ml_algo 6.0.5

Machine learning algorithms written with native dart (without bindings to any popular ML libraries, just pure Dart implementation)

Machine learning algorithms with dart

Table of contents

• What for is the library?
• The library's structure
• Usage

What for is the library?

The main purpose of the library - to give developers, interested both in Dart language and data science, native Dart implementation of machine learning algorithms. This library targeted to dart vm, so, to get smoothest experience with the lib, please, do not use it in a browser.

Following algorithms are implemented:

• Linear regression:

  • Gradient descent algorithm (batch, mini-batch, stochastic) with ridge regularization
  • Lasso regression (feature selection model)

• Linear classifier:

  • Logistic regression (with "one-vs-all" multiclass classification)

The library's structure

To provide main purposes of machine learning, the library exposes the following classes:

• MLData. Factory, that creates instances of different adapters for data. For example, one can create a csv reader, that makes work with csv data easier: you just need to point, where your dataset resides and then get features and labels in convenient data science friendly format.

• CrossValidator. Factory, that creates instances of a cross validator. In a few words, this entity allows researchers to fit different hyperparameters of machine learning algorithms, assessing prediction quality on different parts of a dataset. Wiki article about cross validation process.

• LinearClassifier.logisticRegressor. A class, that performs simplest linear classification. If you want to use this classifier for your data, please, make sure, that your data is linearly separably. Multiclass classification is also supported (see ovr classification)

• LinearRegressor.gradient. An algorithm, that performs geometry-based linear regression using gradient vector of a cost function.

• LinearRegressor.lasso An algorithm, that performs feature selection along with regression process. It uses coordinate descent optimization and subgradient vector instead of gradient descent optimization and gradient vector like in LinearRegressor.gradient to provide regression. If you want to decide, which features are less important - go ahead and use this regressor.

Usage

Real life example

Let's classify records from well-known dataset - Pima Indians Diabets Database via Logistic regressor

Import all necessary packages:

import 'dart:async';

import 'package:ml_algo/ml_algo.dart';

Read csv-file pima_indians_diabetes_database.csv with test data. You can use csv from the library's datasets directory:

final data = MLData.fromCsvFile('datasets/pima_indians_diabetes_database.csv');
final features = await data.features;
final labels = await data.labels;

Data in this file is represented by 768 records and 8 features. Processed features are contained in a data structure of MLMatrix type and processed labels are contained in a data structure of MLVector type. To get more information about these types, please, visit ml_linal repo

Then, we should create an instance of CrossValidator class for fitting hyperparameters of our model

final validator = CrossValidator.KFold();

All are set, so, we can perform our classification. For better hyperparameters fitting, let's create a loop in order to try each value of a chosen hyperparameter in a defined range:

final step = 0.001;
final limit = 0.6;
double minError = double.infinity;
double bestLearningRate = 0.0;
for (double rate = step; rate < limit; rate += step) {
  // ...
}

Let's create a logistic regression classifier instance with stochastic gradient descent optimizer in the loop's body:

final logisticRegressor = LinearClassifier.logisticRegressor(
        iterationsLimit: 100,
        initialLearningRate: rate,
        learningRateType: LearningRateType.constant);

Evaluate our model via accuracy metric:

final error = validator.evaluate(logisticRegressor, featuresMatrix, labels, MetricType.accuracy);
if (error < minError) {
  minError = error;
  bestLearningRate = rate;
}

Let's print score:

print('best error on classification: ${(minError * 100).toFixed(2)}');
print('best learning rate: ${bestLearningRate.toFixed(3)}');

Best model parameters search takes much time so far, so be patient. After the search is over, we will see something like this:

best error on classification: 35.5%
best learning rate: 0.155

All the code above all together:

import 'dart:async';

import 'package:ml_algo/ml_algo.dart';

Future<double> logisticRegression() async {
  final data = CsvMLData.fromFile('datasets/pima_indians_diabetes_database.csv');
  final features = await data.features;
  final labels = await data.labels;

  final validator = CrossValidator.kFold(numberOfFolds: 7);

  final step = 0.001;
  final limit = 0.6;

  double minError = double.infinity;
  double bestLearningRate = 0.0;

  for (double rate = step; rate < limit; rate += step) {
    final logisticRegressor = LinearClassifier.logisticRegressor(
      iterationsLimit: 100,
      initialLearningRate: rate,
      learningRateType: LearningRateType.constant);
    final error = validator.evaluate(logisticRegressor, features, labels, MetricType.accuracy);
    if (error < minError) {
      minError = error;
      bestLearningRate = rate;
    }
  }

  print('best error on classification: ${(minError * 100).toFixed(2)}');
  print('best learning rate: ${bestLearningRate.toFixed(3)}');
}

For more examples please see examples folder

Contacts

If you have questions, feel free to write me on

• Facebook
• Linkedin