Merge remote-tracking branch 'upstream/master' into docfix-multiindex-set_levels

Author: hweecat

ci/azure/posix.yml

@@ -45,13 +45,16 @@ jobs:
           PATTERN: "not slow and not network"
           LOCALE_OVERRIDE: "zh_CN.UTF-8"
 
-        py37_np_dev:
-          ENV_FILE: ci/deps/azure-37-numpydev.yaml
-          CONDA_PY: "37"
-          PATTERN: "not slow and not network"
-          TEST_ARGS: "-W error"
-          PANDAS_TESTING_MODE: "deprecate"
-          EXTRA_APT: "xsel"
+        # https://github.com/pandas-dev/pandas/issues/29432
+        # py37_np_dev:
+        #   ENV_FILE: ci/deps/azure-37-numpydev.yaml
+        #   CONDA_PY: "37"
+        #   PATTERN: "not slow and not network"
+        #   TEST_ARGS: "-W error"
+        #   PANDAS_TESTING_MODE: "deprecate"
+        #   EXTRA_APT: "xsel"
+        #   # TODO:
+        #   continueOnError: true
 
   steps:
     - script: |

doc/source/getting_started/basics.rst

@@ -753,28 +753,51 @@ on an entire ``DataFrame`` or ``Series``, row- or column-wise, or elementwise.
 Tablewise function application
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-``DataFrames`` and ``Series`` can of course just be passed into functions.
+``DataFrames`` and ``Series`` can be passed into functions.
 However, if the function needs to be called in a chain, consider using the :meth:`~DataFrame.pipe` method.
-Compare the following
 
-.. code-block:: python
+First some setup:
+
+.. ipython:: python
 
-   # f, g, and h are functions taking and returning ``DataFrames``
-   >>> f(g(h(df), arg1=1), arg2=2, arg3=3)
+    def extract_city_name(df):
+        """
+        Chicago, IL -> Chicago for city_name column
+        """
+        df['city_name'] = df['city_and_code'].str.split(",").str.get(0)
+        return df
 
-with the equivalent
+    def add_country_name(df, country_name=None):
+        """
+        Chicago -> Chicago-US for city_name column
+        """
+        col = 'city_name'
+        df['city_and_country'] = df[col] + country_name
+        return df
 
-.. code-block:: python
+    df_p = pd.DataFrame({'city_and_code': ['Chicago, IL']})
+
+
+``extract_city_name`` and ``add_country_name`` are functions taking and returning ``DataFrames``.
+
+Now compare the following:
+
+.. ipython:: python
+
+    add_country_name(extract_city_name(df_p), country_name='US')
+
+Is equivalent to:
+
+.. ipython:: python
 
-   >>> (df.pipe(h)
-   ...    .pipe(g, arg1=1)
-   ...    .pipe(f, arg2=2, arg3=3))
+    (df_p.pipe(extract_city_name)
+         .pipe(add_country_name, country_name="US"))
 
 Pandas encourages the second style, which is known as method chaining.
 ``pipe`` makes it easy to use your own or another library's functions
 in method chains, alongside pandas' methods.
 
-In the example above, the functions ``f``, ``g``, and ``h`` each expected the ``DataFrame`` as the first positional argument.
+In the example above, the functions ``extract_city_name`` and ``add_country_name`` each expected a ``DataFrame`` as the first positional argument.
 What if the function you wish to apply takes its data as, say, the second argument?
 In this case, provide ``pipe`` with a tuple of ``(callable, data_keyword)``.
 ``.pipe`` will route the ``DataFrame`` to the argument specified in the tuple.

doc/source/user_guide/style.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Styling\n",
     "\n",
-    "This document is written as a Jupyter Notebook, and can be viewed or downloaded [here](http://nbviewer.ipython.org/github/pandas-dev/pandas/blob/master/doc/source/style.ipynb).\n",
+    "This document is written as a Jupyter Notebook, and can be viewed or downloaded [here](http://nbviewer.ipython.org/github/pandas-dev/pandas/blob/master/doc/source/user_guide/style.ipynb).\n",
     "\n",
     "You can apply **conditional formatting**, the visual styling of a DataFrame\n",
     "depending on the data within, by using the ``DataFrame.style`` property.\n",

environment.yml

@@ -1,11 +1,10 @@
 name: pandas-dev
 channels:
-  - defaults
   - conda-forge
 dependencies:
   # required
   - numpy>=1.15
-  - python=3
+  - python=3.7
   - python-dateutil>=2.6.1
   - pytz
 
