DEV Community

Shubham Kumar
Shubham Kumar

Posted on • Originally published at shubham.codes on

Running PMML models in Erlang using NIF and CPP

#erlang #cpp #nif #machinelearning

Introduction

Erlang is a great language for building concurrent systems that are fault-tolerant and scalable. But it lacks some of the libraries that are available in other languages. One such example is using PMML files for machine learning models. At the time of writing, Erlang doesn't have a library for parsing PMML files. This is a problem for people who want to use Erlang for building machine learning systems. Here I'll show how to use C++ to build a NIF that can be used in Erlang to parse PMML files. More specifically, I'll use the cPMML library to build a NIF that can be used in Erlang.

Erlang NIF

Erlang NIF provides you a way to define your functions in C/C++ and call them in Erlang code natively. The C/C++ program is compiled to generate a library file that can be used in Erlang. This library is dynamically linked to the Erlang VM and is the fastest way of calling the C/C++ code from Erlang. The disadvantage of the approach is that if the C/C++ code crashes, it will crash the Erlang VM. And you will need to maintain the C/C++ code along with the Erlang code.

Prerequisites

cPMML library requires a version of C++ that supports C++11 standard. Also, make sure you have the required header files on the Erlang side.

You can find them on Mac OS or Linux using the find function. If the header files are located in multiple locations, use the Celler one.

find / -name erl_nif.h | grep erl_nif.h
Enter fullscreen mode Exit fullscreen mode

Hello Nif program

C/C++ code

Header file

You need to include the below header file to use the Erlang functionalities. On a lower level, it defines the data structures and environment that Erlang provides to the C/C++ code.

#include <erl_nif.h>
Enter fullscreen mode Exit fullscreen mode

Function Definition

These functions are called from Erlang code. They must follow a specific structure and return a specific type of value. Here, we will define a function that will return a "Hello, World!" string.

ERL_NIF_TERM is the return type of the function. It is an interface for various return types like binary, tuple, list, atom, etc. Meaning, that you can return any of these types from the function.

ErlNifEnv is the pointer to the Erlang environment. It provides you access to various Erlang functionalities like memory management, exception handling and Erlang term creation. For us, it will help in creating Erlang Terms like string.enif_make_string is the function that will create a string from the C/C++ code.

The argc and argv provide the number of arguments and the arguments passed to the function from Erlang code.

Below is the function definition for hello world.

static ERL_NIF_TERM hello_world(ErlNifEnv* env, int argc, const ERL_NIF_TERM argv[]) {
    return enif_make_string(env, "Hello, World!", ERL_NIF_LATIN1);
}
Enter fullscreen mode Exit fullscreen mode

Export functions

You need to specify the functions that you want to export to the Erlang code. The structure is a list of ErlNifFunc objects. Each object has the name of the function that Erlang sees, the number of arguments and the function pointer.

static ErlNifFunc nif_funcs[] = {
    {"hello_world", 0, hello_world}
};
Enter fullscreen mode Exit fullscreen mode

To initialize the NIF library, you need to call the ERL_NIF_INIT function. This takes in the name of your Erlang module and the exported functions.

Let's call our Erlang module hello_nif.

ERL_NIF_INIT(hello_nif, nif_funcs, NULL, NULL, NULL, NULL)
Enter fullscreen mode Exit fullscreen mode

Final code 

extern "C" {
  #include <erl_nif.h>
  static ERL_NIF_TERM hello_world(ErlNifEnv* env, int argc, const ERL_NIF_TERM argv[]) {
      return enif_make_string(env, "Hello, World!", ERL_NIF_LATIN1);
  }
  static ErlNifFunc nif_funcs[] = {
      {"hello_world", 0, hello_world}
  };
}

ERL_NIF_INIT(hello_nif, nif_funcs, NULL, NULL, NULL, NULL);
Enter fullscreen mode Exit fullscreen mode

Erlang code

Erlang module

We will name our Erlang module hello_nif.erl.

-module(hello_nif).
Enter fullscreen mode Exit fullscreen mode

Define your NIF functions

This specifies the functions that are exported from the C/C++ code.

-export([hello_world/0]).
-nifs([hello_world/0]).
Enter fullscreen mode Exit fullscreen mode

Load the library on module load

If you compiled your C/C++ code to a library named hello_nif.so, you can load it using the load_nif function.

-on_load(init/0).

init() ->
    ok = erlang:load_nif("./hello_nif", 0).
Enter fullscreen mode Exit fullscreen mode

Fallback function

The C/C++ code can crash and you need to handle that in the Erlang code. These functions will run when the C/C++ code crashes. You should name each of these functions with the same name in the C/C++ code.

hello_world() ->
    exit(nif_library_not_loaded).
Enter fullscreen mode Exit fullscreen mode

Final code 

-module(hello_nif).
-nifs([hello_world/0]).
-on_load(init/0).

init() ->
    ok = erlang:load_nif("./hello_nif", 0).

hello_world() ->
    exit(nif_library_not_loaded).
Enter fullscreen mode Exit fullscreen mode

Compiling and Running

To compile the C/C++ code you can use gcc.

Mac OS 

gcc -o hello_nif.so hello.c -I /usr/local/lib/erlang/erts-13.2.2.2/include/ -bundle -bundle_loader /usr/local/lib/erlang/erts-13.2.2.2/bin/beam.smp
Enter fullscreen mode Exit fullscreen mode

Linux 

gcc -o hello_nif.so hello.c -I /usr/lib/erlang/erts-13.2.2.2/include -shared -fpic
Enter fullscreen mode Exit fullscreen mode

On Erlng, you can call the hello_world function.

> c(hello_nif).
> hello_nif:hello_world().
"Hello, World!"
Enter fullscreen mode Exit fullscreen mode

cPMML NIF

We saw how to create a simple NIF that returns a string. Now, let's create a NIF that can take input and run prediction using a PMML model file. For this, we will use the same model file we created in the previous post.

We have a PMML model for linear regression, y = 2x + 1 and we want to predict the value of y for a given value of x. Keeping it short, we will expose a function called, predict that will take the input and return the output.

C/C++ code

Assuming you can compile cPMML files as described in the previous post.

Header files 

#include <iostream>
#include <vector>
#include <string>
#include <map>
#include "cPMML.h"

using namespace std;
Enter fullscreen mode Exit fullscreen mode

PMML Parser class

We want to load the model once and use it for multiple predictions. For this, let's create a class that will load the model and call predictions on it. We will maintain only one instance of this class and use it for all the predictions.

class PmmlModelParser {
private:
  cpmml::Model model;

public:
    PmmlModelParser(const string& modelname) {
        model = cpmml::Model(modelname);
    }

    string predict(const unordered_map<string, string>& x_input) {
        return model.predict(x_input);
    }
};

// Global variable
PmmlModelParser *pmmlModelParser = nullptr;
Enter fullscreen mode Exit fullscreen mode

NIF implementation

We will create two functions, init and predict. The init function will take the PMML file as input and load it. The predict function will take the input and return the output.

The below code describes the structure of the NIF functions.

extern "C" {
    #include <erl_nif.h>

    static ERL_NIF_TERM init(ErlNifEnv* env, int argc, const ERL_NIF_TERM argv[]) {}

    static ERL_NIF_TERM predict(ErlNifEnv* env, int argc, const ERL_NIF_TERM argv[]) {}

    static ErlNifFunc nif_funcs[] = {
        {"init", 1, init},
        {"evaluate", 1, predict}
    };
}

ERL_NIF_INIT(lr_model, nif_funcs, NULL, NULL, NULL, NULL)
Enter fullscreen mode Exit fullscreen mode

init function

The init function will take the PMML file as input and load it. We will use the enif_inspect_binary function to get the PMML file as a binary. Then we will convert it to a string and pass it to the PmmlModelParser class.

static ERL_NIF_TERM init(ErlNifEnv* env, int argc, const ERL_NIF_TERM argv[]) {
    ErlNifBinary input_bin;
    if (!enif_inspect_binary(env, argv[0], &input_bin)) {
        return enif_make_badarg(env);
    }
    string input(reinterpret_cast<char*>(input_bin.data), input_bin.size);
    pmmlModelParser = new PmmlModelParser(input);
    return enif_make_atom(env, "ok");
}
Enter fullscreen mode Exit fullscreen mode

predict function

The predict function will take the input and return the output. The input will be a string and the output will be a string on the Erlang side.

But on the C/C++ side, we will convert the input to a map and pass it to the PmmlModelParser class because cPMML library expects a map as input. Don't get intimidated by the code below, it's just converting the Erlang map to a C++ map by iterating over all the keys and value pairs.

For prediction, we will need a map with the key as X and value as the input.

I could have just used a binary input as X and converted it to a string on the C/C++ side. But, to make this more general, I am converting the Erlang map to a C++ map. Now this can be used for any PMML file and not just a specific one.

static ERL_NIF_TERM predict(ErlNifEnv* env, int argc, const ERL_NIF_TERM argv[]) {
  unordered_map<std::string, std::string> cpp_map;

  if (!enif_is_map(env, argv[0]))
  {
    return enif_make_badarg(env);
  }

  ErlNifMapIterator iter;
  if (enif_map_iterator_create(env, argv[0], &iter, ERL_NIF_MAP_ITERATOR_FIRST))
  {
    do
    {
      ERL_NIF_TERM key, value;
      if (enif_map_iterator_get_pair(env, &iter, &key, &value))
      {
        ErlNifBinary key_bin, value_bin;
        if (enif_map_iterator_get_pair(env, &iter, &key, &value))
        {
          char key_str[64], value_str[64];
          if (enif_get_string(env, key, key_str, sizeof(key_str), ERL_NIF_LATIN1) &&
              enif_get_string(env, value, value_str, sizeof(value_str), ERL_NIF_LATIN1))
          {
            cpp_map[key_str] = value_str;
          }
        }
      }
    } while (enif_map_iterator_next(env, &iter));
    enif_map_iterator_destroy(env, &iter);
  }

  string ret = pmmlModelParser->predict(cpp_map);
  return enif_make_string(env, ret.c_str(), ERL_NIF_LATIN1);
}
Enter fullscreen mode Exit fullscreen mode

Erlang code

We will name our Erlang module lr_model.erl.

-module(lr_model).
-export([init/1, evaluate/1]).
-nifs([init/1, evaluate/1]).
-on_load(init/0).

init() ->
    ok = erlang:load_nif("./lr_model", 0).

init(PmmlFile) ->
    exit(problem_loading_nif).

evaluate(Input) ->
    exit(problem_loading_nif).
Enter fullscreen mode Exit fullscreen mode

Compiling and Running

Compiling the C/C++ code will now take an extra parameter to include cPMML library. As the model is predicting the values for y = 2x + 1, we should get ~3 for x = 1 and ~1 for x = 0.

g++ -std=c++11 library.cpp \
-o lr_model.so \
-lcPMML \
-I /usr/local/lib/erlang/erts-13.2.2.2/include/ \
-bundle \
-bundle_loader /usr/local/lib/erlang/erts-13.2.2.2/bin/beam.smp


> c(lr_model).
> lr_model:init(<<"./lr_model.pmml">>).
> lr_model:evaluate(#{"X"=>"0"}).
"0.967265"
> lr_model:evaluate(#{"X"=>"1"}).
"3.007469"
Enter fullscreen mode Exit fullscreen mode

Conclusion

In this blog, we saw how to use C/C++ libraries in Erlang code. We used a PMML file of a linear regression model to predict the values of y = 2x + 1 for a given value of x in Erlang where the code was implemented in C++. We saw how to use the cPMML library to parse the PMML file and use it for predictions.

Top comments (0)

Read next

mikeyoung44 profile image

Tailoring Language Giants: Survey of Personalized Large Language Models

Mike Young -

tinapyp profile image

How I Use Scikit-Learn for Data Science Projects

tinApyp -

mikeyoung44 profile image

Memes Driving AI's Autonomous Evolution: Exploring Hyperstition in Finance and Computing

Mike Young -

mikeyoung44 profile image

Unlocking Efficient Training for AI Language Giants: Deep Optimizer States

Mike Young -