Python EvalEnvironment.capture方法代码示例

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def dmatrix(formula_like, data={}, eval_env=0, return_type="matrix"):
    """Construct a single design matrix given a formula_like and data.

    :arg formula_like: An object that can be used to construct a design
      matrix. See below.
    :arg data: A dict-like object that can be used to look up variables
      referenced in `formula_like`.
    :arg eval_env: Either a :class:`EvalEnvironment` which will be used to
      look up any variables referenced in `formula_like` that cannot be
      found in `data`, or else a depth represented as an
      integer which will be passed to :meth:`EvalEnvironment.capture`.
      ``eval_env=0`` means to use the context of the function calling
      :func:`dmatrix` for lookups. If calling this function from a library,
      you probably want ``eval_env=1``, which means that variables should be
      resolved in *your* caller's namespace.
    :arg return_type: Either ``"matrix"`` or ``"dataframe"``. See below.

    The `formula_like` can take a variety of forms:

    * A formula string like "x1 + x2" (for :func:`dmatrix`) or "y ~ x1 + x2"
      (for :func:`dmatrices`). For details see :ref:`formulas`.
    * A :class:`ModelDesc`, which is a Python object representation of a
      formula. See :ref:`formulas` and :ref:`expert-model-specification` for
      details.
    * A :class:`DesignMatrixBuilder`.
    * An object that has a method called :meth:`__patsy_get_model_desc__`.
      For details see :ref:`expert-model-specification`.
    * A numpy array_like (for :func:`dmatrix`) or a tuple
      (array_like, array_like) (for :func:`dmatrices`). These will have
      metadata added, representation normalized, and then be returned
      directly. In this case `data` and `eval_env` are
      ignored. There is special handling for two cases:

      * :class:`DesignMatrix` objects will have their :class:`DesignInfo`
        preserved. This allows you to set up custom column names and term
        information even if you aren't using the rest of the patsy
        machinery.
      * :class:`pandas.DataFrame` or :class:`pandas.Series` objects will have
        their (row) indexes checked. If two are passed in, their indexes must
        be aligned. If ``return_type="dataframe"``, then their indexes will be
        preserved on the output.
      
    Regardless of the input, the return type is always either:

    * A :class:`DesignMatrix`, if ``return_type="matrix"`` (the default)
    * A :class:`pandas.DataFrame`, if ``return_type="dataframe"``.

    The actual contents of the design matrix is identical in both cases, and
    in both cases a :class:`DesignInfo` will be available in a
    ``.design_info`` attribute on the return value. However, for
    ``return_type="dataframe"``, any pandas indexes on the input (either in
    `data` or directly passed through `formula_like`) will be
    preserved, which may be useful for e.g. time-series models.
    """
    eval_env = EvalEnvironment.capture(eval_env, reference=1)
    (lhs, rhs) = _do_highlevel_design(formula_like, data, eval_env, return_type)
    if lhs.shape[1] != 0:
        raise PatsyError("encountered outcome variables for a model "
                            "that does not expect them")
    return rhs

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def test_formula_factor_origin():
    from patsy.origin import Origin
    desc = ModelDesc.from_formula("a + b", EvalEnvironment.capture(0))
    assert (desc.rhs_termlist[1].factors[0].origin
            == Origin("a + b", 0, 1))
    assert (desc.rhs_termlist[2].factors[0].origin
            == Origin("a + b", 4, 5))

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
    def __init__(self, mapping=None, data=None, environment=None):
        # Allow some sloppiness
        if (isinstance(mapping, pd.DataFrame) and
                (data is None or isinstance(data, aes))):
            mapping, data = data, mapping
        if mapping is None:
            mapping = aes()

        if (data is not None and
                not isinstance(data, pd.DataFrame)):
            raise PlotnineError(
                'data must be a dataframe or None if each '
                'layer will have separate data.')

        # Recognize plydata groups
        if hasattr(data, 'group_indices') and 'group' not in mapping:
            mapping = mapping.copy()
            mapping['group'] = data.group_indices()

        self.data = data
        self.mapping = mapping
        self.facet = facet_null()
        self.labels = make_labels(mapping)
        self.layers = Layers()
        self.guides = guides()
        self.scales = Scales()
        self.theme = None
        self.coordinates = coord_cartesian()
        self.environment = environment or EvalEnvironment.capture(1)
        self.layout = None
        self.figure = None
        self.watermarks = []
        self.axs = None

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
 def __init__(self, *args, **kwargs):
     if args:
         self.data = dict(zip(self.DEFAULT_ARGS, args))
     else:
         self.data = {}
     if kwargs:
         self.data.update(kwargs)
     if 'colour' in self.data:
         self.data['color'] = self.data['colour']
         del self.data['colour']
     self.__eval_env__ = EvalEnvironment.capture(1)

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
 def __init__(self, *args, **kwargs):
     if args:
         self.data = dict(zip(self.DEFAULT_ARGS, args))
     else:
         self.data = {}
     if kwargs:
         self.data.update(kwargs)
     if "colour" in self.data:
         self.data["color"] = self.data["colour"]
         del self.data["colour"]
     if "linetype" in self.data:
         self.data["linestyle"] = self.data["linetype"]
         del self.data["linetype"]
     self.__eval_env__ = EvalEnvironment.capture(1)

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def incr_dbuilders(formula_like, data_iter_maker, eval_env=0):
    """Construct two design matrix builders incrementally from a large data
    set.

