From d0ba953eb8966617dd7147c8d7c846b74e764db1 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Mon, 19 Oct 2015 22:30:13 +0100
Subject: [PATCH 01/20] adding windows build

---
 appveyor.yml                                  |  85 +++++++
 continuous_integration/appveyor/install.ps1   | 229 ++++++++++++++++++
 .../appveyor/requirements.txt                 |  12 +
 .../appveyor/run_with_env.cmd                 |  88 +++++++
 4 files changed, 414 insertions(+)
 create mode 100644 appveyor.yml
 create mode 100644 continuous_integration/appveyor/install.ps1
 create mode 100644 continuous_integration/appveyor/requirements.txt
 create mode 100644 continuous_integration/appveyor/run_with_env.cmd

diff --git a/appveyor.yml b/appveyor.yml
new file mode 100644
index 0000000000..9152276b82
--- /dev/null
+++ b/appveyor.yml
@@ -0,0 +1,85 @@
+# AppVeyor.com is a Continuous Integration service to build and run tests under
+# Windows
+# https://ci.appveyor.com/project/tmylk/gensim
+
+environment:
+  global:
+    # SDK v7.0 MSVC Express 2008's SetEnv.cmd script will fail if the
+    # /E:ON and /V:ON options are not enabled in the batch script intepreter
+    # See: http://stackoverflow.com/a/13751649/163740
+    CMD_IN_ENV: "cmd /E:ON /V:ON /C .\\continuous_integration\\appveyor\\run_with_env.cmd"
+    
+  matrix:
+    - PYTHON: "C:\\Python27"
+      PYTHON_VERSION: "2.7.8"
+      PYTHON_ARCH: "32"
+
+    - PYTHON: "C:\\Python27-x64"
+      PYTHON_VERSION: "2.7.8"
+      PYTHON_ARCH: "64"
+
+    - PYTHON: "C:\\Python35"
+      PYTHON_VERSION: "3.5.0"
+      PYTHON_ARCH: "32"
+
+    - PYTHON: "C:\\Python35-x64"
+      PYTHON_VERSION: "3.5.0"
+      PYTHON_ARCH: "64"
+
+
+
+install:
+  # Install Python (from the official .msi of http://python.org) and pip when
+  # not already installed.
+  - "powershell ./continuous_integration/appveyor/install.ps1"
+  - "SET PATH=%PYTHON%;%PYTHON%\\Scripts;%PATH%"
+
+  # Check that we have the expected version and architecture for Python
+  - "python --version"
+  - "python -c \"import struct; print(struct.calcsize('P') * 8)\""
+
+  # Install the build and runtime dependencies of the project.
+    # Install the build and runtime dependencies of the project.
+  - "%CMD_IN_ENV% pip install --timeout=60 --trusted-host 28daf2247a33ed269873-7b1aad3fab3cc330e1fd9d109892382a.r6.cf2.rackcdn.com -r continuous_integration/appveyor/requirements.txt"
+  - "%CMD_IN_ENV% python setup.py bdist_wheel bdist_wininst "
+  - ps: "ls dist"
+
+  # Install the genreated wheel package to test it
+  - "pip install --pre --no-index --find-links dist/ gensim"
+
+# Not a .NET project, we build scikit-learn in the install step instead
+build: false
+
+test_script:
+  # Change to a non-source folder to make sure we run the tests on the
+  # installed library.
+  - "mkdir empty_folder"
+  - "cd empty_folder"
+
+  - "python -c \"import nose; nose.main()\" -s -v gensim"
+  # Move back to the project folder
+  - "cd .."
+
+artifacts:
+  # Archive the generated wheel package in the ci.appveyor.com build report.
+  - path: dist\*
+# TODO: get a share
+#on_success:
+  # Upload the generated wheel package to Rackspace
+  # On Windows, Apache Libcloud cannot find a standard CA cert bundle so we
+  # disable the ssl checks.
+#  - "python -m wheelhouse_uploader upload --no-ssl-check --local-folder=dist sklearn-windows-wheels"
+
+#notifications:
+#  - provider: Webhook
+#    url: https://webhooks.gitter.im/e/0dc8e57cd38105aeb1b4
+#    on_build_success: false
+#    on_build_failure: True
+
+cache:
+  # Use the appveyor cache to avoid re-downloading large archives such
+  # the MKL numpy and scipy wheels mirrored on a rackspace cloud
+  # container, speed up the appveyor jobs and reduce bandwidth
+  # usage on our rackspace account.
+  - '%APPDATA%\pip\Cache'
+
diff --git a/continuous_integration/appveyor/install.ps1 b/continuous_integration/appveyor/install.ps1
new file mode 100644
