Created
April 14, 2021 22:51
-
-
Save westonpace/1477fe0fcc2a859391f58815e7411688 to your computer and use it in GitHub Desktop.
Example creating a feather file from a row-major double vector
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <iostream> | |
#include <vector> | |
#include <arrow/api.h> | |
#include <arrow/filesystem/api.h> | |
#include <arrow/ipc/api.h> | |
arrow::Status RunMain(int argc, char **argv) { | |
std::vector<std::vector<double>> rows = {{1, 2, 3}, {4, 5, 6}, {7, 8, 9}}; | |
// Convert your row-vector to a vector of columns (arrow::Array) | |
std::vector<arrow::DoubleBuilder> column_builders(rows.size()); | |
for (const auto &row : rows) { | |
for (std::size_t col_idx = 0; col_idx < row.size(); col_idx++) { | |
column_builders[col_idx].Append(row[col_idx]); | |
} | |
} | |
std::vector<std::shared_ptr<arrow::Array>> columns; | |
for (std::size_t col_idx = 0; col_idx < column_builders.size(); col_idx++) { | |
ARROW_ASSIGN_OR_RAISE(auto col, column_builders[col_idx].Finish()); | |
columns.push_back(col); | |
} | |
// Create schema (insert field names here) | |
std::vector<std::shared_ptr<arrow::Field>> fields; | |
for (std::size_t col_idx = 0; col_idx < columns.size(); col_idx++) { | |
fields.push_back( | |
arrow::field("Field " + std::to_string(col_idx), arrow::float64())); | |
} | |
auto schema = arrow::schema(fields); | |
// Create record batch | |
auto record_batch = arrow::RecordBatch::Make( | |
schema, static_cast<int64_t>(rows.size()), columns); | |
// Open output file | |
arrow::fs::LocalFileSystem fs; | |
ARROW_ASSIGN_OR_RAISE(auto output_stream, | |
fs.OpenOutputStream("/tmp/foo.feather")); | |
ARROW_ASSIGN_OR_RAISE(auto writer, | |
arrow::ipc::MakeFileWriter(output_stream, schema)); | |
ARROW_RETURN_NOT_OK(writer->WriteRecordBatch(*record_batch)); | |
return writer->Close(); | |
} | |
int main(int argc, char **argv) { | |
arrow::Status st = RunMain(argc, argv); | |
if (!st.ok()) { | |
std::cerr << st << std::endl; | |
return 1; | |
} | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment