Crate lightgbm3_sys

source ·

Structs

Constants

Statics

Functions

  • LGBM_BoosterAddValidData⚠
    \brief Add new validation data to booster. \param handle Handle of booster \param valid_data Validation dataset \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterCalcNumPredict⚠
    \brief Get number of predictions. \param handle Handle of booster \param num_row Number of rows \param predict_type What should be predicted
  • LGBM_BoosterCreate⚠
    \brief Create a new boosting learner. \param train_data Training dataset \param parameters Parameters in format ‘key1=value1 key2=value2’ \param[out] out Handle of created booster \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterCreateFromModelfile⚠
    \brief Load an existing booster from model file. \param filename Filename of model \param[out] out_num_iterations Number of iterations of this booster \param[out] out Handle of created booster \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterDumpModel⚠
    \brief Dump model to JSON. \param handle Handle of booster \param start_iteration Start index of the iteration that should be dumped \param num_iteration Index of the iteration that should be dumped, <= 0 means dump all \param feature_importance_type Type of feature importance, can be C_API_FEATURE_IMPORTANCE_SPLIT or C_API_FEATURE_IMPORTANCE_GAIN \param buffer_len String buffer length, if buffer_len < out_len, you should re-allocate buffer \param[out] out_len Actual output length \param[out] out_str JSON format string of model, should pre-allocate memory \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterFeatureImportance⚠
    \brief Get model feature importance. \param handle Handle of booster \param num_iteration Number of iterations for which feature importance is calculated, <= 0 means use all \param importance_type Method of importance calculation:
  • LGBM_BoosterFree⚠
    \brief Free space for booster. \param handle Handle of booster to be freed \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterFreePredictSparse⚠
    \brief Method corresponding to LGBM_BoosterPredictSparseOutput to free the allocated data. \param indptr Pointer to output row headers or column headers to be deallocated \param indices Pointer to sparse indices to be deallocated \param data Pointer to sparse data space to be deallocated \param indptr_type Type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64 \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetCurrentIteration⚠
    \brief Get index of the current boosting iteration. \param handle Handle of booster \param[out] out_iteration Index of the current boosting iteration \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetEval⚠
    \brief Get evaluation for training data and validation data. \note
  • LGBM_BoosterGetEvalCounts⚠
    \brief Get number of evaluation metrics. \param handle Handle of booster \param[out] out_len Total number of evaluation metrics \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetEvalNames⚠
    \brief Get names of evaluation metrics. \param handle Handle of booster \param len Number of char* pointers stored at out_strs. If smaller than the max size, only this many strings are copied \param[out] out_len Total number of evaluation metrics \param buffer_len Size of pre-allocated strings. Content is copied up to buffer_len - 1 and null-terminated \param[out] out_buffer_len String sizes required to do the full string copies \param[out] out_strs Names of evaluation metrics, should pre-allocate memory \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetFeatureNames⚠
    \brief Get names of features. \param handle Handle of booster \param len Number of char* pointers stored at out_strs. If smaller than the max size, only this many strings are copied \param[out] out_len Total number of features \param buffer_len Size of pre-allocated strings. Content is copied up to buffer_len - 1 and null-terminated \param[out] out_buffer_len String sizes required to do the full string copies \param[out] out_strs Names of features, should pre-allocate memory \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetLeafValue⚠
    \brief Get leaf value. \param handle Handle of booster \param tree_idx Index of tree \param leaf_idx Index of leaf \param[out] out_val Output result from the specified leaf \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetLinear⚠
    \brief Get int representing whether booster is fitting linear trees. \param handle Handle of booster \param[out] out The address to hold linear trees indicator \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetLoadedParam⚠
    \brief Get parameters as JSON string. \param handle Handle of booster \param buffer_len Allocated space for string \param[out] out_len Actual size of string \param[out] out_str JSON string containing parameters \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetLowerBoundValue⚠
    \brief Get model lower bound value. \param handle Handle of booster \param[out] out_results Result pointing to min value \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetNumClasses⚠
