C#•7mo ago

✅ ML.net multiple Features

Hey 🙂 I have a ML pipeline which looks like this (see image for details)

IEstimator<ITransformer> dataPrepEstimator = 
mlContext.Transforms.Text.FeaturizeText("Features", "Name")
.Append(mlContext.Transforms.Concatenate("Features", features))
.AppendCacheCheckpoint(mlContext);

IEstimator<ITransformer> dataPrepEstimator = 
mlContext.Transforms.Text.FeaturizeText("Features", "Name")
.Append(mlContext.Transforms.Concatenate("Features", features))
.AppendCacheCheckpoint(mlContext);

I thought concatenate would add the features to the Features column, but it creates a second one. When training it does only seem to use the last created Features column. How do I merge(?) the two columns into one feature vector?

2 Replies

Sebi | hrkrx•7mo ago

I just added the featurized text to the Features column like:

IEstimator<ITransformer> dataPrepEstimator = 
mlContext.Transforms.Text.FeaturizeText("TextFeatures", "Name")
.Append(mlContext.Transforms.Concatenate("Features", features))
.AppendCacheCheckpoint(mlContext);

// features = {a, b, c, TextFeatures}

IEstimator<ITransformer> dataPrepEstimator = 
mlContext.Transforms.Text.FeaturizeText("TextFeatures", "Name")
.Append(mlContext.Transforms.Concatenate("Features", features))
.AppendCacheCheckpoint(mlContext);

// features = {a, b, c, TextFeatures}

still my network doesn't react to changes in name ... this seems to be a different issue, but I am greatful for any input!

Accord•7mo ago

Looks like nothing has happened here. I will mark this as stale and this post will be archived until there is new activity.

Gaming

Programming

✅ ML.net multiple Features