index 0000000000..160ba55c07
--- /dev/null
+++ b/continuous_integration/appveyor/install.ps1
@@ -0,0 +1,229 @@
+# Sample script to install Python and pip under Windows
+# Authors: Olivier Grisel, Jonathan Helmus, Kyle Kastner, and Alex Willmer
+# License: CC0 1.0 Universal: http://creativecommons.org/publicdomain/zero/1.0/
+
+$MINICONDA_URL = "http://repo.continuum.io/miniconda/"
+$BASE_URL = "https://www.python.org/ftp/python/"
+$GET_PIP_URL = "https://bootstrap.pypa.io/get-pip.py"
+$GET_PIP_PATH = "C:\get-pip.py"
+
+$PYTHON_PRERELEASE_REGEX = @"
+(?x)
+(?<major>\d+)
+\.
+(?<minor>\d+)
+\.
+(?<micro>\d+)
+(?<prerelease>[a-z]{1,2}\d+)
+"@
+
+
+function Download ($filename, $url) {
+    $webclient = New-Object System.Net.WebClient
+
+    $basedir = $pwd.Path + "\"
+    $filepath = $basedir + $filename
+    if (Test-Path $filename) {
+        Write-Host "Reusing" $filepath
+        return $filepath
+    }
+
+    # Download and retry up to 3 times in case of network transient errors.
+    Write-Host "Downloading" $filename "from" $url
+    $retry_attempts = 2
+    for ($i = 0; $i -lt $retry_attempts; $i++) {
+        try {
+            $webclient.DownloadFile($url, $filepath)
+            break
+        }
+        Catch [Exception]{
+            Start-Sleep 1
+        }
+    }
+    if (Test-Path $filepath) {
+        Write-Host "File saved at" $filepath
+    } else {
+        # Retry once to get the error message if any at the last try
+        $webclient.DownloadFile($url, $filepath)
+    }
+    return $filepath
+}
+
+
+function ParsePythonVersion ($python_version) {
+    if ($python_version -match $PYTHON_PRERELEASE_REGEX) {
+        return ([int]$matches.major, [int]$matches.minor, [int]$matches.micro,
+                $matches.prerelease)
+    }
+    $version_obj = [version]$python_version
+    return ($version_obj.major, $version_obj.minor, $version_obj.build, "")
+}
+
+
+function DownloadPython ($python_version, $platform_suffix) {
+    $major, $minor, $micro, $prerelease = ParsePythonVersion $python_version
+
+    if (($major -le 2 -and $micro -eq 0) `
+        -or ($major -eq 3 -and $minor -le 2 -and $micro -eq 0) `
+        ) {
+        $dir = "$major.$minor"
+        $python_version = "$major.$minor$prerelease"
+    } else {
+        $dir = "$major.$minor.$micro"
+    }
+
+    if ($prerelease) {
+        if (($major -le 2) `
+            -or ($major -eq 3 -and $minor -eq 1) `
+            -or ($major -eq 3 -and $minor -eq 2) `
+            -or ($major -eq 3 -and $minor -eq 3) `
+            ) {
+            $dir = "$dir/prev"
+        }
+    }
+
+    if (($major -le 2) -or ($major -le 3 -and $minor -le 4)) {
+        $ext = "msi"
+        if ($platform_suffix) {
+            $platform_suffix = ".$platform_suffix"
+        }
+    } else {
+        $ext = "exe"
+        if ($platform_suffix) {
+            $platform_suffix = "-$platform_suffix"
+        }
+    }
+
+    $filename = "python-$python_version$platform_suffix.$ext"
+    $url = "$BASE_URL$dir/$filename"
+    $filepath = Download $filename $url
+    return $filepath
+}
+
+
+function InstallPython ($python_version, $architecture, $python_home) {
+    Write-Host "Installing Python" $python_version "for" $architecture "bit architecture to" $python_home
+    if (Test-Path $python_home) {
+        Write-Host $python_home "already exists, skipping."
+        return $false
+    }
+    if ($architecture -eq "32") {
+        $platform_suffix = ""
+    } else {
+        $platform_suffix = "amd64"
+    }
+    $installer_path = DownloadPython $python_version $platform_suffix
+    $installer_ext = [System.IO.Path]::GetExtension($installer_path)
+    Write-Host "Installing $installer_path to $python_home"
+    $install_log = $python_home + ".log"
+    if ($installer_ext -eq '.msi') {
+        InstallPythonMSI $installer_path $python_home $install_log
+    } else {
+        InstallPythonEXE $installer_path $python_home $install_log