    \brief Get number of classes. \param handle Handle of booster \param[out] out_len Number of classes \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetNumFeature⚠
    \brief Get number of features. \param handle Handle of booster \param[out] out_len Total number of features \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetNumPredict⚠
    \brief Get number of predictions for training data and validation data (this can be used to support customized evaluation functions). \param handle Handle of booster \param data_idx Index of data, 0: training data, 1: 1st validation data, 2: 2nd validation data and so on \param[out] out_len Number of predictions \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetPredict⚠
    \brief Get prediction for training data and validation data. \note You should pre-allocate memory for out_result, its length is equal to num_class * num_data. \param handle Handle of booster \param data_idx Index of data, 0: training data, 1: 1st validation data, 2: 2nd validation data and so on \param[out] out_len Length of output result \param[out] out_result Pointer to array with predictions \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterGetUpperBoundValue⚠
    \brief Get model upper bound value. \param handle Handle of booster \param[out] out_results Result pointing to max value \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterLoadModelFromString⚠
    \brief Load an existing booster from string. \param model_str Model string \param[out] out_num_iterations Number of iterations of this booster \param[out] out Handle of created booster \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterMerge⚠
    \brief Merge model from other_handle into handle. \param handle Handle of booster, will merge another booster into this one \param other_handle Other handle of booster \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterNumModelPerIteration⚠
    \brief Get number of trees per iteration. \param handle Handle of booster \param[out] out_tree_per_iteration Number of trees per iteration \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterNumberOfTotalModel⚠
    \brief Get number of weak sub-models. \param handle Handle of booster \param[out] out_models Number of weak sub-models \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterPredictForCSC⚠
    \brief Make prediction for a new dataset in CSC format. \note You should pre-allocate memory for out_result:
  • LGBM_BoosterPredictForCSR⚠
    \brief Make prediction for a new dataset in CSR format. \note You should pre-allocate memory for out_result:
  • LGBM_BoosterPredictForCSRSingleRow⚠
    \brief Make prediction for a new dataset in CSR format. This method re-uses the internal predictor structure from previous calls and is optimized for single row invocation. \note You should pre-allocate memory for out_result:
  • LGBM_BoosterPredictForCSRSingleRowFast⚠
    \brief Faster variant of LGBM_BoosterPredictForCSRSingleRow.
  • LGBM_BoosterPredictForCSRSingleRowFastInit⚠
    \brief Initialize and return a FastConfigHandle for use with LGBM_BoosterPredictForCSRSingleRowFast.
  • LGBM_BoosterPredictForFile⚠
    \brief Make prediction for file. \param handle Handle of booster \param data_filename Filename of file with data \param data_has_header Whether file has header or not \param predict_type What should be predicted
  • LGBM_BoosterPredictForMat⚠
    \brief Make prediction for a new dataset. \note You should pre-allocate memory for out_result:
  • LGBM_BoosterPredictForMatSingleRow⚠
    \brief Make prediction for a new dataset. This method re-uses the internal predictor structure from previous calls and is optimized for single row invocation. \note You should pre-allocate memory for out_result:
  • LGBM_BoosterPredictForMatSingleRowFast⚠
    \brief Faster variant of LGBM_BoosterPredictForMatSingleRow.
  • LGBM_BoosterPredictForMatSingleRowFastInit⚠
    \brief Initialize and return a FastConfigHandle for use with LGBM_BoosterPredictForMatSingleRowFast.
  • LGBM_BoosterPredictForMats⚠
    \brief Make prediction for a new dataset presented in a form of array of pointers to rows. \note You should pre-allocate memory for out_result:
  • LGBM_BoosterPredictSparseOutput⚠
    \brief Make sparse prediction for a new dataset in CSR or CSC format. Currently only used for feature contributions. \note The outputs are pre-allocated, as they can vary for each invocation, but the shape should be the same:
  • LGBM_BoosterRefit⚠
    \brief Refit the tree model using the new data (online learning). \param handle Handle of booster \param leaf_preds Pointer to predicted leaf indices \param nrow Number of rows of leaf_preds \param ncol Number of columns of leaf_preds \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterResetParameter⚠
    \brief Reset config for booster. \param handle Handle of booster \param parameters Parameters in format ‘key1=value1 key2=value2’ \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterResetTrainingData⚠
