I used the arrow c++ version to read the fund net value data in the csv, and then calculated the Sharpe rate. What is embarrassing is that the arrow c++ version takes more time to calculate than the python empirical version. . .
Arrow is a newbie, and it is the first time to implement the function by myself. It is most likely not the most efficient way to implement it, but I have also taken the first step to rewrite backtrader with arrow c++.
- Use arrow to rewrite empirical, just like practicing, the goal is to make it Two files: imperial.h and imperial.cpp
- Rewrite pyfolio with arrow and qt to achieve a more beautiful appearance interface, made into two files: pyfolio.h and pyfolio.cpp
- Rewrite backtrader
c++ version of the file:
my_example.cc
#include <arrow/api.h>
#include <arrow/io/api.h>
#include "arrow/csv/api.h"
#include <arrow/compute/api.h>
#include <iostream>
#include <chrono>
//#include "../empyrical/empyrical.h"
arrow::Status RunMain(){<!-- -->
auto start_time = std::chrono::high_resolution_clock::now();
// First, we need to set up a readable file object that allows us to point the reader to the correct data on disk. We will reuse this object and rebind it into multiple files.
std::shared_ptr<arrow::io::ReadableFile> infile;
// Bind the input file to "test_in.csv"
ARROW_ASSIGN_OR_RAISE(infile, arrow::io::ReadableFile::Open("/home/yun/Documents/fund_nav.csv"));
// (Documentation section: CSV table declaration)
std::shared_ptr<arrow::Table> csv_table;
// The CSV reader has multiple objects for different options. For now, we'll use the default values.
ARROW_ASSIGN_OR_RAISE(
auto csv_reader,
arrow::csv::TableReader::Make(
arrow::io::default_io_context(), infile, arrow::csv::ReadOptions::Defaults(),
arrow::csv::ParseOptions::Defaults(), arrow::csv::ConvertOptions::Defaults()));
//Read the table.
ARROW_ASSIGN_OR_RAISE(csv_table, csv_reader->Read());
// Output the metadata information of the Table
// std::cout << "Table Metadata:" << std::endl;
// std::cout << "Number of columns: " << csv_table->num_columns() << std::endl;
// std::cout << "Number of rows: " << csv_table->num_rows() << std::endl;
// std::cout << "Schema: " << csv_table->schema()->ToString() << std::endl;
// Output the data displayed in the Table
// for (int i = 0; i < csv_table->num_columns(); + + i) {<!-- -->
// std::shared_ptr<arrow::Array> column = csv_table->column(i);
// std::cout << "Column " << i << ": " << column->ToString() << std::endl;
// }
// 1. Method to display table information to std::cout
// std::shared_ptr<arrow::RecordBatch> record_batch;
// arrow::Result<std::shared_ptr<arrow::RecordBatch>> result = csv_table->CombineChunksToBatch(); // Perform an operation and return Result
// if (result.ok()) {<!-- -->
// record_batch = result.ValueOrDie();
// // Use record_batch here
// } else {<!-- -->
// // Handle errors
// std::cerr << "Error: " << result.status().ToString() << std::endl;
// }
// //arrow::PrettyPrint(*record_batch, 2, & amp;std::cout);
// arrow::Status status = arrow::PrettyPrint(*record_batch, 2, & amp;std::cout);
// if (!status.ok()) {<!-- -->
// // Handle errors, such as printing error messages
// std::cerr << "Error: " << status.ToString() << std::endl;
// }
// 2. Method to display table information to std::cout
// std::cout << csv_table->ToString() << std::endl;
// 3. Method to display table information to std::cout
// arrow::Status status = arrow::PrettyPrint(*csv_table, 2, & amp;std::cout);
// if (!status.ok()) {<!-- -->
// // Handle errors, such as printing error messages
