diff --git a/ci/code_checks.sh b/ci/code_checks.sh
index fac5c211cdad8..f0772f72d63d4 100755
--- a/ci/code_checks.sh
+++ b/ci/code_checks.sh
@@ -122,6 +122,10 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
! grep -R --include="*.py" --include="*.pyx" --include="*.rst" -E "\.\. (autosummary|contents|currentmodule|deprecated|function|image|important|include|ipython|literalinclude|math|module|note|raw|seealso|toctree|versionadded|versionchanged|warning):[^:]" ./pandas ./doc/source
RET=$(($RET + $?)) ; echo $MSG "DONE"
+ MSG='Check that the deprecated `assert_raises_regex` is not used (`pytest.raises(match=pattern)` should be used instead)' ; echo $MSG
+ ! grep -R --exclude=*.pyc --exclude=testing.py --exclude=test_testing.py assert_raises_regex pandas
+ RET=$(($RET + $?)) ; echo $MSG "DONE"
+
MSG='Check for modules that pandas should not import' ; echo $MSG
python -c "
import sys
diff --git a/doc/source/io.rst b/doc/source/io.rst
index beb1c1daba962..34dc185c200e6 100644
--- a/doc/source/io.rst
+++ b/doc/source/io.rst
@@ -2854,6 +2854,11 @@ It is often the case that users will insert columns to do temporary computations
in Excel and you may not want to read in those columns. ``read_excel`` takes
a ``usecols`` keyword to allow you to specify a subset of columns to parse.
+.. deprecated:: 0.24.0
+
+Passing in an integer for ``usecols`` has been deprecated. Please pass in a list
+of ints from 0 to ``usecols`` inclusive instead.
+
If ``usecols`` is an integer, then it is assumed to indicate the last column
to be parsed.
diff --git a/doc/source/whatsnew/v0.18.1.txt b/doc/source/whatsnew/v0.18.1.txt
index 34921505a46bf..2445daebb580a 100644
--- a/doc/source/whatsnew/v0.18.1.txt
+++ b/doc/source/whatsnew/v0.18.1.txt
@@ -266,7 +266,7 @@ These changes conform sparse handling to return the correct types and work to ma
``SparseArray.take`` now returns a scalar for scalar input, ``SparseArray`` for others. Furthermore, it handles a negative indexer with the same rule as ``Index`` (:issue:`10560`, :issue:`12796`)
-.. ipython:: python
+.. code-block:: python
s = pd.SparseArray([np.nan, np.nan, 1, 2, 3, np.nan, 4, 5, np.nan, 6])
s.take(0)
diff --git a/doc/source/whatsnew/v0.24.0.txt b/doc/source/whatsnew/v0.24.0.txt
index 73fd526640212..20496c9fb3f31 100644
--- a/doc/source/whatsnew/v0.24.0.txt
+++ b/doc/source/whatsnew/v0.24.0.txt
@@ -970,6 +970,7 @@ Deprecations
- The class ``FrozenNDArray`` has been deprecated. When unpickling, ``FrozenNDArray`` will be unpickled to ``np.ndarray`` once this class is removed (:issue:`9031`)
- Deprecated the `nthreads` keyword of :func:`pandas.read_feather` in favor of
`use_threads` to reflect the changes in pyarrow 0.11.0. (:issue:`23053`)
+- :func:`pandas.read_excel` has deprecated accepting ``usecols`` as an integer. Please pass in a list of ints from 0 to ``usecols`` inclusive instead (:issue:`23527`)
- Constructing a :class:`TimedeltaIndex` from data with ``datetime64``-dtyped data is deprecated, will raise ``TypeError`` in a future version (:issue:`23539`)
.. _whatsnew_0240.deprecations.datetimelike_int_ops:
@@ -1298,6 +1299,7 @@ Notice how we now instead output ``np.nan`` itself instead of a stringified form
- :func:`read_excel()` will correctly show the deprecation warning for previously deprecated ``sheetname`` (:issue:`17994`)
- :func:`read_csv()` and func:`read_table()` will throw ``UnicodeError`` and not coredump on badly encoded strings (:issue:`22748`)
- :func:`read_csv()` will correctly parse timezone-aware datetimes (:issue:`22256`)
+- Bug in :func:`read_csv()` in which memory management was prematurely optimized for the C engine when the data was being read in chunks (:issue:`23509`)
- :func:`read_sas()` will parse numbers in sas7bdat-files that have width less than 8 bytes correctly. (:issue:`21616`)
- :func:`read_sas()` will correctly parse sas7bdat files with many columns (:issue:`22628`)
- :func:`read_sas()` will correctly parse sas7bdat files with data page types having also bit 7 set (so page type is 128 + 256 = 384) (:issue:`16615`)
diff --git a/pandas/_libs/parsers.pyx b/pandas/_libs/parsers.pyx
index 3870a55c22fd6..40aa03caa56eb 100644
--- a/pandas/_libs/parsers.pyx
+++ b/pandas/_libs/parsers.pyx
@@ -132,6 +132,7 @@ cdef extern from "parser/tokenizer.h":
int64_t *word_starts # where we are in the stream
int64_t words_len
int64_t words_cap
+ int64_t max_words_cap # maximum word cap encountered
char *pword_start # pointer to stream start of current field
int64_t word_start # position start of current field
diff --git a/pandas/_libs/src/parser/tokenizer.c b/pandas/_libs/src/parser/tokenizer.c
index 2fce241027d56..e46e1e85f1c81 100644
--- a/pandas/_libs/src/parser/tokenizer.c
+++ b/pandas/_libs/src/parser/tokenizer.c
@@ -197,6 +197,7 @@ int parser_init(parser_t *self) {
sz = sz ? sz : 1;
self->words = (char **)malloc(sz * sizeof(char *));
self->word_starts = (int64_t *)malloc(sz * sizeof(int64_t));
+ self->max_words_cap = sz;
self->words_cap = sz;
self->words_len = 0;
@@ -247,7 +248,7 @@ void parser_del(parser_t *self) {
}
static int make_stream_space(parser_t *self, size_t nbytes) {
- int64_t i, cap;
+ int64_t i, cap, length;
int status;
void *orig_ptr, *newptr;
@@ -287,8 +288,23 @@ static int make_stream_space(parser_t *self, size_t nbytes) {
*/
cap = self->words_cap;
+
+ /**
+ * If we are reading in chunks, we need to be aware of the maximum number
+ * of words we have seen in previous chunks (self->max_words_cap), so
+ * that way, we can properly allocate when reading subsequent ones.
+ *
+ * Otherwise, we risk a buffer overflow if we mistakenly under-allocate
+ * just because a recent chunk did not have as many words.
+ */
+ if (self->words_len + nbytes < self->max_words_cap) {
+ length = self->max_words_cap - nbytes;
+ } else {
+ length = self->words_len;
+ }
+
self->words =
- (char **)grow_buffer((void *)self->words, self->words_len,
+ (char **)grow_buffer((void *)self->words, length,
(int64_t*)&self->words_cap, nbytes,
sizeof(char *), &status);
TRACE(
@@ -1241,6 +1257,19 @@ int parser_trim_buffers(parser_t *self) {
int64_t i;
+ /**
+ * Before we free up space and trim, we should
+ * save how many words we saw when parsing, if
+ * it exceeds the maximum number we saw before.
+ *
+ * This is important for when we read in chunks,
+ * so that we can inform subsequent chunk parsing
+ * as to how many words we could possibly see.
+ */
+ if (self->words_cap > self->max_words_cap) {
+ self->max_words_cap = self->words_cap;
+ }
+
/* trim words, word_starts */
new_cap = _next_pow2(self->words_len) + 1;
if (new_cap < self->words_cap) {
diff --git a/pandas/_libs/src/parser/tokenizer.h b/pandas/_libs/src/parser/tokenizer.h
index 9fc3593aaaf5b..c32c061c7fa89 100644
--- a/pandas/_libs/src/parser/tokenizer.h
+++ b/pandas/_libs/src/parser/tokenizer.h
@@ -142,6 +142,7 @@ typedef struct parser_t {
int64_t *word_starts; // where we are in the stream
int64_t words_len;
int64_t words_cap;
+ int64_t max_words_cap; // maximum word cap encountered
char *pword_start; // pointer to stream start of current field
int64_t word_start; // position start of current field
diff --git a/pandas/core/arrays/datetimelike.py b/pandas/core/arrays/datetimelike.py
index 3fa4f503d2dd5..daf2dcccd284b 100644
--- a/pandas/core/arrays/datetimelike.py
+++ b/pandas/core/arrays/datetimelike.py
@@ -124,8 +124,12 @@ def asi8(self):
# do not cache or you'll create a memory leak
return self._data.view('i8')
- # ------------------------------------------------------------------
- # Array-like Methods
+ # ----------------------------------------------------------------
+ # Array-Like / EA-Interface Methods
+
+ @property
+ def nbytes(self):
+ return self._data.nbytes
@property
def shape(self):
diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
index b0485cc82f07f..a6f688fb0cf7a 100644
--- a/pandas/core/arrays/datetimes.py
+++ b/pandas/core/arrays/datetimes.py
@@ -385,7 +385,7 @@ def _resolution(self):
return libresolution.resolution(self.asi8, self.tz)
# ----------------------------------------------------------------
- # Array-like Methods
+ # Array-Like / EA-Interface Methods
def __array__(self, dtype=None):
if is_object_dtype(dtype):
diff --git a/pandas/core/arrays/period.py b/pandas/core/arrays/period.py
index 482968fdb4766..b343d42ef3b7c 100644
--- a/pandas/core/arrays/period.py
+++ b/pandas/core/arrays/period.py
@@ -272,10 +272,6 @@ def _concat_same_type(cls, to_concat):
# --------------------------------------------------------------------
# Data / Attributes
- @property
- def nbytes(self):
- # TODO(DatetimeArray): remove
- return self._data.nbytes
@cache_readonly
def dtype(self):
@@ -286,10 +282,6 @@ def _ndarray_values(self):
# Ordinals
return self._data
- @property
- def asi8(self):
- return self._data
-
@property
def freq(self):
"""Return the frequency object for this PeriodArray."""
