update on credit card data
This commit is contained in:
mhjensen
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -152,7 +152,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Oct 9, 2019</h4></center> <!-- date -->
|
||||
<center><h4>Oct 17, 2019</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<p>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -135,210 +135,18 @@ MathJax.Hub.Config({
|
||||
|
||||
<h2 id="___sec16" class="anchor">The Credit Card example </h2>
|
||||
Here we use the the <a href="https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients" target="_self">credit card data</a>.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors. More text and clean up of code will be added.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors.
|
||||
|
||||
<p>
|
||||
For categorical data -Scikit-Learn- provides a so-called <b>one-hot encoder</b>.
|
||||
This is called one-hot
|
||||
encoding, because only one attribute will be equal to 1 (hot), while the others will be 0 (cold).
|
||||
<b>Scikit-Learn</b> provides a OneHotEncoder encoder to convert integer categorical values into one-hot
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">os</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
|
||||
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.model_selection</span> <span style="color: #008000; font-weight: bold">import</span> train_test_split
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> OneHotEncoder
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.compose</span> <span style="color: #008000; font-weight: bold">import</span> ColumnTransformer
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> StandardScaler, OneHotEncoder
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> confusion_matrix, accuracy_score, roc_auc_score
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Trying to set the seed</span>
|
||||
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">0</span>)
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">random</span>
|
||||
random<span style="color: #666666">.</span>seed(<span style="color: #666666">0</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Reading file into data frame</span>
|
||||
cwd <span style="color: #666666">=</span> os<span style="color: #666666">.</span>getcwd()
|
||||
filename <span style="color: #666666">=</span> cwd <span style="color: #666666">+</span> <span style="color: #BA2121">'/default of credit card clients.xls'</span>
|
||||
nanDict <span style="color: #666666">=</span> {}
|
||||
df <span style="color: #666666">=</span> pd<span style="color: #666666">.</span>read_excel(filename, header<span style="color: #666666">=1</span>, skiprows<span style="color: #666666">=0</span>, index_col<span style="color: #666666">=0</span>, na_values<span style="color: #666666">=</span>nanDict)
|
||||
|
||||
df<span style="color: #666666">.</span>rename(index<span style="color: #666666">=</span><span style="color: #008000">str</span>, columns<span style="color: #666666">=</span>{<span style="color: #BA2121">"default payment next month"</span>: <span style="color: #BA2121">"defaultPaymentNextMonth"</span>}, inplace<span style="color: #666666">=</span><span style="color: #008000">True</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Features and targets </span>
|
||||
X <span style="color: #666666">=</span> df<span style="color: #666666">.</span>loc[:, df<span style="color: #666666">.</span>columns <span style="color: #666666">!=</span> <span style="color: #BA2121">'defaultPaymentNextMonth'</span>]<span style="color: #666666">.</span>values
|
||||
y <span style="color: #666666">=</span> df<span style="color: #666666">.</span>loc[:, df<span style="color: #666666">.</span>columns <span style="color: #666666">==</span> <span style="color: #BA2121">'defaultPaymentNextMonth'</span>]<span style="color: #666666">.</span>values
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Categorical variables to one-hot's</span>
|
||||
onehotencoder <span style="color: #666666">=</span> OneHotEncoder(categories<span style="color: #666666">=</span><span style="color: #BA2121">"auto"</span>)
|
||||
|
||||
X <span style="color: #666666">=</span> ColumnTransformer(
|
||||
[(<span style="color: #BA2121">""</span>, onehotencoder, [<span style="color: #666666">3</span>]),],
|
||||
remainder<span style="color: #666666">=</span><span style="color: #BA2121">"passthrough"</span>
|
||||
)<span style="color: #666666">.</span>fit_transform(X)
|
||||
|
||||
y<span style="color: #666666">.</span>shape
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train-test split</span>
|
||||
trainingShare <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>
|
||||
seed <span style="color: #666666">=</span> <span style="color: #666666">1</span>
|
||||
XTrain, XTest, yTrain, yTest<span style="color: #666666">=</span>train_test_split(X, y, train_size<span style="color: #666666">=</span>trainingShare, \
|
||||
test_size <span style="color: #666666">=</span> <span style="color: #666666">1-</span>trainingShare,
|
||||
random_state<span style="color: #666666">=</span>seed)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Input Scaling</span>
|
||||
sc <span style="color: #666666">=</span> StandardScaler()
|
||||
XTrain <span style="color: #666666">=</span> sc<span style="color: #666666">.</span>fit_transform(XTrain)
|
||||
XTest <span style="color: #666666">=</span> sc<span style="color: #666666">.</span>transform(XTest)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># One-hot's of the target vector</span>
|
||||
Y_train_onehot, Y_test_onehot <span style="color: #666666">=</span> onehotencoder<span style="color: #666666">.</span>fit_transform(yTrain), onehotencoder<span style="color: #666666">.</span>fit_transform(yTest)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Remove instances with zeros only for past bill statements or paid amounts</span>
|
||||
<span style="color: #BA2121; font-style: italic">'''</span>
|
||||
<span style="color: #BA2121; font-style: italic">df = df.drop(df[(df.BILL_AMT1 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT2 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT3 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT4 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT5 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT6 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT1 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT2 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT3 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT4 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT5 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT6 == 0)].index)</span>
|
||||
<span style="color: #BA2121; font-style: italic">'''</span>
|
||||
df <span style="color: #666666">=</span> df<span style="color: #666666">.</span>drop(df[(df<span style="color: #666666">.</span>BILL_AMT1 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT2 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT3 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT4 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT5 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT6 <span style="color: #666666">==</span> <span style="color: #666666">0</span>)]<span style="color: #666666">.</span>index)
|
||||
|
||||
df <span style="color: #666666">=</span> df<span style="color: #666666">.</span>drop(df[(df<span style="color: #666666">.</span>PAY_AMT1 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT2 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT3 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT4 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT5 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT6 <span style="color: #666666">==</span> <span style="color: #666666">0</span>)]<span style="color: #666666">.</span>index)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LogisticRegression
