Merge branch 'master' of https://github.com/pandas-dev/pandas

Author: m-charlton

appveyor.yml

@@ -17,20 +17,19 @@ environment:
 
   matrix:
 
-    # disable python 3.4 ATM
-    #- PYTHON: "C:\\Python34_64"
-    #  PYTHON_VERSION: "3.4"
-    #  PYTHON_ARCH: "64"
-    #  CONDA_PY: "34"
-    #  CONDA_NPY: "19"
-
-    - PYTHON: "C:\\Python27_64"
+    - CONDA_ROOT: "C:\\Miniconda3.5_64"
+      PYTHON_VERSION: "3.6"
+      PYTHON_ARCH: "64"
+      CONDA_PY: "36"
+      CONDA_NPY: "111"
+
+    - CONDA_ROOT: "C:\\Miniconda3.5_64"
       PYTHON_VERSION: "2.7"
       PYTHON_ARCH: "64"
       CONDA_PY: "27"
       CONDA_NPY: "110"
 
-    - PYTHON: "C:\\Python35_64"
+    - CONDA_ROOT: "C:\\Miniconda3.5_64"
       PYTHON_VERSION: "3.5"
       PYTHON_ARCH: "64"
       CONDA_PY: "35"
@@ -45,9 +44,6 @@ platform:
 # all our python builds have to happen in tests_script...
 build: false
 
-init:
-  - "ECHO %PYTHON_VERSION% %PYTHON%"
-
 install:
   # cancel older builds for the same PR
   - ps: if ($env:APPVEYOR_PULL_REQUEST_NUMBER -and $env:APPVEYOR_BUILD_NUMBER -ne ((Invoke-RestMethod `
@@ -58,7 +54,7 @@ install:
   # this installs the appropriate Miniconda (Py2/Py3, 32/64 bit)
   # updates conda & installs: conda-build jinja2 anaconda-client
   - powershell .\ci\install.ps1
-  - SET PATH=%PYTHON%;%PYTHON%\Scripts;%PATH%
+  - SET PATH=%CONDA_ROOT%;%CONDA_ROOT%\Scripts;%PATH%
   - echo "install"
   - cd
   - ls -ltr
@@ -69,22 +65,15 @@ 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
-
-  # fix conda-build version
-  # https://github.com/conda/conda-build/issues/1001
-  # disabling 3.4 as windows complains upon compiling byte
-  # code
-
-  - cmd: conda install conda-build=1.21.7
+  #- cmd: conda update -q conda
+  - cmd: conda install conda=4.2.15
   - cmd: conda config --set ssl_verify false
 
   # add the pandas channel *before* defaults to have defaults take priority
   - cmd: conda config --add channels conda-forge
   - cmd: conda config --add channels pandas
   - cmd: conda config --remove channels defaults
   - cmd: conda config --add channels defaults
-  - cmd: conda install anaconda-client
 
   # this is now the downloaded conda...
   - cmd: conda info -a
@@ -98,6 +87,8 @@ install:
   - SET REQ=ci\requirements-%PYTHON_VERSION%-%PYTHON_ARCH%.run
   - cmd: echo "installing requirements from %REQ%"
   - cmd: conda install -n pandas -q --file=%REQ%
+  - cmd: conda list -n pandas
+  - cmd: echo "installing requirements from %REQ% - done"
   - ps: conda install -n pandas (conda build ci\appveyor.recipe -q --output)
 
 test_script:

asv_bench/benchmarks/groupby.py

@@ -690,6 +690,3 @@ def time_shift(self):
     def time_transform_dataframe(self):
         # GH 12737
         self.df_nans.groupby('key').transform('first')
-
-
-

asv_bench/benchmarks/plotting.py

@@ -20,6 +20,9 @@ def setup(self):
     def time_plot_regular(self):
         self.df.plot()
 
