API: multi-line, not inplace eval

PEP8 compliance for test_eval and eval.py

Author: chris-b1

doc/source/enhancingperf.rst

@@ -570,18 +570,51 @@ prefix the name of the :class:`~pandas.DataFrame` to the column(s) you're
 interested in evaluating.
 
 In addition, you can perform assignment of columns within an expression.
-This allows for *formulaic evaluation*. Only a single assignment is permitted.
-The assignment target can be a new column name or an existing column name, and
-it must be a valid Python identifier.
+This allows for *formulaic evaluation*.  The assignment target can be a
+new column name or an existing column name, and it must be a valid Python
+identifier.
+
+.. versionadded:: 0.18.0
+
+The ``inplace`` keyword determines whether this assignment will performed
+on the original ``DataFrame`` or return a copy with the new column.
+
+.. warning::
+
+   For backwards compatability, ``inplace`` defaults to ``True`` if not
+   specified. This will change in a future version of pandas - if your
+   code depends on an inplace assignment you should update to explicitly
+   set ``inplace=True``
 
 .. ipython:: python
 
    df = pd.DataFrame(dict(a=range(5), b=range(5, 10)))
-   df.eval('c = a + b')
-   df.eval('d = a + b + c')
-   df.eval('a = 1')
+   df.eval('c = a + b', inplace=True)
+   df.eval('d = a + b + c', inplace=True)
+   df.eval('a = 1', inplace=True)
    df
 
+When ``inplace`` is set to ``False``, a copy of the ``DataFrame`` with the
+new or modified columns is returned and the original frame is unchanged.
+
+.. ipython:: python
+
+   df
+   df.eval('e = a - c', inplace=False)
+   df
+
+.. versionadded:: 0.18.0
+
+As a convenience, multiple assignments can be performed by using a
+multi-line string.
+
+.. ipython:: python
+
+   df.eval("""
+   c = a + b
+   d = a + b + c
+   a = 1""", inplace=False)
+
 The equivalent in standard Python would be
 
 .. ipython:: python
@@ -592,6 +625,23 @@ The equivalent in standard Python would be
    df['a'] = 1
    df
 
