PRO-121: Remove progress estimation (#868)

alancleary · web-flow · commit 3884875cf3a4 · 2026-01-15T16:42:04.000-07:00
* Removed enable_progress_estimation parameter from Python API

* Removed setEnableProgressEstimation method from Java API

* Removed support for progress estimation from C API

* Removed --enable-progress-estimation flag from CLI

* Removed enable_progress_estimation member from Reader class
diff --git a/apis/java/src/main/java/io/tiledb/libvcfnative/LibVCFNative.c b/apis/java/src/main/java/io/tiledb/libvcfnative/LibVCFNative.c
@@ -881,24 +881,6 @@ Java_io_tiledb_libvcfnative_LibVCFNative_tiledb_1vcf_1bed_1file_1get_1last_1erro
   return result;
 }
 
-JNIEXPORT jint JNICALL
-Java_io_tiledb_libvcfnative_LibVCFNative_tiledb_1vcf_1reader_1set_1enable_1progress_1estimation(
-    JNIEnv* env,
-    jclass self,
-    jlong readerPtr,
-    jboolean enableProgressEstimation) {
-  (void)self;
-  tiledb_vcf_reader_t* reader = (tiledb_vcf_reader_t*)readerPtr;
-  if (reader == 0) {
-    return TILEDB_VCF_ERR;
-  }
-
-  int32_t rc = tiledb_vcf_reader_set_enable_progress_estimation(
-      reader, enableProgressEstimation);
-
-  return rc;
-}
-
 JNIEXPORT jint JNICALL
 Java_io_tiledb_libvcfnative_LibVCFNative_tiledb_1vcf_1reader_1set_1debug_1print_1vcf_1regions(
     JNIEnv* env, jclass self, jlong readerPtr, jboolean printVCFRegions) {
diff --git a/apis/java/src/main/java/io/tiledb/libvcfnative/LibVCFNative.h b/apis/java/src/main/java/io/tiledb/libvcfnative/LibVCFNative.h
diff --git a/apis/java/src/main/java/io/tiledb/libvcfnative/LibVCFNative.java b/apis/java/src/main/java/io/tiledb/libvcfnative/LibVCFNative.java
@@ -133,9 +133,6 @@ public static final native int tiledb_vcf_reader_set_tiledb_stats_enabled(
 
   public static final native String tiledb_vcf_version();
 
-  public static final native int tiledb_vcf_reader_set_enable_progress_estimation(
-      long readerPtr, boolean enableProgressEstimation);
-
   public static final native int tiledb_vcf_reader_set_debug_print_vcf_regions(
       long readerPtr, boolean printVCFRegions);
 
diff --git a/apis/java/src/main/java/io/tiledb/libvcfnative/VCFReader.java b/apis/java/src/main/java/io/tiledb/libvcfnative/VCFReader.java
@@ -588,17 +588,6 @@ public String version() {
     return LibVCFNative.tiledb_vcf_version();
   }
 
-  public VCFReader setEnableProgressEstimation(boolean enableProgressEstimation) {
-    int rc =
-        LibVCFNative.tiledb_vcf_reader_set_enable_progress_estimation(
-            this.readerPtr, enableProgressEstimation);
-    if (rc != 0) {
-      String msg = getLastErrorMessage();
-      throw new RuntimeException("Error setting enableProgressEstimation: " + msg);
-    }
-    return this;
-  }
-
   public VCFReader setDebugPrintVCFRegions(boolean debugPrintVCFRegions) {
     int rc =
         LibVCFNative.tiledb_vcf_reader_set_debug_print_vcf_regions(
diff --git a/apis/python/src/tiledbvcf/binding/libtiledbvcf.cc b/apis/python/src/tiledbvcf/binding/libtiledbvcf.cc
@@ -94,9 +94,6 @@ PYBIND11_MODULE(libtiledbvcf, m) {
           &Reader::set_tiledb_tile_cache_percentage)
       .def("set_check_samples_exist", &Reader::set_check_samples_exist)
       .def("version", &Reader::version)
-      .def(
-          "set_enable_progress_estimation",
-          &Reader::set_enable_progress_estimation)
       .def("set_debug_print_vcf_regions", &Reader::set_debug_print_vcf_regions)
       .def("set_debug_print_sample_list", &Reader::set_debug_print_sample_list)
       .def(
diff --git a/apis/python/src/tiledbvcf/binding/reader.cc b/apis/python/src/tiledbvcf/binding/reader.cc
@@ -616,15 +616,6 @@ std::string Reader::version() {
   return version_str;
 }
 
