Avoids exception when pandas.io.json.json_normalize contains items in…

.github/ISSUE_TEMPLATE.md

@@ -10,6 +10,6 @@
 #### Output of ``pd.show_versions()``
 
 <details>
-# Paste the output here
+# Paste the output here pd.show_versions() here
 
 </details>

asv_bench/benchmarks/inference.py

@@ -148,12 +148,12 @@ class to_numeric(object):
     N = 500000
 
     data_dict = {
-        'string-int': (['1'] * (N / 2)) + ([2] * (N / 2)),
-        'string-nint': (['-1'] * (N / 2)) + ([2] * (N / 2)),
+        'string-int': (['1'] * (N // 2)) + ([2] * (N // 2)),
+        'string-nint': (['-1'] * (N // 2)) + ([2] * (N // 2)),
         'datetime64': np.repeat(np.array(['1970-01-01', '1970-01-02'],
                                          dtype='datetime64[D]'), N),
-        'string-float': (['1.1'] * (N / 2)) + ([2] * (N / 2)),
-        'int-list': ([1] * (N / 2)) + ([2] * (N / 2)),
+        'string-float': (['1.1'] * (N // 2)) + ([2] * (N // 2)),
+        'int-list': ([1] * (N // 2)) + ([2] * (N // 2)),
         'int32': np.repeat(np.int32(1), N)
         }
 

ci/lint.sh

@@ -7,16 +7,10 @@ source activate pandas
 RET=0
 
 if [ "$LINT" ]; then
-    echo "Linting"
-    for path in 'api' 'core' 'indexes' 'types' 'formats' 'io' 'stats' 'compat' 'sparse' 'tools' 'tseries' 'tests' 'computation' 'util'
-    do
-        echo "linting -> pandas/$path"
-        flake8 pandas/$path --filename '*.py'
-        if [ $? -ne "0" ]; then
-            RET=1
-        fi
-
-    done
+    # pandas/rpy is deprecated and will be removed.
+    # pandas/src is C code, so no need to search there.
+    echo "Linting  *.py"
+    flake8 pandas --filename '*.py' --exclude pandas/rpy,pandas/src
     echo "Linting *.py DONE"
 
     echo "Linting *.pyx"

ci/requirements-3.4.build

@@ -1,3 +1,3 @@
 numpy=1.8.1
-cython
+cython=0.24.1
 libgfortran=1.0

ci/travis_encrypt_gbq.sh

@@ -1,11 +1,10 @@
 #!/bin/bash
 
 GBQ_JSON_FILE=$1
-GBQ_PROJECT_ID=$2
 
-if [[ $# -ne 2 ]]; then
+if [[ $# -ne 1 ]]; then
     echo -e "Too few arguments.\nUsage: ./travis_encrypt_gbq.sh "\
-    "<gbq-json-credentials-file> <gbq-project-id>"
+    "<gbq-json-credentials-file>"
     exit 1
 fi
 
@@ -23,9 +22,9 @@ echo "Encrypting $GBQ_JSON_FILE..."
 read -d "\n" TRAVIS_KEY TRAVIS_IV <<<$(travis encrypt-file $GBQ_JSON_FILE \
 travis_gbq.json.enc -f | grep -o "\w*_iv\|\w*_key");
 
-echo "Adding your secure key and project id to travis_gbq_config.txt ..."
-echo -e "TRAVIS_IV_ENV=$TRAVIS_IV\nTRAVIS_KEY_ENV=$TRAVIS_KEY\n"\
-"GBQ_PROJECT_ID='$GBQ_PROJECT_ID'" > travis_gbq_config.txt
+echo "Adding your secure key to travis_gbq_config.txt ..."
+echo -e "TRAVIS_IV_ENV=$TRAVIS_IV\nTRAVIS_KEY_ENV=$TRAVIS_KEY"\
+> travis_gbq_config.txt
 
 echo "Done. Removing file $GBQ_JSON_FILE"
 rm $GBQ_JSON_FILE

ci/travis_gbq_config.txt

@@ -1,3 +1,2 @@
 TRAVIS_IV_ENV=encrypted_1d9d7b1f171b_iv
 TRAVIS_KEY_ENV=encrypted_1d9d7b1f171b_key
-GBQ_PROJECT_ID='pandas-travis'

