merge for update

Author: makbigc

.travis.yml

@@ -30,6 +30,12 @@ matrix:
       - python: 3.5
 
     include:
+    - dist: bionic
+      # 18.04
+      python: 3.8-dev
+      env:
+        - JOB="3.8-dev" PATTERN="(not slow and not network)"
+
     - dist: trusty
       env:
         - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network)"
@@ -71,24 +77,27 @@ before_install:
   # This overrides travis and tells it to look nowhere.
   - export BOTO_CONFIG=/dev/null
 
+
 install:
   - echo "install start"
   - ci/prep_cython_cache.sh
   - ci/setup_env.sh
   - ci/submit_cython_cache.sh
   - echo "install done"
 
+
 before_script:
   # display server (for clipboard functionality) needs to be started here,
   # does not work if done in install:setup_env.sh (GH-26103)
   - export DISPLAY=":99.0"
   - echo "sh -e /etc/init.d/xvfb start"
-  - sh -e /etc/init.d/xvfb start
+  - if [ "$JOB" != "3.8-dev" ]; then sh -e /etc/init.d/xvfb start; fi
   - sleep 3
 
 script:
   - echo "script start"
-  - source activate pandas-dev
+  - echo "$JOB"
+  - if [ "$JOB" != "3.8-dev" ]; then source activate pandas-dev; fi
   - ci/run_tests.sh
 
 after_script:

README.md

@@ -1,5 +1,5 @@
 <div align="center">
-  <img src="https://github.com/pandas-dev/pandas/blob/master/doc/logo/pandas_logo.png"><br>
+  <img src="https://dev.pandas.io/static/img/pandas.svg"><br>
 </div>
 
 -----------------

asv_bench/benchmarks/ctors.py

@@ -67,7 +67,7 @@ class SeriesConstructors:
     def setup(self, data_fmt, with_index, dtype):
         if data_fmt in (gen_of_str, gen_of_tuples) and with_index:
             raise NotImplementedError(
-                "Series constructors do not support " "using generators with indexes"
+                "Series constructors do not support using generators with indexes"
             )
         N = 10 ** 4
         if dtype == "float":

asv_bench/benchmarks/eval.py

@@ -27,7 +27,7 @@ def time_add(self, engine, threads):
 
     def time_and(self, engine, threads):
         pd.eval(
-            "(self.df > 0) & (self.df2 > 0) & " "(self.df3 > 0) & (self.df4 > 0)",
+            "(self.df > 0) & (self.df2 > 0) & (self.df3 > 0) & (self.df4 > 0)",
             engine=engine,
         )
 

asv_bench/benchmarks/io/hdf.py

@@ -88,11 +88,11 @@ def time_write_store_table_dc(self):
 
     def time_query_store_table_wide(self):
         self.store.select(
-            "table_wide", where="index > self.start_wide and " "index < self.stop_wide"
+            "table_wide", where="index > self.start_wide and index < self.stop_wide"
         )
 
     def time_query_store_table(self):
-        self.store.select("table", where="index > self.start and " "index < self.stop")
+        self.store.select("table", where="index > self.start and index < self.stop")
 
     def time_store_repr(self):
         repr(self.store)

asv_bench/benchmarks/join_merge.py

@@ -273,10 +273,10 @@ def time_merge_ordered(self):
 
 
 class MergeAsof:
-    params = [["backward", "forward", "nearest"]]
-    param_names = ["direction"]
+    params = [["backward", "forward", "nearest"], [None, 5]]
+    param_names = ["direction", "tolerance"]
 
-    def setup(self, direction):
+    def setup(self, direction, tolerance):
         one_count = 200000
         two_count = 1000000
 
@@ -303,6 +303,9 @@ def setup(self, direction):
         df1["time32"] = np.int32(df1.time)
         df2["time32"] = np.int32(df2.time)
 