-void Reader::set_enable_progress_estimation(
-    const bool& enable_progress_estimation) {
-  auto reader = ptr.get();
-  check_error(
-      reader,
-      tiledb_vcf_reader_set_enable_progress_estimation(
-          reader, enable_progress_estimation));
-}
-
 void Reader::set_debug_print_vcf_regions(const bool& print_vcf_regions) {
   auto reader = ptr.get();
   check_error(
diff --git a/apis/python/src/tiledbvcf/binding/reader.h b/apis/python/src/tiledbvcf/binding/reader.h
@@ -172,9 +172,6 @@ class Reader {
   /** Get Version info for TileDB VCF and TileDB. */
   std::string version();
 
-  /** Set disable progress estimation */
-  void set_enable_progress_estimation(const bool& enable_progress_estimation);
-
   /** Set print vcf regions in verbose mode */
   void set_debug_print_vcf_regions(const bool& print_vcf_regions);
 
diff --git a/apis/python/src/tiledbvcf/dataset.py b/apis/python/src/tiledbvcf/dataset.py
@@ -283,7 +283,6 @@ def read_arrow(
         skip_check_samples: bool = False,
         set_af_filter: str = "",
         scan_all_samples: bool = False,
-        enable_progress_estimation: bool = False,
     ) -> pa.Table:
         """
         Read data from the dataset into a PyArrow Table.
@@ -312,8 +311,6 @@ def read_arrow(
             variants with AF > 0.1, set this to ">0.1".
         scan_all_samples
             Scan all samples when computing internal allele frequency.
-        enable_progress_estimation
-            **DEPRECATED** - This parameter will be removed in a future release.
 
         Returns
         -------
@@ -342,7 +339,6 @@ def read_arrow(
         self.reader.set_check_samples_exist(not skip_check_samples)
         self.reader.set_af_filter(set_af_filter)
         self.reader.set_scan_all_samples(scan_all_samples)
-        self.reader.set_enable_progress_estimation(enable_progress_estimation)
 
         if bed_file is not None:
             self.reader.set_bed_file(bed_file)
@@ -534,7 +530,6 @@ def read(
         skip_check_samples: bool = False,
         set_af_filter: str = "",
         scan_all_samples: bool = False,
-        enable_progress_estimation: bool = False,
     ) -> pd.DataFrame:
         """
         Read data from the dataset into a Pandas DataFrame.
@@ -563,8 +558,6 @@ def read(
         set_af_filter
             Filter variants by internal allele frequency. For example, to include
             variants with AF > 0.1, set this to ">0.1".
-        enable_progress_estimation
-            **DEPRECATED** - This parameter will be removed in a future release.
 
         Returns
         -------
@@ -592,7 +585,6 @@ def read(
         self.reader.set_check_samples_exist(not skip_check_samples)
         self.reader.set_af_filter(set_af_filter)
         self.reader.set_scan_all_samples(scan_all_samples)
-        self.reader.set_enable_progress_estimation(enable_progress_estimation)
 
         if bed_file is not None:
             self.reader.set_bed_file(bed_file)
@@ -606,7 +598,6 @@ def export(
         samples_file: str = None,
         bed_file: str = None,
         skip_check_samples: bool = False,
-        enable_progress_estimation: bool = False,
         merge: bool = False,
         output_format: str = "z",
         output_path: str = "",
@@ -632,8 +623,6 @@ def export(
             variants with AF > 0.1, set this to ">0.1".
         scan_all_samples
             Scan all samples when computing internal allele frequency.
-        enable_progress_estimation
-            **DEPRECATED** - This parameter will be removed in a future release.
         merge
             Merge samples to create a combined VCF file.
         output_format
@@ -661,7 +650,6 @@ def export(
 
