Merge remote-tracking branch 'upstream/master' into categorical-csv-2

Author: TomAugspurger

appveyor.yml

@@ -59,7 +59,7 @@ install:
 
   # install our build environment
   - cmd: conda config --set show_channel_urls true --set always_yes true --set changeps1 false
-  - cmd: conda update -q conda
+  # - cmd: conda update -q conda
   - cmd: conda config --set ssl_verify false
 
   # add the pandas channel *before* defaults to have defaults take priority

ci/install.ps1

@@ -7,7 +7,7 @@ $MINICONDA_URL = "http://repo.continuum.io/miniconda/"
 
 function DownloadMiniconda ($python_version, $platform_suffix) {
     $webclient = New-Object System.Net.WebClient
-    $filename = "Miniconda3-latest-Windows-" + $platform_suffix + ".exe"
+    $filename = "Miniconda3-4.3.21-Windows-" + $platform_suffix + ".exe"
     $url = $MINICONDA_URL + $filename
 
     $basedir = $pwd.Path + "\"
@@ -85,7 +85,7 @@ function UpdateConda ($python_home) {
 
 function main () {
     InstallMiniconda "3.5" $env:PYTHON_ARCH $env:CONDA_ROOT
-    UpdateConda $env:CONDA_ROOT
+    # UpdateConda $env:CONDA_ROOT
     InstallCondaPackages $env:CONDA_ROOT "conda-build jinja2 anaconda-client"
 }
 

ci/install_circle.sh

@@ -10,15 +10,17 @@ echo "[Using clean Miniconda install]"
 rm -rf "$MINICONDA_DIR"
 
 # install miniconda
-wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -q -O miniconda.sh || exit 1
+# wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -q -O miniconda.sh || exit 1
+# Pin miniconda
+wget https://repo.continuum.io/miniconda/Miniconda2-4.3.21-Linux-x86_64.sh -q -O miniconda.sh || exit 1
 bash miniconda.sh -b -p "$MINICONDA_DIR" || exit 1
 
 export PATH="$MINICONDA_DIR/bin:$PATH"
 
 echo "[update conda]"
 conda config --set ssl_verify false || exit 1
 conda config --set always_yes true --set changeps1 false || exit 1
-conda update -q conda
+# conda update -q conda
 
 # add the pandas channel to take priority
 # to add extra packages

ci/install_travis.sh

@@ -34,9 +34,13 @@ fi
 
 # install miniconda
 if [ "${TRAVIS_OS_NAME}" == "osx" ]; then
-    time wget http://repo.continuum.io/miniconda/Miniconda3-latest-MacOSX-x86_64.sh -O miniconda.sh || exit 1
+    # temporarily pin miniconda
+    # time wget http://repo.continuum.io/miniconda/Miniconda3-latest-MacOSX-x86_64.sh -O miniconda.sh || exit 1
+    time wget https://repo.continuum.io/miniconda/Miniconda2-4.3.21-MacOSX-x86_64.sh -O miniconda.sh || exit 1
 else
-    time wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh || exit 1
+    # temporarily pin miniconda
+    # time wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh || exit 1
+    time wget https://repo.continuum.io/miniconda/Miniconda2-4.3.21-Linux-x86_64.sh -O miniconda.sh || exit 1
 fi
 time bash miniconda.sh -b -p "$MINICONDA_DIR" || exit 1
 
@@ -48,7 +52,7 @@ echo
 echo "[update conda]"
 conda config --set ssl_verify false || exit 1
 conda config --set quiet true --set always_yes true --set changeps1 false || exit 1
-conda update -q conda
+# conda update -q conda
 
 echo
 echo "[add channels]"

ci/requirements-2.7_SLOW.run

@@ -16,4 +16,4 @@ s3fs
 psycopg2
 pymysql
 html5lib
-beautiful-soup
+beautifulsoup4

ci/requirements-2.7_WIN.run

@@ -14,5 +14,5 @@ xlsxwriter
 s3fs
 bottleneck
 html5lib
-beautiful-soup
+beautifulsoup4
 jinja2=2.8

ci/requirements_all.txt

@@ -13,7 +13,7 @@ xlrd
 xlwt
 html5lib
 patsy
-beautiful-soup
+beautifulsoup4
 numpy
 cython
 scipy

doc/source/whatsnew/v0.21.0.txt

@@ -516,10 +516,33 @@ Other API Changes
 
 Deprecations
 ~~~~~~~~~~~~
+
 - :func:`read_excel()` has deprecated ``sheetname`` in favor of ``sheet_name`` for consistency with ``.to_excel()`` (:issue:`10559`).
 - ``pd.options.html.border`` has been deprecated in favor of ``pd.options.display.html.border`` (:issue:`15793`).
 - :func:`SeriesGroupBy.nth` has deprecated ``True`` in favor of ``'all'`` for its kwarg ``dropna`` (:issue:`11038`).
 - :func:`DataFrame.as_blocks` is deprecated, as this is exposing the internal implementation (:issue:`17302`)
+- ``pd.TimeGrouper`` is deprecated in favor of :class:`pandas.Grouper` (:issue:`16747`)
+
+.. _whatsnew_0210.deprecations.argmin_min
+
+Series.argmax and Series.argmin
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+- The behavior of :func:`Series.argmax` has been deprecated in favor of :func:`Series.idxmax` (:issue:`16830`)
+- The behavior of :func:`Series.argmin` has been deprecated in favor of :func:`Series.idxmin` (:issue:`16830`)
+
+For compatibility with NumPy arrays, ``pd.Series`` implements ``argmax`` and
+``argmin``. Since pandas 0.13.0, ``argmax`` has been an alias for
+:meth:`pandas.Series.idxmax`, and ``argmin`` has been an alias for
+:meth:`pandas.Series.idxmin`. They return the *label* of the maximum or minimum,
+rather than the *position*.
+
+We've deprecated the current behavior of ``Series.argmax`` and
+``Series.argmin``. Using either of these will emit a ``FutureWarning``. Use
+:meth:`Series.idxmax` if you want the label of the maximum. Use
+``Series.values.argmax()`` if you want the position of the maximum. Likewise for
+the minimum. In a future release ``Series.argmax`` and ``Series.argmin`` will
+return the position of the maximum or minimum.
 
 .. _whatsnew_0210.prior_deprecations:
 
@@ -636,7 +659,7 @@ Sparse
 
 - Bug in ``SparseSeries`` raises ``AttributeError`` when a dictionary is passed in as data (:issue:`16905`)
 - Bug in :func:`SparseDataFrame.fillna` not filling all NaNs when frame was instantiated from SciPy sparse matrix (:issue:`16112`)
-
+- Bug in :func:`SparseSeries.unstack` and :func:`SparseDataFrame.stack` (:issue:`16614`, :issue:`15045`)
 
 Reshaping
 ^^^^^^^^^

doc/sphinxext/numpydoc/numpydoc.py

@@ -43,9 +43,10 @@ def mangle_docstrings(app, what, name, obj, options, lines,
               )
 
     # PANDAS HACK (to remove the list of methods/attributes for Categorical)
-    if what == "class" and (name.endswith(".Categorical") or
-                            name.endswith("CategoricalIndex") or
-                            name.endswith("IntervalIndex")):
+    no_autosummary = [".Categorical", "CategoricalIndex", "IntervalIndex",
+                      "RangeIndex", "Int64Index", "UInt64Index",
+                      "Float64Index"]
+    if what == "class" and any(name.endswith(n) for n in no_autosummary):
         cfg['class_members_list'] = False
 
     if what == 'module':

pandas/_libs/period.pyx

@@ -37,10 +37,10 @@ from tslibs.timezones cimport (
     is_utc, is_tzlocal, get_utcoffset, get_dst_info, maybe_get_tz)
 from tslib cimport _nat_scalar_rules
 
+from tslibs.parsing import parse_time_string, NAT_SENTINEL
 from tslibs.frequencies cimport get_freq_code
 
 from pandas.tseries import offsets
-from pandas.core.tools.datetimes import parse_time_string
 from pandas.tseries import frequencies
 
 cdef int64_t NPY_NAT = util.get_nat()
@@ -1197,6 +1197,8 @@ class Period(_Period):
                 value = str(value)
             value = value.upper()
             dt, _, reso = parse_time_string(value, freq)
+            if dt is NAT_SENTINEL:
+                ordinal = iNaT
 
             if freq is None:
                 try:

pandas/_libs/src/inference.pyx

@@ -1384,165 +1384,6 @@ def convert_sql_column(x):
     return maybe_convert_objects(x, try_float=1)
 
 
-def try_parse_dates(ndarray[object] values, parser=None,
-                    dayfirst=False, default=None):
-    cdef:
-        Py_ssize_t i, n
-        ndarray[object] result
-
-    n = len(values)
-    result = np.empty(n, dtype='O')
-
-    if parser is None:
-        if default is None: # GH2618
-            date=datetime.now()
-            default=datetime(date.year, date.month, 1)
-
-        try:
-            from dateutil.parser import parse
-            parse_date = lambda x: parse(x, dayfirst=dayfirst, default=default)
-        except ImportError: # pragma: no cover
