Python pandas.compat.string_types() Examples

def _validate_where(w):
    """
    Validate that the where statement is of the right type.

    The type may either be String, Expr, or list-like of Exprs.

    Parameters
    ----------
    w : String term expression, Expr, or list-like of Exprs.

    Returns
    -------
    where : The original where clause if the check was successful.

    Raises
    ------
    TypeError : An invalid data type was passed in for w (e.g. dict).
    """

    if not (isinstance(w, (Expr, string_types)) or is_list_like(w)):
        raise TypeError("where must be passed as a string, Expr, "
                        "or list-like of Exprs")

    return w 

def validate(self):
        super(Window, self).validate()

        window = self.window
        if isinstance(window, (list, tuple, np.ndarray)):
            pass
        elif is_integer(window):
            if window <= 0:
                raise ValueError("window must be > 0 ")
            try:
                import scipy.signal as sig
            except ImportError:
                raise ImportError('Please install scipy to generate window '
                                  'weight')

            if not isinstance(self.win_type, compat.string_types):
                raise ValueError('Invalid win_type {0}'.format(self.win_type))
            if getattr(sig, self.win_type, None) is None:
                raise ValueError('Invalid win_type {0}'.format(self.win_type))
        else:
            raise ValueError('Invalid window {0}'.format(window)) 

def update(self, value):
        """
        search order for local (i.e., @variable) variables:

        scope, key_variable
        [('locals', 'local_name'),
         ('globals', 'local_name'),
         ('locals', 'key'),
         ('globals', 'key')]
        """
        key = self.name

        # if it's a variable name (otherwise a constant)
        if isinstance(key, string_types):
            self.env.swapkey(self.local_name, key, new_value=value)

        self.value = value 

def _apply(self, func, name, window=None, center=None,
               check_minp=None, **kwargs):
        """
        Dispatch to apply; we are stripping all of the _apply kwargs and
        performing the original function call on the grouped object.
        """

        def f(x, name=name, *args):
            x = self._shallow_copy(x)

            if isinstance(name, compat.string_types):
                return getattr(x, name)(*args, **kwargs)

            return x.apply(name, *args, **kwargs)

        return self._groupby.apply(f) 

def test_to_html(biggie_df_fixture):
    # TODO: split this test
    df = biggie_df_fixture
    s = df.to_html()

    buf = StringIO()
    retval = df.to_html(buf=buf)
    assert retval is None
    assert buf.getvalue() == s

    assert isinstance(s, compat.string_types)

    df.to_html(columns=['B', 'A'], col_space=17)
    df.to_html(columns=['B', 'A'],
               formatters={'A': lambda x: '{x:.1f}'.format(x=x)})

    df.to_html(columns=['B', 'A'], float_format=str)
    df.to_html(columns=['B', 'A'], col_space=12, float_format=str) 

def aggregate(self, arg, *args, **kwargs):
        """
        Aggregate using input function or dict of {column -> function}

        Parameters
        ----------
        arg : function or dict
            Function to use for aggregating groups. If a function, must either
            work when passed a Panel or when passed to Panel.apply. If
            pass a dict, the keys must be DataFrame column names

        Returns
        -------
        aggregated : Panel
        """
        if isinstance(arg, compat.string_types):
            return getattr(self, arg)(*args, **kwargs)

        return self._aggregate_generic(arg, *args, **kwargs) 

def test_encoding(self, version):

        # GH 4626, proper encoding handling
        raw = read_stata(self.dta_encoding)
        with tm.assert_produces_warning(FutureWarning):
            encoded = read_stata(self.dta_encoding, encoding='latin-1')
        result = encoded.kreis1849[0]

        expected = raw.kreis1849[0]
        assert result == expected
        assert isinstance(result, compat.string_types)

        with tm.ensure_clean() as path:
            with tm.assert_produces_warning(FutureWarning):
                encoded.to_stata(path, write_index=False, version=version,
                                 encoding='latin-1')
            reread_encoded = read_stata(path)
            tm.assert_frame_equal(encoded, reread_encoded) 

def _get_partial_string_timestamp_match_key(self, key, labels):
        """Translate any partial string timestamp matches in key, returning the
        new key (GH 10331)"""
        if isinstance(labels, MultiIndex):
            if (isinstance(key, compat.string_types) and
                    labels.levels[0].is_all_dates):
                # Convert key '2016-01-01' to
                # ('2016-01-01'[, slice(None, None, None)]+)
                key = tuple([key] + [slice(None)] * (len(labels.levels) - 1))