+        df1["timeu64"] = np.uint64(df1.time)
+        df2["timeu64"] = np.uint64(df2.time)
+
         self.df1a = df1[["time", "value1"]]
         self.df2a = df2[["time", "value2"]]
         self.df1b = df1[["time", "key", "value1"]]
@@ -313,22 +316,52 @@ def setup(self, direction):
         self.df2d = df2[["time32", "value2"]]
         self.df1e = df1[["time", "key", "key2", "value1"]]
         self.df2e = df2[["time", "key", "key2", "value2"]]
+        self.df1f = df1[["timeu64", "value1"]]
+        self.df2f = df2[["timeu64", "value2"]]
+
+    def time_on_int(self, direction, tolerance):
+        merge_asof(
+            self.df1a, self.df2a, on="time", direction=direction, tolerance=tolerance
+        )
 
-    def time_on_int(self, direction):
-        merge_asof(self.df1a, self.df2a, on="time", direction=direction)
+    def time_on_int32(self, direction, tolerance):
+        merge_asof(
+            self.df1d, self.df2d, on="time32", direction=direction, tolerance=tolerance
+        )
 
-    def time_on_int32(self, direction):
-        merge_asof(self.df1d, self.df2d, on="time32", direction=direction)
+    def time_on_uint64(self, direction, tolerance):
+        merge_asof(
+            self.df1f, self.df2f, on="timeu64", direction=direction, tolerance=tolerance
+        )
 
-    def time_by_object(self, direction):
-        merge_asof(self.df1b, self.df2b, on="time", by="key", direction=direction)
+    def time_by_object(self, direction, tolerance):
+        merge_asof(
+            self.df1b,
+            self.df2b,
+            on="time",
+            by="key",
+            direction=direction,
+            tolerance=tolerance,
+        )
 
-    def time_by_int(self, direction):
-        merge_asof(self.df1c, self.df2c, on="time", by="key2", direction=direction)
+    def time_by_int(self, direction, tolerance):
+        merge_asof(
+            self.df1c,
+            self.df2c,
+            on="time",
+            by="key2",
+            direction=direction,
+            tolerance=tolerance,
+        )
 
-    def time_multiby(self, direction):
+    def time_multiby(self, direction, tolerance):
         merge_asof(
-            self.df1e, self.df2e, on="time", by=["key", "key2"], direction=direction
+            self.df1e,
+            self.df2e,
+            on="time",
+            by=["key", "key2"],
+            direction=direction,
+            tolerance=tolerance,
         )
 
 

asv_bench/benchmarks/rolling.py

@@ -28,15 +28,15 @@ def peakmem_rolling(self, constructor, window, dtype, method):
 class Apply:
     params = (
         ["DataFrame", "Series"],
-        [10, 1000],
+        [3, 300],
         ["int", "float"],
         [sum, np.sum, lambda x: np.sum(x) + 5],
         [True, False],
     )
-    param_names = ["contructor", "window", "dtype", "function", "raw"]
+    param_names = ["constructor", "window", "dtype", "function", "raw"]
 
     def setup(self, constructor, window, dtype, function, raw):
-        N = 10 ** 5
+        N = 10 ** 3
         arr = (100 * np.random.random(N)).astype(dtype)
         self.roll = getattr(pd, constructor)(arr).rolling(window)
 

azure-pipelines.yml

@@ -33,6 +33,7 @@ jobs:
     condition: true
 
   - script: |
+      sudo apt-get update
       sudo apt-get install -y libc6-dev-i386
       ci/setup_env.sh
     displayName: 'Setup environment and build pandas'

ci/build38.sh

@@ -0,0 +1,19 @@
+#!/bin/bash -e
+# Special build for python3.8 until numpy puts its own wheels up
+
+sudo apt-get install build-essential gcc xvfb
+pip install --no-deps -U pip wheel setuptools
+pip install python-dateutil pytz cython pytest pytest-xdist hypothesis
+
+# Possible alternative for getting numpy:
+pip install --pre -f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com/ numpy
+
+python setup.py build_ext -inplace
+python -m pip install -v --no-build-isolation -e .
+
+python -c "import sys; print(sys.version_info)"
+python -c "import pandas as pd"
+python -c "import hypothesis"
+
+# TODO: Is there anything else in setup_env that we really want to do?
+# ci/setup_env.sh

