Пример #1
0
def guess_data_type(orig_values, namask=None):
    """
    Use heuristics to guess data type.
    """
    valuemap, values = None, orig_values
    is_discrete = is_discrete_values(orig_values)
    if is_discrete:
        valuemap = sorted(is_discrete)
        coltype = DiscreteVariable
    else:
        # try to parse as float
        orig_values = np.asarray(orig_values)
        if namask is None:
            namask = isnastr(orig_values)
        values = np.empty_like(orig_values, dtype=float)
        values[namask] = np.nan
        try:
            np.copyto(values, orig_values, where=~namask, casting="unsafe")
        except ValueError:
            tvar = TimeVariable('_')
            try:
                values[~namask] = [tvar.parse(i) for i in orig_values[~namask]]
            except ValueError:
                coltype = StringVariable
                # return original_values
                values = orig_values
            else:
                coltype = TimeVariable
        else:
            coltype = ContinuousVariable
    return valuemap, values, coltype
Пример #2
0
def guess_data_type(orig_values, namask=None):
    """
    Use heuristics to guess data type.
    """
    valuemap, values = None, orig_values
    is_discrete = is_discrete_values(orig_values)
    orig_values = np.asarray(orig_values, dtype=str)
    if namask is None:
        namask = isnastr(orig_values)
    if is_discrete:
        valuemap = sorted(is_discrete)
        coltype = DiscreteVariable
    else:
        # try to parse as float
        values = np.empty_like(orig_values, dtype=float)
        values[namask] = np.nan
        try:
            np.copyto(values, orig_values, where=~namask, casting="unsafe")
        except ValueError:
            values = orig_values
            coltype = StringVariable
        else:
            coltype = ContinuousVariable

    if coltype is not ContinuousVariable:
        # when not continuous variable it can still be time variable even it
        # was before recognized as a discrete
        tvar = TimeVariable('_')
        # introducing new variable prevent overwriting orig_values and values
        temp_values = np.empty_like(orig_values, dtype=float)
        try:
            temp_values[~namask] = [
                tvar.parse_exact_iso(i) for i in orig_values[~namask]
            ]
        except ValueError:
            pass
        else:
            valuemap = None
            coltype = TimeVariable
            values = temp_values
    return valuemap, values, coltype
Пример #3
0
def guess_data_type(orig_values):
    """
    Use heuristics to guess data type.
    """
    valuemap, values = [], orig_values
    is_discrete = is_discrete_values(orig_values)
    if is_discrete:
        valuemap = sorted(is_discrete)
        coltype = DiscreteVariable
    else:
        try:
            values = [float(i) for i in orig_values]
        except ValueError:
            tvar = TimeVariable('_')
            try:
                values = [tvar.parse(i) for i in orig_values]
            except ValueError:
                coltype = StringVariable
            else:
                coltype = TimeVariable
        else:
            coltype = ContinuousVariable
    return valuemap, values, coltype
Пример #4
0
    def data_table(self, data, headers=None):
        """
        Return Orange.data.Table given rows of `headers` (iterable of iterable)
        and rows of `data` (iterable of iterable; if ``numpy.ndarray``, might
        as well **have it sorted column-major**, e.g. ``order='F'``).

        Basically, the idea of subclasses is to produce those two iterables,
        however they might.

        If `headers` is not provided, the header rows are extracted from `data`,
        assuming they precede it.
        """
        if not headers:
            headers, data = self.parse_headers(data)

        # Consider various header types (single-row, two-row, three-row, none)
        if 3 == len(headers):
            names, types, flags = map(list, headers)
        else:
            if 1 == len(headers):
                HEADER1_FLAG_SEP = '#'
                # First row format either:
                #   1) delimited column names
                #   2) -||- with type and flags prepended, separated by #,
                #      e.g. d#sex,c#age,cC#IQ
                _flags, names = zip(*[
                    i.split(HEADER1_FLAG_SEP, 1) if HEADER1_FLAG_SEP in i else
                    ('', i) for i in headers[0]
                ])
                names = list(names)
            elif 2 == len(headers):
                names, _flags = map(list, headers)
            else:
                # Use heuristics for everything
                names, _flags = [], []
            types = [
                ''.join(filter(str.isupper, flag)).lower() for flag in _flags
            ]
            flags = [Flags.join(filter(str.islower, flag)) for flag in _flags]

        # Determine maximum row length
        rowlen = max(map(len, (names, types, flags)))

        def _equal_length(lst):
            lst.extend([''] * (rowlen - len(lst)))
            return lst

        # Ensure all data is of equal width in a column-contiguous array
        data = np.array([_equal_length(list(row)) for row in data if any(row)],
                        copy=False,
                        dtype=object,
                        order='F')

