Merge master branch

Author: Christopher C. Aycock

.github/ISSUE_TEMPLATE.md

@@ -1,9 +1,12 @@
-#### A small, complete example of the issue
+#### Code Sample, a copy-pastable example if possible
 
 ```python
 # Your code here
 
 ```
+#### Problem description
+
+[this should explain **why** the current behaviour is a problem and why the expected output is a better solution.]
 
 #### Expected Output
 

.gitignore

@@ -27,6 +27,7 @@
 *.class
 *.dll
 *.exe
+*.pxi
 *.o
 *.py[ocd]
 *.so

.travis.yml

@@ -14,13 +14,11 @@ cache:
 
 env:
  global:
- # scatterci API key
- #- secure: "Bx5umgo6WjuGY+5XFa004xjCiX/vq0CyMZ/ETzcs7EIBI1BE/0fIDXOoWhoxbY9HPfdPGlDnDgB9nGqr5wArO2s+BavyKBWg6osZ3dmkfuJPMOWeyCa92EeP+sfKw8e5HSU5MizW9e319wHWOF/xkzdHR7T67Qd5erhv91x4DnQ="
- # ironcache API key
- #- secure: "e4eEFn9nDQc3Xa5BWYkzfX37jaWVq89XidVX+rcCNEr5OlOImvveeXnF1IzbRXznH4Sv0YsLwUd8RGUWOmyCvkONq/VJeqCHWtTMyfaCIdqSyhIP9Odz8r9ahch+Y0XFepBey92AJHmlnTh+2GjCDgIiqq4fzglojnp56Vg1ojA="
- #- secure: "CjmYmY5qEu3KrvMtel6zWFEtMq8ORBeS1S1odJHnjQpbwT1KY2YFZRVlLphfyDQXSz6svKUdeRrCNp65baBzs3DQNA8lIuXGIBYFeJxqVGtYAZZs6+TzBPfJJK798sGOj5RshrOJkFG2rdlWNuTq/XphI0JOrN3nPUkRrdQRpAw="
- # pandas-docs-bot GH
- - secure: "PCzUFR8CHmw9lH84p4ygnojdF7Z8U5h7YfY0RyT+5K/aiQ1ZTU3ZkDTPI0/rR5FVMxsEEKEQKMcc5fvqW0PeD7Q2wRmluloKgT9w4EVEJ1ppKf7lITPcvZR2QgVOvjv4AfDtibLHFNiaSjzoqyJVjM4igjOu8WTlF3JfZcmOQjQ="
+
+ # pandas-docs-travis GH
+ - secure: "U4GkUaX0K5FqHsHlxXiTr53t0zg8l9p3x7Xze3T0l4mEfhJdqVjayizRE0w0Uo3D54YY7X4lCRtI+bzFz20RxAEoEUyIoWtlUP7eNY3XuhViipY7gtYJpS+68VN5MnChzzz73cNj89fLBvCFyYhMTXHSrbm+yHSg6eRlqzzhHWc="
+
+ ## original key - secure: "PCzUFR8CHmw9lH84p4ygnojdF7Z8U5h7YfY0RyT+5K/aiQ1ZTU3ZkDTPI0/rR5FVMxsEEKEQKMcc5fvqW0PeD7Q2wRmluloKgT9w4EVEJ1ppKf7lITPcvZR2QgVOvjv4AfDtibLHFNiaSjzoqyJVjM4igjOu8WTlF3JfZcmOQjQ="
 
 git:
  # for cloning
@@ -34,6 +32,7 @@ matrix:
  compiler: clang
  osx_image: xcode6.4
  env:
+ - PYTHON_VERSION=3.5
  - JOB_NAME: "35_osx"
  - NOSE_ARGS="not slow and not network and not disabled"
  - BUILD_TYPE=conda
@@ -43,6 +42,7 @@ matrix:
  - USE_CACHE=true
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_slow_nnet_LOCALE"
  - NOSE_ARGS="slow and not network and not disabled"
  - LOCALE_OVERRIDE="zh_CN.UTF-8"
@@ -56,6 +56,7 @@ matrix:
  - language-pack-zh-hans
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_nslow"
  - NOSE_ARGS="not slow and not disabled"
  - FULL_DEPS=true
@@ -69,6 +70,7 @@ matrix:
  - python-gtk2
  - python: 3.4
  env:
+ - PYTHON_VERSION=3.4
  - JOB_NAME: "34_nslow"
  - NOSE_ARGS="not slow and not disabled"
  - FULL_DEPS=true
@@ -81,6 +83,7 @@ matrix:
  - xsel
  - python: 3.5
  env:
+ - PYTHON_VERSION=3.5
  - JOB_NAME: "35_nslow"
  - NOSE_ARGS="not slow and not network and not disabled"
  - FULL_DEPS=true
@@ -95,6 +98,7 @@ matrix:
 # In allow_failures
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_slow"
  - JOB_TAG=_SLOW
  - NOSE_ARGS="slow and not network and not disabled"
@@ -104,6 +108,7 @@ matrix:
 # In allow_failures
  - python: 3.4
  env:
+ - PYTHON_VERSION=3.4
  - JOB_NAME: "34_slow"
  - JOB_TAG=_SLOW
  - NOSE_ARGS="slow and not network and not disabled"
@@ -118,16 +123,31 @@ matrix:
 # In allow_failures
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_build_test_conda"
  - JOB_TAG=_BUILD_TEST
  - NOSE_ARGS="not slow and not disabled"
  - FULL_DEPS=true
  - BUILD_TEST=true
  - CACHE_NAME="27_build_test_conda"
  - USE_CACHE=true
+# In allow_failures
+ - python: 3.6-dev
+ env:
+ - PYTHON_VERSION=3.6
+ - JOB_NAME: "36_dev"
+ - JOB_TAG=_DEV
+ - NOSE_ARGS="not slow and not network and not disabled"
+ - PANDAS_TESTING_MODE="deprecate"
+ addons:
+ apt:
+ packages:
+ - libatlas-base-dev
+ - gfortran
 # In allow_failures
  - python: 3.5
  env:
+ - PYTHON_VERSION=3.5
  - JOB_NAME: "35_numpy_dev"
  - JOB_TAG=_NUMPY_DEV
  - NOSE_ARGS="not slow and not network and not disabled"
@@ -142,6 +162,7 @@ matrix:
 # In allow_failures
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_nslow_nnet_COMPAT"
  - NOSE_ARGS="not slow and not network and not disabled"
  - LOCALE_OVERRIDE="it_IT.UTF-8"
@@ -156,6 +177,7 @@ matrix:
 # In allow_failures
  - python: 3.5
  env:
+ - PYTHON_VERSION=3.5
  - JOB_NAME: "35_ascii"
  - JOB_TAG=_ASCII
  - NOSE_ARGS="not slow and not network and not disabled"
@@ -165,6 +187,7 @@ matrix:
 # In allow_failures
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "doc_build"
  - FULL_DEPS=true
  - DOC_BUILD=true
@@ -174,6 +197,7 @@ matrix:
  allow_failures:
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_slow"
  - JOB_TAG=_SLOW
  - NOSE_ARGS="slow and not network and not disabled"
@@ -182,6 +206,7 @@ matrix:
  - USE_CACHE=true
  - python: 3.4
  env:
+ - PYTHON_VERSION=3.4
  - JOB_NAME: "34_slow"
  - JOB_TAG=_SLOW
  - NOSE_ARGS="slow and not network and not disabled"
@@ -195,28 +220,43 @@ matrix:
  - xsel
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_build_test_conda"
  - JOB_TAG=_BUILD_TEST
  - NOSE_ARGS="not slow and not disabled"
  - FULL_DEPS=true
  - BUILD_TEST=true
  - CACHE_NAME="27_build_test_conda"
  - USE_CACHE=true
- - python: 3.5
+ - python: 3.6-dev
  env:
- - JOB_NAME: "35_numpy_dev"
- - JOB_TAG=_NUMPY_DEV
+ - PYTHON_VERSION=3.6
+ - JOB_NAME: "36_dev"
+ - JOB_TAG=_DEV
  - NOSE_ARGS="not slow and not network and not disabled"
  - PANDAS_TESTING_MODE="deprecate"
- - CACHE_NAME="35_numpy_dev"
- - USE_CACHE=true
+ addons:
+ apt:
+ packages:
+ - libatlas-base-dev
+ - gfortran
+ - python: 3.5
+ env:
+ - PYTHON_VERSION=3.5
+ - JOB_NAME: "35_numpy_dev"
+ - JOB_TAG=_NUMPY_DEV
+ - NOSE_ARGS="not slow and not network and not disabled"
+ - PANDAS_TESTING_MODE="deprecate"
+ - CACHE_NAME="35_numpy_dev"
+ - USE_CACHE=true
  addons:
  apt:
  packages:
  - libatlas-base-dev
  - gfortran
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "27_nslow_nnet_COMPAT"
  - NOSE_ARGS="not slow and not network and not disabled"
  - LOCALE_OVERRIDE="it_IT.UTF-8"
@@ -230,6 +270,7 @@ matrix:
  - language-pack-it
  - python: 3.5
  env:
+ - PYTHON_VERSION=3.5
  - JOB_NAME: "35_ascii"
  - JOB_TAG=_ASCII
  - NOSE_ARGS="not slow and not network and not disabled"
@@ -238,6 +279,7 @@ matrix:
  - USE_CACHE=true
  - python: 2.7
  env:
+ - PYTHON_VERSION=2.7
  - JOB_NAME: "doc_build"
  - FULL_DEPS=true
  - DOC_BUILD=true
@@ -249,7 +291,7 @@ before_install:
  - echo "before_install"
  - source ci/travis_process_gbq_encryption.sh
  - echo $VIRTUAL_ENV
- - export PATH="$HOME/miniconda/bin:$PATH"
+ - export PATH="$HOME/miniconda3/bin:$PATH"
  - df -h
  - date
  - pwd