         self.reader.set_regions(",".join(regions))
         self.reader.set_check_samples_exist(not skip_check_samples)
-        self.reader.set_enable_progress_estimation(enable_progress_estimation)
         self.reader.set_merge(merge)
         self.reader.set_output_format(output_format)
         self.reader.set_output_path(output_path)
diff --git a/libtiledbvcf/src/c_api/tiledbvcf.cc b/libtiledbvcf/src/c_api/tiledbvcf.cc
@@ -783,20 +783,6 @@ int32_t tiledb_vcf_reader_set_verbose(
   return TILEDB_VCF_OK;
 }
 
-int32_t tiledb_vcf_reader_set_enable_progress_estimation(
-    tiledb_vcf_reader_t* reader, bool enable_progress_estimation) {
-  if (sanity_check(reader) == TILEDB_VCF_ERR)
-    return TILEDB_VCF_ERR;
-
-  if (SAVE_ERROR_CATCH(
-          reader,
-          reader->reader_->set_enable_progress_estimation(
-              enable_progress_estimation)))
-    return TILEDB_VCF_ERR;
-
-  return TILEDB_VCF_OK;
-}
-
 int32_t tiledb_vcf_reader_set_buffer_percentage(
     tiledb_vcf_reader_t* reader, const float buffer_percentage) {
   if (sanity_check(reader) == TILEDB_VCF_ERR)
diff --git a/libtiledbvcf/src/c_api/tiledbvcf.h b/libtiledbvcf/src/c_api/tiledbvcf.h
@@ -1013,14 +1013,6 @@ TILEDBVCF_EXPORT int32_t tiledb_vcf_reader_read_from_allele_count(
 TILEDBVCF_EXPORT int32_t tiledb_vcf_reader_set_output_dir(
     tiledb_vcf_reader_t* reader, const char* output_dir);
 
-/**
- * Sets verbose mode on or off
- * @param reader VCF reader object
- * @param verbose setting
- */
-TILEDBVCF_EXPORT int32_t tiledb_vcf_reader_set_enable_progress_estimation(
-    tiledb_vcf_reader_t* reader, bool enable_progress_estimation);
-
 /**
  * Sets the percentage of buffer size to tiledb memory budget
  * @param reader VCF reader object
diff --git a/libtiledbvcf/src/cli/tiledbvcf.cc b/libtiledbvcf/src/cli/tiledbvcf.cc
@@ -861,12 +861,6 @@ void add_export(CLI::App& app) {
   add_logging_options(cmd, args->log_level, args->log_file);
   cmd->add_flag("-v,--verbose", args->verbose, "Enable verbose output");
   CLI::deprecate_option(cmd, "--verbose", "--log-level debug");
-  cmd->add_flag(
-      "--enable-progress-estimation",
-      args->enable_progress_estimation,
-      "Enable progress estimation in verbose mode. Progress estimation "
-      "can sometimes cause a performance impact, so enable this with "
-      "consideration.");
   cmd->add_flag(
       "--debug-print-vcf-regions",
       args->debug_params.print_vcf_regions,
diff --git a/libtiledbvcf/src/read/reader.cc b/libtiledbvcf/src/read/reader.cc
@@ -706,29 +706,6 @@ bool Reader::next_read_batch_v2_v3() {
   // Get estimated records for verbose output
   read_state_.total_query_records_processed = 0;
   read_state_.query_estimated_num_records = 1;
-  if (params_.enable_progress_estimation) {
-    if (dataset_->metadata().version == TileDBVCFDataset::Version::V2) {
-      read_state_.query_estimated_num_records =
-          read_state_.query->est_result_size(
-              TileDBVCFDataset::DimensionNames::V2::end_pos) /
-          tiledb_datatype_size(
-              dataset_->data_array()
-                  ->schema()
-                  .domain()
-                  .dimension(TileDBVCFDataset::DimensionNames::V2::end_pos)
-                  .type());
-    } else {
-      read_state_.query_estimated_num_records =
-          read_state_.query->est_result_size(
-              TileDBVCFDataset::DimensionNames::V3::start_pos) /
-          tiledb_datatype_size(
-              dataset_->data_array()
-                  ->schema()
-                  .domain()
-                  .dimension(TileDBVCFDataset::DimensionNames::V3::start_pos)
-                  .type());
-    }
-  }
 
