DOC/CI: run doctests on travis (pandas-dev#19952)

.travis.yml

@@ -56,7 +56,7 @@ matrix:
           - python-gtk2
     - dist: trusty
       env:
-        - JOB="3.6, coverage" ENV_FILE="ci/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
+        - JOB="3.6, coverage" ENV_FILE="ci/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true DOCTEST=true
     # In allow_failures
     - dist: trusty
       env:
@@ -119,6 +119,7 @@ script:
   - ci/script_single.sh
   - ci/script_multi.sh
   - ci/lint.sh
+  - ci/doctests.sh
   - echo "checking imports"
   - source activate pandas && python ci/check_imports.py
   - echo "script done"

ci/build_docs.sh

@@ -8,15 +8,6 @@ fi
 cd "$TRAVIS_BUILD_DIR"
 echo "inside $0"
 
-git show --pretty="format:" --name-only HEAD~5.. --first-parent | grep -P "rst|txt|doc"
-
-# if [ "$?" != "0" ]; then
-#     echo "Skipping doc build, none were modified"
-#     # nope, skip docs build
-#     exit 0
-# fi
-
-
 if [ "$DOC" ]; then
 
     echo "Will build docs"
@@ -60,15 +51,6 @@ if [ "$DOC" ]; then
     git remote -v
 
     git push origin gh-pages -f
-
-    echo "Running doctests"
-    cd "$TRAVIS_BUILD_DIR"
-    pytest --doctest-modules \
-           pandas/core/reshape/concat.py \
-           pandas/core/reshape/pivot.py \
-           pandas/core/reshape/reshape.py \
-           pandas/core/reshape/tile.py
-
 fi
 
 exit 0

ci/doctests.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+
+echo "inside $0"
+
+
+source activate pandas
+cd "$TRAVIS_BUILD_DIR"
+
+RET=0
+
+if [ "$DOCTEST" ]; then
+
+    echo "Running doctests"
+
+    # running all doctests is not yet working
+    # pytest --doctest-modules --ignore=pandas/tests -v  pandas
+
+    # if [ $? -ne "0" ]; then
+    #     RET=1
+    # fi
+
+    # DataFrame / Series docstrings
+    pytest --doctest-modules -v pandas/core/frame.py \
+        -k"-assign -axes -combine -isin -itertuples -join -nlargest -nsmallest -nunique -pivot_table -quantile -query -reindex -reindex_axis -replace -round -set_index -stack -to_dict -to_records -to_stata -transform"
+
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
+
+    pytest --doctest-modules -v pandas/core/series.py \
+        -k"-agg -map -nlargest -nonzero -nsmallest -reindex -searchsorted -to_dict"
+
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
+
+    pytest --doctest-modules -v pandas/core/generic.py \
+        -k"-_set_axis_name -_xs -describe -droplevel -groupby -interpolate -pct_change -pipe -reindex -reindex_axis -resample -sample -to_json -to_xarray -transform -transpose -values -xs"
+
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
+
+    # top-level reshaping functions
+    pytest --doctest-modules -v \
+        pandas/core/reshape/concat.py \
+        pandas/core/reshape/pivot.py \
+        pandas/core/reshape/reshape.py \
+        pandas/core/reshape/tile.py \
+        -k"-crosstab -pivot_table -cut"
+
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
+
+else
+    echo "NOT running doctests"
+fi
+
+exit $RET

doc/source/contributing.rst

@@ -365,6 +365,31 @@ This will identify methods documented in ``doc/source/api.rst`` that are not act
 class methods, and existing methods that are not documented in ``doc/source/api.rst``.
 
 
+Updating a *pandas* docstring
+-----------------------------
+
+When improving a single function or method's docstring, it is not necessarily
+needed to build the full documentation (see next section).
+However, there is a script that checks a docstring (for example for the ``DataFrame.mean`` method)::
+
+    python scripts/validate_docstrings.py pandas.DataFrame.mean
+
+This script will indicate some formatting errors if present, and will also
+run and test the examples included in the docstring.
+Check the :ref:`pandas docstring guide <docstring>` for a detailed guide
+on how to format the docstring.
+
+The examples in the docstring ('doctests') must be valid Python code,
+that in a deterministic way returns the presented output, and that can be
+copied and run by users. This can be checked with the script above, and is
+also tested on Travis. A failing doctest will be a blocker for merging a PR.
+Check the :ref:`examples <docstring.examples>` section in the docstring guide
+for some tips and tricks to get the doctests passing.
+
+When doing a PR with a docstring update, it is good to post the
+output of the validation script in a comment on github.
+
+
 How to build the *pandas* documentation
 ---------------------------------------
 

pandas/core/config.py

@@ -384,7 +384,7 @@ class option_context(object):
     --------
 
     >>> with option_context('display.max_rows', 10, 'display.max_columns', 5):
-            ...
+    ...     ...
 
