DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all \u003cpre\u003e\u003ccode\u003e blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks"); } } catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); } })(); (function(){ try { var __m = "github.com"; var __re = new RegExp('^' + "github\\.com" + '
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix"); } } catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length \u003e 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms"); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links"); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + '
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default"); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers"); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode"); } } catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); } })(); })();
Skip to content

DateTimeTransformer featurizer#4521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 8 commits into from
Dec 17, 2019
Merged

DateTimeTransformer featurizer #4521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
3dcf356
files and changes needed for the DateTimeTransformer
michaelgsharp Dec 4, 2019
1bedb59
updates from PR comments
michaelgsharp Dec 5, 2019
bee2616
removed ability to drop columns from DateTimeTransformer
michaelgsharp Dec 5, 2019
0d10ae7
changes from PR comments
michaelgsharp Dec 5, 2019
6d5625b
updates from PR comments
michaelgsharp Dec 9, 2019
02f808e
updates to fix build issues
michaelgsharp Dec 11, 2019
de2fc12
test for centos7
michaelgsharp Dec 12, 2019
a93e8bf
Fixed CentOS7 check
michaelgsharp Dec 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 84 additions & 0 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Featurizers;

namespace Samples.Dynamic
{
public static class DateTimeTransformer
{
private class DateTimeInput
{
public long Date;
}

public static void Example()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();

// Create a small dataset as an IEnumerable.
// Future Date - 2025 June 30
var samples = new[] { new DateTimeInput() { Date = 1751241600 } };

// Convert training data to IDataView.
var dataview = mlContext.Data.LoadFromEnumerable(samples);

// A pipeline for splitting the time features into individual columns
var pipeline = mlContext.Transforms.FeaturizeDateTime("Date", "DTC");

// The transformed data.
var transformedData = pipeline.Fit(dataview).Transform(dataview);

// Now let's take a look at what this did. We should have created 21 more columns with all the
// DateTime information split into its own columns
var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
transformedData, reuseRowObject: false);

// And we can write out a few rows
Console.WriteLine($"Features column obtained post-transformation.");
foreach (var featureRow in featuresColumn)
Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
featureRow.DTCIsPaidTimeOff);

// Expected output:
// Features columns obtained post-transformation.
// 1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
}

// These columns start with DTC because that is the prefix we picked
private sealed class TransformedData
{
public long Date { get; set; }
public int DTCYear { get; set; }
public byte DTCMonth { get; set; }
public byte DTCDay { get; set; }
public byte DTCHour { get; set; }
public byte DTCMinute { get; set; }
public byte DTCSecond { get; set; }
public byte DTCAmPm { get; set; }
public byte DTCHour12 { get; set; }
public byte DTCDayOfWeek { get; set; }
public byte DTCDayOfQuarter { get; set; }
public ushort DTCDayOfYear { get; set; }
public ushort DTCWeekOfMonth { get; set; }
public byte DTCQuarterOfYear { get; set; }
public byte DTCHalfOfYear { get; set; }
public byte DTCWeekIso { get; set; }
public int DTCYearIso { get; set; }
public string DTCMonthLabel { get; set; }
public string DTCAmPmLabel { get; set; }
public string DTCDayOfWeekLabel { get; set; }
public string DTCHolidayName { get; set; }
public byte DTCIsPaidTimeOff { get; set; }
}
}
}
27 changes: 27 additions & 0 deletions src/Microsoft.ML.Featurizers/Common.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
Expand DownExpand Up@@ -219,5 +220,31 @@ internal static TypeId GetNativeTypeIdFromType(this Type type)

throw new InvalidOperationException($"Unsupported type {type}");
}

// The Native Featurizers do not currently support CentOS7, this method checks the OS and returns true if it is CentOS7.

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about RedHat 7?

internal static bool OsIsCentOS7()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
using (Process process = new Process())

@eerhardteerhardtJan 2, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A more performant way of doing this check would be to read from the file directly. Starting a new process just to get this info is too heavy-weight IMO.

See https://github.com/dotnet/runtime/blob/6f445d6dc237f59d730e0df47f8630b18887d776/src/installer/managed/Microsoft.DotNet.PlatformAbstractions/Native/PlatformApis.cs#L140-L142

{
process.StartInfo.FileName = "/bin/bash";
process.StartInfo.Arguments = "-c \"cat /etc/*-release\"";
process.StartInfo.UseShellExecute = false;
process.StartInfo.RedirectStandardOutput = true;
process.StartInfo.CreateNoWindow = true;
process.Start();

string distro = process.StandardOutput.ReadToEnd().Trim();

process.WaitForExit();
if (distro.Contains("CentOS Linux 7"))
{
return true;
}
}
}
return false;
}
}
}
Loading