@@ -330,6 +322,50 @@ def start_time(self):
def end_time(self):
return self.to_timestamp(how='end')
+ def to_timestamp(self, freq=None, how='start'):
+ """
+ Cast to DatetimeArray/Index.
+
+ Parameters
+ ----------
+ freq : string or DateOffset, optional
+ Target frequency. The default is 'D' for week or longer,
+ 'S' otherwise
+ how : {'s', 'e', 'start', 'end'}
+
+ Returns
+ -------
+ DatetimeArray/Index
+ """
+ from pandas.core.arrays import DatetimeArrayMixin
+
+ how = libperiod._validate_end_alias(how)
+
+ end = how == 'E'
+ if end:
+ if freq == 'B':
+ # roll forward to ensure we land on B date
+ adjust = Timedelta(1, 'D') - Timedelta(1, 'ns')
+ return self.to_timestamp(how='start') + adjust
+ else:
+ adjust = Timedelta(1, 'ns')
+ return (self + self.freq).to_timestamp(how='start') - adjust
+
+ if freq is None:
+ base, mult = frequencies.get_freq_code(self.freq)
+ freq = frequencies.get_to_timestamp_base(base)
+ else:
+ freq = Period._maybe_convert_freq(freq)
+
+ base, mult = frequencies.get_freq_code(freq)
+ new_data = self.asfreq(freq, how=how)
+
+ new_data = libperiod.periodarr_to_dt64arr(new_data.asi8, base)
+ return DatetimeArrayMixin(new_data, freq='infer')
+
+ # --------------------------------------------------------------------
+ # Array-like / EA-Interface Methods
+
def __repr__(self):
return '<{}>\n{}\nLength: {}, dtype: {}'.format(
self.__class__.__name__,
@@ -456,6 +492,8 @@ def value_counts(self, dropna=False):
name=result.index.name)
return Series(result.values, index=index, name=result.name)
+ # --------------------------------------------------------------------
+
def shift(self, periods=1):
"""
Shift values by desired number.
@@ -567,49 +605,9 @@ def asfreq(self, freq=None, how='E'):
return type(self)(new_data, freq=freq)
- def to_timestamp(self, freq=None, how='start'):
- """
- Cast to DatetimeArray/Index
-
- Parameters
- ----------
- freq : string or DateOffset, optional
- Target frequency. The default is 'D' for week or longer,
- 'S' otherwise
- how : {'s', 'e', 'start', 'end'}
-
- Returns
- -------
- DatetimeArray/Index
- """
- from pandas.core.arrays import DatetimeArrayMixin
-
- how = libperiod._validate_end_alias(how)
-
- end = how == 'E'
- if end:
- if freq == 'B':
- # roll forward to ensure we land on B date
- adjust = Timedelta(1, 'D') - Timedelta(1, 'ns')
- return self.to_timestamp(how='start') + adjust
- else:
- adjust = Timedelta(1, 'ns')
- return (self + self.freq).to_timestamp(how='start') - adjust
-
- if freq is None:
- base, mult = frequencies.get_freq_code(self.freq)
- freq = frequencies.get_to_timestamp_base(base)
- else:
- freq = Period._maybe_convert_freq(freq)
-
- base, mult = frequencies.get_freq_code(freq)
- new_data = self.asfreq(freq, how=how)
-
- new_data = libperiod.periodarr_to_dt64arr(new_data.asi8, base)
- return DatetimeArrayMixin(new_data, freq='infer')
-
# ------------------------------------------------------------------
# Formatting
+
def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
""" actually format my specific types """
# TODO(DatetimeArray): remove
@@ -630,9 +628,13 @@ def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
values = np.array([formatter(dt) for dt in values])
return values
+ # Delegation...
+ def strftime(self, date_format):
+ return self._format_native_types(date_format=date_format)
+
def repeat(self, repeats, *args, **kwargs):
"""
- Repeat elements of a Categorical.
+ Repeat elements of a PeriodArray.
See also
--------
@@ -643,10 +645,6 @@ def repeat(self, repeats, *args, **kwargs):
values = self._data.repeat(repeats)
return type(self)(values, self.freq)
- # Delegation...
- def strftime(self, date_format):
- return self._format_native_types(date_format=date_format)
-
def astype(self, dtype, copy=True):
# TODO: Figure out something better here...
# We have DatetimeLikeArrayMixin ->
diff --git a/pandas/core/arrays/sparse.py b/pandas/core/arrays/sparse.py
index a63b3fb53625f..672261c2a407e 100644
--- a/pandas/core/arrays/sparse.py
+++ b/pandas/core/arrays/sparse.py
@@ -284,6 +284,83 @@ def is_dtype(cls, dtype):
return True
return isinstance(dtype, np.dtype) or dtype == 'Sparse'
+ def update_dtype(self, dtype):
+ """Convert the SparseDtype to a new dtype.
+
+ This takes care of converting the ``fill_value``.
+
+ Parameters
+ ----------
+ dtype : Union[str, numpy.dtype, SparseDtype]
+ The new dtype to use.
+
+ * For a SparseDtype, it is simply returned
+ * For a NumPy dtype (or str), the current fill value
+ is converted to the new dtype, and a SparseDtype
+ with `dtype` and the new fill value is returned.
+
+ Returns
+ -------
+ SparseDtype
+ A new SparseDtype with the corret `dtype` and fill value
+ for that `dtype`.
+
+ Raises
+ ------
+ ValueError
+ When the current fill value cannot be converted to the
+ new `dtype` (e.g. trying to convert ``np.nan`` to an
+ integer dtype).
+
+
+ Examples
+ --------
+ >>> SparseDtype(int, 0).update_dtype(float)
+ Sparse[float64, 0.0]
+
+ >>> SparseDtype(int, 1).update_dtype(SparseDtype(float, np.nan))
+ Sparse[float64, nan]
+ """
+ cls = type(self)
+ dtype = pandas_dtype(dtype)
+
+ if not isinstance(dtype, cls):
+ fill_value = astype_nansafe(np.array(self.fill_value),
+ dtype).item()
+ dtype = cls(dtype, fill_value=fill_value)
+
+ return dtype
+
+ @property
+ def _subtype_with_str(self):
+ """
+ Whether the SparseDtype's subtype should be considered ``str``.
+
+ Typically, pandas will store string data in an object-dtype array.
+ When converting values to a dtype, e.g. in ``.astype``, we need to
+ be more specific, we need the actual underlying type.
+
+ Returns
+ -------
+
+ >>> SparseDtype(int, 1)._subtype_with_str
+ dtype('int64')
+
+ >>> SparseDtype(object, 1)._subtype_with_str
+ dtype('O')
+
+ >>> dtype = SparseDtype(str, '')
+ >>> dtype.subtype
+ dtype('O')
+
+ >>> dtype._subtype_with_str
+ str
+ """
+ if isinstance(self.fill_value, compat.string_types):
+ return type(self.fill_value)
+ return self.subtype
+
+
# ----------------------------------------------------------------------------
# Array
@@ -614,7 +691,7 @@ def __array__(self, dtype=None, copy=True):
# Can't put pd.NaT in a datetime64[ns]
fill_value = np.datetime64('NaT')
try:
- dtype = np.result_type(self.sp_values.dtype, fill_value)
+ dtype = np.result_type(self.sp_values.dtype, type(fill_value))
except TypeError:
dtype = object
@@ -996,7 +1073,7 @@ def _take_with_fill(self, indices, fill_value=None):
if len(self) == 0:
# Empty... Allow taking only if all empty
if (indices == -1).all():
- dtype = np.result_type(self.sp_values, fill_value)
+ dtype = np.result_type(self.sp_values, type(fill_value))
taken = np.empty_like(indices, dtype=dtype)
taken.fill(fill_value)
return taken
@@ -1009,7 +1086,7 @@ def _take_with_fill(self, indices, fill_value=None):
if self.sp_index.npoints == 0:
# Avoid taking from the empty self.sp_values
taken = np.full(sp_indexer.shape, fill_value=fill_value,
- dtype=np.result_type(fill_value))
+ dtype=np.result_type(type(fill_value)))
else:
taken = self.sp_values.take(sp_indexer)
@@ -1030,12 +1107,13 @@ def _take_with_fill(self, indices, fill_value=None):
result_type = taken.dtype
if m0.any():
- result_type = np.result_type(result_type, self.fill_value)
+ result_type = np.result_type(result_type,
+ type(self.fill_value))
taken = taken.astype(result_type)
taken[old_fill_indices] = self.fill_value
if m1.any():
- result_type = np.result_type(result_type, fill_value)
+ result_type = np.result_type(result_type, type(fill_value))
taken = taken.astype(result_type)
taken[new_fill_indices] = fill_value
@@ -1061,7 +1139,7 @@ def _take_without_fill(self, indices):
# edge case in take...
# I think just return
out = np.full(indices.shape, self.fill_value,
- dtype=np.result_type(self.fill_value))
+ dtype=np.result_type(type(self.fill_value)))
arr, sp_index, fill_value = make_sparse(out,
fill_value=self.fill_value)
return type(self)(arr, sparse_index=sp_index,
@@ -1073,7 +1151,7 @@ def _take_without_fill(self, indices):
if fillable.any():
# TODO: may need to coerce array to fill value
- result_type = np.result_type(taken, self.fill_value)
+ result_type = np.result_type(taken, type(self.fill_value))
taken = taken.astype(result_type)
taken[fillable] = self.fill_value
@@ -1093,7 +1171,9 @@ def _concat_same_type(cls, to_concat):
fill_value = fill_values[0]
- if len(set(fill_values)) > 1:
+ # np.nan isn't a singleton, so we may end up with multiple
+ # NaNs here, so we ignore tha all NA case too.