+    }
+    if (Test-Path $python_home) {
+        Write-Host "Python $python_version ($architecture) installation complete"
+    } else {
+        Write-Host "Failed to install Python in $python_home"
+        Get-Content -Path $install_log
+        Exit 1
+    }
+}
+
+
+function InstallPythonEXE ($exepath, $python_home, $install_log) {
+    $install_args = "/quiet InstallAllUsers=1 TargetDir=$python_home"
+    RunCommand $exepath $install_args
+}
+
+
+function InstallPythonMSI ($msipath, $python_home, $install_log) {
+    $install_args = "/qn /log $install_log /i $msipath TARGETDIR=$python_home"
+    $uninstall_args = "/qn /x $msipath"
+    RunCommand "msiexec.exe" $install_args
+    if (-not(Test-Path $python_home)) {
+        Write-Host "Python seems to be installed else-where, reinstalling."
+        RunCommand "msiexec.exe" $uninstall_args
+        RunCommand "msiexec.exe" $install_args
+    }
+}
+
+function RunCommand ($command, $command_args) {
+    Write-Host $command $command_args
+    Start-Process -FilePath $command -ArgumentList $command_args -Wait -Passthru
+}
+
+
+function InstallPip ($python_home) {
+    $pip_path = $python_home + "\Scripts\pip.exe"
+    $python_path = $python_home + "\python.exe"
+    if (-not(Test-Path $pip_path)) {
+        Write-Host "Installing pip..."
+        $webclient = New-Object System.Net.WebClient
+        $webclient.DownloadFile($GET_PIP_URL, $GET_PIP_PATH)
+        Write-Host "Executing:" $python_path $GET_PIP_PATH
+        & $python_path $GET_PIP_PATH
+    } else {
+        Write-Host "pip already installed."
+    }
+}
+
+
+function DownloadMiniconda ($python_version, $platform_suffix) {
+    if ($python_version -eq "3.4") {
+        $filename = "Miniconda3-3.5.5-Windows-" + $platform_suffix + ".exe"
+    } else {
+        $filename = "Miniconda-3.5.5-Windows-" + $platform_suffix + ".exe"
+    }
+    $url = $MINICONDA_URL + $filename
+    $filepath = Download $filename $url
+    return $filepath
+}
+
+
+function InstallMiniconda ($python_version, $architecture, $python_home) {
+    Write-Host "Installing Python" $python_version "for" $architecture "bit architecture to" $python_home
+    if (Test-Path $python_home) {
+        Write-Host $python_home "already exists, skipping."
+        return $false
+    }
+    if ($architecture -eq "32") {
+        $platform_suffix = "x86"
+    } else {
+        $platform_suffix = "x86_64"
+    }
+    $filepath = DownloadMiniconda $python_version $platform_suffix
+    Write-Host "Installing" $filepath "to" $python_home
+    $install_log = $python_home + ".log"
+    $args = "/S /D=$python_home"
+    Write-Host $filepath $args
+    Start-Process -FilePath $filepath -ArgumentList $args -Wait -Passthru
+    if (Test-Path $python_home) {
+        Write-Host "Python $python_version ($architecture) installation complete"
+    } else {
+        Write-Host "Failed to install Python in $python_home"
+        Get-Content -Path $install_log
+        Exit 1
+    }
+}
+
+
+function InstallMinicondaPip ($python_home) {
+    $pip_path = $python_home + "\Scripts\pip.exe"
+    $conda_path = $python_home + "\Scripts\conda.exe"
+    if (-not(Test-Path $pip_path)) {
+        Write-Host "Installing pip..."
+        $args = "install --yes pip"
+        Write-Host $conda_path $args
+        Start-Process -FilePath "$conda_path" -ArgumentList $args -Wait -Passthru
+    } else {
+        Write-Host "pip already installed."
+    }
+}
+
+function main () {
+    InstallPython $env:PYTHON_VERSION $env:PYTHON_ARCH $env:PYTHON
+    InstallPip $env:PYTHON
+}
+
+main
diff --git a/continuous_integration/appveyor/requirements.txt b/continuous_integration/appveyor/requirements.txt
new file mode 100644
index 0000000000..3c14aba749
--- /dev/null
+++ b/continuous_integration/appveyor/requirements.txt
@@ -0,0 +1,12 @@
+# fix the versions of numpy to force the use of numpy and scipy to use the whl