        # Data may actually be longer than headers were
        try:
            rowlen = data.shape[1]
        except IndexError:
            pass
        else:
            for lst in (names, types, flags):
                _equal_length(lst)

        NAMEGEN = namegen('Feature ', 1)
        Xcols, attrs = [], []
        Mcols, metas = [], []
        Ycols, clses = [], []
        Wcols = []

        # Iterate through the columns
        for col in range(rowlen):
            flag = Flags(Flags.split(flags[col]))
            if flag.i: continue

            type_flag = types and types[col].strip()
            try:
                orig_values = [
                    np.nan if i in MISSING_VALUES else i
                    for i in (i.strip() for i in data[:, col])
                ]
            except IndexError:
                # No data instances leads here
                orig_values = []
                # In this case, coltype could be anything. It's set as-is
                # only to satisfy test_table.TableTestCase.test_append
                coltype = DiscreteVariable

            coltype_kwargs = {}
            valuemap = []
            values = orig_values

            if type_flag in StringVariable.TYPE_HEADERS:
                coltype = StringVariable
            elif type_flag in ContinuousVariable.TYPE_HEADERS:
                coltype = ContinuousVariable
                try:
                    values = [float(i) for i in orig_values]
                except ValueError:
                    for row, num in enumerate(orig_values):
                        try:
                            float(num)
                        except ValueError:
                            break
                    raise ValueError('Non-continuous value in (1-based) '
                                     'line {}, column {}'.format(
                                         row + len(headers) + 1, col + 1))

            elif type_flag in TimeVariable.TYPE_HEADERS:
                coltype = TimeVariable

            elif (type_flag in DiscreteVariable.TYPE_HEADERS
                  or _RE_DISCRETE_LIST.match(type_flag)):
                if _RE_DISCRETE_LIST.match(type_flag):
                    valuemap = Flags.split(type_flag)
                    coltype_kwargs.update(ordered=True)
                else:
                    valuemap = sorted(set(orig_values) - {np.nan})

            else:
                # No known type specified, use heuristics
                is_discrete = is_discrete_values(orig_values)
                if is_discrete:
                    valuemap = sorted(is_discrete)
                else:
                    try:
                        values = [float(i) for i in orig_values]
                    except ValueError:
                        tvar = TimeVariable('_')
                        try:
                            values = [tvar.parse(i) for i in orig_values]
                        except ValueError:
                            coltype = StringVariable
                        else:
                            coltype = TimeVariable
                    else:
                        coltype = ContinuousVariable

            if valuemap:
                # Map discrete data to ints
                def valuemap_index(val):
                    try:
                        return valuemap.index(val)
                    except ValueError:
                        return np.nan

                values = np.vectorize(valuemap_index,
                                      otypes=[float])(orig_values)
                coltype = DiscreteVariable
                coltype_kwargs.update(values=valuemap)

            if coltype is StringVariable:
                values = ['' if i is np.nan else i for i in orig_values]

            if flag.m or coltype is StringVariable:
                append_to = (Mcols, metas)
            elif flag.w:
                append_to = (Wcols, None)
            elif flag.c:
                append_to = (Ycols, clses)
            else:
                append_to = (Xcols, attrs)

            cols, domain_vars = append_to
            cols.append(col)
            if domain_vars is not None:
                if names and names[col]:
                    # Use existing variable if available
                    var = coltype.make(names[col].strip(), **coltype_kwargs)
                else:
                    # Never use existing for un-named variables
                    var = coltype(next(NAMEGEN), **coltype_kwargs)
                var.attributes.update(flag.attributes)
                domain_vars.append(var)

                # Reorder discrete values to match existing variable
                if var.is_discrete and not var.ordered:
                    new_order, old_order = var.values, coltype_kwargs.get(
                        'values', var.values)
                    if new_order != old_order:
                        offset = len(new_order)
                        column = values if data.ndim > 1 else data
                        column += offset
                        for i, val in enumerate(var.values):
                            try:
                                oldval = old_order.index(val)
                            except ValueError:
                                continue
                            bn.replace(column, offset + oldval,
                                       new_order.index(val))

            if coltype is TimeVariable:
                # Re-parse the values because only now after coltype.make call
                # above, variable var is the correct one
                values = [var.parse(i) for i in orig_values]

            # Write back the changed data. This is needeed to pass the
            # correct, converted values into Table.from_numpy below
            try:
                data[:, col] = values
            except IndexError:
                pass

        domain = Domain(attrs, clses, metas)

        if not data.size:
            return Table.from_domain(domain, 0)

        table = Table.from_numpy(domain, data[:, Xcols].astype(float,
                                                               order='C'),
                                 data[:, Ycols].astype(float, order='C'),
                                 data[:, Mcols].astype(object, order='C'),
                                 data[:, Wcols].astype(float, order='C'))
        return table