ENH: Replace skiprows with skip_rows to begin standardizing underscore usage in keyword arguments

asv_bench/benchmarks/io/csv.py

@@ -87,9 +87,9 @@ class ReadCSVSkipRows(BaseIO):
     goal_time = 0.2
     fname = '__test__.csv'
     params = [None, 10000]
-    param_names = ['skiprows']
+    param_names = ['skip_rows']
 
-    def setup(self, skiprows):
+    def setup(self, skip_rows):
         N = 20000
         index = tm.makeStringIndex(N)
         df = DataFrame({'float1': np.random.randn(N),
@@ -100,8 +100,8 @@ def setup(self, skiprows):
                        index=index)
         df.to_csv(self.fname)
 
-    def time_skipprows(self, skiprows):
-        read_csv(self.fname, skiprows=skiprows)
+    def time_skipprows(self, skip_rows):
+        read_csv(self.fname, skip_rows=skip_rows)
 
 
 class ReadUint64Integers(StringIORewind):

doc/source/cookbook.rst

@@ -1034,7 +1034,7 @@ Option 1: pass rows explicitly to skip rows
 
 .. ipython:: python
 
-    pd.read_csv(StringIO(data), sep=';', skiprows=[11,12],
+    pd.read_csv(StringIO(data), sep=';', skip_rows=[11,12],
             index_col=0, parse_dates=True, header=10)
 
 Option 2: read column names and then data

doc/source/io.rst

@@ -186,7 +186,7 @@ false_values : list, default ``None``
   Values to consider as ``False``.
 skipinitialspace : boolean, default ``False``
   Skip spaces after delimiter.
-skiprows : list-like or integer, default ``None``
+skip_rows : list-like or integer, default ``None``
   Line numbers to skip (0-indexed) or number of lines to skip (int) at the start
   of the file.
 
@@ -197,7 +197,7 @@ skiprows : list-like or integer, default ``None``
 
      data = 'col1,col2,col3\na,b,1\na,b,2\nc,d,3'
      pd.read_csv(StringIO(data))
-     pd.read_csv(StringIO(data), skiprows=lambda x: x % 2 != 0)
+     pd.read_csv(StringIO(data), skip_rows=lambda x: x % 2 != 0)
 
 skipfooter : int, default ``0``
   Number of lines at bottom of file to skip (unsupported with engine='c').
@@ -326,7 +326,7 @@ comment : str, default ``None``
   Indicates remainder of line should not be parsed. If found at the beginning of
   a line, the line will be ignored altogether. This parameter must be a single
   character. Like empty lines (as long as ``skip_blank_lines=True``), fully
-  commented lines are ignored by the parameter `header` but not by `skiprows`.
+  commented lines are ignored by the parameter `header` but not by `skip_rows`.
   For example, if ``comment='#'``, parsing '#empty\\na,b,c\\n1,2,3' with
   `header=0` will result in 'a,b,c' being treated as the header.
 encoding : str, default ``None``
@@ -651,24 +651,24 @@ If ``skip_blank_lines=False``, then ``read_csv`` will not ignore blank lines:
 
    The presence of ignored lines might create ambiguities involving line numbers;
    the parameter ``header`` uses row numbers (ignoring commented/empty
-   lines), while ``skiprows`` uses line numbers (including commented/empty lines):
+   lines), while ``skip_rows`` uses line numbers (including commented/empty lines):
 
    .. ipython:: python
 
       data = '#comment\na,b,c\nA,B,C\n1,2,3'
       pd.read_csv(StringIO(data), comment='#', header=1)
       data = 'A,B,C\n#comment\na,b,c\n1,2,3'
-      pd.read_csv(StringIO(data), comment='#', skiprows=2)
+      pd.read_csv(StringIO(data), comment='#', skip_rows=2)
 
-   If both ``header`` and ``skiprows`` are specified, ``header`` will be
-   relative to the end of ``skiprows``. For example:
+   If both ``header`` and ``skip_rows`` are specified, ``header`` will be
+   relative to the end of ``skip_rows``. For example:
 
    .. ipython:: python
 
       data = '# empty\n# second empty line\n# third empty' \
                 'line\nX,Y,Z\n1,2,3\nA,B,C\n1,2.,4.\n5.,NaN,10.0'
       print(data)
-      pd.read_csv(StringIO(data), comment='#', skiprows=4, header=1)
+      pd.read_csv(StringIO(data), comment='#', skip_rows=4, header=1)
 
 .. _io.comments:
 
@@ -2373,14 +2373,14 @@ Specify a number of rows to skip:
 
 .. code-block:: python
 
-   dfs = pd.read_html(url, skiprows=0)
+   dfs = pd.read_html(url, skip_rows=0)
 
 Specify a number of rows to skip using a list (``xrange`` (Python 2 only) works
 as well):
 
 .. code-block:: python
 
-   dfs = pd.read_html(url, skiprows=range(2))
+   dfs = pd.read_html(url, skip_rows=range(2))
 
 Specify an HTML attribute:
 

pandas/_libs/parsers.pyx

@@ -294,7 +294,7 @@ cdef class TextReader:
         object header, orig_header, names, header_start, header_end
         object index_col
         object low_memory
-        object skiprows
+        object skip_rows
         object dtype
         object encoding
         object compression
@@ -348,7 +348,7 @@ cdef class TextReader:
                   false_values=None,
                   allow_leading_cols=True,
                   low_memory=False,
-                  skiprows=None,
+                  skip_rows=None,
                   skipfooter=0,
                   verbose=False,
                   mangle_dupe_cols=True,
@@ -436,8 +436,8 @@ cdef class TextReader:
         self.parser.error_bad_lines = int(error_bad_lines)
         self.parser.warn_bad_lines = int(warn_bad_lines)
 
-        self.skiprows = skiprows
-        if skiprows is not None:
+        self.skip_rows = skip_rows
+        if skip_rows is not None:
             self._make_skiprow_set()
 
         self.skipfooter = skipfooter
@@ -605,13 +605,13 @@ cdef class TextReader:
             self.parser.quotechar = ord(quote_char)
 
     cdef _make_skiprow_set(self):
-        if isinstance(self.skiprows, (int, np.integer)):
-            parser_set_skipfirstnrows(self.parser, self.skiprows)
-        elif not callable(self.skiprows):
-            for i in self.skiprows:
+        if isinstance(self.skip_rows, (int, np.integer)):
+            parser_set_skipfirstnrows(self.parser, self.skip_rows)
+        elif not callable(self.skip_rows):
+            for i in self.skip_rows:
                 parser_add_skiprow(self.parser, i)
         else:
-            self.parser.skipfunc = <PyObject *> self.skiprows
+            self.parser.skipfunc = <PyObject *> self.skip_rows
 
     cdef _setup_parser_source(self, source):
         cdef:

pandas/io/excel.py

@@ -130,7 +130,7 @@
 
     .. versionadded:: 0.19.0
 
-skiprows : list-like
+skip_rows : list-like
     Rows to skip at the beginning (0-indexed)
 nrows : int, default None
     Number of rows to parse
@@ -295,7 +295,7 @@ def read_excel(io,
                converters=None,
                true_values=None,
                false_values=None,
-               skiprows=None,
+               skip_rows=None,
                nrows=None,
                na_values=None,
                parse_dates=False,
@@ -330,7 +330,7 @@ def read_excel(io,
         converters=converters,
         true_values=true_values,
         false_values=false_values,
-        skiprows=skiprows,
+        skip_rows=skip_rows,
         nrows=nrows,
         na_values=na_values,
         parse_dates=parse_dates,
@@ -422,7 +422,7 @@ def parse(self,
               converters=None,
               true_values=None,
               false_values=None,
-              skiprows=None,
+              skip_rows=None,
               nrows=None,
               na_values=None,
               parse_dates=False,
@@ -457,7 +457,7 @@ def parse(self,
                                  converters=converters,
                                  true_values=true_values,
                                  false_values=false_values,
-                                 skiprows=skiprows,
+                                 skip_rows=skip_rows,
                                  nrows=nrows,
                                  na_values=na_values,
                                  parse_dates=parse_dates,
@@ -511,7 +511,7 @@ def _parse_excel(self,
                      dtype=None,
                      true_values=None,
                      false_values=None,
-                     skiprows=None,
+                     skip_rows=None,
                      nrows=None,
                      na_values=None,
                      verbose=False,
@@ -649,8 +649,8 @@ def _parse_cell(cell_contents, cell_typ):
                     header_names = []
                     control_row = [True] * len(data[0])
                     for row in header:
-                        if is_integer(skiprows):
-                            row += skiprows
+                        if is_integer(skip_rows):
+                            row += skip_rows
 
                         data[row], control_row = _fill_mi_header(
                             data[row], control_row)
@@ -687,7 +687,7 @@ def _parse_cell(cell_contents, cell_typ):
                                     dtype=dtype,
                                     true_values=true_values,
                                     false_values=false_values,
-                                    skiprows=skiprows,
+                                    skip_rows=skip_rows,
                                     nrows=nrows,
                                     na_values=na_values,
                                     parse_dates=parse_dates,

pandas/io/html.py

@@ -85,32 +85,36 @@ def _remove_whitespace(s, regex=_RE_WHITESPACE):
     return regex.sub(' ', s.strip())
 
 
-def _get_skiprows(skiprows):
+def _get_skiprows(skip_rows):
     """Get an iterator given an integer, slice or container.
 