+# of the rackspace folder instead of trying to install from more recent
+# source tarball published on PyPI
+atlas
+cython
+numpy >= 1.3
+scipy  >= 0.7.0
+six >= 1.5.0
+smart_open >= 1.2.1
+nose
+wheel
+wheelhouse_uploader
diff --git a/continuous_integration/appveyor/run_with_env.cmd b/continuous_integration/appveyor/run_with_env.cmd
new file mode 100644
index 0000000000..5da547c499
--- /dev/null
+++ b/continuous_integration/appveyor/run_with_env.cmd
@@ -0,0 +1,88 @@
+:: To build extensions for 64 bit Python 3, we need to configure environment
+:: variables to use the MSVC 2010 C++ compilers from GRMSDKX_EN_DVD.iso of:
+:: MS Windows SDK for Windows 7 and .NET Framework 4 (SDK v7.1)
+::
+:: To build extensions for 64 bit Python 2, we need to configure environment
+:: variables to use the MSVC 2008 C++ compilers from GRMSDKX_EN_DVD.iso of:
+:: MS Windows SDK for Windows 7 and .NET Framework 3.5 (SDK v7.0)
+::
+:: 32 bit builds, and 64-bit builds for 3.5 and beyond, do not require specific
+:: environment configurations.
+::
+:: Note: this script needs to be run with the /E:ON and /V:ON flags for the
+:: cmd interpreter, at least for (SDK v7.0)
+::
+:: More details at:
+:: https://github.com/cython/cython/wiki/64BitCythonExtensionsOnWindows
+:: http://stackoverflow.com/a/13751649/163740
+::
+:: Author: Olivier Grisel
+:: License: CC0 1.0 Universal: http://creativecommons.org/publicdomain/zero/1.0/
+::
+:: Notes about batch files for Python people:
+::
+:: Quotes in values are literally part of the values:
+::      SET FOO="bar"
+:: FOO is now five characters long: " b a r "
+:: If you don't want quotes, don't include them on the right-hand side.
+::
+:: The CALL lines at the end of this file look redundant, but if you move them
+:: outside of the IF clauses, they do not run properly in the SET_SDK_64==Y
+:: case, I don't know why.
+@ECHO OFF
+
+SET COMMAND_TO_RUN=%*
+SET WIN_SDK_ROOT=C:\Program Files\Microsoft SDKs\Windows
+SET WIN_WDK=c:\Program Files (x86)\Windows Kits\10\Include\wdf
+
+:: Extract the major and minor versions, and allow for the minor version to be
+:: more than 9.  This requires the version number to have two dots in it.
+SET MAJOR_PYTHON_VERSION=%PYTHON_VERSION:~0,1%
+IF "%PYTHON_VERSION:~3,1%" == "." (
+    SET MINOR_PYTHON_VERSION=%PYTHON_VERSION:~2,1%
+) ELSE (
+    SET MINOR_PYTHON_VERSION=%PYTHON_VERSION:~2,2%
+)
+
+:: Based on the Python version, determine what SDK version to use, and whether
+:: to set the SDK for 64-bit.
+IF %MAJOR_PYTHON_VERSION% == 2 (
+    SET WINDOWS_SDK_VERSION="v7.0"
+    SET SET_SDK_64=Y
+) ELSE (
+    IF %MAJOR_PYTHON_VERSION% == 3 (
+        SET WINDOWS_SDK_VERSION="v7.1"
+        IF %MINOR_PYTHON_VERSION% LEQ 4 (
+            SET SET_SDK_64=Y
+        ) ELSE (
+            SET SET_SDK_64=N
+            IF EXIST "%WIN_WDK%" (
+                :: See: https://connect.microsoft.com/VisualStudio/feedback/details/1610302/
+                REN "%WIN_WDK%" 0wdf
+            )
+        )
+    ) ELSE (
+        ECHO Unsupported Python version: "%MAJOR_PYTHON_VERSION%"
+        EXIT 1
+    )
+)
+
+IF %PYTHON_ARCH% == 64 (
+    IF %SET_SDK_64% == Y (
+        ECHO Configuring Windows SDK %WINDOWS_SDK_VERSION% for Python %MAJOR_PYTHON_VERSION% on a 64 bit architecture
+        SET DISTUTILS_USE_SDK=1
+        SET MSSdk=1
+        "%WIN_SDK_ROOT%\%WINDOWS_SDK_VERSION%\Setup\WindowsSdkVer.exe" -q -version:%WINDOWS_SDK_VERSION%
+        "%WIN_SDK_ROOT%\%WINDOWS_SDK_VERSION%\Bin\SetEnv.cmd" /x64 /release
+        ECHO Executing: %COMMAND_TO_RUN%
+        call %COMMAND_TO_RUN% || EXIT 1
+    ) ELSE (
+        ECHO Using default MSVC build environment for 64 bit architecture
+        ECHO Executing: %COMMAND_TO_RUN%
+        call %COMMAND_TO_RUN% || EXIT 1
+    )
+) ELSE (
+    ECHO Using default MSVC build environment for 32 bit architecture
+    ECHO Executing: %COMMAND_TO_RUN%
+    call %COMMAND_TO_RUN% || EXIT 1
+)

