Alien-XGBoost

 view release on metacpan or  search on metacpan

xgboost/R-package/tests/testthat/test_helpers.R  view on Meta::CPAN

  imp2plot <- xgb.plot.importance(importance.GLM)
  expect_equal(colnames(imp2plot), c("Feature", "Weight", "Importance"))
  xgb.ggplot.importance(importance.GLM)
  
  # for multiclass
  imp.GLM <- xgb.importance(model = mbst.GLM)
  expect_equal(dim(imp.GLM), c(12, 3))
  expect_equal(imp.GLM$Class, rep(0:2, each=4))
})

test_that("xgb.model.dt.tree and xgb.importance work with a single split model", {
  bst1 <- xgboost(data = sparse_matrix, label = label, max_depth = 1,
                  eta = 1, nthread = 2, nrounds = 1, verbose = 0,
                  objective = "binary:logistic")
  expect_error(dt <- xgb.model.dt.tree(model = bst1), regexp = NA) # no error
  expect_equal(nrow(dt), 3)
  expect_error(imp <- xgb.importance(model = bst1), regexp = NA) # no error
  expect_equal(nrow(imp), 1)
  expect_equal(imp$Gain, 1)
})

xgboost/dmlc-core/src/io/input_split_base.h  view on Meta::CPAN

      : fs_(NULL),
        align_bytes_(8),
        tmp_chunk_(kBufferSize),
        buffer_size_(kBufferSize) {}
  /*!
   * \brief intialize the base before doing anything
   * \param fs the filesystem ptr
   * \param uri the uri of the files
   * \param rank the rank of the split
   * \param nsplit number of splits
   * \param align_bytes the head split must be multiple of align_bytes
   *   this also checks if file size are multiple of align_bytes
   */
  void Init(FileSystem *fs,
            const char *uri,
            size_t align_bytes);
  // to be implemented by child class
  /*!
   * \brief seek to the beginning of the first record
   *        in current file pointer
   * \return how many bytes we read past

xgboost/src/cli_main.cc  view on Meta::CPAN

  /*! \brief path of test dataset */
  std::string test_path;
  /*! \brief the path of test model file, or file to restart training */
  std::string model_in;
  /*! \brief the path of final model file, to be saved */
  std::string model_out;
  /*! \brief the path of directory containing the saved models */
  std::string model_dir;
  /*! \brief name of predict file */
  std::string name_pred;
  /*! \brief data split mode */
  int dsplit;
  /*!\brief limit number of trees in prediction */
  int ntree_limit;
  /*!\brief whether to directly output margin value */
  bool pred_margin;
  /*! \brief whether dump statistics along with model */
  int dump_stats;
  /*! \brief what format to dump the model in */
  std::string dump_format;
  /*! \brief name of feature map */

xgboost/src/cli_main.cc  view on Meta::CPAN

    DMLC_DECLARE_FIELD(model_out).set_default("NULL")
        .describe("Output model path, if any.");
    DMLC_DECLARE_FIELD(model_dir).set_default("./")
        .describe("Output directory of period checkpoint.");
    DMLC_DECLARE_FIELD(name_pred).set_default("pred.txt")
        .describe("Name of the prediction file.");
    DMLC_DECLARE_FIELD(dsplit).set_default(0)
        .add_enum("auto", 0)
        .add_enum("col", 1)
        .add_enum("row", 2)
        .describe("Data split mode.");
    DMLC_DECLARE_FIELD(ntree_limit).set_default(0).set_lower_bound(0)
        .describe("Number of trees used for prediction, 0 means use all trees.");
    DMLC_DECLARE_FIELD(pred_margin).set_default(false)
        .describe("Whether to predict margin value instead of probability.");
    DMLC_DECLARE_FIELD(dump_stats).set_default(false)
        .describe("Whether dump the model statistics.");
    DMLC_DECLARE_FIELD(dump_format).set_default("text")
        .describe("What format to dump the model in.");
    DMLC_DECLARE_FIELD(name_fmap).set_default("NULL")
        .describe("Name of the feature map file.");

xgboost/src/learner.cc  view on Meta::CPAN

        "Number of class option for multi-class classifier. "
        " By default equals 0 and corresponds to binary classifier.");
  }
};

struct LearnerTrainParam : public dmlc::Parameter<LearnerTrainParam> {
  // stored random seed
  int seed;
  // whether seed the PRNG each iteration
  bool seed_per_iteration;
  // data split mode, can be row, col, or none.
  int dsplit;
  // tree construction method
  int tree_method;
  // internal test flag
  std::string test_flag;
  // maximum buffered row value
  float prob_buffer_row;
  // maximum row per batch.
  size_t max_row_perbatch;
  // number of threads to use if OpenMP is enabled

xgboost/src/learner.cc  view on Meta::CPAN

        .set_default(false)
        .describe(
            "Seed PRNG determnisticly via iterator number, "
            "this option will be switched on automatically on distributed "
            "mode.");
    DMLC_DECLARE_FIELD(dsplit)
        .set_default(0)
        .add_enum("auto", 0)
        .add_enum("col", 1)
        .add_enum("row", 2)
        .describe("Data split mode for distributed training.");
    DMLC_DECLARE_FIELD(tree_method)
        .set_default(0)
        .add_enum("auto", 0)
        .add_enum("approx", 1)
        .add_enum("exact", 2)
        .add_enum("hist", 3)
        .add_enum("gpu_exact", 4)
        .add_enum("gpu_hist", 5)
        .describe("Choice of tree construction method.");
    DMLC_DECLARE_FIELD(test_flag).set_default("").describe(