ci/travis_process_gbq_encryption.sh

@@ -2,10 +2,12 @@
 
 source ci/travis_gbq_config.txt
 
-if [[ -n ${!TRAVIS_IV_ENV} ]]; then
+if [[ -n ${SERVICE_ACCOUNT_KEY} ]]; then
+    echo "${SERVICE_ACCOUNT_KEY}" > ci/travis_gbq.json;
+elif [[ -n ${!TRAVIS_IV_ENV} ]]; then
     openssl aes-256-cbc -K ${!TRAVIS_KEY_ENV} -iv ${!TRAVIS_IV_ENV} \
     -in ci/travis_gbq.json.enc -out ci/travis_gbq.json -d;
-    export GBQ_PROJECT_ID=$GBQ_PROJECT_ID;
+    export GBQ_PROJECT_ID='pandas-travis';
     echo 'Successfully decrypted gbq credentials'
 fi
 

doc/source/contributing.rst

@@ -643,20 +643,22 @@ on Travis-CI and are only accessible from the pandas-dev/pandas repository. The
 credentials won't be available on forks of pandas. Here are the steps to run
 gbq integration tests on a forked repository:
 
-#. First, complete all the steps in the `Encrypting Files Prerequisites
-   <https://docs.travis-ci.com/user/encrypting-files/>`__ section.
-#. Sign into `Travis <https://travis-ci.org/>`__ using your GitHub account.
-#. Enable your forked repository of pandas for testing in `Travis
-   <https://travis-ci.org/profile/>`__.
-#. Run the following command from terminal where the current working directory
-   is the ``ci`` folder::
-
-    ./travis_encrypt_gbq.sh <gbq-json-credentials-file> <gbq-project-id>
-
-#. Create a new branch from the branch used in your pull request. Commit the
-   encrypted file called ``travis_gbq.json.enc`` as well as the file
-   ``travis_gbq_config.txt``, in an otherwise empty commit. DO NOT commit the
-   ``*.json`` file which contains your unencrypted private key.
+#. Go to `Travis CI <https://travis-ci.org/>`__ and sign in with your GitHub
+   account.
+#. Click on the ``+`` icon next to the ``My Repositories`` list and enable
+   Travis builds for your fork.
+#. Click on the gear icon to edit your travis build, and add two environment
+   variables:
+
+   - ``GBQ_PROJECT_ID`` with the value being the ID of your BigQuery project.
+
+   - ``SERVICE_ACCOUNT_KEY`` with the value being the contents of the JSON key
+     that you downloaded for your service account. Use single quotes around
+     your JSON key to ensure that it is treated as a string.
+
+   For both environment variables, keep the "Display value in build log" option
+   DISABLED. These variables contain sensitive data and you do not want their
+   contents being exposed in build logs.
 #. Your branch should be tested automatically once it is pushed. You can check
    the status by visiting your Travis branches page which exists at the
    following location: https://travis-ci.org/your-user-name/pandas/branches .

doc/source/ecosystem.rst

@@ -143,7 +143,7 @@ both "column wise min/max and global min/max coloring."
 API
 -----
 
-`pandas-datareader <https://github.com/pandas-dev/pandas-datareader>`__
+`pandas-datareader <https://github.com/pydata/pandas-datareader>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 ``pandas-datareader`` is a remote data access library for pandas. ``pandas.io`` from pandas < 0.17.0 is now refactored/split-off to and importable from ``pandas_datareader`` (PyPI:``pandas-datareader``). Many/most of the supported APIs have at least a documentation paragraph in the `pandas-datareader docs <https://pandas-datareader.readthedocs.io/en/latest/>`_:
 

doc/source/io.rst

@@ -2789,7 +2789,7 @@ both on the writing (serialization), and reading (deserialization).
    | 0.17 / Python 3      | >=0.18 / any Python    |
    +----------------------+------------------------+
    | 0.18                 | >= 0.18                |
-   +======================+========================+
+   +----------------------+------------------------+
 
    Reading (files packed by older versions) is backward-compatibile, except for files packed with 0.17 in Python 2, in which case only they can only be unpacked in Python 2.
 

doc/source/release.rst

@@ -37,6 +37,50 @@ analysis / manipulation tool available in any language.
 * Binary installers on PyPI: http://pypi.python.org/pypi/pandas
 * Documentation: http://pandas.pydata.org
 