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.model_selection</span> <span style="color: #008000; font-weight: bold">import</span> GridSearchCV
|
||||
|
||||
lambdas<span style="color: #666666">=</span>np<span style="color: #666666">.</span>logspace(<span style="color: #666666">-5</span>,<span style="color: #666666">7</span>,<span style="color: #666666">13</span>)
|
||||
parameters <span style="color: #666666">=</span> [{<span style="color: #BA2121">'C'</span>: <span style="color: #666666">1./</span>lambdas, <span style="color: #BA2121">"solver"</span>:[<span style="color: #BA2121">"lbfgs"</span>]}]<span style="color: #408080; font-style: italic">#*len(parameters)}]</span>
|
||||
scoring <span style="color: #666666">=</span> [<span style="color: #BA2121">'accuracy'</span>, <span style="color: #BA2121">'roc_auc'</span>]
|
||||
logReg <span style="color: #666666">=</span> LogisticRegression()
|
||||
gridSearch <span style="color: #666666">=</span> GridSearchCV(logReg, parameters, cv<span style="color: #666666">=5</span>, scoring<span style="color: #666666">=</span>scoring, refit<span style="color: #666666">=</span><span style="color: #BA2121">'roc_auc'</span>)
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># "refit" gives the metric used deciding best model. </span>
|
||||
<span style="color: #408080; font-style: italic"># See more http://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html</span>
|
||||
gridSearch<span style="color: #666666">.</span>fit(XTrain, yTrain<span style="color: #666666">.</span>ravel())
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">gridSearchSummary</span>(method, scoring):
|
||||
<span style="color: #BA2121; font-style: italic">"""Prints best parameters from Grid search</span>
|
||||
<span style="color: #BA2121; font-style: italic"> and AUC with standard deviation for all </span>
|
||||
<span style="color: #BA2121; font-style: italic"> parameter combos """</span>
|
||||
|
||||
method <span style="color: #666666">=</span> <span style="color: #008000">eval</span>(method)
|
||||
<span style="color: #008000; font-weight: bold">if</span> scoring <span style="color: #666666">==</span> <span style="color: #BA2121">'accuracy'</span>:
|
||||
mean <span style="color: #666666">=</span> <span style="color: #BA2121">'mean_test_score'</span>
|
||||
sd <span style="color: #666666">=</span> <span style="color: #BA2121">'std_test_score'</span>
|
||||
<span style="color: #008000; font-weight: bold">elif</span> scoring <span style="color: #666666">==</span> <span style="color: #BA2121">'auc'</span>:
|
||||
mean <span style="color: #666666">=</span> <span style="color: #BA2121">'mean_test_roc_auc'</span>
|
||||
sd <span style="color: #666666">=</span> <span style="color: #BA2121">'std_test_roc_auc'</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Best: </span><span style="color: #BB6688; font-weight: bold">%f</span><span style="color: #BA2121"> using </span><span style="color: #BB6688; font-weight: bold">%s</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> (method<span style="color: #666666">.</span>best_score_, method<span style="color: #666666">.</span>best_params_))
|
||||
means <span style="color: #666666">=</span> method<span style="color: #666666">.</span>cv_results_[mean]
|
||||
stds <span style="color: #666666">=</span> method<span style="color: #666666">.</span>cv_results_[sd]
|
||||
params <span style="color: #666666">=</span> method<span style="color: #666666">.</span>cv_results_[<span style="color: #BA2121">'params'</span>]
|
||||
<span style="color: #008000; font-weight: bold">for</span> mean, stdev, param <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">zip</span>(means, stds, params):
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"</span><span style="color: #BB6688; font-weight: bold">%f</span><span style="color: #BA2121"> (</span><span style="color: #BB6688; font-weight: bold">%f</span><span style="color: #BA2121">) with: </span><span style="color: #BB6688; font-weight: bold">%r</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> (mean, stdev, param))
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">createConfusionMatrix</span>(method, printOut<span style="color: #666666">=</span><span style="color: #008000">True</span>):
|
||||
<span style="color: #BA2121; font-style: italic">"""</span>
|
||||
<span style="color: #BA2121; font-style: italic"> Computes and prints confusion matrices, accuracy scores,</span>
|
||||
<span style="color: #BA2121; font-style: italic"> and AUC for test and training sets </span>
|
||||
<span style="color: #BA2121; font-style: italic"> """</span>
|
||||
confusionArray <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(<span style="color: #666666">6</span>, dtype<span style="color: #666666">=</span><span style="color: #008000">object</span>)
|
||||
method <span style="color: #666666">=</span> <span style="color: #008000">eval</span>(method)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train</span>
|
||||
yPredTrain <span style="color: #666666">=</span> method<span style="color: #666666">.</span>predict(XTrain)
|
||||
yPredTrain <span style="color: #666666">=</span> (yPredTrain <span style="color: #666666">></span> <span style="color: #666666">0.5</span>)
|
||||
cm <span style="color: #666666">=</span> confusion_matrix(
|
||||
yTrain, yPredTrain)
|
||||
cm <span style="color: #666666">=</span> np<span style="color: #666666">.</span>around(cm<span style="color: #666666">/</span>cm<span style="color: #666666">.</span>sum(axis<span style="color: #666666">=1</span>)[:,<span style="color: #008000">None</span>], <span style="color: #666666">2</span>)
|
||||
confusionArray[<span style="color: #666666">0</span>] <span style="color: #666666">=</span> cm
|
||||
|
||||
accScore <span style="color: #666666">=</span> accuracy_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #666666">1</span>] <span style="color: #666666">=</span> accScore
|
||||
|
||||
AUC <span style="color: #666666">=</span> roc_auc_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #666666">2</span>] <span style="color: #666666">=</span> AUC
|
||||
|
||||
<span style="color: #008000; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">################### Training ###############'</span>)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Training Confusion matrix: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, cm)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Training Accuracy score: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, accScore)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Train AUC: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, AUC)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Test</span>
|
||||
yPred <span style="color: #666666">=</span> method<span style="color: #666666">.</span>predict(XTest)
|
||||
yPred <span style="color: #666666">=</span> (yPred <span style="color: #666666">></span> <span style="color: #666666">0.5</span>)
|
||||
cm <span style="color: #666666">=</span> confusion_matrix(
|
||||
yTest, yPred)
|
||||
cm <span style="color: #666666">=</span> np<span style="color: #666666">.</span>around(cm<span style="color: #666666">/</span>cm<span style="color: #666666">.</span>sum(axis<span style="color: #666666">=1</span>)[:,<span style="color: #008000">None</span>], <span style="color: #666666">2</span>)
|
||||
confusionArray[<span style="color: #666666">3</span>] <span style="color: #666666">=</span> cm
|
||||
|
||||
accScore <span style="color: #666666">=</span> accuracy_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #666666">4</span>] <span style="color: #666666">=</span> accScore
|
||||
|
||||
