "PTRATIO", "B", "LSTAT").setLabelCol("convert").setPredictionCol("p");

        BatchOperator out = lr.fit(csvSourceBatchOp).transform(csvSourceBatchOp);

        CsvSinkBatchOp csvSinkBatchOp = new CsvSinkBatchOp("./house_price3.csv");

        csvSinkBatchOp.linkFrom(out);

        BatchOperator.execute();
    }