From 85d36d66b6dc33858c169812748a548a822b1548 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Mon, 19 Oct 2015 22:48:57 +0100
Subject: [PATCH 02/20] remove atlas

---
 continuous_integration/appveyor/requirements.txt | 1 -
 1 file changed, 1 deletion(-)

diff --git a/continuous_integration/appveyor/requirements.txt b/continuous_integration/appveyor/requirements.txt
index 3c14aba749..a99d8f42d3 100644
--- a/continuous_integration/appveyor/requirements.txt
+++ b/continuous_integration/appveyor/requirements.txt
@@ -1,7 +1,6 @@
 # fix the versions of numpy to force the use of numpy and scipy to use the whl
 # of the rackspace folder instead of trying to install from more recent
 # source tarball published on PyPI
-atlas
 cython
 numpy >= 1.3
 scipy  >= 0.7.0

From 4fac2db3456a369fe1d9301ef6aea580cadeaccc Mon Sep 17 00:00:00 2001
From: Lev Konstantinovskiy <lev.konst@gmail.com>
Date: Mon, 2 Nov 2015 12:01:40 +0000
Subject: [PATCH 03/20] Exact versions of numpy and scipy

to download pre-built wheels from rackspaces
---
 continuous_integration/appveyor/requirements.txt | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/continuous_integration/appveyor/requirements.txt b/continuous_integration/appveyor/requirements.txt
index a99d8f42d3..56ca16eddf 100644
--- a/continuous_integration/appveyor/requirements.txt
+++ b/continuous_integration/appveyor/requirements.txt
@@ -1,11 +1,12 @@
 # fix the versions of numpy to force the use of numpy and scipy to use the whl
 # of the rackspace folder instead of trying to install from more recent
 # source tarball published on PyPI
+numpy==1.9.3
+scipy==0.16.0
 cython
-numpy >= 1.3
-scipy  >= 0.7.0
 six >= 1.5.0
 smart_open >= 1.2.1
 nose
 wheel
 wheelhouse_uploader
+

From 8f59800b7aed25209f964705d18e3b714389a917 Mon Sep 17 00:00:00 2001
From: Lev Konstantinovskiy <lev.konst@gmail.com>
Date: Mon, 2 Nov 2015 12:14:59 +0000
Subject: [PATCH 04/20] find_links on rackspace

---
 continuous_integration/appveyor/requirements.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/continuous_integration/appveyor/requirements.txt b/continuous_integration/appveyor/requirements.txt
index 56ca16eddf..444d01ded7 100644
--- a/continuous_integration/appveyor/requirements.txt
+++ b/continuous_integration/appveyor/requirements.txt
@@ -1,3 +1,9 @@
+# Fetch numpy and scipy wheels from the sklearn rackspace wheelhouse.
+# Those wheels were collected from http://www.lfd.uci.edu/~gohlke/pythonlibs/
+# This is a temporary solution. As soon as numpy and scipy provide official
+# wheel for windows we ca delete this --find-links line.
+--find-links http://28daf2247a33ed269873-7b1aad3fab3cc330e1fd9d109892382a.r6.cf2.rackcdn.com/
+
 # fix the versions of numpy to force the use of numpy and scipy to use the whl
 # of the rackspace folder instead of trying to install from more recent
 # source tarball published on PyPI

From cf2b7d5ca58ab3e3af4f2ef99ef436ca4cb3f9cf Mon Sep 17 00:00:00 2001
From: Lev Konstantinovskiy <lev.konst@gmail.com>
Date: Mon, 2 Nov 2015 12:41:17 +0000
Subject: [PATCH 05/20] Upload using wheelhouse_uploader

---
 appveyor.yml | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/appveyor.yml b/appveyor.yml
index 9152276b82..6ac858faf9 100644
--- a/appveyor.yml
+++ b/appveyor.yml
@@ -8,6 +8,9 @@ environment:
     # /E:ON and /V:ON options are not enabled in the batch script intepreter
     # See: http://stackoverflow.com/a/13751649/163740
     CMD_IN_ENV: "cmd /E:ON /V:ON /C .\\continuous_integration\\appveyor\\run_with_env.cmd"
+    WHEELHOUSE_UPLOADER_USERNAME: sklearn-appveyor
+    WHEELHOUSE_UPLOADER_SECRET:
+      secure: BQm8KfEj6v2Y+dQxb2syQvTFxDnHXvaNktkLcYSq7jfbTOO6eH9n09tfQzFUVcWZ
     
   matrix:
     - PYTHON: "C:\\Python27"
@@ -64,11 +67,11 @@ artifacts:
   # Archive the generated wheel package in the ci.appveyor.com build report.
   - path: dist\*
 # TODO: get a share
-#on_success:
+on_success:
   # Upload the generated wheel package to Rackspace
   # On Windows, Apache Libcloud cannot find a standard CA cert bundle so we
   # disable the ssl checks.
-#  - "python -m wheelhouse_uploader upload --no-ssl-check --local-folder=dist sklearn-windows-wheels"
+  - "python -m wheelhouse_uploader upload --no-ssl-check --local-folder=dist sklearn-windows-wheels"
 
 #notifications:
 #  - provider: Webhook

From 0b227ca5742b8ba7e076b9c387049088be961d1a Mon Sep 17 00:00:00 2001
From: Lev Konstantinovskiy <lev.konst@gmail.com>
Date: Mon, 2 Nov 2015 12:42:41 +0000
Subject: [PATCH 06/20] Update appveyor.yml

---
 appveyor.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/appveyor.yml b/appveyor.yml
index 6ac858faf9..185f853e96 100644
--- a/appveyor.yml
+++ b/appveyor.yml
@@ -8,6 +8,7 @@ environment:
     # /E:ON and /V:ON options are not enabled in the batch script intepreter
     # See: http://stackoverflow.com/a/13751649/163740
     CMD_IN_ENV: "cmd /E:ON /V:ON /C .\\continuous_integration\\appveyor\\run_with_env.cmd"
+    # TODO: use gensim's username
     WHEELHOUSE_UPLOADER_USERNAME: sklearn-appveyor
     WHEELHOUSE_UPLOADER_SECRET:
       secure: BQm8KfEj6v2Y+dQxb2syQvTFxDnHXvaNktkLcYSq7jfbTOO6eH9n09tfQzFUVcWZ

From 212cc2a78eb1427671ff9e230c9e18473c8217ec Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Tue, 3 Nov 2015 03:55:30 +0000
Subject: [PATCH 07/20] fix testScoring failing on win

---
 gensim/test/test_word2vec.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/test/test_word2vec.py b/gensim/test/test_word2vec.py
index 2194063db6..296eaa578e 100644
--- a/gensim/test/test_word2vec.py
+++ b/gensim/test/test_word2vec.py
@@ -190,7 +190,7 @@ def testScoring(self):
         model = word2vec.Word2Vec(sentences, size=2, min_count=1)
 
         # just score and make sure they exist
-        scores = model.score(sentences)
+        scores = model.score(sentences, len(sentences))
         self.assertEqual(len(scores),len(sentences))
 
 

From 996e1954f7522f970f1cdb0fa8e835e904668b41 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Tue, 3 Nov 2015 17:57:26 +0000
Subject: [PATCH 08/20] removing unicode from authors name

---
 setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index ed53a50229..9c8b0982ac 100644
--- a/setup.py
+++ b/setup.py
@@ -124,7 +124,7 @@ def readfile(fname):
     cmdclass={'build_ext': custom_build_ext},
     packages=find_packages(),
 