AUC <span style="color: #666666">=</span> roc_auc_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #666666">5</span>] <span style="color: #666666">=</span> AUC
|
||||
|
||||
<span style="color: #008000; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">################### Testing ###############'</span>)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Test Confusion matrix: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, cm)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Test Accuracy score: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, accScore)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">TestAUC: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, AUC)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">return</span> confusionArray
|
||||
|
||||
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">seaborn</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">scikitplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">skplt</span>
|
||||
|
||||
seaborn<span style="color: #666666">.</span>set(style<span style="color: #666666">=</span><span style="color: #BA2121">"white"</span>, context<span style="color: #666666">=</span><span style="color: #BA2121">"notebook"</span>, font_scale<span style="color: #666666">=1.5</span>,
|
||||
rc<span style="color: #666666">=</span>{<span style="color: #BA2121">"axes.grid"</span>: <span style="color: #008000">True</span>, <span style="color: #BA2121">"legend.frameon"</span>: <span style="color: #008000">False</span>,
|
||||
<span style="color: #BA2121">"lines.markeredgewidth"</span>: <span style="color: #666666">1.4</span>, <span style="color: #BA2121">"lines.markersize"</span>: <span style="color: #666666">10</span>})
|
||||
seaborn<span style="color: #666666">.</span>set_context(<span style="color: #BA2121">"notebook"</span>, font_scale<span style="color: #666666">=1.5</span>, rc<span style="color: #666666">=</span>{<span style="color: #BA2121">"lines.linewidth"</span>: <span style="color: #666666">4.5</span>})
|
||||
|
||||
yPred <span style="color: #666666">=</span> gridSearch<span style="color: #666666">.</span>predict_proba(XTest)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(yTest<span style="color: #666666">.</span>ravel()<span style="color: #666666">.</span>shape, yPred<span style="color: #666666">.</span>shape)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred_onehot)</span>
|
||||
skplt<span style="color: #666666">.</span>metrics<span style="color: #666666">.</span>plot_cumulative_gain(yTest<span style="color: #666666">.</span>ravel(), yPred)
|
||||
|
||||
defaults <span style="color: #666666">=</span> <span style="color: #008000">sum</span>(yTest <span style="color: #666666">==</span> <span style="color: #666666">1</span>)
|
||||
total <span style="color: #666666">=</span> <span style="color: #008000">len</span>(yTest)
|
||||
defaultRate <span style="color: #666666">=</span> defaults<span style="color: #666666">/</span>total
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">bestCurve</span>(defaults, total, defaultRate):
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>, <span style="color: #666666">1</span>, total)
|
||||
|
||||
y1 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>, <span style="color: #666666">1</span>, defaults)
|
||||
y2 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>ones(total<span style="color: #666666">-</span>defaults)
|
||||
y3 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>concatenate([y1,y2])
|
||||
<span style="color: #008000; font-weight: bold">return</span> x, y3
|
||||
|
||||
x, best <span style="color: #666666">=</span> bestCurve(defaults<span style="color: #666666">=</span>defaults, total<span style="color: #666666">=</span>total, defaultRate<span style="color: #666666">=</span>defaultRate)
|
||||
plt<span style="color: #666666">.</span>plot(x, best)
|
||||
|
||||
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> OneHotEncoder
|
||||
encoder <span style="color: #666666">=</span> OneHotEncoder()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -133,7 +133,103 @@ MathJax.Hub.Config({
|
||||
<a name="part0018"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec17" class="anchor">Analysis of the credi card example </h2>
|
||||
<h2 id="___sec17" class="anchor">How to read the Credit Card data </h2>
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">os</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
|
||||
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.model_selection</span> <span style="color: #008000; font-weight: bold">import</span> train_test_split
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> OneHotEncoder
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.compose</span> <span style="color: #008000; font-weight: bold">import</span> ColumnTransformer
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> StandardScaler, OneHotEncoder
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> confusion_matrix, accuracy_score, roc_auc_score
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Trying to set the seed</span>
|
||||
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">0</span>)
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">random</span>
|
||||
random<span style="color: #666666">.</span>seed(<span style="color: #666666">0</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Reading file into data frame</span>
|
||||
cwd <span style="color: #666666">=</span> os<span style="color: #666666">.</span>getcwd()
|
||||
filename <span style="color: #666666">=</span> cwd <span style="color: #666666">+</span> <span style="color: #BA2121">'/default of credit card clients.xls'</span>
|
||||
nanDict <span style="color: #666666">=</span> {}
|
||||
df <span style="color: #666666">=</span> pd<span style="color: #666666">.</span>read_excel(filename, header<span style="color: #666666">=1</span>, skiprows<span style="color: #666666">=0</span>, index_col<span style="color: #666666">=0</span>, na_values<span style="color: #666666">=</span>nanDict)
|
||||
|
||||
df<span style="color: #666666">.</span>rename(index<span style="color: #666666">=</span><span style="color: #008000">str</span>, columns<span style="color: #666666">=</span>{<span style="color: #BA2121">"default payment next month"</span>: <span style="color: #BA2121">"defaultPaymentNextMonth"</span>}, inplace<span style="color: #666666">=</span><span style="color: #008000">True</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Features and targets </span>
|
||||
X <span style="color: #666666">=</span> df<span style="color: #666666">.</span>loc[:, df<span style="color: #666666">.</span>columns <span style="color: #666666">!=</span> <span style="color: #BA2121">'defaultPaymentNextMonth'</span>]<span style="color: #666666">.</span>values
|
||||
y <span style="color: #666666">=</span> df<span style="color: #666666">.</span>loc[:, df<span style="color: #666666">.</span>columns <span style="color: #666666">==</span> <span style="color: #BA2121">'defaultPaymentNextMonth'</span>]<span style="color: #666666">.</span>values
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Categorical variables to one-hot's</span>
|
||||
onehotencoder <span style="color: #666666">=</span> OneHotEncoder(categories<span style="color: #666666">=</span><span style="color: #BA2121">"auto"</span>)
|
||||
|
||||
X <span style="color: #666666">=</span> ColumnTransformer(
|
||||
[(<span style="color: #BA2121">""</span>, onehotencoder, [<span style="color: #666666">3</span>]),],
|
||||
remainder<span style="color: #666666">=</span><span style="color: #BA2121">"passthrough"</span>
|
||||
)<span style="color: #666666">.</span>fit_transform(X)
|
||||
|
||||
y<span style="color: #666666">.</span>shape
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train-test split</span>
|
||||