    :func:`incr_dbuilders` is to :func:`incr_dbuilder` as :func:`dmatrices` is
    to :func:`dmatrix`. See :func:`incr_dbuilder` for details.
    """
    eval_env = EvalEnvironment.capture(eval_env, reference=1)
    builders = _try_incr_builders(formula_like, data_iter_maker, eval_env)
    if builders is None:
        raise PatsyError("bad formula-like object")
    if len(builders[0].design_info.column_names) == 0:
        raise PatsyError("model is missing required outcome variables")
    return builders

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def test_evalfactor_reraise():
    # From issue #11:
    env = EvalEnvironment.capture()
    data = {"X" : [0,1,2,3], "Y" : [1,2,3,4]}
    formula = "C(X) + Y"
    new_data = {"X" : [0,0,1,2,3,3,4], "Y" : [1,2,3,4,5,6,7]}
    info = dmatrix(formula, data)
    # This will produce a PatsyError, which is originally raised within the
    # call to C() (which has no way to know where it is being called
    # from). But EvalFactor should notice this, and add a useful origin:
    try:
        build_design_matrices([info.design_info.builder], new_data)
    except PatsyError, e:
        assert e.origin == Origin(formula, 0, 4)

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def _do_eval_formula_tests(tests): # pragma: no cover
    for code, result in six.iteritems(tests):
        if len(result) == 2:
            result = (False, []) + result
        eval_env = EvalEnvironment.capture(0)
        model_desc = ModelDesc.from_formula(code, eval_env)
        print(repr(code))
        print(result)
        print(model_desc)
        lhs_intercept, lhs_termlist, rhs_intercept, rhs_termlist = result
        _assert_terms_match(model_desc.lhs_termlist,
                            lhs_intercept, lhs_termlist)
        _assert_terms_match(model_desc.rhs_termlist,
                            rhs_intercept, rhs_termlist)

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def dmatrices(formula_like, data={}, eval_env=0, NA_action="drop", return_type="matrix"):
    """Construct two design matrices given a formula_like and data.

    This function is identical to :func:`dmatrix`, except that it requires
    (and returns) two matrices instead of one. By convention, the first matrix
    is the "outcome" or "y" data, and the second is the "predictor" or "x"
    data.

    See :func:`dmatrix` for details.
    """
    eval_env = EvalEnvironment.capture(eval_env, reference=1)
    (lhs, rhs) = _do_highlevel_design(formula_like, data, eval_env, NA_action, return_type)
    if lhs.shape[1] == 0:
        raise PatsyError("model is missing required outcome variables")
    return (lhs, rhs)

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def _apply_transforms(data, aes):
    """Adds columns from the aes included transformations

    Possible transformations are "factor(<col>)" and
    expressions which can be used with eval.

    Parameters
    ----------
    data : DataFrame
        the original dataframe
    aes : aesthetics
        the aesthetic

    Returns
    -------
    data : DateFrame
        Transformed DataFrame
    """
    data = data.copy()
    for ae, name in aes.items():
        if (isinstance(name, six.string_types) and (name not in data)):
            # here we assume that it is a transformation
            # if the mapping is to a single value (color="red"), this will be handled by pandas and
            # assigned to the whole index. See also the last case in mapping building in get_layer!
            from patsy.eval import EvalEnvironment
            def factor(s, levels=None, labels=None):
                # TODO: This factor implementation needs improvements...
                # probably only gonna happen after https://github.com/pydata/pandas/issues/5313 is
                # implemented in pandas ...
                if levels or labels:
                    print("factor levels or labels are not yet implemented.")
                return s.apply(str)
            # use either the captured eval_env from aes or use the env one steps up
            env = EvalEnvironment.capture(eval_env=(aes.__eval_env__ or 1))
            # add factor as a special case
            env.add_outer_namespace({"factor":factor})
            try:
                new_val = env.eval(name, inner_namespace=data)
            except Exception as e:
                msg = "Could not evaluate the '%s' mapping: '%s' (original error: %s)"
                raise Exception(msg % (ae, name, str(e)))
            try:
                data[name] = new_val
            except Exception as e:
                msg = """The '%s' mapping: '%s' produced a value of type '%s', but only single items
                and lists/arrays can be used. (original error: %s)"""
                raise Exception(msg % (ae, name, str(type(new_val)), str(e)))
    return data

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
    def _evaluate_aes_expressions(self):
        """
        Evaluates patsy expressions within the aesthetics. For example, 'x + 1'
        , 'factor(x)', or 'pd.cut(price, bins=10)')
        """
        for key, item in self._aes.items():
            if item not in self.data:
                def factor(s, levels=None, labels=None):
                    return s.apply(str)

                env = EvalEnvironment.capture(eval_env=(self._aes.__eval_env__ or 1)).with_outer_namespace({ "factor": factor, "pd": pd, "np": np })
                try:
                    new_val = env.eval(item, inner_namespace=self.data)
                    self.data[item] = new_val
                except:
                    pass

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def incr_dbuilder(formula_like, data_iter_maker, eval_env=0, NA_action="drop"):
    """Construct a design matrix builder incrementally from a large data set.

