DataFrame: sampleFromRows method added (#15)

gyrdym · Dec 17, 2020 · e6be0f6 · e6be0f6
1 parent 51db910
commit e6be0f6
Show file tree

Hide file tree

Showing 13 changed files with 261 additions and 155 deletions.
diff --git a/.github/workflows/ci_pipeline.yml b/.github/workflows/ci_pipeline.yml
@@ -0,0 +1,37 @@
+name: CI pipeline
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    container:
+      image:  google/dart:latest
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Print Dart SDK version
+        run: dart --version
+
+      - name: Install dependencies
+        run: dart pub get
+
+      - name: Analyze project source
+        run: dart analyze --fatal-infos
+
+      - name: Run tests
+        run: dart test
+
+      - name: Code coverage
+        run: dart pub run test_coverage
+
+      - name: Coveralls GitHub Action
+        uses: coverallsapp/github-action@v1.1.2
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
diff --git a/.travis.yml b/.travis.yml
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.3.0
+- `DataFrame`: `sampleFromRows` method added
+- `CI`: github actions set up
+
 ## 0.2.0
 - `DataFrame`: `shuffle` method added
 

diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-[![Build Status](https://travis-ci.com/gyrdym/ml_dataframe.svg?branch=master)](https://travis-ci.com/gyrdym/ml_dataframe)
+[![Build Status](https://github.com/gyrdym/ml_dataframe/workflows/CI%20pipeline/badge.svg)](https://github.com/gyrdym/ml_dataframe/actions?query=branch%3Amaster+)
 [![Coverage Status](https://coveralls.io/repos/github/gyrdym/ml_dataframe/badge.svg?branch=master)](https://coveralls.io/github/gyrdym/ml_dataframe?branch=master)
 [![pub package](https://img.shields.io/pub/v/ml_dataframe.svg)](https://pub.dartlang.org/packages/ml_dataframe)
 [![Gitter Chat](https://badges.gitter.im/gyrdym/gyrdym.svg)](https://gitter.im/gyrdym/)

diff --git a/analysis_options.yaml b/analysis_options.yaml
@@ -1 +1 @@
-include: package:ml_tech/analysis_options.yaml
+include: package:pedantic/analysis_options.yaml
diff --git a/lib/src/data_frame/data_frame.dart b/lib/src/data_frame/data_frame.dart
@@ -148,7 +148,7 @@ abstract class DataFrame implements Serializable {
   DataFrame addSeries(Series series);
 
   /// Returns a dataframe, sampled from series that are obtained from the
-  /// provided series [indices] or series [names].
+  /// series [indices] or series [names].
   ///
   /// If [indices] are specified, [names] parameter will be ignored.
   ///
@@ -158,6 +158,12 @@ abstract class DataFrame implements Serializable {
     Iterable<String> names,
   });
 
+  /// Returns a dataframe, sampled from rows that are obtained from the
+  /// rows [indices]
+  ///
+  /// Rows indices may be repeating.
+  DataFrame sampleFromRows(Iterable<int> indices);
+
   /// Returns a new [DataFrame] without specified series
   DataFrame dropSeries({
     Iterable<int> seriesIndices,

diff --git a/lib/src/data_frame/data_frame_impl.dart b/lib/src/data_frame/data_frame_impl.dart
@@ -13,7 +13,6 @@ import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/linalg.dart';
 import 'package:ml_linalg/matrix.dart';
 import 'package:quiver/iterables.dart';
-import 'dart:math' as math;
 
 part 'data_frame_impl.g.dart';
 
@@ -107,6 +106,18 @@ class DataFrameImpl with SerializableMixin implements DataFrame {
     return _sampleFromSeries(names);
   }
 
+  @override
+  DataFrame sampleFromRows(Iterable<int> indices) {
+    final rowsAsList = rows.toList(growable: false);
+    final selectedRows = indices.map((index) => rowsAsList[index]);
+
+    return DataFrame(
+      selectedRows,
+      headerExists: false,
+      header: header,
+    );
+  }
+
   @override
   DataFrame addSeries(Series newSeries) {
     if (newSeries.data.length != shape.first) {

diff --git a/lib/src/data_frame/factories/from_raw_data.dart b/lib/src/data_frame/factories/from_raw_data.dart
@@ -14,13 +14,17 @@ DataFrame fromRawData(Iterable<Iterable<dynamic>> data, {
 }) {
   final columnsNum = columns.isNotEmpty
       ? columns.length
-      : data.first.length;
+      : data.isEmpty
+        ? predefinedHeader.length
+        : data.first.length;
 
   final header = getHeader(
       columnsNum,
       autoHeaderPrefix,
       headerExists
-          ? data.first.map((dynamic el) => el.toString())
+          ? data.isEmpty
+            ? []
+            : data.first.map((dynamic el) => el.toString())
           : [],
       predefinedHeader);