+
+pandas 0.19.1
+-------------
+
+**Release date:** November 3, 2016
+
+This is a minor bug-fix release from 0.19.0 and includes some small regression fixes,
+bug fixes and performance improvements.
+
+See the :ref:`v0.19.1 Whatsnew <whatsnew_0191>` page for an overview of all
+bugs that have been fixed in 0.19.1.
+
+Thanks
+~~~~~~
+
+- Adam Chainz
+- Anthonios Partheniou
+- Arash Rouhani
+- Ben Kandel
+- Brandon M. Burroughs
+- Chris
+- chris-b1
+- Chris Warth
+- David Krych
+- dubourg
+- gfyoung
+- Iván Vallés Pérez
+- Jeff Reback
+- Joe Jevnik
+- Jon M. Mease
+- Joris Van den Bossche
+- Josh Owen
+- Keshav Ramaswamy
+- Larry Ren
+- mattrijk
+- Michael Felt
+- paul-mannino
+- Piotr Chromiec
+- Robert Bradshaw
+- Sinhrks
+- Thiago Serafim
+- Tom Bird
+
+
 pandas 0.19.0
 -------------
 

doc/source/whatsnew/v0.13.0.txt

@@ -600,7 +600,7 @@ Enhancements
   .. ipython:: python
 
      t = Timestamp('20130101 09:01:02')
-     t + pd.datetools.Nano(123)
+     t + pd.tseries.offsets.Nano(123)
 
 - A new method, ``isin`` for DataFrames, which plays nicely with boolean indexing. The argument to ``isin``, what we're comparing the DataFrame to, can be a DataFrame, Series, dict, or array of values. See :ref:`the docs<indexing.basics.indexing_isin>` for more.
 

doc/source/whatsnew/v0.19.1.txt

@@ -1,15 +1,12 @@
 .. _whatsnew_0191:
 
-v0.19.1 (????, 2016)
----------------------
+v0.19.1 (November 3, 2016)
+--------------------------
 
-This is a minor bug-fix release from 0.19.0 and includes a large number of
-bug fixes along with several new features, enhancements, and performance improvements.
+This is a minor bug-fix release from 0.19.0 and includes some small regression fixes,
+bug fixes and performance improvements.
 We recommend that all users upgrade to this version.
 
-Highlights include:
-
-
 .. contents:: What's new in v0.19.1
     :local:
     :backlinks: none
@@ -21,60 +18,45 @@ Performance Improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
 - Fixed performance regression in factorization of ``Period`` data (:issue:`14338`)
+- Fixed performance regression in ``Series.asof(where)`` when ``where`` is a scalar (:issue:`14461`)
+- Improved performance in ``DataFrame.asof(where)`` when ``where`` is a scalar (:issue:`14461`)
 - Improved performance in ``.to_json()`` when ``lines=True`` (:issue:`14408`)
-- Improved performance in ``Series.asof(where)`` when ``where`` is a scalar (:issue:`14461)
-- Improved performance in ``DataFrame.asof(where)`` when ``where`` is a scalar (:issue:`14461)
-
-
+- Improved performance in certain types of `loc` indexing with a MultiIndex (:issue:`14551`).
 
 
 .. _whatsnew_0191.bug_fixes:
 
