flink-ml-lib/src/main/java/org/apache/flink/ml/classification/linearsvc/LinearSVC.java [80:106]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                    DenseVector features =
                                            ((Vector) dataPoint.getField(getFeaturesCol()))
                                                    .toDense();
                                    return new LabeledPointWithWeight(features, label, weight);
                                });

        DataStream<DenseVector> initModelData =
                DataStreamUtils.reduce(
                                trainData.map(x -> x.getFeatures().size()),
                                (ReduceFunction<Integer>)
                                        (t0, t1) -> {
                                            Preconditions.checkState(
                                                    t0.equals(t1),
                                                    "The training data should all have same dimensions.");
                                            return t0;
                                        })
                        .map(DenseVector::new);

        Optimizer optimizer =
                new SGD(
                        getMaxIter(),
                        getLearningRate(),
                        getGlobalBatchSize(),
                        getTol(),
                        getReg(),
                        getElasticNet());
        DataStream<DenseVector> rawModelData =
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



flink-ml-lib/src/main/java/org/apache/flink/ml/regression/linearregression/LinearRegression.java [76:102]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                    DenseVector features =
                                            ((Vector) dataPoint.getField(getFeaturesCol()))
                                                    .toDense();
                                    return new LabeledPointWithWeight(features, label, weight);
                                });

        DataStream<DenseVector> initModelData =
                DataStreamUtils.reduce(
                                trainData.map(x -> x.getFeatures().size()),
                                (ReduceFunction<Integer>)
                                        (t0, t1) -> {
                                            Preconditions.checkState(
                                                    t0.equals(t1),
                                                    "The training data should all have same dimensions.");
                                            return t0;
                                        })
                        .map(DenseVector::new);

        Optimizer optimizer =
                new SGD(
                        getMaxIter(),
                        getLearningRate(),
                        getGlobalBatchSize(),
                        getTol(),
                        getReg(),
                        getElasticNet());
        DataStream<DenseVector> rawModelData =
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -