.gitignore

@@ -56,3 +56,4 @@ testing/udf/Makefile
 scripts/ibis-testing*
 ibis_testing*
 .tox/
+.asv/

README.md

@@ -1,6 +1,5 @@
-[![circleci-badge](https://circleci.com/gh/cloudera/ibis.svg?style=shield&circle-token=b84ff8383cbb0d6788ee0f9635441cb962949a4f)](https://circleci.com/gh/cloudera/ibis/tree/master)
-
-[![codecov.io](http://codecov.io/github/cloudera/ibis/coverage.svg?branch=master)](http://codecov.io/github/cloudera/ibis?branch=master)
+[![circleci](https://circleci.com/gh/ibis-project/ibis.svg?style=shield&circle-token=b84ff8383cbb0d6788ee0f9635441cb962949a4f)](https://circleci.com/gh/ibis-project/ibis/tree/master)
+[![appveyor](https://ci.appveyor.com/api/projects/status/github/ibis-project/ibis?branch=master&svg=true)](https://ci.appveyor.com/project/cpcloud/ibis-xh5g1)
 
 Current release from Anaconda.org [![Anaconda-Server Badge](https://anaconda.org/conda-forge/ibis-framework/badges/version.svg)](https://anaconda.org/conda-forge/ibis-framework)
 
@@ -20,10 +19,11 @@ At this time, Ibis provides tools for the interacting with the following
 systems:
 
 - [Apache Impala (incubating)](http://impala.io/)
-- [Apache Kudu (incubating)](http://getkudu.io)
+- [Apache Kudu](http://getkudu.io)
 - Hadoop Distributed File System (HDFS)
 - PostgreSQL (Experimental)
 - SQLite
+- Direct execution of ibis expressions against pandas object (Experimental)
 
 Learn more about using the library at http://docs.ibis-project.org and read the
 project blog at http://ibis-project.org for news and updates.

appveyor.yml

@@ -0,0 +1,39 @@
+build: off
+
+platform:
+  - x64
+
+environment:
+  PGUSER: "postgres"
+  PGPASSWORD: "Password12!"
+  IBIS_TEST_POSTGRES_DB: "ibis_testing"
+  IBIS_TEST_CRUNCHBASE_DB: "%USERPROFILE%\\crunchbase.db"
+  IBIS_TEST_SQLITE_DB_PATH: "%USERPROFILE%\\ibis_testing.db"
+  PG: "\"C:\\Program Files\\PostgreSQL\\9.6\\bin\\createdb\" ibis_testing"
+  CHOCO: "C:\\ProgramData\\chocolatey\\bin"
+
+  matrix:
+    - PYTHON: "C:\\Python27-x64"
+    - PYTHON: "C:\\Python34-x64"
+    - PYTHON: "C:\\Python35-x64"
+    - PYTHON: "C:\\Python36-x64"
+
+services:
+  - postgresql
+
+test_script:
+  - "%PYTHON%\\python.exe -m pip install -U pip"
+  - "%PYTHON%\\python.exe -m pip install -U setuptools"
+  - "%PYTHON%\\python.exe -m pip install -e .\"[sqlite, postgres, visualization, pandas]\""
+  - "%PYTHON%\\python.exe -m pip install flake8 mock pytest"
+  - "%PYTHON%\\python.exe -m flake8"
+
+  - "curl -o crunchbase.db https://storage.googleapis.com/ibis-ci-data/crunchbase.db"
+  - "mv crunchbase.db %IBIS_TEST_CRUNCHBASE_DB%"
+  - "curl -o ibis-testing-data.tar.gz https://storage.googleapis.com/ibis-ci-data/ibis-testing-data.tar.gz"
+  - "7z x ibis-testing-data.tar.gz"
+  - "7z x ibis-testing-data.tar"
+  - "mv ibis-testing-data\\ibis_testing.db %IBIS_TEST_SQLITE_DB_PATH%"
+  - "%PG%\\createdb.exe %IBIS_TEST_POSTGRES_DB%"
+
+  - "%PYTHON%\\python.exe -m pytest --tb=short -m \"not impala and not hdfs and not postgresql\" ibis"

asv.conf.json

@@ -0,0 +1,150 @@
+{
+    // The version of the config file format.  Do not change, unless
+    // you know what you are doing.
+    "version": 1,
+
+    // The name of the project being benchmarked
+    "project": "ibis",
+
+    // The project's homepage
+    "project_url": "http://www.ibis-project.org/",
+
+    // The URL or local path of the source code repository for the
+    // project being benchmarked
+    "repo": ".",
+
+    // List of branches to benchmark. If not provided, defaults to "master"
+    // (for git) or "default" (for mercurial).
+    // "branches": ["master"], // for git
+    // "branches": ["default"],    // for mercurial
+
+    // The DVCS being used.  If not set, it will be automatically
+    // determined from "repo" by looking at the protocol in the URL
+    // (if remote), or by looking for special directories, such as
+    // ".git" (if local).
+    // "dvcs": "git",
+
+    // The tool to use to create environments.  May be "conda",
+    // "virtualenv" or other value depending on the plugins in use.
+    // If missing or the empty string, the tool will be automatically
+    // determined by looking for tools on the PATH environment
+    // variable.
+    "environment_type": "conda",
+
+    // timeout in seconds for installing any dependencies in environment
+    // defaults to 10 min
+    //"install_timeout": 600,
+
+    // the base URL to show a commit for the project.
+    "show_commit_url": "https://github.com/ibis-project/ibis/commit/",
+
+    // The Pythons you'd like to test against.  If not provided, defaults
+    // to the current version of Python used to run `asv`.
+    "pythons": ["3.5"],
+
+    // The matrix of dependencies to test.  Each key is the name of a
+    // package (in PyPI) and the values are version numbers.  An empty
+    // list or empty string indicates to just test against the default
+    // (latest) version. null indicates that the package is to not be
+    // installed. If the package to be tested is only available from
+    // PyPi, and the 'environment_type' is conda, then you can preface
+    // the package name by 'pip+', and the package will be installed via
+    // pip (with all the conda available packages installed first,
+    // followed by the pip installed packages).
+    //
+    "matrix": {
+        "numpy": [""],
+	"pandas": [""],
+	"toolz": [""],
+        "six": [""],
+	"graphviz": [""],
+	"multipledispatch": [""],
+	"python-graphviz": [""],
+	"pip+hdfs": [""],
+	"impyla": [""],
+	"sqlalchemy": [""],
+	"pip+thrift": [""],
+	"pip+thriftpy": [""]
+    },
+
+    // Combinations of libraries/python versions can be excluded/included
+    // from the set to test. Each entry is a dictionary containing additional
+    // key-value pairs to include/exclude.
+    //
+    // An exclude entry excludes entries where all values match. The
+    // values are regexps that should match the whole string.
+    //
+    // An include entry adds an environment. Only the packages listed
+    // are installed. The 'python' key is required. The exclude rules
+    // do not apply to includes.
+    //
+    // In addition to package names, the following keys are available:
+    //
+    // - python
+    //     Python version, as in the *pythons* variable above.
+    // - environment_type
+    //     Environment type, as above.
+    // - sys_platform
+    //     Platform, as in sys.platform. Possible values for the common
+    //     cases: 'linux2', 'win32', 'cygwin', 'darwin'.
+    //
+    // "exclude": [
+    //     {"python": "3.2", "sys_platform": "win32"}, // skip py3.2 on windows
+    //     {"environment_type": "conda", "six": null}, // don't run without six on conda
+    // ],
+    //
+    // "include": [
+    //     // additional env for python2.7
+    //     {"python": "2.7", "numpy": "1.8"},
+    //     // additional env if run on windows+conda
+    //     {"platform": "win32", "environment_type": "conda", "python": "2.7", "libpython": ""},
+    // ],
+
+    // The directory (relative to the current directory) that benchmarks are
+    // stored in.  If not provided, defaults to "benchmarks"
+    // "benchmark_dir": "benchmarks",
+
+    // The directory (relative to the current directory) to cache the Python
+    // environments in.  If not provided, defaults to "env"
+    "env_dir": ".asv/env",
+
+    // The directory (relative to the current directory) that raw benchmark
+    // results are stored in.  If not provided, defaults to "results".
+    "results_dir": ".asv/results",
+
+    // The directory (relative to the current directory) that the html tree
+    // should be written to.  If not provided, defaults to "html".
+    "html_dir": ".asv/html",
+
+    // The number of characters to retain in the commit hashes.
+    // "hash_length": 8,
+
+    // `asv` will cache wheels of the recent builds in each
+    // environment, making them faster to install next time.  This is
+    // number of builds to keep, per environment.
+    // "wheel_cache_size": 0
+
+    // The commits after which the regression search in `asv publish`
+    // should start looking for regressions. Dictionary whose keys are
+    // regexps matching to benchmark names, and values corresponding to
+    // the commit (exclusive) after which to start looking for
+    // regressions.  The default is to start from the first commit
+    // with results. If the commit is `null`, regression detection is
+    // skipped for the matching benchmark.
+    //
+    // "regressions_first_commits": {
+    //    "some_benchmark": "352cdf",  // Consider regressions only after this commit
+    //    "another_benchmark": null,   // Skip regression detection altogether
+    // }
+
+    // The thresholds for relative change in results, after which `asv
+    // publish` starts reporting regressions. Dictionary of the same
+    // form as in ``regressions_first_commits``, with values
+    // indicating the thresholds.  If multiple entries match, the
+    // maximum is taken. If no entry matches, the default is 5%.
+    //
+    // "regressions_thresholds": {
+    //    "some_benchmark": 0.01,     // Threshold of 1%
+    //    "another_benchmark": 0.5,   // Threshold of 50%
+    // }
+}