    \brief Reset training data for booster. \param handle Handle of booster \param train_data Training dataset \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterRollbackOneIter⚠
    \brief Rollback one iteration. \param handle Handle of booster \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterSaveModel⚠
    \brief Save model into file. \param handle Handle of booster \param start_iteration Start index of the iteration that should be saved \param num_iteration Index of the iteration that should be saved, <= 0 means save all \param feature_importance_type Type of feature importance, can be C_API_FEATURE_IMPORTANCE_SPLIT or C_API_FEATURE_IMPORTANCE_GAIN \param filename The name of the file \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterSaveModelToString⚠
    \brief Save model to string. \param handle Handle of booster \param start_iteration Start index of the iteration that should be saved \param num_iteration Index of the iteration that should be saved, <= 0 means save all \param feature_importance_type Type of feature importance, can be C_API_FEATURE_IMPORTANCE_SPLIT or C_API_FEATURE_IMPORTANCE_GAIN \param buffer_len String buffer length, if buffer_len < out_len, you should re-allocate buffer \param[out] out_len Actual output length \param[out] out_str String of model, should pre-allocate memory \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterSetLeafValue⚠
    \brief Set leaf value. \param handle Handle of booster \param tree_idx Index of tree \param leaf_idx Index of leaf \param val Leaf value \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterShuffleModels⚠
    \brief Shuffle models. \param handle Handle of booster \param start_iter The first iteration that will be shuffled \param end_iter The last iteration that will be shuffled \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterUpdateOneIter⚠
    \brief Update the model for one iteration. \param handle Handle of booster \param[out] is_finished 1 means the update was successfully finished (cannot split any more), 0 indicates failure \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterUpdateOneIterCustom⚠
    \brief Update the model by specifying gradient and Hessian directly (this can be used to support customized loss functions). \note The length of the arrays referenced by grad and hess must be equal to num_class * num_train_data, this is not verified by the library, the caller must ensure this. \param handle Handle of booster \param grad The first order derivative (gradient) statistics \param hess The second order derivative (Hessian) statistics \param[out] is_finished 1 means the update was successfully finished (cannot split any more), 0 indicates failure \return 0 when succeed, -1 when failure happens
  • LGBM_BoosterValidateFeatureNames⚠
    \brief Check that the feature names of the data match the ones used to train the booster. \param handle Handle of booster \param data_names Array with the feature names in the data \param data_num_features Number of features in the data \return 0 when succeed, -1 when failure happens
  • LGBM_ByteBufferFree⚠
    \brief Free space for byte buffer. \param handle Handle of byte buffer to be freed \return 0 when succeed, -1 when failure happens
  • LGBM_ByteBufferGetAt⚠
    \brief Get a ByteBuffer value at an index. \param handle Handle of byte buffer to be read \param index Index of value to return \param[out] out_val Byte value at index to return \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetAddFeaturesFrom⚠
    \brief Add features from source to target. \param target The handle of the dataset to add features to \param source The handle of the dataset to take features from \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateByReference⚠
    \brief Allocate the space for dataset and bucket feature bins according to reference dataset. \param reference Used to align bin mapper with other dataset \param num_total_row Number of total rows \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromCSC⚠
    \brief Create a dataset from CSC format. \param col_ptr Pointer to column headers \param col_ptr_type Type of col_ptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64 \param indices Pointer to row indices \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param ncol_ptr Number of columns in the matrix + 1 \param nelem Number of nonzero elements in the matrix \param num_row Number of rows \param parameters Additional parameters \param reference Used to align bin mapper with other dataset, nullptr means isn’t used \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromCSR⚠
    \brief Create a dataset from CSR format. \param indptr Pointer to row headers \param indptr_type Type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64 \param indices Pointer to column indices \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nindptr Number of rows in the matrix + 1 \param nelem Number of nonzero elements in the matrix \param num_col Number of columns \param parameters Additional parameters \param reference Used to align bin mapper with other dataset, nullptr means isn’t used \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromCSRFunc⚠