trainingShare <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>
|
||||
seed <span style="color: #666666">=</span> <span style="color: #666666">1</span>
|
||||
XTrain, XTest, yTrain, yTest<span style="color: #666666">=</span>train_test_split(X, y, train_size<span style="color: #666666">=</span>trainingShare, \
|
||||
test_size <span style="color: #666666">=</span> <span style="color: #666666">1-</span>trainingShare,
|
||||
random_state<span style="color: #666666">=</span>seed)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Input Scaling</span>
|
||||
sc <span style="color: #666666">=</span> StandardScaler()
|
||||
XTrain <span style="color: #666666">=</span> sc<span style="color: #666666">.</span>fit_transform(XTrain)
|
||||
XTest <span style="color: #666666">=</span> sc<span style="color: #666666">.</span>transform(XTest)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># One-hot's of the target vector</span>
|
||||
Y_train_onehot, Y_test_onehot <span style="color: #666666">=</span> onehotencoder<span style="color: #666666">.</span>fit_transform(yTrain), onehotencoder<span style="color: #666666">.</span>fit_transform(yTest)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Remove instances with zeros only for past bill statements or paid amounts</span>
|
||||
<span style="color: #BA2121; font-style: italic">'''</span>
|
||||
<span style="color: #BA2121; font-style: italic">df = df.drop(df[(df.BILL_AMT1 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT2 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT3 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT4 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT5 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT6 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT1 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT2 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT3 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT4 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT5 == 0) &</span>
|
||||
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT6 == 0)].index)</span>
|
||||
<span style="color: #BA2121; font-style: italic">'''</span>
|
||||
df <span style="color: #666666">=</span> df<span style="color: #666666">.</span>drop(df[(df<span style="color: #666666">.</span>BILL_AMT1 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT2 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT3 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT4 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT5 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>BILL_AMT6 <span style="color: #666666">==</span> <span style="color: #666666">0</span>)]<span style="color: #666666">.</span>index)
|
||||
|
||||
df <span style="color: #666666">=</span> df<span style="color: #666666">.</span>drop(df[(df<span style="color: #666666">.</span>PAY_AMT1 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT2 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT3 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT4 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT5 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&</span>
|
||||
(df<span style="color: #666666">.</span>PAY_AMT6 <span style="color: #666666">==</span> <span style="color: #666666">0</span>)]<span style="color: #666666">.</span>index)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LogisticRegression
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.model_selection</span> <span style="color: #008000; font-weight: bold">import</span> GridSearchCV
|
||||
|
||||
lambdas<span style="color: #666666">=</span>np<span style="color: #666666">.</span>logspace(<span style="color: #666666">-5</span>,<span style="color: #666666">7</span>,<span style="color: #666666">13</span>)
|
||||
parameters <span style="color: #666666">=</span> [{<span style="color: #BA2121">'C'</span>: <span style="color: #666666">1./</span>lambdas, <span style="color: #BA2121">"solver"</span>:[<span style="color: #BA2121">"lbfgs"</span>]}]<span style="color: #408080; font-style: italic">#*len(parameters)}]</span>
|
||||
scoring <span style="color: #666666">=</span> [<span style="color: #BA2121">'accuracy'</span>, <span style="color: #BA2121">'roc_auc'</span>]
|
||||
logReg <span style="color: #666666">=</span> LogisticRegression()
|
||||
gridSearch <span style="color: #666666">=</span> GridSearchCV(logReg, parameters, cv<span style="color: #666666">=5</span>, scoring<span style="color: #666666">=</span>scoring, refit<span style="color: #666666">=</span><span style="color: #BA2121">'roc_auc'</span>)
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
|
||||
@@ -62,7 +62,7 @@ Automatically generated HTML file from DocOnce source
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -117,7 +117,7 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs015.html#___sec14" style="font-size: 80%;">More classes</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs016.html#___sec15" style="font-size: 80%;">A simple classification problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs017.html#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">Analysis of the credi card example</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._LogReg-bs018.html#___sec17" style="font-size: 80%;">How to read the Credit Card data</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -152,7 +152,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Oct 9, 2019</h4></center> <!-- date -->
|
||||
<center><h4>Oct 17, 2019</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<p>
|
||||
|
||||
@@ -148,7 +148,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p> <br>
|
||||
<center><h4>Oct 9, 2019</h4></center> <!-- date -->
|
||||
<center><h4>Oct 17, 2019</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
|
||||
@@ -668,7 +668,24 @@ methods</a>.
|
||||
<section>
|
||||
<h2 id="___sec16">The Credit Card example </h2>
|
||||
Here we use the the <a href="https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients" target="_blank">credit card data</a>.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors. More text and clean up of code will be added.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors.
|
||||
|
||||
<p>
|
||||
For categorical data -Scikit-Learn- provides a so-called <b>one-hot encoder</b>.
|
||||
This is called one-hot
|
||||
encoding, because only one attribute will be equal to 1 (hot), while the others will be 0 (cold).
|
||||
<b>Scikit-Learn</b> provides a OneHotEncoder encoder to convert integer categorical values into one-hot
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> OneHotEncoder
|
||||
encoder = OneHotEncoder()
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec17">How to read the Credit Card data </h2>
|
||||
|
||||
<p>
|
||||
|
||||
@@ -764,120 +781,6 @@ scoring = [<span style="color: #CD5555">'accuracy'</span>, <span style="
|
||||
logReg = LogisticRegression()
|
||||
gridSearch = GridSearchCV(logReg, parameters, cv=<span style="color: #B452CD">5</span>, scoring=scoring, refit=<span style="color: #CD5555">'roc_auc'</span>)
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #228B22"># "refit" gives the metric used deciding best model. </span>
|
||||
<span style="color: #228B22"># See more http://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html</span>
|
||||
gridSearch.fit(XTrain, yTrain.ravel())
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">gridSearchSummary</span>(method, scoring):
|
||||
<span style="color: #CD5555">"""Prints best parameters from Grid search</span>
|
||||
<span style="color: #CD5555"> and AUC with standard deviation for all </span>
|
||||
<span style="color: #CD5555"> parameter combos """</span>
|
||||
|
||||
method = <span style="color: #658b00">eval</span>(method)
|
||||