asv_bench/benchmarks/algorithms.py

@@ -1,5 +1,6 @@
 import numpy as np
 import pandas as pd
+from pandas.util import testing as tm
 
 
 class algorithm(object):
@@ -55,3 +56,35 @@ def time_add_overflow_neg_arr(self):
 
  def time_add_overflow_mixed_arr(self):
  self.checked_add(self.arr, self.arrmixed)
+
+
+class hashing(object):
+ goal_time = 0.2
+
+ def setup(self):
+ N = 100000
+
+ self.df = pd.DataFrame(
+ {'A': pd.Series(tm.makeStringIndex(100).take(
+ np.random.randint(0, 100, size=N))),
+ 'B': pd.Series(tm.makeStringIndex(10000).take(
+ np.random.randint(0, 10000, size=N))),
+ 'D': np.random.randn(N),
+ 'E': np.arange(N),
+ 'F': pd.date_range('20110101', freq='s', periods=N),
+ 'G': pd.timedelta_range('1 day', freq='s', periods=N),
+ })
+ self.df['C'] = self.df['B'].astype('category')
+ self.df.iloc[10:20] = np.nan
+
+ def time_frame(self):
+ self.df.hash()
+
+ def time_series_int(self):
+ self.df.E.hash()
+
+ def time_series_string(self):
+ self.df.B.hash()
+
+ def time_series_categorical(self):
+ self.df.C.hash()

asv_bench/benchmarks/replace.py

@@ -32,6 +32,30 @@ def time_replace_large_dict(self):
  self.s.replace(self.to_rep, inplace=True)
 
 
+class replace_convert(object):
+ goal_time = 0.5
+
+ def setup(self):
+ self.n = (10 ** 3)
+ self.to_ts = dict(((i, pd.Timestamp(i)) for i in range(self.n)))
+ self.to_td = dict(((i, pd.Timedelta(i)) for i in range(self.n)))
+ self.s = Series(np.random.randint(self.n, size=(10 ** 3)))
+ self.df = DataFrame({'A': np.random.randint(self.n, size=(10 ** 3)),
+ 'B': np.random.randint(self.n, size=(10 ** 3))})
+
+ def time_replace_series_timestamp(self):
+ self.s.replace(self.to_ts)
+
+ def time_replace_series_timedelta(self):
+ self.s.replace(self.to_td)
+
+ def time_replace_frame_timestamp(self):
+ self.df.replace(self.to_ts)
+
+ def time_replace_frame_timedelta(self):
+ self.df.replace(self.to_td)
+
+
 class replace_replacena(object):
  goal_time = 0.2
 

ci/install-2.7_NUMPY_DEV.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+echo "install 3.6 dev"
+
+conda config --set add_pip_as_python_dependency false
+conda create -n pandas python=3.6 -c conda-forge/label/prerelease
+
+source activate pandas
+
+# ensure we have pip
+python -m ensurepip
+
+# install deps
+pip3.6 install nose cython numpy pytz python-dateutil
+
+true