+ if not (len(set(fill_values)) == 1 or isna(fill_values).all()):
warnings.warn("Concatenating sparse arrays with multiple fill "
"values: '{}'. Picking the first and "
"converting the rest.".format(fill_values),
@@ -1212,13 +1292,10 @@ def astype(self, dtype=None, copy=True):
IntIndex
Indices: array([2, 3], dtype=int32)
"""
- dtype = pandas_dtype(dtype)
-
- if not isinstance(dtype, SparseDtype):
- dtype = SparseDtype(dtype, fill_value=self.fill_value)
-
+ dtype = self.dtype.update_dtype(dtype)
+ subtype = dtype._subtype_with_str
sp_values = astype_nansafe(self.sp_values,
- dtype.subtype,
+ subtype,
copy=copy)
if sp_values is self.sp_values and copy:
sp_values = sp_values.copy()
diff --git a/pandas/core/arrays/timedeltas.py b/pandas/core/arrays/timedeltas.py
index 1f78e0c00bf00..9dbdd6ff8b562 100644
--- a/pandas/core/arrays/timedeltas.py
+++ b/pandas/core/arrays/timedeltas.py
@@ -190,6 +190,9 @@ def _generate_range(cls, start, end, periods, freq, closed=None):
return cls._simple_new(index, freq=freq)
+ # ----------------------------------------------------------------
+ # Array-Like / EA-Interface Methods
+
# ----------------------------------------------------------------
# Arithmetic Methods
@@ -412,20 +415,25 @@ def sequence_to_td64ns(data, copy=False, unit="ns", errors="raise"):
array : list-like
copy : bool, default False
unit : str, default "ns"
+ The timedelta unit to treat integers as multiples of.
errors : {"raise", "coerce", "ignore"}, default "raise"
+ How to handle elements that cannot be converted to timedelta64[ns].
+ See ``pandas.to_timedelta`` for details.
Returns
-------
- ndarray[timedelta64[ns]]
+ converted : numpy.ndarray
+ The sequence converted to a numpy array with dtype ``timedelta64[ns]``.
inferred_freq : Tick or None
+ The inferred frequency of the sequence.
Raises
------
- ValueError : data cannot be converted to timedelta64[ns]
+ ValueError : Data cannot be converted to timedelta64[ns].
Notes
-----
- Unlike `pandas.to_timedelta`, if setting `errors=ignore` will not cause
+ Unlike `pandas.to_timedelta`, if setting ``errors=ignore`` will not cause
errors to be ignored; they are caught and subsequently ignored at a
higher level.
"""
@@ -497,12 +505,13 @@ def ints_to_td64ns(data, unit="ns"):
Parameters
----------
- data : np.ndarray with integer-dtype
+ data : numpy.ndarray with integer-dtype
unit : str, default "ns"
+ The timedelta unit to treat integers as multiples of.
Returns
-------
- ndarray[timedelta64[ns]]
+ numpy.ndarray : timedelta64[ns] array converted from data
bool : whether a copy was made
"""
copy_made = False
@@ -538,15 +547,18 @@ def objects_to_td64ns(data, unit="ns", errors="raise"):
----------
data : ndarray or Index
unit : str, default "ns"
+ The timedelta unit to treat integers as multiples of.
errors : {"raise", "coerce", "ignore"}, default "raise"
+ How to handle elements that cannot be converted to timedelta64[ns].
+ See ``pandas.to_timedelta`` for details.
Returns
-------
- ndarray[timedelta64[ns]]
+ numpy.ndarray : timedelta64[ns] array converted from data
Raises
------
- ValueError : data cannot be converted to timedelta64[ns]
+ ValueError : Data cannot be converted to timedelta64[ns].
Notes
-----
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index 34f25c5634d5b..2c7f6ae8e3533 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -11,6 +11,8 @@
import pandas as pd
from pandas._libs import properties, Timestamp, iNaT
+from pandas.errors import AbstractMethodError
+
from pandas.core.dtypes.common import (
ensure_int64,
ensure_object,
@@ -200,7 +202,7 @@ def _constructor(self):
"""Used when a manipulation result has the same dimensions as the
original.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def __unicode__(self):
# unicode representation based upon iterating over self
@@ -221,7 +223,7 @@ def _constructor_sliced(self):
"""Used when a manipulation result has one lower dimension(s) as the
original, such as DataFrame single columns slicing.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
@property
def _constructor_expanddim(self):
@@ -2884,7 +2886,7 @@ def _iget_item_cache(self, item):
return lower
def _box_item_values(self, key, values):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _maybe_cache_changed(self, item, value):
"""The object has called back to us saying maybe it has changed.
diff --git a/pandas/core/groupby/generic.py b/pandas/core/groupby/generic.py
index 451f1199ac8e6..b0477c7d3a8ad 100644
--- a/pandas/core/groupby/generic.py
+++ b/pandas/core/groupby/generic.py
@@ -18,6 +18,7 @@
import pandas.compat as compat
from pandas.compat import lzip, map
from pandas.compat.numpy import _np_version_under1p13
+from pandas.errors import AbstractMethodError
from pandas.util._decorators import Appender, Substitution
from pandas.core.dtypes.cast import maybe_downcast_to_dtype
@@ -240,7 +241,7 @@ def _aggregate_generic(self, func, *args, **kwargs):
return self._wrap_generic_output(result, obj)
def _wrap_aggregated_output(self, output, names=None):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _aggregate_item_by_item(self, func, *args, **kwargs):
# only for axis==0
@@ -1659,4 +1660,4 @@ def _aggregate_item_by_item(self, func, *args, **kwargs):
raise ValueError("axis value must be greater than 0")
def _wrap_aggregated_output(self, output, names=None):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
index ea7507799fa9a..12327e1cf148e 100644
--- a/pandas/core/groupby/groupby.py
+++ b/pandas/core/groupby/groupby.py
@@ -20,6 +20,7 @@ class providing the base-class of operations.
import pandas.compat as compat
from pandas.compat import callable, range, set_function_name, zip
from pandas.compat.numpy import function as nv
+from pandas.errors import AbstractMethodError
from pandas.util._decorators import Appender, Substitution, cache_readonly
from pandas.util._validators import validate_kwargs
@@ -706,7 +707,7 @@ def _iterate_slices(self):
yield self._selection_name, self._selected_obj
def transform(self, func, *args, **kwargs):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _cumcount_array(self, ascending=True):
"""
@@ -861,7 +862,7 @@ def _python_agg_general(self, func, *args, **kwargs):
return self._wrap_aggregated_output(output)
def _wrap_applied_output(self, *args, **kwargs):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _concat_objects(self, keys, values, not_indexed_same=False):
from pandas.core.reshape.concat import concat
diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py
index 390334a89cbfe..125bd9a5e855d 100644
--- a/pandas/core/groupby/ops.py
+++ b/pandas/core/groupby/ops.py
@@ -13,6 +13,7 @@
from pandas._libs import NaT, groupby as libgroupby, iNaT, lib, reduction
from pandas.compat import lzip, range, zip
+from pandas.errors import AbstractMethodError
from pandas.util._decorators import cache_readonly
from pandas.core.dtypes.common import (
@@ -841,7 +842,7 @@ def _chop(self, sdata, slice_obj):
return sdata.iloc[slice_obj]
def apply(self, f):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
class SeriesSplitter(DataSplitter):
diff --git a/pandas/core/indexes/datetimelike.py b/pandas/core/indexes/datetimelike.py
index 59429488a7c2f..4547f47314bad 100644
--- a/pandas/core/indexes/datetimelike.py
+++ b/pandas/core/indexes/datetimelike.py
@@ -4,44 +4,33 @@
"""
import warnings
-from pandas import compat
-from pandas.compat.numpy import function as nv
-from pandas.core.tools.timedeltas import to_timedelta
-
import numpy as np
-from pandas._libs import lib, iNaT, NaT
-from pandas._libs.tslibs.timestamps import round_nsint64, RoundTo
+from pandas._libs import NaT, iNaT, lib
+from pandas._libs.tslibs.timestamps import RoundTo, round_nsint64
+import pandas.compat as compat
+from pandas.compat.numpy import function as nv
+from pandas.errors import AbstractMethodError
+from pandas.util._decorators import Appender, cache_readonly
from pandas.core.dtypes.common import (
- ensure_int64,
- is_dtype_equal,
- is_float,
- is_integer,
- is_list_like,
- is_scalar,
- is_bool_dtype,
- is_period_dtype,
- is_categorical_dtype,
- is_datetime_or_timedelta_dtype,
- is_float_dtype,
- is_integer_dtype,
- is_object_dtype,
- is_string_dtype)
-from pandas.core.dtypes.generic import (
- ABCIndex, ABCSeries, ABCIndexClass)
+ ensure_int64, is_bool_dtype, is_categorical_dtype,
+ is_datetime_or_timedelta_dtype, is_dtype_equal, is_float, is_float_dtype,
+ is_integer, is_integer_dtype, is_list_like, is_object_dtype,
+ is_period_dtype, is_scalar, is_string_dtype)
+import pandas.core.dtypes.concat as _concat
+from pandas.core.dtypes.generic import ABCIndex, ABCIndexClass, ABCSeries