<span style="color: #8B008B; font-weight: bold">if</span> scoring == <span style="color: #CD5555">'accuracy'</span>:
|
||||
mean = <span style="color: #CD5555">'mean_test_score'</span>
|
||||
sd = <span style="color: #CD5555">'std_test_score'</span>
|
||||
<span style="color: #8B008B; font-weight: bold">elif</span> scoring == <span style="color: #CD5555">'auc'</span>:
|
||||
mean = <span style="color: #CD5555">'mean_test_roc_auc'</span>
|
||||
sd = <span style="color: #CD5555">'std_test_roc_auc'</span>
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">"Best: %f using %s"</span> % (method.best_score_, method.best_params_))
|
||||
means = method.cv_results_[mean]
|
||||
stds = method.cv_results_[sd]
|
||||
params = method.cv_results_[<span style="color: #CD5555">'params'</span>]
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> mean, stdev, param <span style="color: #8B008B">in</span> <span style="color: #658b00">zip</span>(means, stds, params):
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">"%f (%f) with: %r"</span> % (mean, stdev, param))
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">createConfusionMatrix</span>(method, printOut=<span style="color: #658b00">True</span>):
|
||||
<span style="color: #CD5555">"""</span>
|
||||
<span style="color: #CD5555"> Computes and prints confusion matrices, accuracy scores,</span>
|
||||
<span style="color: #CD5555"> and AUC for test and training sets </span>
|
||||
<span style="color: #CD5555"> """</span>
|
||||
confusionArray = np.zeros(<span style="color: #B452CD">6</span>, dtype=<span style="color: #658b00">object</span>)
|
||||
method = <span style="color: #658b00">eval</span>(method)
|
||||
|
||||
<span style="color: #228B22"># Train</span>
|
||||
yPredTrain = method.predict(XTrain)
|
||||
yPredTrain = (yPredTrain > <span style="color: #B452CD">0.5</span>)
|
||||
cm = confusion_matrix(
|
||||
yTrain, yPredTrain)
|
||||
cm = np.around(cm/cm.sum(axis=<span style="color: #B452CD">1</span>)[:,<span style="color: #658b00">None</span>], <span style="color: #B452CD">2</span>)
|
||||
confusionArray[<span style="color: #B452CD">0</span>] = cm
|
||||
|
||||
accScore = accuracy_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #B452CD">1</span>] = accScore
|
||||
|
||||
AUC = roc_auc_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #B452CD">2</span>] = AUC
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\n################### Training ###############'</span>)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTraining Confusion matrix: \n'</span>, cm)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTraining Accuracy score: \n'</span>, accScore)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTrain AUC: \n'</span>, AUC)
|
||||
|
||||
<span style="color: #228B22"># Test</span>
|
||||
yPred = method.predict(XTest)
|
||||
yPred = (yPred > <span style="color: #B452CD">0.5</span>)
|
||||
cm = confusion_matrix(
|
||||
yTest, yPred)
|
||||
cm = np.around(cm/cm.sum(axis=<span style="color: #B452CD">1</span>)[:,<span style="color: #658b00">None</span>], <span style="color: #B452CD">2</span>)
|
||||
confusionArray[<span style="color: #B452CD">3</span>] = cm
|
||||
|
||||
accScore = accuracy_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #B452CD">4</span>] = accScore
|
||||
|
||||
AUC = roc_auc_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #B452CD">5</span>] = AUC
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\n################### Testing ###############'</span>)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTest Confusion matrix: \n'</span>, cm)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTest Accuracy score: \n'</span>, accScore)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTestAUC: \n'</span>, AUC)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">return</span> confusionArray
|
||||
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">seaborn</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">scikitplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">skplt</span>
|
||||
|
||||
seaborn.set(style=<span style="color: #CD5555">"white"</span>, context=<span style="color: #CD5555">"notebook"</span>, font_scale=<span style="color: #B452CD">1.5</span>,
|
||||
rc={<span style="color: #CD5555">"axes.grid"</span>: <span style="color: #658b00">True</span>, <span style="color: #CD5555">"legend.frameon"</span>: <span style="color: #658b00">False</span>,
|
||||
<span style="color: #CD5555">"lines.markeredgewidth"</span>: <span style="color: #B452CD">1.4</span>, <span style="color: #CD5555">"lines.markersize"</span>: <span style="color: #B452CD">10</span>})
|
||||
seaborn.set_context(<span style="color: #CD5555">"notebook"</span>, font_scale=<span style="color: #B452CD">1.5</span>, rc={<span style="color: #CD5555">"lines.linewidth"</span>: <span style="color: #B452CD">4.5</span>})
|
||||
|
||||
yPred = gridSearch.predict_proba(XTest)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(yTest.ravel().shape, yPred.shape)
|
||||
|
||||
<span style="color: #228B22">#skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred_onehot)</span>
|
||||
skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred)
|
||||
|
||||
defaults = <span style="color: #658b00">sum</span>(yTest == <span style="color: #B452CD">1</span>)
|
||||
total = <span style="color: #658b00">len</span>(yTest)
|
||||
defaultRate = defaults/total
|
||||
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">bestCurve</span>(defaults, total, defaultRate):
|
||||
x = np.linspace(<span style="color: #B452CD">0</span>, <span style="color: #B452CD">1</span>, total)
|
||||
|
||||
y1 = np.linspace(<span style="color: #B452CD">0</span>, <span style="color: #B452CD">1</span>, defaults)
|
||||
y2 = np.ones(total-defaults)
|
||||
y3 = np.concatenate([y1,y2])
|
||||
<span style="color: #8B008B; font-weight: bold">return</span> x, y3
|
||||
|
||||
x, best = bestCurve(defaults=defaults, total=total, defaultRate=defaultRate)
|
||||
plt.plot(x, best)
|
||||
|
||||
|
||||
plt.show()
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec17">Analysis of the credi card example </h2>
|
||||
</section>
|
||||
|
||||
|
||||
|
||||
@@ -56,7 +56,7 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -98,7 +98,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Oct 9, 2019</h4></center> <!-- date -->
|
||||
<center><h4>Oct 17, 2019</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- !split -->
|
||||
@@ -570,7 +570,23 @@ methods</a>.
|
||||
|
||||
<h2 id="___sec16">The Credit Card example </h2>
|
||||
Here we use the the <a href="https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients" target="_blank">credit card data</a>.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors. More text and clean up of code will be added.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors.
|
||||
|
||||
<p>
|
||||
For categorical data -Scikit-Learn- provides a so-called <b>one-hot encoder</b>.
|
||||
This is called one-hot
|
||||
encoding, because only one attribute will be equal to 1 (hot), while the others will be 0 (cold).
|
||||
<b>Scikit-Learn</b> provides a OneHotEncoder encoder to convert integer categorical values into one-hot
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> OneHotEncoder
|
||||
encoder = OneHotEncoder()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec17">How to read the Credit Card data </h2>
|
||||
|
||||
<p>
|
||||
|
||||
@@ -668,118 +684,6 @@ gridSearch = GridSearchCV(logReg, parameters, cv=<span style="color: #B452CD">5<
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #228B22"># "refit" gives the metric used deciding best model. </span>
|
||||
<span style="color: #228B22"># See more http://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html</span>
|
||||
gridSearch.fit(XTrain, yTrain.ravel())
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">gridSearchSummary</span>(method, scoring):