    :arg formula_like: Similar to :func:`dmatrix`, except that explicit
      matrices are not allowed. Must be a formula string, a
      :class:`ModelDesc`, a :class:`DesignInfo`, or an object with a
      ``__patsy_get_model_desc__`` method.
    :arg data_iter_maker: A zero-argument callable which returns an iterator
      over dict-like data objects. This must be a callable rather than a
      simple iterator because sufficiently complex formulas may require
      multiple passes over the data (e.g. if there are nested stateful
      transforms).
    :arg eval_env: Either a :class:`EvalEnvironment` which will be used to
      look up any variables referenced in `formula_like` that cannot be
      found in `data`, or else a depth represented as an
      integer which will be passed to :meth:`EvalEnvironment.capture`.
      ``eval_env=0`` means to use the context of the function calling
      :func:`incr_dbuilder` for lookups. If calling this function from a
      library, you probably want ``eval_env=1``, which means that variables
      should be resolved in *your* caller's namespace.
    :arg NA_action: An :class:`NAAction` object or string, used to determine
      what values count as 'missing' for purposes of determining the levels of
      categorical factors.
    :returns: A :class:`DesignInfo`

    Tip: for `data_iter_maker`, write a generator like::

      def iter_maker():
          for data_chunk in my_data_store:
              yield data_chunk

    and pass `iter_maker` (*not* `iter_maker()`).

    .. versionadded:: 0.2.0
       The ``NA_action`` argument.
    """
    eval_env = EvalEnvironment.capture(eval_env, reference=1)
    design_infos = _try_incr_builders(formula_like, data_iter_maker, eval_env,
                                      NA_action)
    if design_infos is None:
        raise PatsyError("bad formula-like object")
    if len(design_infos[0].column_names) > 0:
        raise PatsyError("encountered outcome variables for a model "
                         "that does not expect them")
    return design_infos[1]

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def Q(name):
    """A way to 'quote' variable names, especially ones that do not otherwise
    meet Python's variable name rules.

    If ``x`` is a variable, ``Q("x")`` returns the value of ``x``. (Note that
    ``Q`` takes the *string* ``"x"``, not the value of ``x`` itself.) This
    works even if instead of ``x``, we have a variable name that would not
    otherwise be legal in Python.

    For example, if you have a column of data named `weight.in.kg`, then you
    can't write::

      y ~ weight.in.kg

    because Python will try to find a variable named ``weight``, that has an
    attribute named ``in``, that has an attribute named ``kg``. (And worse
    yet, ``in`` is a reserved word, which makes this example doubly broken.)
    Instead, write::

      y ~ Q("weight.in.kg")

    and all will be well. Note, though, that this requires embedding a Python
    string inside your formula, which may require some care with your quote
    marks. Some standard options include::

      my_fit_function("y ~ Q('weight.in.kg')", ...)
      my_fit_function('y ~ Q("weight.in.kg")', ...)
      my_fit_function("y ~ Q(\\"weight.in.kg\\")", ...)

    Note also that ``Q`` is an ordinary Python function, which means that you
    can use it in more complex expressions. For example, this is a legal
    formula::

      y ~ np.sqrt(Q("weight.in.kg"))
    """
    from patsy.eval import EvalEnvironment

    env = EvalEnvironment.capture(1)
    try:
        return env.namespace[name]
    except KeyError:
        raise NameError, "no data named %r found" % (name,)

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
    def _evaluate_expressions(self, data):
        """
        Evaluates patsy expressions within the aesthetics. For example, 'x + 1'
        , 'factor(x)', or 'pd.cut(price, bins=10)')
        """
        for key, item in self.data.items():
            if item not in data:
                def factor(s, levels=None, labels=None):
                    return s.apply(str)

                env = EvalEnvironment.capture(eval_env=(self.__eval_env__ or 1)).with_outer_namespace({ "factor": factor, "pd": pd, "np": np })
                try:
                    new_val = env.eval(item, inner_namespace=data)
                    data[item] = new_val
                except:
                    msg = "Invalid column: '%s'" % str(item)
                    matches = difflib.get_close_matches(item, data.columns)
                    msg += "\ndid you mean one of the following:\n"
                    for match in matches:
                        msg += "    - %s\n" % match
                    raise Exception(msg)
        return data

# 需要导入模块: from patsy.eval import EvalEnvironment [as 别名]
# 或者: from patsy.eval.EvalEnvironment import capture [as 别名]
def _get_env(eval_env):
    if isinstance(eval_env, int):
        # Here eval_env=0 refers to our caller's caller.
        return EvalEnvironment.capture(eval_env + 2)
    return eval_env