from pandas.core.dtypes.missing import isna
-from pandas.core import common as com, algorithms, ops
-
-import pandas.io.formats.printing as printing
+from pandas.core import algorithms, ops
from pandas.core.arrays import PeriodArray
from pandas.core.arrays.datetimelike import DatetimeLikeArrayMixin
+import pandas.core.indexes.base as ibase
from pandas.core.indexes.base import Index, _index_shared_docs
-from pandas.util._decorators import Appender, cache_readonly
-import pandas.core.dtypes.concat as _concat
+from pandas.core.tools.timedeltas import to_timedelta
+
+import pandas.io.formats.printing as printing
-import pandas.core.indexes.base as ibase
_index_doc_kwargs = dict(ibase._index_doc_kwargs)
@@ -543,7 +532,7 @@ def argmax(self, axis=None, *args, **kwargs):
@property
def _formatter_func(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _format_attrs(self):
"""
diff --git a/pandas/core/indexes/datetimes.py b/pandas/core/indexes/datetimes.py
index c82cff19573e3..b754b2705d034 100644
--- a/pandas/core/indexes/datetimes.py
+++ b/pandas/core/indexes/datetimes.py
@@ -1,57 +1,45 @@
# pylint: disable=E1101
from __future__ import division
+
+from datetime import datetime, time, timedelta
import operator
import warnings
-from datetime import time, datetime, timedelta
import numpy as np
from pytz import utc
-from pandas.core.base import _shared_docs
+from pandas._libs import (
+ Timestamp, index as libindex, join as libjoin, lib, tslib as libts)
+from pandas._libs.tslibs import (
+ ccalendar, conversion, fields, parsing, timezones)
+import pandas.compat as compat
+from pandas.util._decorators import Appender, Substitution, cache_readonly
from pandas.core.dtypes.common import (
- _INT64_DTYPE,
- _NS_DTYPE,
- is_datetime64_dtype,
- is_datetimetz,
- is_dtype_equal,
- is_integer,
- is_float,
- is_integer_dtype,
- is_datetime64_ns_dtype,
- is_period_dtype,
- is_string_like,
- is_list_like,
- is_scalar,
- pandas_dtype,
- ensure_int64)
+ _INT64_DTYPE, _NS_DTYPE, ensure_int64, is_datetime64_dtype,
+ is_datetime64_ns_dtype, is_datetimetz, is_dtype_equal, is_float,
+ is_integer, is_integer_dtype, is_list_like, is_period_dtype, is_scalar,
+ is_string_like, pandas_dtype)
+import pandas.core.dtypes.concat as _concat
from pandas.core.dtypes.generic import ABCSeries
from pandas.core.dtypes.missing import isna
-import pandas.core.dtypes.concat as _concat
-from pandas.core.arrays.datetimes import DatetimeArrayMixin, _to_m8
from pandas.core.arrays import datetimelike as dtl
-
+from pandas.core.arrays.datetimes import (
+ DatetimeArrayMixin as DatetimeArray, _to_m8)
+from pandas.core.base import _shared_docs
+import pandas.core.common as com
from pandas.core.indexes.base import Index, _index_shared_docs
+from pandas.core.indexes.datetimelike import (
+ DatelikeOps, DatetimeIndexOpsMixin, TimelikeOps, wrap_array_method,
+ wrap_field_accessor)
from pandas.core.indexes.numeric import Int64Index
from pandas.core.ops import get_op_result_name
-import pandas.compat as compat
-from pandas.tseries.frequencies import to_offset, Resolution
-from pandas.core.indexes.datetimelike import (
- DatelikeOps, TimelikeOps, DatetimeIndexOpsMixin,
- wrap_field_accessor, wrap_array_method)
-from pandas.tseries.offsets import (
- CDay, prefix_mapping)
-
-from pandas.util._decorators import Appender, cache_readonly, Substitution
-import pandas.core.common as com
-import pandas.tseries.offsets as offsets
import pandas.core.tools.datetimes as tools
-from pandas._libs import (lib, index as libindex, tslib as libts,
- join as libjoin, Timestamp)
-from pandas._libs.tslibs import (timezones, conversion, fields, parsing,
- ccalendar)
+from pandas.tseries import offsets
+from pandas.tseries.frequencies import Resolution, to_offset
+from pandas.tseries.offsets import CDay, prefix_mapping
def _new_DatetimeIndex(cls, d):
@@ -68,7 +56,7 @@ def _new_DatetimeIndex(cls, d):
return result
-class DatetimeIndex(DatetimeArrayMixin, DatelikeOps, TimelikeOps,
+class DatetimeIndex(DatetimeArray, DatelikeOps, TimelikeOps,
DatetimeIndexOpsMixin, Int64Index):
"""
Immutable ndarray of datetime64 data, represented internally as int64, and
@@ -182,8 +170,6 @@ class DatetimeIndex(DatetimeArrayMixin, DatelikeOps, TimelikeOps,
pandas.to_datetime : Convert argument to datetime
"""
- _resolution = cache_readonly(DatetimeArrayMixin._resolution.fget)
-
_typ = 'datetimeindex'
_join_precedence = 10
@@ -227,8 +213,6 @@ def _join_i8_wrapper(joinf, **kwargs):
_is_numeric_dtype = False
_infer_as_myclass = True
- _timezone = cache_readonly(DatetimeArrayMixin._timezone.fget)
- is_normalized = cache_readonly(DatetimeArrayMixin.is_normalized.fget)
# --------------------------------------------------------------------
# Constructors
@@ -268,8 +252,7 @@ def __new__(cls, data=None,
# if dtype has an embedded tz, capture it
tz = dtl.validate_tz_from_dtype(dtype, tz)
- if not isinstance(data, (np.ndarray, Index, ABCSeries,
- DatetimeArrayMixin)):
+ if not isinstance(data, (np.ndarray, Index, ABCSeries, DatetimeArray)):
# other iterable of some kind
if not isinstance(data, (list, tuple)):
data = list(data)
@@ -283,7 +266,7 @@ def __new__(cls, data=None,
data = tools.to_datetime(data, dayfirst=dayfirst,
yearfirst=yearfirst)
- if isinstance(data, DatetimeArrayMixin):
+ if isinstance(data, DatetimeArray):
if tz is None:
tz = data.tz
elif data.tz is None:
@@ -1125,43 +1108,47 @@ def slice_indexer(self, start=None, end=None, step=None, kind=None):
# --------------------------------------------------------------------
# Wrapping DatetimeArray
- year = wrap_field_accessor(DatetimeArrayMixin.year)
- month = wrap_field_accessor(DatetimeArrayMixin.month)
- day = wrap_field_accessor(DatetimeArrayMixin.day)
- hour = wrap_field_accessor(DatetimeArrayMixin.hour)
- minute = wrap_field_accessor(DatetimeArrayMixin.minute)
- second = wrap_field_accessor(DatetimeArrayMixin.second)
- microsecond = wrap_field_accessor(DatetimeArrayMixin.microsecond)
- nanosecond = wrap_field_accessor(DatetimeArrayMixin.nanosecond)
- weekofyear = wrap_field_accessor(DatetimeArrayMixin.weekofyear)
+ _timezone = cache_readonly(DatetimeArray._timezone.fget)
+ is_normalized = cache_readonly(DatetimeArray.is_normalized.fget)
+ _resolution = cache_readonly(DatetimeArray._resolution.fget)
+
+ year = wrap_field_accessor(DatetimeArray.year)
+ month = wrap_field_accessor(DatetimeArray.month)
+ day = wrap_field_accessor(DatetimeArray.day)
+ hour = wrap_field_accessor(DatetimeArray.hour)
+ minute = wrap_field_accessor(DatetimeArray.minute)
+ second = wrap_field_accessor(DatetimeArray.second)
+ microsecond = wrap_field_accessor(DatetimeArray.microsecond)
+ nanosecond = wrap_field_accessor(DatetimeArray.nanosecond)
+ weekofyear = wrap_field_accessor(DatetimeArray.weekofyear)
week = weekofyear
- dayofweek = wrap_field_accessor(DatetimeArrayMixin.dayofweek)
+ dayofweek = wrap_field_accessor(DatetimeArray.dayofweek)
weekday = dayofweek
- weekday_name = wrap_field_accessor(DatetimeArrayMixin.weekday_name)
+ weekday_name = wrap_field_accessor(DatetimeArray.weekday_name)
- dayofyear = wrap_field_accessor(DatetimeArrayMixin.dayofyear)
- quarter = wrap_field_accessor(DatetimeArrayMixin.quarter)
- days_in_month = wrap_field_accessor(DatetimeArrayMixin.days_in_month)
+ dayofyear = wrap_field_accessor(DatetimeArray.dayofyear)
+ quarter = wrap_field_accessor(DatetimeArray.quarter)
+ days_in_month = wrap_field_accessor(DatetimeArray.days_in_month)
daysinmonth = days_in_month
- is_month_start = wrap_field_accessor(DatetimeArrayMixin.is_month_start)
- is_month_end = wrap_field_accessor(DatetimeArrayMixin.is_month_end)
- is_quarter_start = wrap_field_accessor(DatetimeArrayMixin.is_quarter_start)
- is_quarter_end = wrap_field_accessor(DatetimeArrayMixin.is_quarter_end)
- is_year_start = wrap_field_accessor(DatetimeArrayMixin.is_year_start)
- is_year_end = wrap_field_accessor(DatetimeArrayMixin.is_year_end)
- is_leap_year = wrap_field_accessor(DatetimeArrayMixin.is_leap_year)
-
- tz_localize = wrap_array_method(DatetimeArrayMixin.tz_localize, True)
- tz_convert = wrap_array_method(DatetimeArrayMixin.tz_convert, True)
- to_perioddelta = wrap_array_method(DatetimeArrayMixin.to_perioddelta,
+ is_month_start = wrap_field_accessor(DatetimeArray.is_month_start)
+ is_month_end = wrap_field_accessor(DatetimeArray.is_month_end)
+ is_quarter_start = wrap_field_accessor(DatetimeArray.is_quarter_start)
+ is_quarter_end = wrap_field_accessor(DatetimeArray.is_quarter_end)
+ is_year_start = wrap_field_accessor(DatetimeArray.is_year_start)
+ is_year_end = wrap_field_accessor(DatetimeArray.is_year_end)
+ is_leap_year = wrap_field_accessor(DatetimeArray.is_leap_year)
+
+ tz_localize = wrap_array_method(DatetimeArray.tz_localize, True)
+ tz_convert = wrap_array_method(DatetimeArray.tz_convert, True)
+ to_perioddelta = wrap_array_method(DatetimeArray.to_perioddelta,
False)
- to_period = wrap_array_method(DatetimeArrayMixin.to_period, True)
- normalize = wrap_array_method(DatetimeArrayMixin.normalize, True)
- to_julian_date = wrap_array_method(DatetimeArrayMixin.to_julian_date,
+ to_period = wrap_array_method(DatetimeArray.to_period, True)
+ normalize = wrap_array_method(DatetimeArray.normalize, True)
+ to_julian_date = wrap_array_method(DatetimeArray.to_julian_date,
False)
- month_name = wrap_array_method(DatetimeArrayMixin.month_name, True)
- day_name = wrap_array_method(DatetimeArrayMixin.day_name, True)
+ month_name = wrap_array_method(DatetimeArray.month_name, True)
+ day_name = wrap_array_method(DatetimeArray.day_name, True)
# --------------------------------------------------------------------
diff --git a/pandas/core/indexes/period.py b/pandas/core/indexes/period.py
index 128068959ebd3..7890f03a1eba7 100644
--- a/pandas/core/indexes/period.py
+++ b/pandas/core/indexes/period.py
@@ -256,8 +256,12 @@ def _simple_new(cls, values, name=None, freq=None, **kwargs):
result._reset_identity()
return result
+ # ------------------------------------------------------------------------
+ # Wrapping PeriodArray
+
# ------------------------------------------------------------------------
# Data
+
@property
def _ndarray_values(self):
return self._data._ndarray_values
@@ -361,13 +365,6 @@ def asfreq(self, freq=None, how='E'):
result = self._data.asfreq(freq=freq, how=how)
return self._simple_new(result, name=self.name)
- def _nat_new(self, box=True):
- # TODO(DatetimeArray): remove this
- result = self._data._nat_new(box=box)
- if box:
- result = self._simple_new(result, name=self.name)
- return result
-
def to_timestamp(self, freq=None, how='start'):
from pandas import DatetimeIndex
result = self._data.to_timestamp(freq=freq, how=how)
@@ -425,6 +422,7 @@ def _maybe_convert_timedelta(self, other):
# ------------------------------------------------------------------------
# Indexing
+
@cache_readonly
def _engine(self):
return self._engine_type(lambda: self, len(self))
diff --git a/pandas/core/indexes/timedeltas.py b/pandas/core/indexes/timedeltas.py
index 35e17c7400892..d9625d38b85de 100644
--- a/pandas/core/indexes/timedeltas.py
+++ b/pandas/core/indexes/timedeltas.py
@@ -2,44 +2,36 @@
from datetime import datetime
import numpy as np
+
+from pandas._libs import (
+ NaT, Timedelta, index as libindex, join as libjoin, lib)
+import pandas.compat as compat
+from pandas.util._decorators import Appender, Substitution
+
from pandas.core.dtypes.common import (
- _TD_DTYPE,
- is_integer,
- is_float,
- is_list_like,
- is_scalar,
- is_timedelta64_dtype,
- is_timedelta64_ns_dtype,
- pandas_dtype,
- ensure_int64)
+ _TD_DTYPE, ensure_int64, is_float, is_integer, is_list_like, is_scalar,
+ is_timedelta64_dtype, is_timedelta64_ns_dtype, pandas_dtype)
+import pandas.core.dtypes.concat as _concat
from pandas.core.dtypes.missing import isna
+from pandas.core.arrays import datetimelike as dtl
from pandas.core.arrays.timedeltas import (
- TimedeltaArrayMixin, _is_convertible_to_td, _to_m8,
+ TimedeltaArrayMixin as TimedeltaArray, _is_convertible_to_td, _to_m8,
sequence_to_td64ns)
-from pandas.core.arrays import datetimelike as dtl
-
-from pandas.core.indexes.base import Index
-from pandas.core.indexes.numeric import Int64Index
-import pandas.compat as compat
-
-from pandas.tseries.frequencies import to_offset
from pandas.core.base import _shared_docs
-from pandas.core.indexes.base import _index_shared_docs
import pandas.core.common as com
-from pandas.core.ops import get_op_result_name
-import pandas.core.dtypes.concat as _concat
-from pandas.util._decorators import Appender, Substitution
+from pandas.core.indexes.base import Index, _index_shared_docs
from pandas.core.indexes.datetimelike import (
- TimelikeOps, DatetimeIndexOpsMixin, wrap_arithmetic_op,
- wrap_array_method, wrap_field_accessor)
-from pandas.core.tools.timedeltas import (
- _coerce_scalar_to_timedelta_type)
-from pandas._libs import (lib, index as libindex,
- join as libjoin, Timedelta, NaT)
+ DatetimeIndexOpsMixin, TimelikeOps, wrap_arithmetic_op, wrap_array_method,
+ wrap_field_accessor)
+from pandas.core.indexes.numeric import Int64Index
+from pandas.core.ops import get_op_result_name
+from pandas.core.tools.timedeltas import _coerce_scalar_to_timedelta_type
+
+from pandas.tseries.frequencies import to_offset
-class TimedeltaIndex(TimedeltaArrayMixin, DatetimeIndexOpsMixin,
+class TimedeltaIndex(TimedeltaArray, DatetimeIndexOpsMixin,
TimelikeOps, Int64Index):
"""
Immutable ndarray of timedelta64 data, represented internally as int64, and
@@ -223,8 +215,7 @@ def _maybe_update_attributes(self, attrs):
return attrs
def _evaluate_with_timedelta_like(self, other, op):
- result = TimedeltaArrayMixin._evaluate_with_timedelta_like(self, other,
- op)
+ result = TimedeltaArray._evaluate_with_timedelta_like(self, other, op)
return wrap_arithmetic_op(self, other, result)
def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
@@ -236,12 +227,12 @@ def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
# -------------------------------------------------------------------
# Wrapping TimedeltaArray
- days = wrap_field_accessor(TimedeltaArrayMixin.days)
- seconds = wrap_field_accessor(TimedeltaArrayMixin.seconds)
- microseconds = wrap_field_accessor(TimedeltaArrayMixin.microseconds)
- nanoseconds = wrap_field_accessor(TimedeltaArrayMixin.nanoseconds)
+ days = wrap_field_accessor(TimedeltaArray.days)
+ seconds = wrap_field_accessor(TimedeltaArray.seconds)
+ microseconds = wrap_field_accessor(TimedeltaArray.microseconds)
+ nanoseconds = wrap_field_accessor(TimedeltaArray.nanoseconds)
- total_seconds = wrap_array_method(TimedeltaArrayMixin.total_seconds, True)
+ total_seconds = wrap_array_method(TimedeltaArray.total_seconds, True)
# -------------------------------------------------------------------
diff --git a/pandas/io/common.py b/pandas/io/common.py
index 155cf566b4c40..3a67238a66450 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -10,12 +10,11 @@
import pandas.compat as compat
from pandas.compat import BytesIO, StringIO, string_types, text_type
from pandas.errors import ( # noqa
- DtypeWarning, EmptyDataError, ParserError, ParserWarning)
+ AbstractMethodError, DtypeWarning, EmptyDataError, ParserError,
+ ParserWarning)
from pandas.core.dtypes.common import is_file_like, is_number
-import pandas.core.common as com
-
from pandas.io.formats.printing import pprint_thing
# gh-12665: Alias for now and remove later.
@@ -67,7 +66,7 @@ def __iter__(self):
return self
def __next__(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
if not compat.PY3:
diff --git a/pandas/io/excel.py b/pandas/io/excel.py
index 2e93c237bb7ea..c25a7670cce44 100644
--- a/pandas/io/excel.py
+++ b/pandas/io/excel.py
@@ -95,6 +95,10 @@
usecols : int, str, list-like, or callable default None
* If None, then parse all columns,
* If int, then indicates last column to be parsed
+
+ .. deprecated:: 0.24.0
+ Pass in a list of ints instead from 0 to `usecols` inclusive.
+
* If string, then indicates comma separated list of Excel column letters
and column ranges (e.g. "A:E" or "A,C,E:F"). Ranges are inclusive of
both sides.
@@ -778,6 +782,10 @@ def _maybe_convert_usecols(usecols):
return usecols
if is_integer(usecols):
+ warnings.warn(("Passing in an integer for `usecols` has been "
+ "deprecated. Please pass in a list of ints from "
+ "0 to `usecols` inclusive instead."),
+ FutureWarning, stacklevel=2)
return lrange(usecols + 1)
if isinstance(usecols, compat.string_types):
diff --git a/pandas/io/html.py b/pandas/io/html.py
index bcbb07c6dddfb..c967bdd29df1f 100644
--- a/pandas/io/html.py
+++ b/pandas/io/html.py
@@ -12,12 +12,11 @@
from pandas.compat import (
binary_type, iteritems, lmap, lrange, raise_with_traceback, string_types,
u)
-from pandas.errors import EmptyDataError
+from pandas.errors import AbstractMethodError, EmptyDataError
from pandas.core.dtypes.common import is_list_like
from pandas import Series
-import pandas.core.common as com
from pandas.io.common import _is_url, _validate_header_arg, urlopen
from pandas.io.formats.printing import pprint_thing
@@ -256,7 +255,7 @@ def _text_getter(self, obj):
text : str or unicode
The text from an individual DOM node.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _parse_td(self, obj):
"""Return the td elements from a row element.