// std::cerr << "Error: " << status.ToString() << std::endl;
// }
//Start calculating Sharpe rate
// std::cout << "There are trading days in a year" << AnnualizationFactors::DAILY << "days" << std::endl;
// std::cout << DAILY << std::endl;
// Calculate the rate of return
arrow::Datum fund_returns;
arrow::Datum fund_diff;
std::shared_ptr<arrow::ChunkedArray> cum_nav = csv_table->GetColumnByName("Reweighted Net Value");
std::shared_ptr<arrow::ChunkedArray> now_cum_nav = cum_nav->Slice(1,cum_nav->length()-1);
std::shared_ptr<arrow::ChunkedArray> pre_cum_nav = cum_nav->Slice(0,cum_nav->length()-1);
ARROW_ASSIGN_OR_RAISE(fund_diff, arrow::compute::CallFunction(
"subtract", {<!-- -->now_cum_nav,pre_cum_nav}));
ARROW_ASSIGN_OR_RAISE(fund_returns, arrow::compute::CallFunction(
"divide", {<!-- -->fund_diff,pre_cum_nav}));
// // Get the result array
// std::cout << "Datum kind: " << fund_returns.ToString()
// << " content type: " << fund_returns.type()->ToString() << std::endl;
// // std::cout << fund_returns.scalar_as<arrow::DoubleScalar>().value << std::endl;
// std::cout << fund_returns.chunked_array()->ToString() << std::endl;
// Calculate Sharpe ratio
arrow::Datum avg_return;
arrow::Datum avg_std;
arrow::Datum daily_sharpe_ratio;
arrow::Datum sharpe_ratio;
arrow::Datum sqrt_year;
// Create Arrow Double scalar
double days_of_year_double = 252.0;
std::shared_ptr<arrow::Scalar> days_of_year = arrow::MakeScalar(days_of_year_double);
ARROW_ASSIGN_OR_RAISE(sqrt_year, arrow::compute::CallFunction(
"sqrt", {<!-- -->days_of_year}));
ARROW_ASSIGN_OR_RAISE(avg_return, arrow::compute::CallFunction(
"mean", {<!-- -->fund_returns}));
arrow::compute::VarianceOptions variance_options;
variance_options.ddof = 1;
ARROW_ASSIGN_OR_RAISE(avg_std, arrow::compute::CallFunction(
"stddev", {<!-- -->fund_returns}, & amp;variance_options));
ARROW_ASSIGN_OR_RAISE(daily_sharpe_ratio, arrow::compute::CallFunction(
"divide", {<!-- -->avg_return,avg_std}));
ARROW_ASSIGN_OR_RAISE(sharpe_ratio, arrow::compute::CallFunction(
"multiply", {<!-- -->daily_sharpe_ratio,sqrt_year}));
std::cout << "The calculated Sharpe ratio: " << sharpe_ratio.scalar_as<arrow::DoubleScalar>().value << std::endl;
auto end_time = std::chrono::high_resolution_clock::now();
auto duration = std::chrono::duration_cast<std::chrono::microseconds>(end_time - start_time);
std::cout << "c++ reads the data and then calculates the Sharpe rate. The total time spent is: " << duration.count()/1000.0 << " ms" << std::endl;
return arrow::Status::OK();
}
// (Documentation part: main function)
int main() {<!-- -->
arrow::Status st = RunMain();
if (!st.ok()) {<!-- -->
std::cerr << st << std::endl;
return 1;
}
return 0;
}
CMakeLists.txt
cmake_minimum_required(VERSION 3.16) project(MyExample) find_package(Arrow REQUIRED) find_package(Parquet REQUIRED) find_package(ArrowDataset REQUIRED) add_executable(my_example my_example.cc) target_link_libraries(my_example PRIVATE Arrow::arrow_shared Parquet::parquet_shared ArrowDataset::arrow_dataset_shared)
In the same folder, run
cmake -B build cmake --build build ./build/my_example
The python running code is as follows:
import pandas as pd
import empyrical as ep
import time
a = time.perf_counter()
data = pd.read_csv("/home/yun/Documents/fund_nav.csv")
returns = data['Net weighted value'].pct_change().dropna()
sharpe_ratio = ep.sharpe_ratio(returns)
print("Calculated sharpe_ratio: ", sharpe_ratio)
b = time.perf_counter()
print(f"Python reads the data and then calculates the Sharpe rate. The total time spent is: {<!-- -->(b-a)*1000.0} ms")