    \brief Create a dataset from CSR format through callbacks. \param get_row_funptr Pointer to std::function<void(int idx, std::vector<std::pair<int, double>>& ret)> (called for every row and expected to clear and fill ret) \param num_rows Number of rows \param num_col Number of columns \param parameters Additional parameters \param reference Used to align bin mapper with other dataset, nullptr means isn’t used \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromFile⚠
    \brief Load dataset from file (like LightGBM CLI version does). \param filename The name of the file \param parameters Additional parameters \param reference Used to align bin mapper with other dataset, nullptr means isn’t used \param[out] out A loaded dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromMat⚠
    \brief Create dataset from dense matrix. \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nrow Number of rows \param ncol Number of columns \param is_row_major 1 for row-major, 0 for column-major \param parameters Additional parameters \param reference Used to align bin mapper with other dataset, nullptr means isn’t used \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromMats⚠
    \brief Create dataset from array of dense matrices. \param nmat Number of dense matrices \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nrow Number of rows \param ncol Number of columns \param is_row_major 1 for row-major, 0 for column-major \param parameters Additional parameters \param reference Used to align bin mapper with other dataset, nullptr means isn’t used \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromSampledColumn⚠
    \brief Allocate the space for dataset and bucket feature bins according to sampled data. \param sample_data Sampled data, grouped by the column \param sample_indices Indices of sampled data \param ncol Number of columns \param num_per_col Size of each sampling column \param num_sample_row Number of sampled rows \param num_local_row Total number of rows local to machine \param num_dist_row Number of total distributed rows \param parameters Additional parameters \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetCreateFromSerializedReference⚠
    \brief Allocate the space for dataset and bucket feature bins according to serialized reference dataset. \param ref_buffer A binary representation of the dataset schema (feature groups, bins, etc.) \param ref_buffer_size The size of the reference array in bytes \param num_row Number of total rows the dataset will contain \param num_classes Number of classes (will be used only in case of multiclass and specifying initial scores) \param parameters Additional parameters \param[out] out Created dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetDumpText⚠
    \brief Save dataset to text file, intended for debugging use only. \param handle Handle of dataset \param filename The name of the file \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetFree⚠
    \brief Free space for dataset. \param handle Handle of dataset to be freed \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetGetFeatureNames⚠
    \brief Get feature names of dataset. \param handle Handle of dataset \param len Number of char* pointers stored at out_strs. If smaller than the max size, only this many strings are copied \param[out] num_feature_names Number of feature names \param buffer_len Size of pre-allocated strings. Content is copied up to buffer_len - 1 and null-terminated \param[out] out_buffer_len String sizes required to do the full string copies \param[out] feature_names Feature names, should pre-allocate memory \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetGetFeatureNumBin⚠
    \brief Get number of bins for feature. \param handle Handle of dataset \param feature Index of the feature \param[out] out The address to hold number of bins \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetGetField⚠
    \brief Get info vector from dataset. \param handle Handle of dataset \param field_name Field name \param[out] out_len Used to set result length \param[out] out_ptr Pointer to the result \param[out] out_type Type of result pointer, can be C_API_DTYPE_INT32, C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetGetNumData⚠
    \brief Get number of data points. \param handle Handle of dataset \param[out] out The address to hold number of data points \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetGetNumFeature⚠
    \brief Get number of features. \param handle Handle of dataset \param[out] out The address to hold number of features \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetGetSubset⚠
    \brief Create subset of a data. \param handle Handle of full dataset \param used_row_indices Indices used in subset \param num_used_row_indices Length of used_row_indices \param parameters Additional parameters \param[out] out Subset of data \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetInitStreaming⚠