+    def time_plot_regular_compat(self):
+        self.df.plot(x_compat=True)
+
 
 class Misc(object):
     goal_time = 0.6

ci/appveyor.recipe/meta.yaml

@@ -1,6 +1,6 @@
 package:
     name: pandas
-    version: 0.18.1
+    version: 0.20.0
 
 build:
     number: {{environ.get('APPVEYOR_BUILD_NUMBER', 0)}}  # [win]

ci/install.ps1

@@ -84,9 +84,9 @@ function UpdateConda ($python_home) {
 
 
 function main () {
-    InstallMiniconda $env:PYTHON_VERSION $env:PYTHON_ARCH $env:PYTHON
-    UpdateConda $env:PYTHON
-    InstallCondaPackages $env:PYTHON "conda-build jinja2 anaconda-client"
+    InstallMiniconda "3.5" $env:PYTHON_ARCH $env:CONDA_ROOT
+    UpdateConda $env:CONDA_ROOT
+    InstallCondaPackages $env:CONDA_ROOT "conda-build jinja2 anaconda-client"
 }
 
 main

ci/install_appveyor.ps1

@@ -0,0 +1,13 @@
+python-dateutil
+pytz
+numpy
+openpyxl
+xlsxwriter
+xlrd
+#xlwt
+scipy
+feather-format
+numexpr
+pytables
+matplotlib
+blosc

ci/requirements-3.6-64.run

@@ -0,0 +1 @@
+xlwt

ci/requirements-3.6.pip

@@ -2,3 +2,19 @@ python-dateutil
 pytz
 numpy
 scipy
+openpyxl
+xlsxwriter
+xlrd
+# xlwt (installed via pip)
+numexpr
+pytables
+# matplotlib (not avail on defaults ATM)
+lxml
+html5lib
+jinja2
+sqlalchemy
+pymysql
+# psycopg2 (not avail on defaults ATM)
+beautifulsoup4
+s3fs
+xarray

ci/requirements-3.6.run

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+source activate pandas
+
+echo "install 36"
+
+conda install -n pandas -c conda-forge feather-format

ci/requirements-3.6.sh

@@ -418,7 +418,6 @@ Reshaping, sorting
    Series.reorder_levels
    Series.sort_values
    Series.sort_index
-   Series.sortlevel
    Series.swaplevel
    Series.unstack
    Series.searchsorted
@@ -931,7 +930,6 @@ Reshaping, sorting, transposing
    DataFrame.reorder_levels
    DataFrame.sort_values
    DataFrame.sort_index
-   DataFrame.sortlevel
    DataFrame.nlargest
    DataFrame.nsmallest
    DataFrame.swaplevel

doc/source/api.rst

@@ -187,6 +187,16 @@ skipinitialspace : boolean, default ``False``
 skiprows : list-like or integer, default ``None``
   Line numbers to skip (0-indexed) or number of lines to skip (int) at the start
   of the file.
+
+  If callable, the callable function will be evaluated against the row
+  indices, returning True if the row should be skipped and False otherwise:
+
+  .. ipython:: python
+
+     data = 'col1,col2,col3\na,b,1\na,b,2\nc,d,3'
+     pd.read_csv(StringIO(data))
+     pd.read_csv(StringIO(data), skiprows=lambda x: x % 2 != 0)
+
 skipfooter : int, default ``0``
   Number of lines at bottom of file to skip (unsupported with engine='c').
 skip_footer : int, default ``0``
@@ -644,6 +654,15 @@ file, either using the column names, position numbers or a callable:
     pd.read_csv(StringIO(data), usecols=[0, 2, 3])
     pd.read_csv(StringIO(data), usecols=lambda x: x.upper() in ['A', 'C'])
 
+The ``usecols`` argument can also be used to specify which columns not to
+use in the final result:
+
+.. ipython:: python
+   pd.read_csv(StringIO(data), usecols=lambda x: x not in ['a', 'c'])
+
+In this case, the callable is specifying that we exclude the "a" and "c"
+columns from the output.
+
 Comments and Empty Lines
 ''''''''''''''''''''''''
 
@@ -1206,6 +1225,19 @@ You can elect to skip bad lines:
     0  1  2   3
     1  8  9  10
 
+You can also use the ``usecols`` parameter to eliminate extraneous column
+data that appear in some lines but not others:
+
+.. code-block:: ipython
+
+   In [30]: pd.read_csv(StringIO(data), usecols=[0, 1, 2])
+
+    Out[30]:
+       a  b   c
+    0  1  2   3
+    1  4  5   6
+    2  8  9  10
+
 .. _io.quoting:
 
 Quoting and Escape Characters