|
||||
<span style="color: #CD5555">"""Prints best parameters from Grid search</span>
|
||||
<span style="color: #CD5555"> and AUC with standard deviation for all </span>
|
||||
<span style="color: #CD5555"> parameter combos """</span>
|
||||
|
||||
method = <span style="color: #658b00">eval</span>(method)
|
||||
<span style="color: #8B008B; font-weight: bold">if</span> scoring == <span style="color: #CD5555">'accuracy'</span>:
|
||||
mean = <span style="color: #CD5555">'mean_test_score'</span>
|
||||
sd = <span style="color: #CD5555">'std_test_score'</span>
|
||||
<span style="color: #8B008B; font-weight: bold">elif</span> scoring == <span style="color: #CD5555">'auc'</span>:
|
||||
mean = <span style="color: #CD5555">'mean_test_roc_auc'</span>
|
||||
sd = <span style="color: #CD5555">'std_test_roc_auc'</span>
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">"Best: %f using %s"</span> % (method.best_score_, method.best_params_))
|
||||
means = method.cv_results_[mean]
|
||||
stds = method.cv_results_[sd]
|
||||
params = method.cv_results_[<span style="color: #CD5555">'params'</span>]
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> mean, stdev, param <span style="color: #8B008B">in</span> <span style="color: #658b00">zip</span>(means, stds, params):
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">"%f (%f) with: %r"</span> % (mean, stdev, param))
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">createConfusionMatrix</span>(method, printOut=<span style="color: #658b00">True</span>):
|
||||
<span style="color: #CD5555">"""</span>
|
||||
<span style="color: #CD5555"> Computes and prints confusion matrices, accuracy scores,</span>
|
||||
<span style="color: #CD5555"> and AUC for test and training sets </span>
|
||||
<span style="color: #CD5555"> """</span>
|
||||
confusionArray = np.zeros(<span style="color: #B452CD">6</span>, dtype=<span style="color: #658b00">object</span>)
|
||||
method = <span style="color: #658b00">eval</span>(method)
|
||||
|
||||
<span style="color: #228B22"># Train</span>
|
||||
yPredTrain = method.predict(XTrain)
|
||||
yPredTrain = (yPredTrain > <span style="color: #B452CD">0.5</span>)
|
||||
cm = confusion_matrix(
|
||||
yTrain, yPredTrain)
|
||||
cm = np.around(cm/cm.sum(axis=<span style="color: #B452CD">1</span>)[:,<span style="color: #658b00">None</span>], <span style="color: #B452CD">2</span>)
|
||||
confusionArray[<span style="color: #B452CD">0</span>] = cm
|
||||
|
||||
accScore = accuracy_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #B452CD">1</span>] = accScore
|
||||
|
||||
AUC = roc_auc_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #B452CD">2</span>] = AUC
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\n################### Training ###############'</span>)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTraining Confusion matrix: \n'</span>, cm)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTraining Accuracy score: \n'</span>, accScore)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTrain AUC: \n'</span>, AUC)
|
||||
|
||||
<span style="color: #228B22"># Test</span>
|
||||
yPred = method.predict(XTest)
|
||||
yPred = (yPred > <span style="color: #B452CD">0.5</span>)
|
||||
cm = confusion_matrix(
|
||||
yTest, yPred)
|
||||
cm = np.around(cm/cm.sum(axis=<span style="color: #B452CD">1</span>)[:,<span style="color: #658b00">None</span>], <span style="color: #B452CD">2</span>)
|
||||
confusionArray[<span style="color: #B452CD">3</span>] = cm
|
||||
|
||||
accScore = accuracy_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #B452CD">4</span>] = accScore
|
||||
|
||||
AUC = roc_auc_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #B452CD">5</span>] = AUC
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\n################### Testing ###############'</span>)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTest Confusion matrix: \n'</span>, cm)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTest Accuracy score: \n'</span>, accScore)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\nTestAUC: \n'</span>, AUC)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">return</span> confusionArray
|
||||
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">seaborn</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">scikitplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">skplt</span>
|
||||
|
||||
seaborn.set(style=<span style="color: #CD5555">"white"</span>, context=<span style="color: #CD5555">"notebook"</span>, font_scale=<span style="color: #B452CD">1.5</span>,
|
||||
rc={<span style="color: #CD5555">"axes.grid"</span>: <span style="color: #658b00">True</span>, <span style="color: #CD5555">"legend.frameon"</span>: <span style="color: #658b00">False</span>,
|
||||
<span style="color: #CD5555">"lines.markeredgewidth"</span>: <span style="color: #B452CD">1.4</span>, <span style="color: #CD5555">"lines.markersize"</span>: <span style="color: #B452CD">10</span>})
|
||||
seaborn.set_context(<span style="color: #CD5555">"notebook"</span>, font_scale=<span style="color: #B452CD">1.5</span>, rc={<span style="color: #CD5555">"lines.linewidth"</span>: <span style="color: #B452CD">4.5</span>})
|
||||
|
||||
yPred = gridSearch.predict_proba(XTest)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(yTest.ravel().shape, yPred.shape)
|
||||
|
||||
<span style="color: #228B22">#skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred_onehot)</span>
|
||||
skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred)
|
||||
|
||||
defaults = <span style="color: #658b00">sum</span>(yTest == <span style="color: #B452CD">1</span>)
|
||||
total = <span style="color: #658b00">len</span>(yTest)
|
||||
defaultRate = defaults/total
|
||||
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">bestCurve</span>(defaults, total, defaultRate):
|
||||
x = np.linspace(<span style="color: #B452CD">0</span>, <span style="color: #B452CD">1</span>, total)
|
||||
|
||||
y1 = np.linspace(<span style="color: #B452CD">0</span>, <span style="color: #B452CD">1</span>, defaults)
|
||||
y2 = np.ones(total-defaults)
|
||||
y3 = np.concatenate([y1,y2])
|
||||
<span style="color: #8B008B; font-weight: bold">return</span> x, y3
|
||||
|
||||
x, best = bestCurve(defaults=defaults, total=total, defaultRate=defaultRate)
|
||||
plt.plot(x, best)
|
||||
|
||||
|
||||
plt.show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec17">Analysis of the credi card example </h2>
|
||||
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
|
||||
|
||||
+19
-115
@@ -61,7 +61,7 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
('More classes', 2, None, '___sec14'),
|
||||
('A simple classification problem', 2, None, '___sec15'),
|
||||
('The Credit Card example', 2, None, '___sec16'),
|
||||
('Analysis of the credi card example', 2, None, '___sec17')]}
|
||||
('How to read the Credit Card data', 2, None, '___sec17')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -103,7 +103,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Oct 9, 2019</h4></center> <!-- date -->
|
||||
<center><h4>Oct 17, 2019</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- !split -->
|
||||
@@ -575,7 +575,23 @@ methods</a>.
|
||||
|
||||
<h2 id="___sec16">The Credit Card example </h2>
|
||||
Here we use the the <a href="https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients" target="_blank">credit card data</a>.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors. More text and clean up of code will be added.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors.
|
||||
|
||||
<p>
|
||||
For categorical data -Scikit-Learn- provides a so-called <b>one-hot encoder</b>.
|
||||
This is called one-hot
|
||||
encoding, because only one attribute will be equal to 1 (hot), while the others will be 0 (cold).