    \brief Initialize the Dataset for streaming. \param dataset Handle of dataset \param has_weights Whether the dataset has Metadata weights \param has_init_scores Whether the dataset has Metadata initial scores \param has_queries Whether the dataset has Metadata queries/groups \param nclasses Number of initial score classes \param nthreads Number of external threads that will use the PushRows APIs \param omp_max_threads Maximum number of OpenMP threads (-1 for default) \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetMarkFinished⚠
    \brief Mark the Dataset as complete by calling dataset->FinishLoad. \param dataset Handle of dataset \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetPushRows⚠
    \brief Push data to existing dataset, if nrow + start_row == num_total_row, will call dataset->FinishLoad. \param dataset Handle of dataset \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nrow Number of rows \param ncol Number of columns \param start_row Row start index \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetPushRowsByCSR⚠
    \brief Push data to existing dataset, if nrow + start_row == num_total_row, will call dataset->FinishLoad. \param dataset Handle of dataset \param indptr Pointer to row headers \param indptr_type Type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64 \param indices Pointer to column indices \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nindptr Number of rows in the matrix + 1 \param nelem Number of nonzero elements in the matrix \param num_col Number of columns \param start_row Row start index \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetPushRowsByCSRWithMetadata⚠
    \brief Push CSR data to existing dataset. (See LGBM_DatasetPushRowsWithMetadata for more details.) \param dataset Handle of dataset \param indptr Pointer to row headers \param indptr_type Type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64 \param indices Pointer to column indices \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nindptr Number of rows in the matrix + 1 \param nelem Number of nonzero elements in the matrix \param start_row Row start index \param label Pointer to array with nindptr-1 labels \param weight Optional pointer to array with nindptr-1 weights \param init_score Optional pointer to array with (nindptr-1)*nclasses initial scores, in column format \param query Optional pointer to array with nindptr-1 query values \param tid The id of the calling thread, from 0…N-1 threads \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetPushRowsWithMetadata⚠
    \brief Push data to existing dataset. The general flow for a streaming scenario is: 1. create Dataset “schema” (e.g. LGBM_DatasetCreateFromSampledColumn) 2. init them for thread-safe streaming (LGBM_DatasetInitStreaming) 3. push data (LGBM_DatasetPushRowsWithMetadata or LGBM_DatasetPushRowsByCSRWithMetadata) 4. call LGBM_DatasetMarkFinished \param dataset Handle of dataset \param data Pointer to the data space \param data_type Type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64 \param nrow Number of rows \param ncol Number of feature columns \param start_row Row start index, i.e., the index at which to start inserting data \param label Pointer to array with nrow labels \param weight Optional pointer to array with nrow weights \param init_score Optional pointer to array with nrow*nclasses initial scores, in column format \param query Optional pointer to array with nrow query values \param tid The id of the calling thread, from 0…N-1 threads \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetSaveBinary⚠
    \brief Save dataset to binary file. \param handle Handle of dataset \param filename The name of the file \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetSerializeReferenceToBinary⚠
    \brief Create a dataset schema representation as a binary byte array (excluding data). \param handle Handle of dataset \param[out] out The output byte array \param[out] out_len The length of the output byte array (returned for convenience) \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetSetFeatureNames⚠
    \brief Save feature names to dataset. \param handle Handle of dataset \param feature_names Feature names \param num_feature_names Number of feature names \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetSetField⚠
    \brief Set vector to a content in info. \note
  • LGBM_DatasetSetWaitForManualFinish⚠
    \brief Set whether or not the Dataset waits for a manual MarkFinished call or calls FinishLoad on itself automatically. Set to 1 for streaming scenario, and use LGBM_DatasetMarkFinished to manually finish the Dataset. \param dataset Handle of dataset \param wait Whether to wait or not (1 or 0) \return 0 when succeed, -1 when failure happens
  • LGBM_DatasetUpdateParamChecking⚠