@@ -22,7 +21,7 @@ dependencies:
   - flake8-comprehensions  # used by flake8, linting of unnecessary comprehensions
   - flake8-rst>=0.6.0,<=0.7.0  # linting of code blocks in rst files
   - isort  # check that imports are in the right order
-  - mypy
+  - mypy=0.720
   - pycodestyle  # used by flake8
 
   # documentation
@@ -54,7 +53,6 @@ dependencies:
   - moto  # mock S3
   - pytest>=4.0.2
   - pytest-cov
-  - pytest-mock
   - pytest-xdist
   - seaborn
   - statsmodels

pandas/_libs/algos.pyx

@@ -1150,6 +1150,77 @@ def rank_2d(rank_t[:, :] in_arr, axis=0, ties_method='average',
         return ranks
 
 
+ctypedef fused diff_t:
+    float64_t
+    float32_t
+    int8_t
+    int16_t
+    int32_t
+    int64_t
+
+ctypedef fused out_t:
+    float32_t
+    float64_t
+
+
+@cython.boundscheck(False)
+@cython.wraparound(False)
+def diff_2d(ndarray[diff_t, ndim=2] arr,
+            ndarray[out_t, ndim=2] out,
+            Py_ssize_t periods, int axis):
+    cdef:
+        Py_ssize_t i, j, sx, sy, start, stop
+        bint f_contig = arr.flags.f_contiguous
+
+    # Disable for unsupported dtype combinations,
+    #  see https://github.com/cython/cython/issues/2646
+    if (out_t is float32_t
+            and not (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
+        raise NotImplementedError
+    elif (out_t is float64_t
+          and (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
+        raise NotImplementedError
+    else:
+        # We put this inside an indented else block to avoid cython build
+        #  warnings about unreachable code
+        sx, sy = (<object>arr).shape
+        with nogil:
+            if f_contig:
+                if axis == 0:
+                    if periods >= 0:
+                        start, stop = periods, sx
+                    else:
+                        start, stop = 0, sx + periods
+                    for j in range(sy):
+                        for i in range(start, stop):
+                            out[i, j] = arr[i, j] - arr[i - periods, j]
+                else:
+                    if periods >= 0:
+                        start, stop = periods, sy
+                    else:
+                        start, stop = 0, sy + periods
+                    for j in range(start, stop):
+                        for i in range(sx):
+                            out[i, j] = arr[i, j] - arr[i, j - periods]
+            else:
+                if axis == 0:
+                    if periods >= 0:
+                        start, stop = periods, sx
+                    else:
+                        start, stop = 0, sx + periods
+                    for i in range(start, stop):
+                        for j in range(sy):
+                            out[i, j] = arr[i, j] - arr[i - periods, j]
+                else:
+                    if periods >= 0:
+                        start, stop = periods, sy
+                    else:
+                        start, stop = 0, sy + periods
+                    for i in range(sx):
+                        for j in range(start, stop):
+                            out[i, j] = arr[i, j] - arr[i, j - periods]
+
+
 # generated from template
 include "algos_common_helper.pxi"
 include "algos_take_helper.pxi"

pandas/_libs/algos_common_helper.pxi.in

@@ -4,77 +4,6 @@ Template for each `dtype` helper function using 1-d template
 WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
 """
 