            if isinstance(key, tuple):
                # Convert (..., '2016-01-01', ...) in tuple to
                # (..., slice('2016-01-01', '2016-01-01', None), ...)
                new_key = []
                for i, component in enumerate(key):
                    if (isinstance(component, compat.string_types) and
                            labels.levels[i].is_all_dates):
                        new_key.append(slice(component, component, None))
                    else:
                        new_key.append(component)
                key = tuple(new_key)

        return key 

def asarray_tuplesafe(values, dtype=None):

    if not (isinstance(values, (list, tuple)) or hasattr(values, '__array__')):
        values = list(values)
    elif isinstance(values, ABCIndexClass):
        return values.values

    if isinstance(values, list) and dtype in [np.object_, object]:
        return construct_1d_object_array_from_listlike(values)

    result = np.asarray(values, dtype=dtype)

    if issubclass(result.dtype.type, compat.string_types):
        result = np.asarray(values, dtype=object)

    if result.ndim == 2:
        # Avoid building an array of arrays:
        # TODO: verify whether any path hits this except #18819 (invalid)
        values = [tuple(x) for x in values]
        result = construct_1d_object_array_from_listlike(values)

    return result 

def test_iter(self):
        # GH3638
        strs = 'google', 'wikimedia', 'wikipedia', 'wikitravel'
        ds = Series(strs)

        for s in ds.str:
            # iter must yield a Series
            assert isinstance(s, Series)

            # indices of each yielded Series should be equal to the index of
            # the original Series
            tm.assert_index_equal(s.index, ds.index)

            for el in s:
                # each element of the series is either a basestring/str or nan
                assert isinstance(el, compat.string_types) or isna(el)

        # desired behavior is to iterate until everything would be nan on the
        # next iter so make sure the last element of the iterator was 'l' in
        # this case since 'wikitravel' is the longest string
        assert s.dropna().values.item() == 'l' 

def index_labels_to_array(labels, dtype=None):
    """
    Transform label or iterable of labels to array, for use in Index.

    Parameters
    ----------
    dtype : dtype
        If specified, use as dtype of the resulting array, otherwise infer.

    Returns
    -------
    array
    """
    if isinstance(labels, (compat.string_types, tuple)):
        labels = [labels]

    if not isinstance(labels, (list, np.ndarray)):
        try:
            labels = list(labels)
        except TypeError:  # non-iterable
            labels = [labels]

    labels = asarray_tuplesafe(labels, dtype=dtype)

    return labels 

def convert_to_index_sliceable(obj, key):
    """
    if we are index sliceable, then return my slicer, otherwise return None
    """
    idx = obj.index
    if isinstance(key, slice):
        return idx._convert_slice_indexer(key, kind='getitem')

    elif isinstance(key, compat.string_types):

        # we are an actual column
        if obj._data.items.contains(key):
            return None

        # We might have a datetimelike string that we can translate to a
        # slice here via partial string indexing
        if idx.is_all_dates:
            try:
                return idx._get_string_slice(key)
            except (KeyError, ValueError, NotImplementedError):
                return None

    return None 

def __eq__(self, other):
        if isinstance(other, compat.string_types):
            from pandas.tseries.frequencies import to_offset
            try:
                # GH#23524 if to_offset fails, we are dealing with an
                #  incomparable type so == is False and != is True
                other = to_offset(other)
            except ValueError:
                # e.g. "infer"
                return False

        if isinstance(other, Tick):
            return self.delta == other.delta
        else:
            return False

    # This is identical to DateOffset.__hash__, but has to be redefined here
    # for Python 3, because we've redefined __eq__. 

def searchsorted(self, value, side='left', sorter=None):
        if isinstance(value, Period):
            if value.freq != self.freq:
                msg = DIFFERENT_FREQ.format(cls=type(self).__name__,
                                            own_freq=self.freqstr,
                                            other_freq=value.freqstr)
                raise IncompatibleFrequency(msg)
            value = value.ordinal
        elif isinstance(value, compat.string_types):
            try:
                value = Period(value, freq=self.freq).ordinal
            except DateParseError:
                raise KeyError("Cannot interpret '{}' as period".format(value))

        return self._ndarray_values.searchsorted(value, side=side,
                                                 sorter=sorter) 

def get_finder(freq):
    if isinstance(freq, compat.string_types):
        freq = get_freq(freq)
    fgroup = resolution.get_freq_group(freq)