+.. versionadded:: 0.18.0
+
+The ``query`` method gained the ``inplace`` keyword which determines
+whether the query modifies the original frame.
+
+.. ipython:: python
+
+   df = pd.DataFrame(dict(a=range(5), b=range(5, 10)))
+   df.query('a > 2')
+   df.query('a > 2', inplace=True)
+   df
+
+.. warning::
+
+   Unlike with ``eval``, the default value for ``inplace`` for ``query``
+   is ``False``.  This is consistent with prior versions of pandas.
+
 Local Variables
 ~~~~~~~~~~~~~~~
 

doc/source/whatsnew/v0.18.0.txt

@@ -295,15 +295,60 @@ date strings is no longer supported and raises a ``ValueError``. (:issue:`11818`
 
 - ``.memory_usage`` now includes values in the index, as does memory_usage in ``.info`` (:issue:`11597`)
 
+Changes to eval
+^^^^^^^^^^^^^^^
 
+In prior versions, new columns assignments in an ``eval`` expression resulted
+in an inplace change to the ``DataFrame``. (:issue:`9297`)
 
+.. ipython:: python
 
+   df = pd.DataFrame({'a': np.linspace(0, 10, 5), 'b': range(5)})
+   df.eval('c = a + b')
+   df
 
+In version 0.18.0, a new ``inplace`` keyword was added to choose whether the
+assignment should be done inplace or return a copy.
 
+.. ipython:: python
 
+   df
+   df.eval('d = c - b', inplace=False)
+   df
+   df.eval('d = c - b', inplace=True)
+   df
 
+.. warning::
+
+   For backwards compatability, ``inplace`` defaults to ``True`` if not specified.
+   This will change in a future version of pandas - if your code depends on an
+   inplace assignment you should update to explicitly set ``inplace=True``
 
+The ``inplace`` keyword parameter was also added the ``query`` method.  
 
+.. ipython:: python
+
+   df.query('a > 5')
+   df.query('a > 5', inplace=True)
+   df
+
+.. warning::
+
+   Note that the default value for ``inplace`` in a ``query``
+   is ``False``, which is consistent with prior verions.
+
+``eval`` has also been updated to allow multi-line expressions for multiple
+assignments.  These expressions will be evaluated one at a time in order.  Only
+assginments are valid for multi-line expressions.
+
+.. ipython:: python
+
+   df
+   df.eval("""
+   e = d + a
+   f = e - 22
+   g = f / 2.0""", inplace=True)
+   df
 
 .. _whatsnew_0180.deprecations:
 
@@ -412,7 +457,7 @@ Bug Fixes
 - Bug in ``pd.read_clipboard`` and ``pd.to_clipboard`` functions not supporting Unicode; upgrade included ``pyperclip`` to v1.5.15 (:issue:`9263`)
 
 
-
+- Bug in ``DataFrame.query`` containing an assignment (:issue:`8664`)
 
 
 

pandas/computation/eval.py

@@ -3,11 +3,12 @@
 """Top level ``eval`` module.
 """
 
+import warnings
 import tokenize
 from pandas.core import common as com
 from pandas.computation.expr import Expr, _parsers, tokenize_string
 from pandas.computation.scope import _ensure_scope
-from pandas.compat import DeepChainMap, builtins
+from pandas.compat import string_types
 from pandas.computation.engines import _engines
 from distutils.version import LooseVersion
 
@@ -138,7 +139,7 @@ def _check_for_locals(expr, stack_level, parser):
 
 def eval(expr, parser='pandas', engine='numexpr', truediv=True,
          local_dict=None, global_dict=None, resolvers=(), level=0,
-         target=None):
+         target=None, inplace=None):
     """Evaluate a Python expression as a string using various backends.
 
     The following arithmetic operations are supported: ``+``, ``-``, ``*``,
@@ -196,6 +197,13 @@ def eval(expr, parser='pandas', engine='numexpr', truediv=True,
         scope. Most users will **not** need to change this parameter.
     target : a target object for assignment, optional, default is None
         essentially this is a passed in resolver
+    inplace : bool, default True
+        If expression mutates, whether to modify object inplace or return
+        copy with mutation.
+
+        WARNING: inplace=None currently falls back to to True, but
+        in a future version, will default to False.  Use inplace=True
+        explicitly rather than relying on the default.
 
     Returns
     -------
@@ -214,29 +222,78 @@ def eval(expr, parser='pandas', engine='numexpr', truediv=True,
     pandas.DataFrame.query
     pandas.DataFrame.eval
     """
-    expr = _convert_expression(expr)
-    _check_engine(engine)
-    _check_parser(parser)
-    _check_resolvers(resolvers)
-    _check_for_locals(expr, level, parser)
-
-    # get our (possibly passed-in) scope
-    level += 1
-    env = _ensure_scope(level, global_dict=global_dict,
-                        local_dict=local_dict, resolvers=resolvers,
-                        target=target)
-
-    parsed_expr = Expr(expr, engine=engine, parser=parser, env=env,
-                       truediv=truediv)
-
-    # construct the engine and evaluate the parsed expression
-    eng = _engines[engine]
-    eng_inst = eng(parsed_expr)
-    ret = eng_inst.evaluate()
-
-    # assign if needed
-    if env.target is not None and parsed_expr.assigner is not None:
-        env.target[parsed_expr.assigner] = ret
-        return None
+    first_expr = True
+    if isinstance(expr, string_types):
+        exprs = [e for e in expr.splitlines() if e != '']
+    else:
+        exprs = [expr]
+    multi_line = len(exprs) > 1
+
+    if multi_line and target is None:
+        raise ValueError("multi-line expressions are only valid in the "
+                         "context of data, use DataFrame.eval")
+
+    first_expr = True
+    for expr in exprs:
+        expr = _convert_expression(expr)
+        _check_engine(engine)
+        _check_parser(parser)
+        _check_resolvers(resolvers)
+        _check_for_locals(expr, level, parser)
+
+        # get our (possibly passed-in) scope
+        level += 1
+        env = _ensure_scope(level, global_dict=global_dict,
+                            local_dict=local_dict, resolvers=resolvers,
+                            target=target)
+
+        parsed_expr = Expr(expr, engine=engine, parser=parser, env=env,
+                           truediv=truediv)
+
+        # construct the engine and evaluate the parsed expression
+        eng = _engines[engine]
+        eng_inst = eng(parsed_expr)
+        ret = eng_inst.evaluate()
+
+        if parsed_expr.assigner is None and multi_line:
+            raise ValueError("Multi-line expressions are only valid"
+                             " if all expressions contain an assignment")
+
+        # assign if needed
+        if env.target is not None and parsed_expr.assigner is not None:
+            if inplace is None:
+                warnings.warn(
+                    "eval expressions containing an assignment currently"
+                    "default to operating inplace.\nThis will change in "
+                    "a future version of pandas, use inplace=True to "
+                    "avoid this warning.",
+                    FutureWarning, stacklevel=3)
+                inplace = True
+
+            # if returning a copy, copy only on the first assignment
+            if not inplace and first_expr:
+                target = env.target.copy()
+            else:
+                target = env.target
+
+            target[parsed_expr.assigner] = ret
+
+            if not resolvers:
+                resolvers = ({parsed_expr.assigner: ret},)
+            else:
+                # existing resolver needs updated to handle
+                # case of mutating existing column in copy
+                for resolver in resolvers:
+                    if parsed_expr.assigner in resolver:
+                        resolver[parsed_expr.assigner] = ret
+                        break
+                else:
+                    resolvers += ({parsed_expr.assigner: ret},)
+
+            ret = None
+            first_expr = False
+
+    if not inplace and inplace is not None:
+        return target
 
     return ret