-            def parse_date(s):
-                try:
-                    return datetime.strptime(s, '%m/%d/%Y')
-                except Exception:
-                    return s
-        # EAFP here
-        try:
-            for i from 0 <= i < n:
-                if values[i] == '':
-                    result[i] = np.nan
-                else:
-                    result[i] = parse_date(values[i])
-        except Exception:
-            # failed
-            return values
-    else:
-        parse_date = parser
-
-        try:
-            for i from 0 <= i < n:
-                if values[i] == '':
-                    result[i] = np.nan
-                else:
-                    result[i] = parse_date(values[i])
-        except Exception:
-            # raise if passed parser and it failed
-            raise
-
-    return result
-
-
-def try_parse_date_and_time(ndarray[object] dates, ndarray[object] times,
-                            date_parser=None, time_parser=None,
-                            dayfirst=False, default=None):
-    cdef:
-        Py_ssize_t i, n
-        ndarray[object] result
-
-    from datetime import date, time, datetime, timedelta
-
-    n = len(dates)
-    if len(times) != n:
-        raise ValueError('Length of dates and times must be equal')
-    result = np.empty(n, dtype='O')
-
-    if date_parser is None:
-        if default is None: # GH2618
-            date=datetime.now()
-            default=datetime(date.year, date.month, 1)
-
-        try:
-            from dateutil.parser import parse
-            parse_date = lambda x: parse(x, dayfirst=dayfirst, default=default)
-        except ImportError: # pragma: no cover
-            def parse_date(s):
-                try:
-                    return date.strptime(s, '%m/%d/%Y')
-                except Exception:
-                    return s
-    else:
-        parse_date = date_parser
-
-    if time_parser is None:
-        try:
-            from dateutil.parser import parse
-            parse_time = lambda x: parse(x)
-        except ImportError: # pragma: no cover
-            def parse_time(s):
-                try:
-                    return time.strptime(s, '%H:%M:%S')
-                except Exception:
-                    return s
-
-    else:
-        parse_time = time_parser
-
-    for i from 0 <= i < n:
-        d = parse_date(str(dates[i]))
-        t = parse_time(str(times[i]))
-        result[i] = datetime(d.year, d.month, d.day,
-                             t.hour, t.minute, t.second)
-
-    return result
-
-
-def try_parse_year_month_day(ndarray[object] years, ndarray[object] months,
-                             ndarray[object] days):
-    cdef:
-        Py_ssize_t i, n
-        ndarray[object] result
-
-    from datetime import datetime
-
-    n = len(years)
-    if len(months) != n or len(days) != n:
-        raise ValueError('Length of years/months/days must all be equal')
-    result = np.empty(n, dtype='O')
-
-    for i from 0 <= i < n:
-        result[i] = datetime(int(years[i]), int(months[i]), int(days[i]))
-
-    return result
-
-
-def try_parse_datetime_components(ndarray[object] years,
-                                  ndarray[object] months,
-                                  ndarray[object] days,
-                                  ndarray[object] hours,
-                                  ndarray[object] minutes,
-                                  ndarray[object] seconds):
-
-    cdef:
-        Py_ssize_t i, n
-        ndarray[object] result
-        int secs
-        double float_secs
-        double micros
-
-    from datetime import datetime
-
-    n = len(years)
-    if (len(months) != n or len(days) != n or len(hours) != n or
-        len(minutes) != n or len(seconds) != n):
-        raise ValueError('Length of all datetime components must be equal')
-    result = np.empty(n, dtype='O')
-
-    for i from 0 <= i < n:
-        float_secs = float(seconds[i])
-        secs = int(float_secs)
-
-        micros = float_secs - secs
-        if micros > 0:
-            micros = micros * 1000000
-
-        result[i] = datetime(int(years[i]), int(months[i]), int(days[i]),
-                             int(hours[i]), int(minutes[i]), secs,
-                             int(micros))
-
-    return result
-
-
 def sanitize_objects(ndarray[object] values, set na_values,
                      convert_empty=True):
     cdef: