Merge branch 'master' into 24893-pivot_table

Author: mabelvj

.gitignore

@@ -57,6 +57,7 @@ dist
 # wheel files
 *.whl
 **/wheelhouse/*
+pip-wheel-metadata
 # coverage
 .coverage
 coverage.xml

.pre-commit-config.yaml

@@ -15,3 +15,4 @@ repos:
     hooks:
     -   id: isort
         language: python_venv
+        exclude: ^pandas/__init__\.py$|^pandas/core/api\.py$

.travis.yml

@@ -30,6 +30,12 @@ matrix:
       - python: 3.5
 
     include:
+    - dist: bionic
+      # 18.04
+      python: 3.8.0
+      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:

MANIFEST.in

@@ -3,6 +3,7 @@ include LICENSE
 include RELEASE.md
 include README.md
 include setup.py
+include pyproject.toml
 
 graft doc
 prune doc/build
@@ -14,6 +15,7 @@ graft pandas
 global-exclude *.bz2
 global-exclude *.csv
 global-exclude *.dta
+global-exclude *.feather
 global-exclude *.gz
 global-exclude *.h5
 global-exclude *.html
@@ -23,7 +25,10 @@ global-exclude *.pickle
 global-exclude *.png
 global-exclude *.pyc
 global-exclude *.pyd
+global-exclude *.ods
+global-exclude *.odt
 global-exclude *.sas7bdat
+global-exclude *.sav
 global-exclude *.so
 global-exclude *.xls
 global-exclude *.xlsm

Makefile

@@ -18,7 +18,7 @@ black:
 	black . --exclude '(asv_bench/env|\.egg|\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|_build|buck-out|build|dist|setup.py)'
 
 develop: build
-	python setup.py develop
+	python -m pip install --no-build-isolation -e .
 
 doc:
 	-rm -rf doc/build doc/source/generated

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>
 
 -----------------
@@ -188,16 +188,17 @@ python setup.py install
 
 or for installing in [development mode](https://pip.pypa.io/en/latest/reference/pip_install.html#editable-installs):
 
+
 ```sh
-python setup.py develop
+python -m pip install -e . --no-build-isolation --no-use-pep517
 ```
 
-Alternatively, you can use `pip` if you want all the dependencies pulled
-in automatically (the `-e` option is for installing it in [development
-mode](https://pip.pypa.io/en/latest/reference/pip_install.html#editable-installs)):
+If you have `make`, you can also use `make develop` to run the same command.
+
+or alternatively
 
 ```sh
-pip install -e .
+python setup.py develop
 ```
 
 See the full instructions for [installing from source](https://pandas.pydata.org/pandas-docs/stable/install.html#installing-from-source).
@@ -224,7 +225,7 @@ Most development discussion is taking place on github in this repo. Further, the
 
 All contributions, bug reports, bug fixes, documentation improvements, enhancements and ideas are welcome.
 
-A detailed overview on how to contribute can be found in the **[contributing guide](https://dev.pandas.io/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
+A detailed overview on how to contribute can be found in the **[contributing guide](https://dev.pandas.io/docs/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
 
 If you are simply looking to start working with the pandas codebase, navigate to the [GitHub "issues" tab](https://github.com/pandas-dev/pandas/issues) and start looking through interesting issues. There are a number of issues listed under [Docs](https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open) and [good first issue](https://github.com/pandas-dev/pandas/issues?labels=good+first+issue&sort=updated&state=open) where you could start out.
 

asv_bench/benchmarks/categoricals.py

@@ -282,4 +282,18 @@ def time_sort_values(self):
         self.index.sort_values(ascending=False)
 
 
+class SearchSorted:
+    def setup(self):
+        N = 10 ** 5
+        self.ci = tm.makeCategoricalIndex(N).sort_values()
+        self.c = self.ci.values
+        self.key = self.ci.categories[1]
+
+    def time_categorical_index_contains(self):
+        self.ci.searchsorted(self.key)
+
+    def time_categorical_contains(self):
+        self.c.searchsorted(self.key)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

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/frame_methods.py

@@ -609,4 +609,15 @@ def time_dataframe_describe(self):
         self.df.describe()
 
 
+class SelectDtypes:
+    params = [100, 1000]
+    param_names = ["n"]
+
+    def setup(self, n):
+        self.df = DataFrame(np.random.randn(10, n))
+
+    def time_select_dtypes(self, n):
+        self.df.select_dtypes(include="int")
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

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/offset.py

@@ -1,8 +1,5 @@
-from datetime import datetime
 import warnings
 
-import numpy as np
-
 import pandas as pd
 
 try:
@@ -54,24 +51,6 @@ def time_apply_index(self, offset):
         offset.apply_index(self.rng)
 
 
-class OnOffset:
-
-    params = offsets
-    param_names = ["offset"]
-
-    def setup(self, offset):
-        self.dates = [
-            datetime(2016, m, d)
-            for m in [10, 11, 12]
-            for d in [1, 2, 3, 28, 29, 30, 31]
-            if not (m == 11 and d == 31)
-        ]
-
-    def time_on_offset(self, offset):
-        for date in self.dates:
-            offset.onOffset(date)
-
-
 class OffsetSeriesArithmetic:
 
     params = offsets
@@ -99,31 +78,3 @@ def setup(self, offset):
     def time_add_offset(self, offset):
         with warnings.catch_warnings(record=True):
             self.data + offset
-
-
-class OffestDatetimeArithmetic:
-
-    params = offsets
-    param_names = ["offset"]
-
-    def setup(self, offset):
-        self.date = datetime(2011, 1, 1)
-        self.dt64 = np.datetime64("2011-01-01 09:00Z")
-
-    def time_apply(self, offset):
-        offset.apply(self.date)
-
-    def time_apply_np_dt64(self, offset):
-        offset.apply(self.dt64)
-
-    def time_add(self, offset):
-        self.date + offset
-
-    def time_add_10(self, offset):
-        self.date + (10 * offset)
-
-    def time_subtract(self, offset):
-        self.date - offset
-
-    def time_subtract_10(self, offset):
-        self.date - (10 * offset)