     Parameters
     ----------
-    skiprows : int, slice, container
+    skip_rows : int, slice, container
         The iterator to use to skip rows; can also be a slice.
 
     Raises
     ------
     TypeError
-        * If `skiprows` is not a slice, integer, or Container
+        * If `skip_rows` is not a slice, integer, or Container
 
     Returns
     -------
     it : iterable
         A proper iterator to use to skip rows of a DataFrame.
     """
-    if isinstance(skiprows, slice):
-        return lrange(skiprows.start or 0, skiprows.stop, skiprows.step or 1)
-    elif isinstance(skiprows, numbers.Integral) or is_list_like(skiprows):
-        return skiprows
-    elif skiprows is None:
+    if isinstance(skip_rows, slice):
+        return lrange(
+            skip_rows.start or 0,
+            skip_rows.stop,
+            skip_rows.step or 1
+        )
+    elif isinstance(skip_rows, numbers.Integral) or is_list_like(skip_rows):
+        return skip_rows
+    elif skip_rows is None:
         return 0
     raise TypeError('%r is not a valid type for skipping rows' %
-                    type(skiprows).__name__)
+                    type(skip_rows).__name__)
 
 
 def _read(obj):
@@ -779,7 +783,7 @@ def _expand_elements(body):
 def _data_to_frame(**kwargs):
     head, body, foot = kwargs.pop('data')
     header = kwargs.pop('header')
-    kwargs['skiprows'] = _get_skiprows(kwargs['skiprows'])
+    kwargs['skip_rows'] = _get_skiprows(kwargs['skip_rows'])
     if head:
         body = head + body
 
@@ -922,7 +926,7 @@ def _parse(flavor, io, match, attrs, encoding, displayed_only, **kwargs):
 
 
 def read_html(io, match='.+', flavor=None, header=None, index_col=None,
-              skiprows=None, attrs=None, parse_dates=False,
+              skip_rows=None, attrs=None, parse_dates=False,
               tupleize_cols=None, thousands=',', encoding=None,
               decimal='.', converters=None, na_values=None,
               keep_default_na=True, displayed_only=True):
@@ -956,7 +960,7 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
     index_col : int or list-like or None, optional
         The column (or list of columns) to use to create the index.
 
-    skiprows : int or list-like or slice or None, optional
+    skip_rows : int or list-like or slice or None, optional
         0-based. Number of rows to skip after parsing the column integer. If a
         sequence of integers or a slice is given, will skip the rows indexed by
         that sequence.  Note that a single element sequence means 'skip the nth
@@ -1060,7 +1064,7 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
         .. versionadded:: 0.21.0
 
     Similar to :func:`~pandas.read_csv` the `header` argument is applied
-    **after** `skiprows` is applied.
+    **after** `skip_rows` is applied.
 
     This function will *always* return a list of :class:`DataFrame` *or*
     it will fail, e.g., it will *not* return an empty list.
@@ -1077,13 +1081,13 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
     _importers()
 
     # Type check here. We don't want to parse only to fail because of an
-    # invalid value of an integer skiprows.
-    if isinstance(skiprows, numbers.Integral) and skiprows < 0:
+    # invalid value of an integer skip_rows.
+    if isinstance(skip_rows, numbers.Integral) and skip_rows < 0:
         raise ValueError('cannot skip rows starting from the end of the '
                          'data (you passed a negative value)')
     _validate_header_arg(header)
     return _parse(flavor=flavor, io=io, match=match, header=header,
-                  index_col=index_col, skiprows=skiprows,
+                  index_col=index_col, skip_rows=skip_rows,
                   parse_dates=parse_dates, tupleize_cols=tupleize_cols,
                   thousands=thousands, attrs=attrs, encoding=encoding,
                   decimal=decimal, converters=converters, na_values=na_values,