benchmarks/benchmarks.py

@@ -0,0 +1,85 @@
+import ibis
+
+
+class Suite:
+    def setup(self):
+        self.t = t = ibis.table((('_timestamp', 'int32'),
+                                 ('dim1', 'int32'),
+                                 ('dim2', 'int32'),
+                                 ('valid_seconds', 'int32'),
+                                 ('meas1', 'int32'),
+                                 ('meas2', 'int32'),
+                                 ('year', 'int32'),
+                                 ('month', 'int32'),
+                                 ('day', 'int32'),
+                                 ('hour', 'int32'),
+                                 ('minute', 'int32')), name='t')
+        self.base = (
+            (t.year > 2016) | (
+                (t.year == 2016) & (t.month > 6)) | (
+                    (t.year == 2016) & (t.month == 6) &
+                    (t.day > 6)) | (
+                        (t.year == 2016) & (t.month == 6) &
+                        (t.day == 6) & (t.hour > 6)) |
+            ((t.year == 2016) & (t.month == 6) &
+             (t.day == 6) & (t.hour == 6) &
+             (t.minute >= 5))) & ((t.year < 2016) | (
+                 (t.year == 2016) & (t.month < 6)) | (
+                     (t.year == 2016) & (t.month == 6) &
+                     (t.day < 6)) | (
+                         (t.year == 2016) & (t.month == 6) &
+                         (t.day == 6) & (t.hour < 6)) | (
+                             (t.year == 2016) &
+                             (t.month == 6) & (t.day == 6) &
+                             (t.hour == 6) &
+                             (t.minute <= 5)))
+        self.expr = self.large_expr
+
+    @property
+    def large_expr(self):
+        src_table = self.t[self.base]
+        src_table = src_table.mutate(_timestamp=(
+            src_table['_timestamp'] - src_table['_timestamp'] % 3600
+        ).cast('int32').name('_timestamp'), valid_seconds=300)
+
+        aggs = []
+        for meas in ['meas1', 'meas2']:
+            aggs.append(src_table[meas].sum().cast('float').name(meas))
+        src_table = src_table.aggregate(
+            aggs, by=['_timestamp', 'dim1', 'dim2', 'valid_seconds'])
+
+        part_keys = ['year', 'month', 'day', 'hour', 'minute']
+        ts_col = src_table['_timestamp'].cast('timestamp')
+        new_cols = {}
+        for part_key in part_keys:
+            part_col = getattr(ts_col, part_key)()
+            new_cols[part_key] = part_col
+        src_table = src_table.mutate(**new_cols)
+        return src_table[[
+            '_timestamp', 'dim1', 'dim2', 'meas1', 'meas2',
+            'year', 'month', 'day', 'hour', 'minute'
+        ]]
+
+
+class Construction(Suite):
+
+    def time_large_expr_construction(self):
+        self.large_expr
+
+
+class Formatting(Suite):
+
+    def time_base_expr_formatting(self):
+        str(self.base)
+
+    def time_large_expr_formatting(self):
+        str(self.expr)
+
+
+class Compilation(Suite):
+
+    def time_impala_base_compile(self):
+        ibis.impala.compile(self.base)
+
+    def time_impala_large_expr_compile(self):
+        ibis.impala.compile(self.expr)

ci/asvconfig.py

@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+
+if __name__ == '__main__':
+    import os
+    import json
+    import socket
+
+    import asv
+
+    hostname = 'circle' if os.environ.get('CIRCLECI') else socket.gethostname()
+    machine_info = asv.machine.Machine.get_defaults()
+    machine_info['machine'] = hostname
+    machine_info['ram'] = '{:d}GB'.format(int(machine_info['ram']) // 1000000)
+    print(json.dumps({hostname: machine_info, 'version': 1}, indent=2))

ci/run.sh

@@ -0,0 +1,12 @@
+#!/bin/bash -e
+
+function run()
+{
+    local python_version="${1}"
+    local no_dots_python_version="${python_version//.}"
+    pyenv install --skip-existing "${python_version}"
+    pyenv local "${python_version}"
+    tox -e "py${no_dots_python_version:0:2}"
+}
+
+run "$@"