-ctypedef fused diff_t:
-    float64_t
-    float32_t
-    int8_t
-    int16_t
-    int32_t
-    int64_t
-
-ctypedef fused out_t:
-    float32_t
-    float64_t
-
-
-@cython.boundscheck(False)
-@cython.wraparound(False)
-def diff_2d(ndarray[diff_t, ndim=2] arr,
-            ndarray[out_t, ndim=2] out,
-            Py_ssize_t periods, int axis):
-    cdef:
-        Py_ssize_t i, j, sx, sy, start, stop
-        bint f_contig = arr.flags.f_contiguous
-
-    # Disable for unsupported dtype combinations,
-    #  see https://github.com/cython/cython/issues/2646
-    if (out_t is float32_t
-            and not (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
-        raise NotImplementedError
-    elif (out_t is float64_t
-          and (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
-        raise NotImplementedError
-    else:
-        # We put this inside an indented else block to avoid cython build
-        #  warnings about unreachable code
-        sx, sy = (<object>arr).shape
-        with nogil:
-            if f_contig:
-                if axis == 0:
-                    if periods >= 0:
-                        start, stop = periods, sx
-                    else:
-                        start, stop = 0, sx + periods
-                    for j in range(sy):
-                        for i in range(start, stop):
-                            out[i, j] = arr[i, j] - arr[i - periods, j]
-                else:
-                    if periods >= 0:
-                        start, stop = periods, sy
-                    else:
-                        start, stop = 0, sy + periods
-                    for j in range(start, stop):
-                        for i in range(sx):
-                            out[i, j] = arr[i, j] - arr[i, j - periods]
-            else:
-                if axis == 0:
-                    if periods >= 0:
-                        start, stop = periods, sx
-                    else:
-                        start, stop = 0, sx + periods
-                    for i in range(start, stop):
-                        for j in range(sy):
-                            out[i, j] = arr[i, j] - arr[i - periods, j]
-                else:
-                    if periods >= 0:
-                        start, stop = periods, sy
-                    else:
-                        start, stop = 0, sy + periods
-                    for i in range(sx):
-                        for j in range(start, stop):
-                            out[i, j] = arr[i, j] - arr[i, j - periods]
-
-
 # ----------------------------------------------------------------------
 # ensure_dtype
 # ----------------------------------------------------------------------

pandas/_libs/lib.pyx

@@ -125,7 +125,7 @@ def is_scalar(val: object) -> bool:
         - Interval
         - DateOffset
         - Fraction
-        - Number
+        - Number.
 
     Returns
     -------
@@ -867,9 +867,10 @@ def is_list_like(obj: object, allow_sets: bool = True):
 
     Parameters
     ----------
-    obj : The object to check
-    allow_sets : boolean, default True
-        If this parameter is False, sets will not be considered list-like
+    obj : object
+        The object to check.
+    allow_sets : bool, default True
+        If this parameter is False, sets will not be considered list-like.
 
         .. versionadded:: 0.24.0
 

pandas/_libs/missing.pyx

@@ -121,7 +121,7 @@ cpdef ndarray[uint8_t] isnaobj(ndarray arr):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def isnaobj_old(ndarray arr):
+def isnaobj_old(arr: ndarray) -> ndarray:
     """
     Return boolean mask denoting which elements of a 1-D array are na-like,
     defined as being any of:
@@ -156,7 +156,7 @@ def isnaobj_old(ndarray arr):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def isnaobj2d(ndarray arr):
+def isnaobj2d(arr: ndarray) -> ndarray:
     """
     Return boolean mask denoting which elements of a 2-D array are na-like,
     according to the criteria defined in `checknull`:
@@ -198,7 +198,7 @@ def isnaobj2d(ndarray arr):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def isnaobj2d_old(ndarray arr):
+def isnaobj2d_old(arr: ndarray) -> ndarray:
     """
     Return boolean mask denoting which elements of a 2-D array are na-like,
     according to the criteria defined in `checknull_old`:

pandas/_libs/window.pyx

@@ -69,8 +69,8 @@ def _check_minp(win, minp, N, floor=None) -> int:
     if not util.is_integer_object(minp):
         raise ValueError("min_periods must be an integer")
     if minp > win:
-        raise ValueError("min_periods (%d) must be <= "
-                         "window (%d)" % (minp, win))
+        raise ValueError("min_periods (minp) must be <= "
+                         "window (win)".format(minp=minp, win=win))
     elif minp > N:
         minp = N + 1
     elif minp < 0:

pandas/core/arrays/interval.py

@@ -260,9 +260,9 @@ def _from_factorized(cls, values, original):
         Whether the intervals are closed on the left-side, right-side, both
         or neither.
     copy : bool, default False
-        copy the data
+        Copy the data.
     dtype : dtype or None, default None
-        If None, dtype will be inferred
+        If None, dtype will be inferred.
 
         .. versionadded:: 0.23.0
 
@@ -383,16 +383,16 @@ def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
     Parameters
     ----------
     data : array-like (1-dimensional)
-        Array of tuples
+        Array of tuples.
     closed : {'left', 'right', 'both', 'neither'}, default 'right'
         Whether the intervals are closed on the left-side, right-side, both
         or neither.
     copy : bool, default False
-        by-default copy the data, this is compat only and ignored
+        By-default copy the data, this is compat only and ignored.
     dtype : dtype or None, default None
-        If None, dtype will be inferred
+        If None, dtype will be inferred.
 
-        ..versionadded:: 0.23.0
+        .. versionadded:: 0.23.0
 
     Returns
     -------