    if fgroup == FreqGroup.FR_ANN:
        return _annual_finder
    elif fgroup == FreqGroup.FR_QTR:
        return _quarterly_finder
    elif freq == FreqGroup.FR_MTH:
        return _monthly_finder
    elif ((freq >= FreqGroup.FR_BUS) or fgroup == FreqGroup.FR_WK):
        return _daily_finder
    else:  # pragma: no cover
        errmsg = "Unsupported frequency: {freq}".format(freq=freq)
        raise NotImplementedError(errmsg) 

def is_dtype(cls, dtype):
        """
        Return a boolean if we if the passed type is an actual dtype that we
        can match (via string or type)
        """

        if isinstance(dtype, compat.string_types):
            # PeriodDtype can be instantiated from freq string like "U",
            # but doesn't regard freq str like "U" as dtype.
            if dtype.startswith('period[') or dtype.startswith('Period['):
                try:
                    if cls._parse_dtype_strict(dtype) is not None:
                        return True
                    else:
                        return False
                except ValueError:
                    return False
            else:
                return False
        return super(PeriodDtype, cls).is_dtype(dtype) 

def _convert_1d(values, units, axis):
        if not hasattr(axis, 'freq'):
            raise TypeError('Axis must have `freq` set to convert to Periods')
        valid_types = (compat.string_types, datetime,
                       Period, pydt.date, pydt.time, np.datetime64)
        if (isinstance(values, valid_types) or is_integer(values) or
                is_float(values)):
            return get_datevalue(values, axis.freq)
        elif isinstance(values, PeriodIndex):
            return values.asfreq(axis.freq)._ndarray_values
        elif isinstance(values, Index):
            return values.map(lambda x: get_datevalue(x, axis.freq))
        elif lib.infer_dtype(values, skipna=False) == 'period':
            # https://github.com/pandas-dev/pandas/issues/24304
            # convert ndarray[period] -> PeriodIndex
            return PeriodIndex(values, freq=axis.freq)._ndarray_values
        elif isinstance(values, (list, tuple, np.ndarray, Index)):
            return [get_datevalue(x, axis.freq) for x in values]
        return values 

def construct_from_string(cls, string):
        """
        attempt to construct this type from a string, raise a TypeError
        if its not possible
        """
        if not isinstance(string, compat.string_types):
            msg = "a string needs to be passed, got type {typ}"
            raise TypeError(msg.format(typ=type(string)))

        if (string.lower() == 'interval' or
           cls._match.search(string) is not None):
                return cls(string)

        msg = ('Incorrectly formatted string passed to constructor. '
               'Valid formats include Interval or Interval[dtype] '
               'where dtype is numeric, datetime, or timedelta')
        raise TypeError(msg) 

def __eq__(self, other):
        if isinstance(other, compat.string_types):
            return other == self.name

        return (isinstance(other, DatetimeTZDtype) and
                self.unit == other.unit and
                str(self.tz) == str(other.tz)) 

def update_dtype(self, dtype):
        """
        Returns a CategoricalDtype with categories and ordered taken from dtype
        if specified, otherwise falling back to self if unspecified

        Parameters
        ----------
        dtype : CategoricalDtype

        Returns
        -------
        new_dtype : CategoricalDtype
        """
        if isinstance(dtype, compat.string_types) and dtype == 'category':
            # dtype='category' should not change anything
            return self
        elif not self.is_dtype(dtype):
            msg = ('a CategoricalDtype must be passed to perform an update, '
                   'got {dtype!r}').format(dtype=dtype)
            raise ValueError(msg)
        elif dtype.categories is not None and dtype.ordered is self.ordered:
            return dtype

        # dtype is CDT: keep current categories/ordered if None
        new_categories = dtype.categories
        if new_categories is None:
            new_categories = self.categories

        new_ordered = dtype.ordered
        if new_ordered is None:
            new_ordered = self.ordered

        return CategoricalDtype(new_categories, new_ordered) 

def construct_from_string(cls, string):
        """
        Construct a DatetimeTZDtype from a string.

        Parameters
        ----------
        string : str
            The string alias for this DatetimeTZDtype.
            Should be formatted like ``datetime64[ns, <tz>]``,
            where ``<tz>`` is the timezone name.

