Method from_train

nltk/classify/weka.py:282–311

Constructs an ARFF_Formatter instance with class labels and feature types determined from the given data. Handles boolean, numeric and string (note: not nominal) types.

(tokens)

    @staticmethod
    def from_train(tokens):
        """
        Constructs an ARFF_Formatter instance with class labels and feature
        types determined from the given data. Handles boolean, numeric and
        string (note: not nominal) types.
        """
        # Find the set of all attested labels.
        labels = {label for (tok, label) in tokens}

        # Determine the types of all features.
        features = {}
        for tok, label in tokens:
            for fname, fval in tok.items():
                if issubclass(type(fval), bool):
                    ftype = "{True, False}"
                elif issubclass(type(fval), (int, float, bool)):
                    ftype = "NUMERIC"
                elif issubclass(type(fval), str):
                    ftype = "STRING"
                elif fval is None:
                    continue  # can't tell the type.
                else:
                    raise ValueError("Unsupported value type %r" % ftype)

                if features.get(fname, ftype) != ftype:
                    raise ValueError("Inconsistent type for %s" % fname)
                features[fname] = ftype
        features = sorted(features.items())

        return ARFF_Formatter(labels, features)

    def header_section(self):
        """Returns an ARFF header as a string."""