-    author=u'Radim Řehůřek',
+    author=u'Radim Rehurek',
     author_email='me@radimrehurek.com',
 
     url='http://radimrehurek.com/gensim',

From d83e13f6e4bd898c4c25ef4a1145f4558086a097 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Wed, 4 Nov 2015 07:52:50 +0000
Subject: [PATCH 09/20] Investigating OverflowError in w2v

---
 gensim/models/word2vec.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
index 488d5fb5df..71edb542a1 100755
--- a/gensim/models/word2vec.py
+++ b/gensim/models/word2vec.py
@@ -962,7 +962,9 @@ def reset_weights(self):
     def seeded_vector(self, seed_string):
         """Create one 'random' vector (but deterministic by seed_string)"""
         # Note: built-in hash() may vary by Python version or even (in Py3.x) per launch
-        once = random.RandomState(uint32(self.hashfxn(seed_string)))
+        self.hashfxn(seed_string) 
+        ui = uint32(h)
+        once = random.RandomState(ui)
         return (once.rand(self.vector_size) - 0.5) / self.vector_size
 
     def save_word2vec_format(self, fname, fvocab=None, binary=False):

From f36b40096ea2f678cd064540cca4766cd384c7e6 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Wed, 4 Nov 2015 09:02:39 +0000
Subject: [PATCH 10/20] typo fix

---
 gensim/models/word2vec.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
index 71edb542a1..31357b2a8c 100755
--- a/gensim/models/word2vec.py
+++ b/gensim/models/word2vec.py
@@ -962,7 +962,7 @@ def reset_weights(self):
     def seeded_vector(self, seed_string):
         """Create one 'random' vector (but deterministic by seed_string)"""
         # Note: built-in hash() may vary by Python version or even (in Py3.x) per launch
-        self.hashfxn(seed_string) 
+        h = self.hashfxn(seed_string)
         ui = uint32(h)
         once = random.RandomState(ui)
         return (once.rand(self.vector_size) - 0.5) / self.vector_size

From e2acd5affce163efc123c898315b1a659d5badd9 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Thu, 5 Nov 2015 18:40:25 +0000
Subject: [PATCH 11/20] change LDA test to int_

---
 gensim/test/test_ldamodel.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index ba0df78b38..e19d150cac 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -218,7 +218,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
-            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int64))
+            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int_))
             self.assertTrue(isinstance(v, float))
 
     def testShowTopic(self):

From 10238bee0aca7ab9c06ca434f79d3eb46137b6e5 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Thu, 5 Nov 2015 18:52:58 +0000
Subject: [PATCH 12/20] word2vec Overflow workaround

---
 gensim/models/word2vec.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
index 31357b2a8c..0c6dc37f1a 100755
--- a/gensim/models/word2vec.py
+++ b/gensim/models/word2vec.py
@@ -962,9 +962,7 @@ def reset_weights(self):
     def seeded_vector(self, seed_string):
         """Create one 'random' vector (but deterministic by seed_string)"""
         # Note: built-in hash() may vary by Python version or even (in Py3.x) per launch
-        h = self.hashfxn(seed_string)
-        ui = uint32(h)
-        once = random.RandomState(ui)
+        once = random.RandomState(self.hashfxn(seed_string) & 0xffffffff)
         return (once.rand(self.vector_size) - 0.5) / self.vector_size
 
     def save_word2vec_format(self, fname, fvocab=None, binary=False):

From 989274be1a3da7fafbed37f920896894cdefda8c Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Thu, 5 Nov 2015 19:18:46 +0000
Subject: [PATCH 13/20] lda test int32 or int64

---
 gensim/test/test_ldamodel.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index e19d150cac..076d238301 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -218,7 +218,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
-            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int_))
+            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k,numpy.int64))
             self.assertTrue(isinstance(v, float))
 
     def testShowTopic(self):

From 5b319801d335c6fa76f956bbc77c8bc383b7c38d Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Thu, 5 Nov 2015 19:57:27 +0000
Subject: [PATCH 14/20] lda print type of k

---
 gensim/test/test_ldamodel.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index 076d238301..d4dba1b969 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -218,6 +218,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
+            print type(k)
             self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k,numpy.int64))
             self.assertTrue(isinstance(v, float))
 

From 6c3ebba4667f854af050de1a85c9ae6b11747f68 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Thu, 5 Nov 2015 21:01:40 +0000
Subject: [PATCH 15/20] lda print type of k

