问如何“记住”训练后实际预测的绝对编码？

EN

    # Before: D.schema == {num_col_1: int, cat_col_1: str, cat_col_2: str, ...}

    # assign unique index for each distinct label for categorical column annd store in a new column
    # http://spark.apache.org/docs/latest/ml-features.html#stringindexer
    label_indexer = StringIndexer(inputCol="cat_col_i", outputCol="cat_col_i_index").fit(D)
    D = label_indexer.transform(D)

    # After: D.schema == {num_col_1: int, cat_col_1: str, cat_col_2: str, ..., cat_col_1_index: int, cat_col_2_index: int, ...}

    map = {}
    for all categorical column names colname in D:
        map[colname] = []
        # create mapping dict for all categorical values for all 
        # see https://spark.apache.org/docs/latest/sql-programming-guide.html#untyped-dataset-operations-aka-dataframe-operations
        for all rows r in D.select(colname, '%s_index' % colname).drop_duplicates():
            enc_from = r['%s' % colname]
            enc_to = r['%s_index' % colname]
            map[colname].append((enc_from, enc_to))

        # for cats that may appear later that have yet to be seen 
        # (IDK if this is best practice, may be another way, see https://medium.com/@vaibhavshukla182/how-to-solve-mismatch-in-train-and-test-set-after-categorical-encoding-8320ed03552f)
        map[colname].append(('NOVEL_CAT', map[colname].len))
        # sort by index encoding
        map[colname].sort(key = lamdba pair: pair[1])    

    {
        'cat_col_1': [('orig_label_11', 0), ('orig_label_12', 1), ...],
        'cat_col_2': [(), (), ...],
        ...
        'cat_col_n': [(orig_label_n1, 0), ...]
    }

    for all categorical column names colname in ds:
        enc_from = ds[colname]
        # make zero vector for 1-hot for category 
        col_onehot = zeros.(size = map[colname].len)
        for label, index in map[colname]:
            if (label == enc_from):
                col_onehot[index] = 1
                # make new column in sample for 1-hot vector
                ds['%s_onehot' % colname] = col_onehot
                break

StringIndexerModel sim = new StringIndexer()
        .setInputCol(field)
        .setOutputCol(field + "_INDEX")
        .setHandleInvalid("skip")
        .fit(dataset);

sim.write().overwrite().save("IndexMappingModels/" + field + "_INDEX");

StringIndexerModel sim = StringIndexerModel.load("IndexMappingModels/" + field + "_INDEX");

dataset = sim.transform(dataset);