@@ -271,7 +270,7 @@ def _parse_td(self, obj):
list of node-like
These are the elements of each row, i.e., the columns.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _parse_thead_tr(self, table):
"""
@@ -286,7 +285,7 @@ def _parse_thead_tr(self, table):
list of node-like
These are the row elements of a table.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _parse_tbody_tr(self, table):
"""
@@ -305,7 +304,7 @@ def _parse_tbody_tr(self, table):
list of node-like
These are the
row elements of a table.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _parse_tfoot_tr(self, table):
"""
@@ -320,7 +319,7 @@ def _parse_tfoot_tr(self, table):
list of node-like
These are the
row elements of a table.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _parse_tables(self, doc, match, attrs):
"""
@@ -346,7 +345,7 @@ def _parse_tables(self, doc, match, attrs):
list of node-like
HTML elements to be parsed into raw data.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _equals_tag(self, obj, tag):
"""
@@ -365,7 +364,7 @@ def _equals_tag(self, obj, tag):
boolean
Whether `obj`'s tag name is `tag`
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _build_doc(self):
"""
@@ -376,7 +375,7 @@ def _build_doc(self):
node-like
The DOM from which to parse the table element.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _parse_thead_tbody_tfoot(self, table_html):
"""
diff --git a/pandas/io/json/json.py b/pandas/io/json/json.py
index af7b390de213d..4453416a97f89 100644
--- a/pandas/io/json/json.py
+++ b/pandas/io/json/json.py
@@ -7,11 +7,11 @@
import pandas._libs.json as json
from pandas._libs.tslibs import iNaT
from pandas.compat import StringIO, long, to_str, u
+from pandas.errors import AbstractMethodError
from pandas.core.dtypes.common import is_period_dtype
from pandas import DataFrame, MultiIndex, Series, compat, isna, to_datetime
-import pandas.core.common as com
from pandas.core.reshape.concat import concat
from pandas.io.common import (
@@ -97,7 +97,7 @@ def __init__(self, obj, orient, date_format, double_precision,
self._format_axes()
def _format_axes(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def write(self):
return self._write(self.obj, self.orient, self.double_precision,
@@ -658,7 +658,7 @@ def _convert_axes(self):
setattr(self.obj, axis, new_axis)
def _try_convert_types(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _try_convert_data(self, name, data, use_dtypes=True,
convert_dates=True):
@@ -771,7 +771,7 @@ def _try_convert_to_date(self, data):
return data, False
def _try_convert_dates(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
class SeriesParser(Parser):
diff --git a/pandas/io/parquet.py b/pandas/io/parquet.py
index 3d72b1ec3a47f..aad59f9805a3b 100644
--- a/pandas/io/parquet.py
+++ b/pandas/io/parquet.py
@@ -4,9 +4,9 @@
from warnings import catch_warnings
from pandas.compat import string_types
+from pandas.errors import AbstractMethodError
from pandas import DataFrame, get_option
-import pandas.core.common as com
from pandas.io.common import get_filepath_or_buffer, is_s3_url
@@ -67,10 +67,10 @@ def validate_dataframe(df):
raise ValueError("Index level names must be strings")
def write(self, df, path, compression, **kwargs):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def read(self, path, columns=None, **kwargs):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
class PyArrowImpl(BaseImpl):
diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
index cb2ee64100728..75b2d0366b06a 100755
--- a/pandas/io/parsers.py
+++ b/pandas/io/parsers.py
@@ -21,7 +21,8 @@
import pandas.compat as compat
from pandas.compat import (
PY3, StringIO, lrange, lzip, map, range, string_types, u, zip)
-from pandas.errors import EmptyDataError, ParserError, ParserWarning
+from pandas.errors import (
+ AbstractMethodError, EmptyDataError, ParserError, ParserWarning)
from pandas.util._decorators import Appender
from pandas.core.dtypes.cast import astype_nansafe
@@ -34,7 +35,6 @@
from pandas.core import algorithms
from pandas.core.arrays import Categorical
-import pandas.core.common as com
from pandas.core.frame import DataFrame
from pandas.core.index import (
Index, MultiIndex, RangeIndex, ensure_index_from_sequences)
@@ -1064,7 +1064,7 @@ def _make_engine(self, engine='c'):
self._engine = klass(self.f, **self.options)
def _failover_to_python(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def read(self, nrows=None):
nrows = _validate_integer('nrows', nrows)
diff --git a/pandas/io/pytables.py b/pandas/io/pytables.py
index 41e14e482d061..4c28e0f88b1ae 100644
--- a/pandas/io/pytables.py
+++ b/pandas/io/pytables.py
@@ -1674,7 +1674,7 @@ def cvalues(self):
def __iter__(self):
return iter(self.values)
- def maybe_set_size(self, min_itemsize=None, **kwargs):
+ def maybe_set_size(self, min_itemsize=None):
""" maybe set a string col itemsize:
min_itemsize can be an integer or a dict with this columns name
with an integer size """
@@ -1687,13 +1687,13 @@ def maybe_set_size(self, min_itemsize=None, **kwargs):
self.typ = _tables(
).StringCol(itemsize=min_itemsize, pos=self.pos)
- def validate(self, handler, append, **kwargs):
+ def validate(self, handler, append):
self.validate_names()
def validate_names(self):
pass
- def validate_and_set(self, handler, append, **kwargs):
+ def validate_and_set(self, handler, append):
self.set_table(handler.table)
self.validate_col()
self.validate_attr(append)
@@ -3772,7 +3772,7 @@ def read_coordinates(self, where=None, start=None, stop=None, **kwargs):
return Index(coords)
- def read_column(self, column, where=None, start=None, stop=None, **kwargs):
+ def read_column(self, column, where=None, start=None, stop=None):
"""return a single column from the table, generally only indexables
are interesting
"""
@@ -4727,7 +4727,7 @@ class Selection(object):
"""
- def __init__(self, table, where=None, start=None, stop=None, **kwargs):
+ def __init__(self, table, where=None, start=None, stop=None):
self.table = table
self.where = where
self.start = start
diff --git a/pandas/io/stata.py b/pandas/io/stata.py
index df0d47b063411..66e996075f1ed 100644
--- a/pandas/io/stata.py
+++ b/pandas/io/stata.py
@@ -461,7 +461,8 @@ def parse_dates_safe(dates, delta=False, year=False, days=False):
excessive_string_length_error = """
Fixed width strings in Stata .dta files are limited to 244 (or fewer)
-characters. Column '%s' does not satisfy this restriction.
+characters. Column '%s' does not satisfy this restriction. Use the
+'version=117' parameter to write the newer (Stata 13 and later) format.
"""
diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py
index 405c534e8528b..1c70ece434abb 100644
--- a/pandas/plotting/_core.py
+++ b/pandas/plotting/_core.py
@@ -12,6 +12,7 @@
from pandas.util._decorators import cache_readonly, Appender
from pandas.compat import range, lrange, map, zip, string_types
import pandas.compat as compat
+from pandas.errors import AbstractMethodError
import pandas.core.common as com
from pandas.core.base import PandasObject
@@ -373,7 +374,7 @@ def _compute_plot_data(self):
self.data = numeric_data
def _make_plot(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _add_table(self):
if self.table is False:
diff --git a/pandas/tests/arrays/sparse/test_array.py b/pandas/tests/arrays/sparse/test_array.py
index c15696705ab82..0e5a8280cc467 100644
--- a/pandas/tests/arrays/sparse/test_array.py
+++ b/pandas/tests/arrays/sparse/test_array.py
@@ -477,6 +477,34 @@ def test_astype_all(self, any_real_dtype):
tm.assert_numpy_array_equal(np.asarray(res.values),
vals.astype(typ))
+ @pytest.mark.parametrize('array, dtype, expected', [
+ (SparseArray([0, 1]), 'float',
+ SparseArray([0., 1.], dtype=SparseDtype(float, 0.0))),
+ (SparseArray([0, 1]), bool, SparseArray([False, True])),
+ (SparseArray([0, 1], fill_value=1), bool,
+ SparseArray([False, True], dtype=SparseDtype(bool, True))),
+ pytest.param(
+ SparseArray([0, 1]), 'datetime64[ns]',
+ SparseArray(np.array([0, 1], dtype='datetime64[ns]'),
+ dtype=SparseDtype('datetime64[ns]',
+ pd.Timestamp('1970'))),
+ marks=[pytest.mark.xfail(reason="NumPy-7619", strict=True)],
+ ),
+ (SparseArray([0, 1, 10]), str,
+ SparseArray(['0', '1', '10'], dtype=SparseDtype(str, '0'))),
+ (SparseArray(['10', '20']), float, SparseArray([10.0, 20.0])),
+ (SparseArray([0, 1, 0]), object,
+ SparseArray([0, 1, 0], dtype=SparseDtype(object, 0))),
+ ])
+ def test_astype_more(self, array, dtype, expected):
+ result = array.astype(dtype)
+ tm.assert_sp_array_equal(result, expected)
+
+ def test_astype_nan_raises(self):
+ arr = SparseArray([1.0, np.nan])
+ with pytest.raises(ValueError, match='Cannot convert non-finite'):
+ arr.astype(int)
+
def test_set_fill_value(self):
arr = SparseArray([1., np.nan, 2.], fill_value=np.nan)
arr.fill_value = 2