ci/code_checks.sh

@@ -122,7 +122,7 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     MSG='Check for non-standard imports' ; echo $MSG
     invgrep -R --include="*.py*" -E "from pandas.core.common import " pandas
     invgrep -R --include="*.py*" -E "from collections.abc import " pandas
-    # invgrep -R --include="*.py*" -E "from numpy import nan " pandas  # GH#24822 not yet implemented since the offending imports have not all been removed
+    invgrep -R --include="*.py*" -E "from numpy import nan " pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for use of exec' ; echo $MSG
@@ -171,10 +171,6 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     invgrep -R --include="*.py" --include="*.pyx" --include="*.rst" -E "\.\. (autosummary|contents|currentmodule|deprecated|function|image|important|include|ipython|literalinclude|math|module|note|raw|seealso|toctree|versionadded|versionchanged|warning):[^:]" ./pandas ./doc/source
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Check that the deprecated `assert_raises_regex` is not used (`pytest.raises(match=pattern)` should be used instead)' ; echo $MSG
-    invgrep -R --exclude=*.pyc --exclude=testing.py --exclude=test_util.py assert_raises_regex pandas
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
     # Check for the following code in testing: `unittest.mock`, `mock.Mock()` or `mock.patch`
     MSG='Check that unittest.mock is not used (pytest builtin monkeypatch fixture should be used instead)' ; echo $MSG
     invgrep -r -E --include '*.py' '(unittest(\.| import )mock|mock\.Mock\(\)|mock\.patch)' pandas/tests/
@@ -208,7 +204,7 @@ import sys
 import pandas
 
 blacklist = {'bs4', 'gcsfs', 'html5lib', 'http', 'ipython', 'jinja2', 'hypothesis',
-             'lxml', 'numexpr', 'openpyxl', 'py', 'pytest', 's3fs', 'scipy',
+             'lxml', 'matplotlib', 'numexpr', 'openpyxl', 'py', 'pytest', 's3fs', 'scipy',
              'tables', 'urllib.request', 'xlrd', 'xlsxwriter', 'xlwt'}
 
 # GH#28227 for some of these check for top-level modules, while others are

ci/deps/azure-36-32bit.yaml

@@ -3,6 +3,7 @@ channels:
   - defaults
   - conda-forge
 dependencies:
+  - attrs=19.1.0
   - gcc_linux-32
   - gcc_linux-32
   - gxx_linux-32
@@ -11,7 +12,7 @@ dependencies:
   - python=3.6.*
   - pytz=2017.2
   # universal
-  - pytest>=4.0.2,<5.0.0
+  - pytest
   - pytest-xdist
   - pytest-mock
   - pytest-azurepipelines

ci/setup_env.sh

@@ -1,5 +1,9 @@
 #!/bin/bash -e
 
+if [ "$JOB" == "3.8-dev" ]; then
+    /bin/bash ci/build38.sh
+    exit 0
+fi
 
 # edit the locale file if needed
 if [ -n "$LOCALE_OVERRIDE" ]; then
@@ -51,6 +55,7 @@ echo
 echo "update conda"
 conda config --set ssl_verify false
 conda config --set quiet true --set always_yes true --set changeps1 false
+conda install pip  # create conda to create a historical artifact for pip & setuptools
 conda update -n base conda
 
 echo "conda info -a"
@@ -118,8 +123,8 @@ conda list pandas
 echo "[Build extensions]"
 python setup.py build_ext -q -i
 
-# XXX: Some of our environments end up with old verisons of pip (10.x)
-# Adding a new enough verison of pip to the requirements explodes the
+# XXX: Some of our environments end up with old versions of pip (10.x)
+# Adding a new enough version of pip to the requirements explodes the
 # solve time. Just using pip to update itself.
 # - py35_macos
 # - py35_compat