---
 gensim/test/test_ldamodel.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index d4dba1b969..298252791f 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -218,7 +218,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
-            print type(k)
+            print(type(k))
             self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k,numpy.int64))
             self.assertTrue(isinstance(v, float))
 

From 1840370cce7863e2e86a4ed7f473a753231ff360 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Fri, 6 Nov 2015 08:35:03 +0000
Subject: [PATCH 16/20] lda print type of k

---
 gensim/test/test_ldamodel.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index 298252791f..1b6020eff7 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -218,7 +218,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
-            print(type(k))
+            logging.warning(str(type(k)))
             self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k,numpy.int64))
             self.assertTrue(isinstance(v, float))
 

From 9e7e39c07817a9e30fc2c8e3bab1014e43c419dc Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Fri, 6 Nov 2015 09:14:26 +0000
Subject: [PATCH 17/20] lda print type of k

---
 gensim/test/test_ldamodel.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index 1b6020eff7..dc05776e60 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -219,7 +219,9 @@ def testGetTopicTerms(self):
 
         for k, v in topic_terms:
             logging.warning(str(type(k)))
-            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k,numpy.int64))
+            logging.warning(isinstance(k, numpy.int32))
+            logging.warning(isinstance(k, int) or isinstance(k, numpy.int32))
+            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k, numpy.int64))
             self.assertTrue(isinstance(v, float))
 
     def testShowTopic(self):

From f8b43ead245f3d7cd9ad4fa4a37326843b37345c Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Fri, 6 Nov 2015 09:49:01 +0000
Subject: [PATCH 18/20] lda test numbers.Integral

---
 gensim/test/test_ldamodel.py | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index dc05776e60..1022397ee1 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -218,10 +218,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
-            logging.warning(str(type(k)))
-            logging.warning(isinstance(k, numpy.int32))
-            logging.warning(isinstance(k, int) or isinstance(k, numpy.int32))
-            self.assertTrue(isinstance(k, int) or isinstance(k, numpy.int32) or isinstance(k, numpy.int64))
+            self.assertTrue(isinstance(k, numpy.numbers.Integral))
             self.assertTrue(isinstance(v, float))
 
     def testShowTopic(self):

From 53b6ad3f255f100848843e8eccf22eeae682d0d5 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Fri, 6 Nov 2015 11:35:41 +0000
Subject: [PATCH 19/20] lda test numbers.Integral

---
 gensim/test/test_ldamodel.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/gensim/test/test_ldamodel.py b/gensim/test/test_ldamodel.py
index 1022397ee1..bbcb65ed42 100644
--- a/gensim/test/test_ldamodel.py
+++ b/gensim/test/test_ldamodel.py
@@ -14,6 +14,7 @@
 import os
 import os.path
 import tempfile
+import numbers
 
 import six
 import numpy
@@ -218,7 +219,7 @@ def testGetTopicTerms(self):
         topic_terms = self.model.get_topic_terms(1)
 
         for k, v in topic_terms:
-            self.assertTrue(isinstance(k, numpy.numbers.Integral))
+            self.assertTrue(isinstance(k, numbers.Integral))
             self.assertTrue(isinstance(v, float))
 
     def testShowTopic(self):

From 72217672f1ea0f4a7d04fab2ced69d1a00742dc3 Mon Sep 17 00:00:00 2001
From: tmylk <lev.konst@gmail.com>
Date: Fri, 6 Nov 2015 12:02:01 +0000
Subject: [PATCH 20/20] remove wheel upload until share is ready

---
 appveyor.yml | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/appveyor.yml b/appveyor.yml
index 185f853e96..b75d14e23e 100644
--- a/appveyor.yml
+++ b/appveyor.yml
@@ -68,11 +68,11 @@ artifacts:
   # Archive the generated wheel package in the ci.appveyor.com build report.
   - path: dist\*
 # TODO: get a share
-on_success:
-  # Upload the generated wheel package to Rackspace
-  # On Windows, Apache Libcloud cannot find a standard CA cert bundle so we
-  # disable the ssl checks.
-  - "python -m wheelhouse_uploader upload --no-ssl-check --local-folder=dist sklearn-windows-wheels"
+#on_success:
+#  # Upload the generated wheel package to Rackspace
+#  # On Windows, Apache Libcloud cannot find a standard CA cert bundle so we
+#  # disable the ssl checks.
+#  - "python -m wheelhouse_uploader upload --no-ssl-check --local-folder=dist sklearn-windows-wheels"
 
 #notifications:
 #  - provider: Webhook