diff --git a/pandas/tests/arrays/sparse/test_dtype.py b/pandas/tests/arrays/sparse/test_dtype.py
index 7c310693cf26c..2d386de0d31a3 100644
--- a/pandas/tests/arrays/sparse/test_dtype.py
+++ b/pandas/tests/arrays/sparse/test_dtype.py
@@ -139,3 +139,23 @@ def test_parse_subtype(string, expected):
def test_construct_from_string_fill_value_raises(string):
with pytest.raises(TypeError, match='fill_value in the string is not'):
SparseDtype.construct_from_string(string)
+
+
+@pytest.mark.parametrize('original, dtype, expected', [
+ (SparseDtype(int, 0), float, SparseDtype(float, 0.0)),
+ (SparseDtype(int, 1), float, SparseDtype(float, 1.0)),
+ (SparseDtype(int, 1), str, SparseDtype(object, '1')),
+ (SparseDtype(float, 1.5), int, SparseDtype(int, 1)),
+])
+def test_update_dtype(original, dtype, expected):
+ result = original.update_dtype(dtype)
+ assert result == expected
+
+
+@pytest.mark.parametrize("original, dtype", [
+ (SparseDtype(float, np.nan), int),
+ (SparseDtype(str, 'abc'), int),
+])
+def test_update_dtype_raises(original, dtype):
+ with pytest.raises(ValueError):
+ original.update_dtype(dtype)
diff --git a/pandas/tests/arrays/test_datetimelike.py b/pandas/tests/arrays/test_datetimelike.py
index 5ba99a48e34ad..bb4022c9cac9a 100644
--- a/pandas/tests/arrays/test_datetimelike.py
+++ b/pandas/tests/arrays/test_datetimelike.py
@@ -4,7 +4,8 @@
import pandas as pd
from pandas.core.arrays import (
- DatetimeArrayMixin, PeriodArray, TimedeltaArrayMixin)
+ DatetimeArrayMixin as DatetimeArray, PeriodArray,
+ TimedeltaArrayMixin as TimedeltaArray)
import pandas.util.testing as tm
@@ -61,7 +62,7 @@ def test_array_object_dtype(self, tz_naive_fixture):
# GH#23524
tz = tz_naive_fixture
dti = pd.date_range('2016-01-01', periods=3, tz=tz)
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
expected = np.array(list(dti))
@@ -76,7 +77,7 @@ def test_array(self, tz_naive_fixture):
# GH#23524
tz = tz_naive_fixture
dti = pd.date_range('2016-01-01', periods=3, tz=tz)
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
expected = dti.asi8.view('M8[ns]')
result = np.array(arr)
@@ -91,7 +92,7 @@ def test_array_i8_dtype(self, tz_naive_fixture):
# GH#23524
tz = tz_naive_fixture
dti = pd.date_range('2016-01-01', periods=3, tz=tz)
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
expected = dti.asi8
result = np.array(arr, dtype='i8')
@@ -108,7 +109,7 @@ def test_array_i8_dtype(self, tz_naive_fixture):
def test_from_dti(self, tz_naive_fixture):
tz = tz_naive_fixture
dti = pd.date_range('2016-01-01', periods=3, tz=tz)
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
assert list(dti) == list(arr)
# Check that Index.__new__ knows what to do with DatetimeArray
@@ -119,7 +120,7 @@ def test_from_dti(self, tz_naive_fixture):
def test_astype_object(self, tz_naive_fixture):
tz = tz_naive_fixture
dti = pd.date_range('2016-01-01', periods=3, tz=tz)
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
asobj = arr.astype('O')
assert isinstance(asobj, np.ndarray)
assert asobj.dtype == 'O'
@@ -129,11 +130,11 @@ def test_astype_object(self, tz_naive_fixture):
def test_to_perioddelta(self, datetime_index, freqstr):
# GH#23113
dti = datetime_index
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
expected = dti.to_perioddelta(freq=freqstr)
result = arr.to_perioddelta(freq=freqstr)
- assert isinstance(result, TimedeltaArrayMixin)
+ assert isinstance(result, TimedeltaArray)
# placeholder until these become actual EA subclasses and we can use
# an EA-specific tm.assert_ function
@@ -142,7 +143,7 @@ def test_to_perioddelta(self, datetime_index, freqstr):
@pytest.mark.parametrize('freqstr', ['D', 'B', 'W', 'M', 'Q', 'Y'])
def test_to_period(self, datetime_index, freqstr):
dti = datetime_index
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
expected = dti.to_period(freq=freqstr)
result = arr.to_period(freq=freqstr)
@@ -156,7 +157,7 @@ def test_to_period(self, datetime_index, freqstr):
def test_bool_properties(self, datetime_index, propname):
# in this case _bool_ops is just `is_leap_year`
dti = datetime_index
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
assert dti.freq == arr.freq
result = getattr(arr, propname)
@@ -167,7 +168,7 @@ def test_bool_properties(self, datetime_index, propname):
@pytest.mark.parametrize('propname', pd.DatetimeIndex._field_ops)
def test_int_properties(self, datetime_index, propname):
dti = datetime_index
- arr = DatetimeArrayMixin(dti)
+ arr = DatetimeArray(dti)
result = getattr(arr, propname)
expected = np.array(getattr(dti, propname), dtype=result.dtype)
@@ -178,7 +179,7 @@ def test_int_properties(self, datetime_index, propname):
class TestTimedeltaArray(object):
def test_from_tdi(self):
tdi = pd.TimedeltaIndex(['1 Day', '3 Hours'])
- arr = TimedeltaArrayMixin(tdi)
+ arr = TimedeltaArray(tdi)
assert list(arr) == list(tdi)
# Check that Index.__new__ knows what to do with TimedeltaArray
@@ -188,7 +189,7 @@ def test_from_tdi(self):
def test_astype_object(self):
tdi = pd.TimedeltaIndex(['1 Day', '3 Hours'])
- arr = TimedeltaArrayMixin(tdi)
+ arr = TimedeltaArray(tdi)
asobj = arr.astype('O')
assert isinstance(asobj, np.ndarray)
assert asobj.dtype == 'O'
@@ -196,7 +197,7 @@ def test_astype_object(self):
def test_to_pytimedelta(self, timedelta_index):
tdi = timedelta_index
- arr = TimedeltaArrayMixin(tdi)
+ arr = TimedeltaArray(tdi)
expected = tdi.to_pytimedelta()
result = arr.to_pytimedelta()
@@ -205,7 +206,7 @@ def test_to_pytimedelta(self, timedelta_index):
def test_total_seconds(self, timedelta_index):
tdi = timedelta_index
- arr = TimedeltaArrayMixin(tdi)
+ arr = TimedeltaArray(tdi)
expected = tdi.total_seconds()
result = arr.total_seconds()
@@ -215,7 +216,7 @@ def test_total_seconds(self, timedelta_index):
@pytest.mark.parametrize('propname', pd.TimedeltaIndex._field_ops)
def test_int_properties(self, timedelta_index, propname):
tdi = timedelta_index
- arr = TimedeltaArrayMixin(tdi)
+ arr = TimedeltaArray(tdi)
result = getattr(arr, propname)
expected = np.array(getattr(tdi, propname), dtype=result.dtype)
@@ -248,9 +249,9 @@ def test_to_timestamp(self, how, period_index):
pi = period_index
arr = PeriodArray(pi)
- expected = DatetimeArrayMixin(pi.to_timestamp(how=how))
+ expected = DatetimeArray(pi.to_timestamp(how=how))
result = arr.to_timestamp(how=how)
- assert isinstance(result, DatetimeArrayMixin)
+ assert isinstance(result, DatetimeArray)
# placeholder until these become actual EA subclasses and we can use
# an EA-specific tm.assert_ function
diff --git a/pandas/tests/arrays/test_datetimes.py b/pandas/tests/arrays/test_datetimes.py
index a15295cfbd81a..2b630b98b69a2 100644
--- a/pandas/tests/arrays/test_datetimes.py
+++ b/pandas/tests/arrays/test_datetimes.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
"""
Tests for DatetimeArray
"""
diff --git a/pandas/tests/arrays/test_period.py b/pandas/tests/arrays/test_period.py
index 95a1d1781456c..63b34db13705e 100644
--- a/pandas/tests/arrays/test_period.py
+++ b/pandas/tests/arrays/test_period.py
@@ -190,7 +190,7 @@ def test_setitem_raises_type():
# ----------------------------------------------------------------------------
# Ops
-def tet_sub_period():
+def test_sub_period():
arr = period_array(['2000', '2001'], freq='D')
other = pd.Period("2000", freq="M")
with pytest.raises(IncompatibleFrequency, match="freq"):
diff --git a/pandas/tests/arrays/test_timedeltas.py b/pandas/tests/arrays/test_timedeltas.py
new file mode 100644
index 0000000000000..3ff807daeeab9
--- /dev/null
+++ b/pandas/tests/arrays/test_timedeltas.py
@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+
+
+class TestTimedeltaArray(object):
+ pass
diff --git a/pandas/tests/io/parser/common.py b/pandas/tests/io/parser/common.py
index 18690a18f7cb3..67a3bd6f9b75e 100644
--- a/pandas/tests/io/parser/common.py
+++ b/pandas/tests/io/parser/common.py
@@ -458,6 +458,22 @@ def test_read_chunksize_generated_index(self):
tm.assert_frame_equal(pd.concat(reader), df)
+ def test_read_chunksize_jagged_names(self):
+ # see gh-23509
+ data = "\n".join(["0"] * 7 + [",".join(["0"] * 10)])
+ reader = self.read_csv(StringIO(data), names=range(10), chunksize=4)
+
+ expected = DataFrame()
+
+ for i in range(10):
+ if i == 0:
+ expected[i] = [0] * 8
+ else:
+ expected[i] = [np.nan] * 7 + [0]
+
+ result = pd.concat(reader)
+ tm.assert_frame_equal(result, expected)
+
def test_read_text_list(self):
data = """A,B,C\nfoo,1,2,3\nbar,4,5,6"""
as_list = [['A', 'B', 'C'], ['foo', '1', '2', '3'], ['bar',
diff --git a/pandas/tests/io/parser/test_parsers.py b/pandas/tests/io/parser/test_parsers.py
index 50d927176a7b4..21286e9b82323 100644
--- a/pandas/tests/io/parser/test_parsers.py
+++ b/pandas/tests/io/parser/test_parsers.py
@@ -6,9 +6,9 @@
from pandas._libs.tslib import Timestamp
from pandas.compat import StringIO
+from pandas.errors import AbstractMethodError
from pandas import DataFrame, read_csv, read_table