 Bug Fixes
 ~~~~~~~~~
 
-
-
-
+- Source installs from PyPI will now again work without ``cython`` installed, as in previous versions (:issue:`14204`)
+- Compat with Cython 0.25 for building (:issue:`14496`)
+- Fixed regression where user-provided file handles were closed in ``read_csv`` (c engine) (:issue:`14418`).
+- Fixed regression in ``DataFrame.quantile`` when missing values where present in some columns (:issue:`14357`).
+- Fixed regression in ``Index.difference`` where the ``freq`` of a ``DatetimeIndex`` was incorrectly set (:issue:`14323`)
+- Added back ``pandas.core.common.array_equivalent`` with a deprecation warning (:issue:`14555`).
+- Bug in ``pd.read_csv`` for the C engine in which quotation marks were improperly parsed in skipped rows (:issue:`14459`)
+- Bug in ``pd.read_csv`` for Python 2.x in which Unicode quote characters were no longer being respected (:issue:`14477`)
+- Fixed regression in ``Index.append`` when categorical indices were appended (:issue:`14545`).
+- Fixed regression in ``pd.DataFrame`` where constructor fails when given dict with ``None`` value (:issue:`14381`)
+- Fixed regression in ``DatetimeIndex._maybe_cast_slice_bound`` when index is empty (:issue:`14354`).
 - Bug in localizing an ambiguous timezone when a boolean is passed (:issue:`14402`)
 - Bug in ``TimedeltaIndex`` addition with a Datetime-like object where addition overflow in the negative direction was not being caught (:issue:`14068`, :issue:`14453`)
-
-
-
 - Bug in string indexing against data with ``object`` ``Index`` may raise ``AttributeError`` (:issue:`14424`)
 - Corrrecly raise ``ValueError`` on empty input to ``pd.eval()`` and ``df.query()`` (:issue:`13139`)
-
-
 - Bug in ``RangeIndex.intersection`` when result is a empty set (:issue:`14364`).
-- Bug in union of differences from a ``DatetimeIndex`; this is a regression in 0.19.0 from 0.18.1 (:issue:`14323`)
-
 - Bug in groupby-transform broadcasting that could cause incorrect dtype coercion (:issue:`14457`)
-
-
 - Bug in ``Series.__setitem__`` which allowed mutating read-only arrays (:issue:`14359`).
-
-
-- Source installs from PyPI will now work without ``cython`` installed, as in previous versions (:issue:`14204`)
 - Bug in ``DataFrame.insert`` where multiple calls with duplicate columns can fail (:issue:`14291`)
-
 - ``pd.merge()`` will raise ``ValueError`` with non-boolean parameters in passed boolean type arguments (:issue:`14434`)
-
-
 - Bug in ``Timestamp`` where dates very near the minimum (1677-09) could underflow on creation (:issue:`14415`)
-
 - Bug in ``pd.concat`` where names of the ``keys`` were not propagated to the resulting ``MultiIndex`` (:issue:`14252`)
 - Bug in ``pd.concat`` where ``axis`` cannot take string parameters ``'rows'`` or ``'columns'`` (:issue:`14369`)
 - Bug in ``pd.concat`` with dataframes heterogeneous in length and tuple ``keys`` (:issue:`14438`)
 - Bug in ``MultiIndex.set_levels`` where illegal level values were still set after raising an error (:issue:`13754`)
 - Bug in ``DataFrame.to_json`` where ``lines=True`` and a value contained a ``}`` character (:issue:`14391`)
 - Bug in ``df.groupby`` causing an ``AttributeError`` when grouping a single index frame by a column and the index level (:issue`14327`)
 - Bug in ``df.groupby`` where ``TypeError`` raised when ``pd.Grouper(key=...)`` is passed in a list (:issue:`14334`)
-
-
-
-
-
-
-
-
-- Bug in ``pd.pivot_table`` may raise ``TypeError`` or ``ValueError`` when ``index`` or ``columns`` is not scalar and ``values`` is not specified (:issue:`14380`)
+- Bug in ``pd.pivot_table`` may raise ``TypeError`` or ``ValueError`` when ``index`` or ``columns``
+  is not scalar and ``values`` is not specified (:issue:`14380`)
+- Enhancement in ``pandas.io.json.json_normalize``Added errors{'raise','ignore'} for keys not found in meta (:issue: '14505')

pandas/api/tests/test_api.py

@@ -1,5 +1,7 @@
 # -*- coding: utf-8 -*-
 
+import numpy as np
+
 import pandas as pd
 from pandas.core import common as com
 from pandas import api
@@ -184,6 +186,11 @@ def test_deprecation_core_common(self):
         for t in self.allowed:
             self.check_deprecation(getattr(com, t), getattr(types, t))
 
+    def test_deprecation_core_common_array_equivalent(self):
+
+        with tm.assert_produces_warning(DeprecationWarning):
+            com.array_equivalent(np.array([1, 2]), np.array([1, 2]))
+
     def test_deprecation_core_common_moved(self):
 
         # these are in pandas.types.common

pandas/core/common.py

@@ -64,6 +64,15 @@ def wrapper(*args, **kwargs):
     setattr(m, t, outer(t))
 
 
+# deprecate array_equivalent
+
+def array_equivalent(*args, **kwargs):
+    warnings.warn("'pandas.core.common.array_equivalent' is deprecated and "
+                  "is no longer public API", DeprecationWarning, stacklevel=2)
+    from pandas.types import missing
+    return missing.array_equivalent(*args, **kwargs)
+
+
 class PandasError(Exception):
     pass
 

pandas/core/generic.py

@@ -4008,6 +4008,8 @@ def asfreq(self, freq, method=None, how=None, normalize=False):
         -------
         converted : type of caller
 
+        Notes
+        -----
         To learn more about the frequency strings, please see `this link
         <http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases>`__.
         """

pandas/core/groupby.py

@@ -6,7 +6,7 @@
 import warnings
 import copy
 
-from pandas.compat import(
+from pandas.compat import (
     zip, range, long, lzip,
     callable, map
 )