|
||||
<b>Scikit-Learn</b> provides a OneHotEncoder encoder to convert integer categorical values into one-hot
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> OneHotEncoder
|
||||
encoder <span style="color: #666666">=</span> OneHotEncoder()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec17">How to read the Credit Card data </h2>
|
||||
|
||||
<p>
|
||||
|
||||
@@ -673,118 +689,6 @@ gridSearch <span style="color: #666666">=</span> GridSearchCV(logReg, parameters
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># "refit" gives the metric used deciding best model. </span>
|
||||
<span style="color: #408080; font-style: italic"># See more http://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html</span>
|
||||
gridSearch<span style="color: #666666">.</span>fit(XTrain, yTrain<span style="color: #666666">.</span>ravel())
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">gridSearchSummary</span>(method, scoring):
|
||||
<span style="color: #BA2121; font-style: italic">"""Prints best parameters from Grid search</span>
|
||||
<span style="color: #BA2121; font-style: italic"> and AUC with standard deviation for all </span>
|
||||
<span style="color: #BA2121; font-style: italic"> parameter combos """</span>
|
||||
|
||||
method <span style="color: #666666">=</span> <span style="color: #008000">eval</span>(method)
|
||||
<span style="color: #008000; font-weight: bold">if</span> scoring <span style="color: #666666">==</span> <span style="color: #BA2121">'accuracy'</span>:
|
||||
mean <span style="color: #666666">=</span> <span style="color: #BA2121">'mean_test_score'</span>
|
||||
sd <span style="color: #666666">=</span> <span style="color: #BA2121">'std_test_score'</span>
|
||||
<span style="color: #008000; font-weight: bold">elif</span> scoring <span style="color: #666666">==</span> <span style="color: #BA2121">'auc'</span>:
|
||||
mean <span style="color: #666666">=</span> <span style="color: #BA2121">'mean_test_roc_auc'</span>
|
||||
sd <span style="color: #666666">=</span> <span style="color: #BA2121">'std_test_roc_auc'</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Best: </span><span style="color: #BB6688; font-weight: bold">%f</span><span style="color: #BA2121"> using </span><span style="color: #BB6688; font-weight: bold">%s</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> (method<span style="color: #666666">.</span>best_score_, method<span style="color: #666666">.</span>best_params_))
|
||||
means <span style="color: #666666">=</span> method<span style="color: #666666">.</span>cv_results_[mean]
|
||||
stds <span style="color: #666666">=</span> method<span style="color: #666666">.</span>cv_results_[sd]
|
||||
params <span style="color: #666666">=</span> method<span style="color: #666666">.</span>cv_results_[<span style="color: #BA2121">'params'</span>]
|
||||
<span style="color: #008000; font-weight: bold">for</span> mean, stdev, param <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">zip</span>(means, stds, params):
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"</span><span style="color: #BB6688; font-weight: bold">%f</span><span style="color: #BA2121"> (</span><span style="color: #BB6688; font-weight: bold">%f</span><span style="color: #BA2121">) with: </span><span style="color: #BB6688; font-weight: bold">%r</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> (mean, stdev, param))
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">createConfusionMatrix</span>(method, printOut<span style="color: #666666">=</span><span style="color: #008000">True</span>):
|
||||
<span style="color: #BA2121; font-style: italic">"""</span>
|
||||
<span style="color: #BA2121; font-style: italic"> Computes and prints confusion matrices, accuracy scores,</span>
|
||||
<span style="color: #BA2121; font-style: italic"> and AUC for test and training sets </span>
|
||||
<span style="color: #BA2121; font-style: italic"> """</span>
|
||||
confusionArray <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(<span style="color: #666666">6</span>, dtype<span style="color: #666666">=</span><span style="color: #008000">object</span>)
|
||||
method <span style="color: #666666">=</span> <span style="color: #008000">eval</span>(method)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train</span>
|
||||
yPredTrain <span style="color: #666666">=</span> method<span style="color: #666666">.</span>predict(XTrain)
|
||||
yPredTrain <span style="color: #666666">=</span> (yPredTrain <span style="color: #666666">></span> <span style="color: #666666">0.5</span>)
|
||||
cm <span style="color: #666666">=</span> confusion_matrix(
|
||||
yTrain, yPredTrain)
|
||||
cm <span style="color: #666666">=</span> np<span style="color: #666666">.</span>around(cm<span style="color: #666666">/</span>cm<span style="color: #666666">.</span>sum(axis<span style="color: #666666">=1</span>)[:,<span style="color: #008000">None</span>], <span style="color: #666666">2</span>)
|
||||
confusionArray[<span style="color: #666666">0</span>] <span style="color: #666666">=</span> cm
|
||||
|
||||
accScore <span style="color: #666666">=</span> accuracy_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #666666">1</span>] <span style="color: #666666">=</span> accScore
|
||||
|
||||
AUC <span style="color: #666666">=</span> roc_auc_score(yTrain, yPredTrain)
|
||||
confusionArray[<span style="color: #666666">2</span>] <span style="color: #666666">=</span> AUC
|
||||
|
||||
<span style="color: #008000; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">################### Training ###############'</span>)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Training Confusion matrix: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, cm)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Training Accuracy score: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, accScore)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Train AUC: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, AUC)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Test</span>
|
||||
yPred <span style="color: #666666">=</span> method<span style="color: #666666">.</span>predict(XTest)
|
||||
yPred <span style="color: #666666">=</span> (yPred <span style="color: #666666">></span> <span style="color: #666666">0.5</span>)
|
||||
cm <span style="color: #666666">=</span> confusion_matrix(
|
||||
yTest, yPred)
|
||||
cm <span style="color: #666666">=</span> np<span style="color: #666666">.</span>around(cm<span style="color: #666666">/</span>cm<span style="color: #666666">.</span>sum(axis<span style="color: #666666">=1</span>)[:,<span style="color: #008000">None</span>], <span style="color: #666666">2</span>)
|
||||
confusionArray[<span style="color: #666666">3</span>] <span style="color: #666666">=</span> cm
|
||||
|
||||
accScore <span style="color: #666666">=</span> accuracy_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #666666">4</span>] <span style="color: #666666">=</span> accScore
|
||||
|
||||
AUC <span style="color: #666666">=</span> roc_auc_score(yTest, yPred)
|
||||
confusionArray[<span style="color: #666666">5</span>] <span style="color: #666666">=</span> AUC
|
||||
|
||||
<span style="color: #008000; font-weight: bold">if</span> printOut:
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">################### Testing ###############'</span>)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Test Confusion matrix: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, cm)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">Test Accuracy score: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, accScore)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">TestAUC: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, AUC)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">return</span> confusionArray
|
||||
|
||||
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">seaborn</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">scikitplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">skplt</span>
|
||||
|
||||
seaborn<span style="color: #666666">.</span>set(style<span style="color: #666666">=</span><span style="color: #BA2121">"white"</span>, context<span style="color: #666666">=</span><span style="color: #BA2121">"notebook"</span>, font_scale<span style="color: #666666">=1.5</span>,
|
||||
rc<span style="color: #666666">=</span>{<span style="color: #BA2121">"axes.grid"</span>: <span style="color: #008000">True</span>, <span style="color: #BA2121">"legend.frameon"</span>: <span style="color: #008000">False</span>,
|
||||
<span style="color: #BA2121">"lines.markeredgewidth"</span>: <span style="color: #666666">1.4</span>, <span style="color: #BA2121">"lines.markersize"</span>: <span style="color: #666666">10</span>})
|
||||
seaborn<span style="color: #666666">.</span>set_context(<span style="color: #BA2121">"notebook"</span>, font_scale<span style="color: #666666">=1.5</span>, rc<span style="color: #666666">=</span>{<span style="color: #BA2121">"lines.linewidth"</span>: <span style="color: #666666">4.5</span>})
|
||||
|
||||
yPred <span style="color: #666666">=</span> gridSearch<span style="color: #666666">.</span>predict_proba(XTest)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(yTest<span style="color: #666666">.</span>ravel()<span style="color: #666666">.</span>shape, yPred<span style="color: #666666">.</span>shape)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred_onehot)</span>
|
||||
skplt<span style="color: #666666">.</span>metrics<span style="color: #666666">.</span>plot_cumulative_gain(yTest<span style="color: #666666">.</span>ravel(), yPred)
|
||||
|
||||
defaults <span style="color: #666666">=</span> <span style="color: #008000">sum</span>(yTest <span style="color: #666666">==</span> <span style="color: #666666">1</span>)
|
||||
total <span style="color: #666666">=</span> <span style="color: #008000">len</span>(yTest)
|
||||
defaultRate <span style="color: #666666">=</span> defaults<span style="color: #666666">/</span>total
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">bestCurve</span>(defaults, total, defaultRate):
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>, <span style="color: #666666">1</span>, total)
|
||||
|
||||
y1 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>, <span style="color: #666666">1</span>, defaults)
|
||||
y2 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>ones(total<span style="color: #666666">-</span>defaults)
|
||||
y3 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>concatenate([y1,y2])
|
||||
<span style="color: #008000; font-weight: bold">return</span> x, y3
|
||||
|
||||
x, best <span style="color: #666666">=</span> bestCurve(defaults<span style="color: #666666">=</span>defaults, total<span style="color: #666666">=</span>total, defaultRate<span style="color: #666666">=</span>defaultRate)
|
||||
plt<span style="color: #666666">.</span>plot(x, best)
|
||||
|
||||
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec17">Analysis of the credi card example </h2>
|
||||
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
"<!-- Author: --> \n",
|
||||
"**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n",
|
||||
"\n",
|
||||
"Date: **Oct 9, 2019**\n",
|
||||
"Date: **Oct 17, 2019**\n",
|
||||
"\n",
|
||||
"Copyright 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
|
||||
"\n",
|
||||
@@ -669,7 +669,12 @@
|
||||
"source": [
|
||||
"## The Credit Card example\n",
|
||||
"Here we use the the [credit card data](https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients). \n",
|
||||
"The data are from an extensive database from Taiwan and include more than ten predictors. More text and clean up of code will be added."