    \brief Raise errors for attempts to update dataset parameters. \param old_parameters Current dataset parameters \param new_parameters New dataset parameters \return 0 when succeed, -1 when failure happens
  • LGBM_DumpParamAliases⚠
    \brief Dump all parameter names with their aliases to JSON. \param buffer_len String buffer length, if buffer_len < out_len, you should re-allocate buffer \param[out] out_len Actual output length \param[out] out_str JSON format string of parameters, should pre-allocate memory \return 0 when succeed, -1 when failure happens
  • LGBM_FastConfigFree⚠
    \brief Release FastConfig object.
  • LGBM_GetLastError⚠
    \brief Get string message of the last error. \return Error information
  • LGBM_GetSampleCount⚠
    \brief Get number of samples based on parameters and total number of rows of data. \param num_total_row Number of total rows \param parameters Additional parameters, namely, bin_construct_sample_cnt is used to calculate returned value \param[out] out Number of samples. This value is used to pre-allocate memory to hold sample indices when calling LGBM_SampleIndices \return 0 when succeed, -1 when failure happens
  • LGBM_NetworkFree⚠
    \brief Finalize the network. \return 0 when succeed, -1 when failure happens
  • LGBM_NetworkInit⚠
    \brief Initialize the network. \param machines List of machines in format ‘ip1:port1,ip2:port2’ \param local_listen_port TCP listen port for local machines \param listen_time_out Socket time-out in minutes \param num_machines Total number of machines \return 0 when succeed, -1 when failure happens
  • LGBM_NetworkInitWithFunctions⚠
    \brief Initialize the network with external collective functions. \param num_machines Total number of machines \param rank Rank of local machine \param reduce_scatter_ext_fun The external reduce-scatter function \param allgather_ext_fun The external allgather function \return 0 when succeed, -1 when failure happens
  • LGBM_RegisterLogCallback⚠
    \brief Register a callback function for log redirecting. \param callback The callback function to register \return 0 when succeed, -1 when failure happens
  • LGBM_SampleIndices⚠
    \brief Create sample indices for total number of rows. \note You should pre-allocate memory for out, you can get its length by LGBM_GetSampleCount. \param num_total_row Number of total rows \param parameters Additional parameters, namely, bin_construct_sample_cnt and data_random_seed are used to produce the output \param[out] out Created indices, type is int32_t \param[out] out_len Number of indices \return 0 when succeed, -1 when failure happens
  • __asprintf⚠
  • __getdelim⚠
  • __memcmpeq⚠
  • __mempcpy⚠
  • __overflow⚠
  • __stpcpy⚠
  • __stpncpy⚠
  • __strtok_r⚠
  • __uflow⚠
  • asprintf⚠
  • basename⚠
  • bcmp⚠
  • bcopy⚠
  • bzero⚠
  • clearerr⚠
  • clearerr_unlocked⚠
  • ctermid⚠
  • cuserid⚠
  • dprintf⚠
  • explicit_bzero⚠
  • fclose⚠
  • fcloseall⚠
  • fdopen⚠
  • feof⚠
  • feof_unlocked⚠
  • ferror⚠
  • ferror_unlocked⚠
  • fflush⚠
  • fflush_unlocked⚠
  • ffs⚠
  • ffsl⚠
  • ffsll⚠
  • fgetc⚠
  • fgetc_unlocked⚠
  • fgetpos⚠
  • fgetpos64⚠
  • fgets⚠
  • fgets_unlocked⚠
  • fileno⚠
  • fileno_unlocked⚠
  • flockfile⚠
  • fmemopen⚠
  • fopen⚠
  • fopen64⚠
  • fopencookie⚠
  • fprintf⚠
  • fputc⚠
  • fputc_unlocked⚠
  • fputs⚠
  • fputs_unlocked⚠
  • fread⚠
  • fread_unlocked⚠
  • freopen⚠
  • freopen64⚠
  • fscanf⚠
  • fscanf1⚠
  • fseek⚠
  • fseeko⚠
  • fseeko64⚠
  • fsetpos⚠
  • fsetpos64⚠
  • ftell⚠
  • ftello⚠
  • ftello64⚠
  • ftrylockfile⚠
  • funlockfile⚠
  • fwrite⚠
  • fwrite_unlocked⚠
  • getc⚠
  • getc_unlocked⚠
  • getchar⚠
  • getchar_unlocked⚠
  • getdelim⚠
  • getline⚠
  • gets⚠
  • getw⚠
  • index⚠
  • memccpy⚠
  • memchr⚠
  • memcmp⚠
  • memcpy⚠
  • memfrob⚠
  • memmem⚠
  • memmove⚠
  • mempcpy⚠
  • memrchr⚠
  • memset⚠
  • obstack_printf⚠
  • obstack_vprintf⚠
  • open_memstream⚠
  • pclose⚠
  • perror⚠
  • popen⚠
  • printf⚠
  • putc⚠
  • putc_unlocked⚠
  • putchar⚠
  • putchar_unlocked⚠
  • puts⚠
  • putw⚠
  • rawmemchr⚠
  • remove⚠
  • rename⚠
  • renameat⚠
  • renameat2⚠
  • rewind⚠
  • rindex⚠
  • scanf⚠
  • scanf1⚠
  • setbuf⚠
  • setbuffer⚠
  • setlinebuf⚠
  • setvbuf⚠
  • sigabbrev_np⚠
  • sigdescr_np⚠
  • snprintf⚠
  • sprintf⚠
  • sscanf⚠
  • sscanf1⚠
  • stpcpy⚠
  • stpncpy⚠
  • strcasecmp⚠
  • strcasecmp_l⚠
  • strcasestr⚠
  • strcat⚠
  • strchr⚠
  • strchrnul⚠
  • strcmp⚠
  • strcoll⚠
  • strcoll_l⚠
  • strcpy⚠
  • strcspn⚠
  • strdup⚠
  • strerror⚠
  • strerror_l⚠
  • strerror_r⚠
  • strerrordesc_np⚠
  • strerrorname_np⚠
  • strfry⚠
  • strlen⚠
  • strncasecmp⚠
  • strncasecmp_l⚠
  • strncat⚠
  • strncmp⚠
  • strncpy⚠
  • strndup⚠
  • strnlen⚠
  • strpbrk⚠
  • strrchr⚠
  • strsep⚠
  • strsignal⚠
  • strspn⚠
  • strstr⚠
  • strtok⚠
  • strtok_r⚠
  • strverscmp⚠
  • strxfrm⚠
  • strxfrm_l⚠
  • tempnam⚠
  • tmpfile⚠
  • tmpfile64⚠
  • tmpnam⚠
  • tmpnam_r⚠
  • ungetc⚠
  • vasprintf⚠
  • vdprintf⚠
  • vfprintf⚠
  • vfscanf⚠
  • vfscanf1⚠
  • vprintf⚠
  • vscanf⚠
  • vscanf1⚠
  • vsnprintf⚠
  • vsprintf⚠
  • vsscanf⚠
  • vsscanf1⚠

Type Definitions

Unions