   return true;
 }
@@ -935,18 +912,6 @@ bool Reader::next_read_batch_v4() {
   read_state_.total_query_records_processed = 0;
   read_state_.query_estimated_num_records = 1;
 
-  if (params_.enable_progress_estimation) {
-    read_state_.query_estimated_num_records =
-        read_state_.query->est_result_size(
-            TileDBVCFDataset::DimensionNames::V4::start_pos) /
-        tiledb_datatype_size(
-            dataset_->data_array()
-                ->schema()
-                .domain()
-                .dimension(TileDBVCFDataset::DimensionNames::V4::start_pos)
-                .type());
-  }
-
   return true;
 }
 
@@ -1154,26 +1119,11 @@ bool Reader::read_current_batch() {
       complete = process_query_results_v2();
     }
 
-    if (params_.enable_progress_estimation &&
-        read_state_.query_estimated_num_records > 0) {
-      LOG_INFO(
-          "Processed {} cells in {:.3f} sec. Reported {} cells. Approximately "
-          "{:.1f}% completed with query cells.",
-          read_state_.query_results.num_cells(),
-          utils::chrono_duration(processing_start_timer),
-          read_state_.last_num_records_exported - old_num_exported,
-          std::min(
-              100.0,
-              read_state_.total_query_records_processed /
-                  static_cast<double>(read_state_.query_estimated_num_records) *
-                  100.0));
-    } else {
-      LOG_INFO(
-          "Processed {} cells in {:.3f} sec. Reported {} cells.",
-          read_state_.query_results.num_cells(),
-          utils::chrono_duration(processing_start_timer),
-          read_state_.last_num_records_exported - old_num_exported);
-    }
+    LOG_INFO(
+        "Processed {} cells in {:.3f} sec. Reported {} cells.",
+        read_state_.query_results.num_cells(),
+        utils::chrono_duration(processing_start_timer),
+        read_state_.last_num_records_exported - old_num_exported);
 
     // Return early if we couldn't process all the results.
     if (!complete)
@@ -2808,13 +2758,6 @@ void Reader::set_check_samples_exist(const bool check_samples_exist) {
   params_.check_samples_exist = check_samples_exist;
 }
 
-void Reader::set_enable_progress_estimation(
-    const bool& enable_progress_estimation) {
-  LOG_DEBUG(
-      "setting enable_progress_estimation to {}", enable_progress_estimation);
-  params_.enable_progress_estimation = enable_progress_estimation;
-}
-
 void Reader::set_debug_print_vcf_regions(const bool print_vcf_regions) {
   params_.debug_params.print_vcf_regions = print_vcf_regions;
 }
diff --git a/libtiledbvcf/src/read/reader.h b/libtiledbvcf/src/read/reader.h
@@ -123,11 +123,6 @@ struct ExportParams {
   // because we have to fetch the list of samples from the VCF header array
   bool check_samples_exist = true;
 
-  // Should we skip trying to estimate the number of records and percent
-  // complete? This is useful when you want verbose but not the performance
-  // impact.
-  bool enable_progress_estimation = false;
-
   // Debug parameters for optional debug information
   struct DebugParams debug_params;
 
@@ -521,12 +516,6 @@ class Reader {
    */
   void set_scan_all_samples(bool scan_all_samples);
 
-  /**
-   * Sets disabling of progress estimation in verbose mode
-   * @param enable_progress_estimation setting
-   */
-  void set_enable_progress_estimation(const bool& enable_progress_estimation);
-
   /**
    * Percentage of buffer size to tiledb memory budget
    * @param buffer_percentage