-import pandas.core.common as com
import pandas.util.testing as tm
from .c_parser_only import CParserTests
@@ -46,7 +46,7 @@ def read_table(self, *args, **kwargs):
raise NotImplementedError
def float_precision_choices(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
@pytest.fixture(autouse=True)
def setup_method(self, datapath):
diff --git a/pandas/tests/io/test_excel.py b/pandas/tests/io/test_excel.py
index 49a3a3d58672d..9b147d53c06c4 100644
--- a/pandas/tests/io/test_excel.py
+++ b/pandas/tests/io/test_excel.py
@@ -105,23 +105,34 @@ def get_exceldf(self, basename, ext, *args, **kwds):
class ReadingTestsBase(SharedItems):
# This is based on ExcelWriterBase
- @td.skip_if_no('xlrd', '1.0.1') # GH-22682
+ @td.skip_if_no("xlrd", "1.0.1") # see gh-22682
def test_usecols_int(self, ext):
- dfref = self.get_csv_refdf('test1')
- dfref = dfref.reindex(columns=['A', 'B', 'C'])
- df1 = self.get_exceldf('test1', ext, 'Sheet1', index_col=0, usecols=3)
- df2 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
- index_col=0, usecols=3)
+ df_ref = self.get_csv_refdf("test1")
+ df_ref = df_ref.reindex(columns=["A", "B", "C"])
- with tm.assert_produces_warning(FutureWarning):
- df3 = self.get_exceldf('test1', ext, 'Sheet2', skiprows=[1],
+ # usecols as int
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ df1 = self.get_exceldf("test1", ext, "Sheet1",
+ index_col=0, usecols=3)
+
+ # usecols as int
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ df2 = self.get_exceldf("test1", ext, "Sheet2", skiprows=[1],
+ index_col=0, usecols=3)
+
+ # parse_cols instead of usecols, usecols as int
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ df3 = self.get_exceldf("test1", ext, "Sheet2", skiprows=[1],
index_col=0, parse_cols=3)
# TODO add index to xls file)
- tm.assert_frame_equal(df1, dfref, check_names=False)
- tm.assert_frame_equal(df2, dfref, check_names=False)
- tm.assert_frame_equal(df3, dfref, check_names=False)
+ tm.assert_frame_equal(df1, df_ref, check_names=False)
+ tm.assert_frame_equal(df2, df_ref, check_names=False)
+ tm.assert_frame_equal(df3, df_ref, check_names=False)
@td.skip_if_no('xlrd', '1.0.1') # GH-22682
def test_usecols_list(self, ext):
diff --git a/pandas/tests/test_resample.py b/pandas/tests/test_resample.py
index 756385f0cfb56..7e0342e8b987a 100644
--- a/pandas/tests/test_resample.py
+++ b/pandas/tests/test_resample.py
@@ -24,12 +24,11 @@
notna, Timestamp, Timedelta)
from pandas.compat import range, lrange, zip, OrderedDict
-from pandas.errors import UnsupportedFunctionCall
+from pandas.errors import AbstractMethodError, UnsupportedFunctionCall
import pandas.tseries.offsets as offsets
from pandas.tseries.offsets import Minute, BDay
from pandas.core.groupby.groupby import DataError
-import pandas.core.common as com
from pandas.core.indexes.datetimes import date_range
from pandas.core.indexes.period import period_range, PeriodIndex, Period
@@ -599,7 +598,7 @@ def index(self, _index_start, _index_end, _index_freq):
@pytest.fixture
def _series_name(self):
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
@pytest.fixture
def _static_values(self, index):
diff --git a/pandas/tseries/offsets.py b/pandas/tseries/offsets.py
index 25c419e485db1..067a7d4622ca2 100644
--- a/pandas/tseries/offsets.py
+++ b/pandas/tseries/offsets.py
@@ -9,7 +9,6 @@
from pandas.core.dtypes.generic import ABCPeriod
from pandas.core.tools.datetimes import to_datetime
-import pandas.core.common as com
# import after tools, dateutil check
from dateutil.easter import easter
@@ -29,6 +28,7 @@
roll_yearday,
shift_month,
BaseOffset)
+from pandas.errors import AbstractMethodError
__all__ = ['Day', 'BusinessDay', 'BDay', 'CustomBusinessDay', 'CDay',
@@ -1097,7 +1097,7 @@ def apply(self, other):
def _apply(self, n, other):
"""Handle specific apply logic for child classes"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
@apply_index_wraps
def apply_index(self, i):
@@ -1137,11 +1137,11 @@ def _get_roll(self, i, before_day_of_month, after_day_of_month):
The roll array is based on the fact that i gets rolled back to
the first day of the month.
"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
def _apply_index_days(self, i, roll):
"""Apply the correct day for each date in i"""
- raise com.AbstractMethodError(self)
+ raise AbstractMethodError(self)
class SemiMonthEnd(SemiMonthOffset):
diff --git a/scripts/tests/test_validate_docstrings.py b/scripts/tests/test_validate_docstrings.py
index ccd5f56141a6a..c1bdab73c2671 100644
--- a/scripts/tests/test_validate_docstrings.py
+++ b/scripts/tests/test_validate_docstrings.py
@@ -350,6 +350,35 @@ def private_classes(self):
This mentions NDFrame, which is not correct.
"""
+ def unknown_section(self):
+ """
+ This section has an unknown section title.
+
+ Unknown Section
+ ---------------
+ This should raise an error in the validation.
+ """
+
+ def sections_in_wrong_order(self):
+ """
+ This docstring has the sections in the wrong order.
+
+ Parameters
+ ----------
+ name : str
+ This section is in the right position.
+
+ Examples
+ --------
+ >>> print('So far Examples is good, as it goes before Parameters')
+ So far Examples is good, as it goes before Parameters
+
+ See Also
+ --------
+ function : This should generate an error, as See Also needs to go
+ before Examples.
+ """
+
class BadSummaries(object):
@@ -706,6 +735,11 @@ def test_bad_generic_functions(self, func):
('BadGenericDocStrings', 'private_classes',
("Private classes (NDFrame) should not be mentioned in public "
'docstrings',)),
+ ('BadGenericDocStrings', 'unknown_section',
+ ('Found unknown section "Unknown Section".',)),
+ ('BadGenericDocStrings', 'sections_in_wrong_order',
+ ('Wrong order of sections. "See Also" should be located before '
+ '"Notes"',)),
('BadSeeAlso', 'desc_no_period',
('Missing period at end of description for See Also "Series.iloc"',)),
('BadSeeAlso', 'desc_first_letter_lowercase',
diff --git a/scripts/validate_docstrings.py b/scripts/validate_docstrings.py
index ed84e58049cae..7da77a1f60ad5 100755
--- a/scripts/validate_docstrings.py
+++ b/scripts/validate_docstrings.py
@@ -56,6 +56,9 @@
PRIVATE_CLASSES = ['NDFrame', 'IndexOpsMixin']
DIRECTIVES = ['versionadded', 'versionchanged', 'deprecated']
+ALLOWED_SECTIONS = ['Parameters', 'Attributes', 'Methods', 'Returns', 'Yields',
+ 'Other Parameters', 'Raises', 'Warns', 'See Also', 'Notes',
+ 'References', 'Examples']
ERROR_MSGS = {
'GL01': 'Docstring text (summary) should start in the line immediately '
'after the opening quotes (not in the same line, or leaving a '
@@ -69,6 +72,10 @@
'mentioned in public docstrings',
'GL05': 'Tabs found at the start of line "{line_with_tabs}", please use '
'whitespace only',
+ 'GL06': 'Found unknown section "{section}". Allowed sections are: '
+ '{allowed_sections}',
+ 'GL07': 'Wrong order of sections. "{wrong_section}" should be located '
+ 'before "{goes_before}", the right order is: {sorted_sections}',
'SS01': 'No summary found (a short summary in a single line should be '
'present at the beginning of the docstring)',
'SS02': 'Summary does not start with a capital letter',
@@ -353,6 +360,18 @@ def double_blank_lines(self):
prev = row.strip()
return False
+ @property
+ def section_titles(self):
+ sections = []
+ self.doc._doc.reset()
+ while not self.doc._doc.eof():
+ content = self.doc._read_to_next_section()
+ if (len(content) > 1
+ and len(content[0]) == len(content[1])
+ and set(content[1]) == {'-'}):
+ sections.append(content[0])
+ return sections
+
@property
def summary(self):
return ' '.join(self.doc['Summary'])
@@ -580,6 +599,25 @@ def validate_one(func_name):
if re.match("^ *\t", line):
errs.append(error('GL05', line_with_tabs=line.lstrip()))
+ unseen_sections = list(ALLOWED_SECTIONS)
+ for section in doc.section_titles:
+ if section not in ALLOWED_SECTIONS:
+ errs.append(error('GL06',
+ section=section,
+ allowed_sections=', '.join(ALLOWED_SECTIONS)))
+ else:
+ if section in unseen_sections:
+ section_idx = unseen_sections.index(section)
+ unseen_sections = unseen_sections[section_idx + 1:]
+ else:
+ section_idx = ALLOWED_SECTIONS.index(section)
+ goes_before = ALLOWED_SECTIONS[section_idx + 1]
+ errs.append(error('GL07',
+ sorted_sections=' > '.join(ALLOWED_SECTIONS),
+ wrong_section=section,
+ goes_before=goes_before))
+ break
+
if not doc.summary:
errs.append(error('SS01'))
else:
diff --git a/setup.cfg b/setup.cfg
index 2e07182196d5b..9f5384170a245 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -120,9 +120,6 @@ skip=
pandas/core/indexes/numeric.py,
pandas/core/indexes/interval.py,
pandas/core/indexes/multi.py,
- pandas/core/indexes/timedeltas.py,
- pandas/core/indexes/datetimelike.py,
- pandas/core/indexes/datetimes.py,
pandas/core/indexes/base.py,
pandas/core/indexes/accessors.py,
pandas/core/indexes/period.py,