class EvolveNet::Data

• EvolveNet::Data
• Reference
• Object

Direct Known Subclasses

• EvolveNet::TestData
• EvolveNet::TrainingData

Defined in:

evolvenet/data/data.cr

Constant Summary

Log = ::Log.for(self)

Constructors

• .new(raw_inputs : Array(Array(Float64)), raw_outputs : Array(Array(Float64)))
• .new(inputs : Array(Array(Number)), outputs : Array(Array(Number)))
• .new(data : Array(Array(Array(Number))))

Class Method Summary

• .new_with_csv_input_target(csv_file_path, input_column_range, target_column)

Instance Method Summary

• #array_for_label(a_label)

  Takes a label as a String and returns the corresponding output array

• #confusion_matrix(model)
• #denormalize(x, xmin, xmax)
• #denormalize_outputs(outputs : Array(Number))
• #inputs : Array(Array(Float32 | Float64 | Int32 | Int64))
• #inputs=(inputs : Array(Array(Float32 | Float64 | Int32 | Int64)))
• #label_encoder
• #label_for_array(an_array)

  Takes an output array of 0,1s and returns the corresponding label

• #labels : Array(String)
• #labels=(label_array)

  Receives an array of labels (String or Symbol) and sets them for this Data object

• #normalize(x, xmin, xmax)
• #normalize_inputs(inputs : Array(Number))
• #normalize_min_max
• #normalize_outputs(outputs : Array(Number))
• #normalized_data
• #normalized_inputs : Array(Array(Float64))
• #normalized_inputs=(normalized_inputs : Array(Array(Float64)))
• #normalized_outputs : Array(Array(Float64))
• #normalized_outputs=(normalized_outputs : Array(Array(Float64)))
• #one_hot_encoder
• #ordinal_encoder
• #outputs : Array(Array(Float32 | Float64 | Int32 | Int64))
• #outputs=(outputs : Array(Array(Float32 | Float64 | Int32 | Int64)))
• #raw_confusion_matrix(model)
• #raw_data
• #set_zero_to_average(cols = Array[Int32])
• #size
• #split(factor)

  Splits the receiver in a TrainingData and a TestData object according to factor

• #to_onehot(data : Array(Array(Float64)), vector_size : Int32)

Constructor Detail

Class Method Detail

Instance Method Detail