Skip to content

Commit

Permalink
reformatted samples not in specific folder (#3949)
Browse files Browse the repository at this point in the history
  • Loading branch information
@sierralee51
sierralee51 authored Jul 2, 2019
1 parent 01b3ec7 commit 1c1d3a4
Show file tree
Hide file tree
Showing 4 changed files with 295 additions and 143 deletions.
84 changes: 61 additions & 23 deletions docs/samples/Microsoft.ML.Samples/Dynamic/NgramExtraction.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9,15 +9,21 @@ public static partial class TransformSamples
{
public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging,
// as well as the source of randomness.
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var ml = new MLContext();

// Get a small dataset as an IEnumerable and convert to IDataView.
var data = new List<SampleSentimentData>() {
new SampleSentimentData { Sentiment = true, SentimentText = "Best game I've ever played." },
new SampleSentimentData { Sentiment = false, SentimentText = "==RUDE== Dude, 2" },
new SampleSentimentData { Sentiment = true, SentimentText = "Until the next game, this is the best Xbox game!" } };
new SampleSentimentData { Sentiment = true,
SentimentText = "Best game I've ever played." },

new SampleSentimentData { Sentiment = false,
SentimentText = "==RUDE== Dude, 2" },

new SampleSentimentData { Sentiment = true,
SentimentText = "Until the next game," +
"this is the best Xbox game!" } };

// Convert IEnumerable to IDataView.
var trainData = ml.Data.LoadFromEnumerable(data);
Expand All @@ -29,23 +35,42 @@ public static void Example()
// false ==RUDE== Dude, 2.
// true Until the next game, this is the best Xbox game!

// A pipeline to tokenize text as characters and then combine them together into n-grams
// The pipeline uses the default settings to featurize.
// A pipeline to tokenize text as characters and then combine them
// together into n-grams. The pipeline uses the default settings to
// featurize.

var charsPipeline = ml.Transforms.Text
.TokenizeIntoCharactersAsKeys("Chars", "SentimentText",
useMarkerCharacters: false);

var ngramOnePipeline = ml.Transforms.Text
.ProduceNgrams("CharsUnigrams", "Chars", ngramLength: 1);

var charsPipeline = ml.Transforms.Text.TokenizeIntoCharactersAsKeys("Chars", "SentimentText", useMarkerCharacters: false);
var ngramOnePipeline = ml.Transforms.Text.ProduceNgrams("CharsUnigrams", "Chars", ngramLength: 1);
var ngramTwpPipeline = ml.Transforms.Text.ProduceNgrams("CharsTwograms", "Chars");
var oneCharsPipeline = charsPipeline.Append(ngramOnePipeline);
var twoCharsPipeline = charsPipeline.Append(ngramTwpPipeline);
var ngramTwpPipeline = ml.Transforms.Text
.ProduceNgrams("CharsTwograms", "Chars");

var oneCharsPipeline = charsPipeline
.Append(ngramOnePipeline);

var twoCharsPipeline = charsPipeline
.Append(ngramTwpPipeline);

// The transformed data for pipelines.
var transformedData_onechars = oneCharsPipeline.Fit(trainData).Transform(trainData);
var transformedData_twochars = twoCharsPipeline.Fit(trainData).Transform(trainData);
var transformedData_onechars = oneCharsPipeline.Fit(trainData)
.Transform(trainData);

var transformedData_twochars = twoCharsPipeline.Fit(trainData)
.Transform(trainData);

// Small helper to print the text inside the columns, in the console.
Action<string, IEnumerable<VBuffer<float>>, VBuffer<ReadOnlyMemory<char>>> printHelper = (columnName, column, names) =>
Action<string, IEnumerable<VBuffer<float>>,
VBuffer<ReadOnlyMemory<char>>>
printHelper = (columnName, column, names) =>
{
Console.WriteLine($"{columnName} column obtained post-transformation.");
Console.WriteLine(
$"{columnName} column obtained post-transformation.");
var slots = names.GetValues();
foreach (var featureRow in column)
{
Expand All @@ -54,21 +79,33 @@ public static void Example()
Console.WriteLine("");
}
Console.WriteLine("===================================================");
Console.WriteLine(
"===================================================");
};
// Preview of the CharsUnigrams column obtained after processing the input.
// Preview of the CharsUnigrams column obtained after processing the
// input.
VBuffer<ReadOnlyMemory<char>> slotNames = default;
transformedData_onechars.Schema["CharsUnigrams"].GetSlotNames(ref slotNames);
var charsOneGramColumn = transformedData_onechars.GetColumn<VBuffer<float>>(transformedData_onechars.Schema["CharsUnigrams"]);
transformedData_onechars.Schema["CharsUnigrams"]
.GetSlotNames(ref slotNames);

var charsOneGramColumn = transformedData_onechars
.GetColumn<VBuffer<float>>(transformedData_onechars
.Schema["CharsUnigrams"]);

printHelper("CharsUnigrams", charsOneGramColumn, slotNames);

// CharsUnigrams column obtained post-transformation.
// 'B' - 1 'e' - 6 's' - 1 't' - 1 '<?>' - 4 'g' - 1 'a' - 2 'm' - 1 'I' - 1 ''' - 1 'v' - 2 ...
// 'e' - 1 '<?>' - 2 'd' - 1 '=' - 4 'R' - 1 'U' - 1 'D' - 2 'E' - 1 'u' - 1 ',' - 1 '2' - 1
// 'B' - 0 'e' - 6 's' - 3 't' - 6 '<?>' - 9 'g' - 2 'a' - 2 'm' - 2 'I' - 0 ''' - 0 'v' - 0 ...
// Preview of the CharsTwoGrams column obtained after processing the input.
var charsTwoGramColumn = transformedData_twochars.GetColumn<VBuffer<float>>(transformedData_twochars.Schema["CharsTwograms"]);
transformedData_twochars.Schema["CharsTwograms"].GetSlotNames(ref slotNames);
var charsTwoGramColumn = transformedData_twochars
.GetColumn<VBuffer<float>>(transformedData_twochars
.Schema["CharsTwograms"]);

transformedData_twochars.Schema["CharsTwograms"]
.GetSlotNames(ref slotNames);

printHelper("CharsTwograms", charsTwoGramColumn, slotNames);

// CharsTwograms column obtained post-transformation.
Expand All @@ -78,7 +115,8 @@ public static void Example()
}

/// <summary>
/// A dataset that contains a tweet and the sentiment assigned to that tweet: 0 - negative and 1 - positive sentiment.
/// A dataset that contains a tweet and the sentiment assigned to that
/// tweet: 0 - negative and 1 - positive sentiment.
/// </summary>
public class SampleSentimentData
{
Expand Down
Loading

0 comments on commit 1c1d3a4

Please sign in to comment.