        Examples
        --------
        >>> DatetimeTZDtype.construct_from_string('datetime64[ns, UTC]')
        datetime64[ns, UTC]
        """
        if isinstance(string, compat.string_types):
            msg = "Could not construct DatetimeTZDtype from '{}'"
            try:
                match = cls._match.match(string)
                if match:
                    d = match.groupdict()
                    return cls(unit=d['unit'], tz=d['tz'])
            except Exception:
                # TODO(py3): Change this pass to `raise TypeError(msg) from e`
                pass
            raise TypeError(msg.format(string))

        raise TypeError("Could not construct DatetimeTZDtype") 

def _hashed_indexing_key(self, key):
        """
        validate and return the hash for the provided key

        *this is internal for use for the cython routines*

        Parameters
        ----------
        key : string or tuple

        Returns
        -------
        np.uint64

        Notes
        -----
        we need to stringify if we have mixed levels

        """
        from pandas.core.util.hashing import hash_tuples, hash_tuple

        if not isinstance(key, tuple):
            return hash_tuples(key)

        if not len(key) == self.nlevels:
            raise KeyError

        def f(k, stringify):
            if stringify and not isinstance(k, compat.string_types):
                k = str(k)
            return k
        key = tuple(f(k, stringify)
                    for k, stringify in zip(key, self._have_mixed_levels))
        return hash_tuple(key) 

def _try_aggregate_string_function(self, arg, *args, **kwargs):
        """
        if arg is a string, then try to operate on it:
        - try to find a function (or attribute) on ourselves
        - try to find a numpy function
        - raise

        """
        assert isinstance(arg, compat.string_types)

        f = getattr(self, arg, None)
        if f is not None:
            if callable(f):
                return f(*args, **kwargs)

            # people may try to aggregate on a non-callable attribute
            # but don't let them think they can pass args to it
            assert len(args) == 0
            assert len([kwarg for kwarg in kwargs
                        if kwarg not in ['axis', '_level']]) == 0
            return f

        f = getattr(np, arg, None)
        if f is not None:
            return f(self, *args, **kwargs)

        raise ValueError("{arg} is an unknown string function".format(arg=arg)) 

def __new__(cls, name, env, side=None, encoding=None):
        klass = Constant if not isinstance(name, string_types) else cls
        supr_new = super(Term, klass).__new__
        return supr_new(klass) 

def visit(self, node, **kwargs):
        if isinstance(node, string_types):
            clean = self.preparser(node)
            try:
                node = ast.fix_missing_locations(ast.parse(clean))
            except SyntaxError as e:
                from keyword import iskeyword
                if any(iskeyword(x) for x in clean.split()):
                    e.msg = ("Python keyword not valid identifier"
                             " in numexpr query")
                raise e

        method = 'visit_' + node.__class__.__name__
        visitor = getattr(self, method)
        return visitor(node, **kwargs) 

def maybe_expression(s):
    """ loose checking if s is a pytables-acceptable expression """
    if not isinstance(s, string_types):
        return False
    ops = ExprVisitor.binary_ops + ExprVisitor.unary_ops + ('=',)

    # make sure we have an op at least
    return any(op in s for op in ops) 

def __new__(cls, name, env, side=None, encoding=None):
        klass = Constant if not isinstance(name, string_types) else cls
        supr_new = StringMixin.__new__
        return supr_new(klass) 

def _should_fill(lname, rname):
    if (not isinstance(lname, compat.string_types) or
            not isinstance(rname, compat.string_types)):
        return True
    return lname == rname 

def _maybe_cast_slice_bound(self, label, side, kind):
        """
        If label is a string or a datetime, cast it to Period.ordinal according
        to resolution.

        Parameters
        ----------
        label : object
        side : {'left', 'right'}
        kind : {'ix', 'loc', 'getitem'}

        Returns
        -------
        bound : Period or object

        Notes
        -----
        Value of `side` parameter should be validated in caller.

        """
        assert kind in ['ix', 'loc', 'getitem']

        if isinstance(label, datetime):
            return Period(label, freq=self.freq)
        elif isinstance(label, compat.string_types):
            try:
                _, parsed, reso = parse_time_string(label, self.freq)
                bounds = self._parsed_string_to_bounds(reso, parsed)
                return bounds[0 if side == 'left' else 1]
            except Exception:
                raise KeyError(label)
        elif is_integer(label) or is_float(label):
            self._invalid_indexer('slice', label)

        return label 

def _summary(self, name=None):
        """
        Return a summarized representation.

        Parameters
        ----------
        name : str
            name to use in the summary representation

        Returns
        -------
        String with a summarized representation of the index
        """
        if len(self) > 0:
            head = self[0]
            if (hasattr(head, 'format') and
                    not isinstance(head, compat.string_types)):
                head = head.format()
            tail = self[-1]
            if (hasattr(tail, 'format') and
                    not isinstance(tail, compat.string_types)):
                tail = tail.format()
            index_summary = ', %s to %s' % (pprint_thing(head),
                                            pprint_thing(tail))
        else:
            index_summary = ''

        if name is None:
            name = type(self).__name__
        return '%s: %s entries%s' % (name, len(self), index_summary)