     """
 

pandas/core/frame.py

@@ -314,15 +314,13 @@ class DataFrame(NDFrame):
 
     Constructing DataFrame from numpy ndarray:
 
-    >>> df2 = pd.DataFrame(np.random.randint(low=0, high=10, size=(5, 5)),
-    ...                    columns=['a', 'b', 'c', 'd', 'e'])
+    >>> df2 = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]),
+    ...                    columns=['a', 'b', 'c'])
     >>> df2
-        a   b   c   d   e
-    0   2   8   8   3   4
-    1   4   2   9   0   9
-    2   1   0   7   8   0
-    3   5   1   7   1   3
-    4   6   0   2   4   2
+       a  b  c
+    0  1  2  3
+    1  4  5  6
+    2  7  8  9
 
     See also
     --------

pandas/core/generic.py

@@ -738,14 +738,14 @@ def droplevel(self, level, axis=0):
         Examples
         --------
         >>> df = pd.DataFrame([
-        ...:     [1, 2, 3, 4],
-        ...:     [5, 6, 7, 8],
-        ...:     [9, 10, 11, 12]
-        ...: ]).set_index([0, 1]).rename_axis(['a', 'b'])
+        ...     [1, 2, 3, 4],
+        ...     [5, 6, 7, 8],
+        ...     [9, 10, 11, 12]
+        ... ]).set_index([0, 1]).rename_axis(['a', 'b'])
 
         >>> df.columns = pd.MultiIndex.from_tuples([
-        ...:    ('c', 'e'), ('d', 'f')
-        ...:], names=['level_1', 'level_2'])
+        ...    ('c', 'e'), ('d', 'f')
+        ... ], names=['level_1', 'level_2'])
 
         >>> df
         level_1   c   d

pandas/util/testing.py

@@ -591,7 +591,7 @@ def set_defaultencoding(encoding):
 
 
 def capture_stdout(f):
-    """
+    r"""
     Decorator to capture stdout in a buffer so that it can be checked
     (or suppressed) during testing.
 
@@ -609,7 +609,6 @@ def capture_stdout(f):
     --------
 
     >>> from pandas.util.testing import capture_stdout
-    >>>
     >>> import sys
     >>>
     >>> @capture_stdout
@@ -639,7 +638,7 @@ def wrapper(*args, **kwargs):
 
 
 def capture_stderr(f):
-    """
+    r"""
     Decorator to capture stderr in a buffer so that it can be checked
     (or suppressed) during testing.
 
@@ -657,7 +656,6 @@ def capture_stderr(f):
     --------
 
     >>> from pandas.util.testing import capture_stderr
-    >>>
     >>> import sys
     >>>
     >>> @capture_stderr
@@ -2370,7 +2368,7 @@ def wrapper(*args, **kwargs):
 
 def assert_raises_regex(_exception, _regexp, _callable=None,
                         *args, **kwargs):
-    r"""
+    """
     Check that the specified Exception is raised and that the error message
     matches a given regular expression pattern. This may be a regular
     expression object or a string containing a regular expression suitable
@@ -2396,6 +2394,7 @@ def assert_raises_regex(_exception, _regexp, _callable=None,
     AssertionError: "pear" does not match "'apple'"
 
     You can also use this in a with statement.
+
     >>> with assert_raises_regex(TypeError, 'unsupported operand type\(s\)'):
     ...     1 + {}
     >>> with assert_raises_regex(TypeError, 'banana'):

setup.cfg

@@ -38,5 +38,5 @@ markers =
     slow: mark a test as slow
     network: mark a test as network
     high_memory: mark a test as a high-memory only
+doctest_optionflags = NORMALIZE_WHITESPACE IGNORE_EXCEPTION_DETAIL
 addopts = --strict-data-files
-doctest_optionflags= NORMALIZE_WHITESPACE IGNORE_EXCEPTION_DETAIL