|
||||
"The data are from an extensive database from Taiwan and include more than ten predictors.\n",
|
||||
"\n",
|
||||
"For categorical data -Scikit-Learn- provides a so-called **one-hot encoder**.\n",
|
||||
"This is called one-hot\n",
|
||||
"encoding, because only one attribute will be equal to 1 (hot), while the others will be 0 (cold).\n",
|
||||
"**Scikit-Learn** provides a OneHotEncoder encoder to convert integer categorical values into one-hot"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -679,6 +684,25 @@
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.preprocessing import OneHotEncoder\n",
|
||||
"encoder = OneHotEncoder()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## How to read the Credit Card data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import os\n",
|
||||
@@ -771,129 +795,6 @@
|
||||
"logReg = LogisticRegression()\n",
|
||||
"gridSearch = GridSearchCV(logReg, parameters, cv=5, scoring=scoring, refit='roc_auc')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\n",
|
||||
"# \"refit\" gives the metric used deciding best model. \n",
|
||||
"# See more http://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html\n",
|
||||
"gridSearch.fit(XTrain, yTrain.ravel())\n",
|
||||
"\n",
|
||||
"def gridSearchSummary(method, scoring):\n",
|
||||
" \"\"\"Prints best parameters from Grid search\n",
|
||||
" and AUC with standard deviation for all \n",
|
||||
" parameter combos \"\"\"\n",
|
||||
" \n",
|
||||
" method = eval(method)\n",
|
||||
" if scoring == 'accuracy':\n",
|
||||
" mean = 'mean_test_score'\n",
|
||||
" sd = 'std_test_score'\n",
|
||||
" elif scoring == 'auc':\n",
|
||||
" mean = 'mean_test_roc_auc'\n",
|
||||
" sd = 'std_test_roc_auc'\n",
|
||||
" print(\"Best: %f using %s\" % (method.best_score_, method.best_params_))\n",
|
||||
" means = method.cv_results_[mean]\n",
|
||||
" stds = method.cv_results_[sd]\n",
|
||||
" params = method.cv_results_['params']\n",
|
||||
" for mean, stdev, param in zip(means, stds, params):\n",
|
||||
" print(\"%f (%f) with: %r\" % (mean, stdev, param))\n",
|
||||
"\n",
|
||||
"def createConfusionMatrix(method, printOut=True):\n",
|
||||
" \"\"\"\n",
|
||||
" Computes and prints confusion matrices, accuracy scores,\n",
|
||||
" and AUC for test and training sets \n",
|
||||
" \"\"\"\n",
|
||||
" confusionArray = np.zeros(6, dtype=object)\n",
|
||||
" method = eval(method)\n",
|
||||
" \n",
|
||||
" # Train\n",
|
||||
" yPredTrain = method.predict(XTrain)\n",
|
||||
" yPredTrain = (yPredTrain > 0.5)\n",
|
||||
" cm = confusion_matrix(\n",
|
||||
" yTrain, yPredTrain) \n",
|
||||
" cm = np.around(cm/cm.sum(axis=1)[:,None], 2)\n",
|
||||
" confusionArray[0] = cm\n",
|
||||
" \n",
|
||||
" accScore = accuracy_score(yTrain, yPredTrain)\n",
|
||||
" confusionArray[1] = accScore\n",
|
||||
" \n",
|
||||
" AUC = roc_auc_score(yTrain, yPredTrain)\n",
|
||||
" confusionArray[2] = AUC\n",
|
||||
" \n",
|
||||
" if printOut:\n",
|
||||
" print('\\n################### Training ###############')\n",
|
||||
" print('\\nTraining Confusion matrix: \\n', cm)\n",
|
||||
" print('\\nTraining Accuracy score: \\n', accScore)\n",
|
||||
" print('\\nTrain AUC: \\n', AUC)\n",
|
||||
" \n",
|
||||
" # Test\n",
|
||||
" yPred = method.predict(XTest)\n",
|
||||
" yPred = (yPred > 0.5)\n",
|
||||
" cm = confusion_matrix(\n",
|
||||
" yTest, yPred) \n",
|
||||
" cm = np.around(cm/cm.sum(axis=1)[:,None], 2)\n",
|
||||
" confusionArray[3] = cm\n",
|
||||
" \n",
|
||||
" accScore = accuracy_score(yTest, yPred)\n",
|
||||
" confusionArray[4] = accScore\n",
|
||||
" \n",
|
||||
" AUC = roc_auc_score(yTest, yPred)\n",
|
||||
" confusionArray[5] = AUC\n",
|
||||
" \n",
|
||||
" if printOut:\n",
|
||||
" print('\\n################### Testing ###############')\n",
|
||||
" print('\\nTest Confusion matrix: \\n', cm)\n",
|
||||
" print('\\nTest Accuracy score: \\n', accScore)\n",
|
||||
" print('\\nTestAUC: \\n', AUC) \n",
|
||||
" \n",
|
||||
" return confusionArray\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn\n",
|
||||
"import scikitplot as skplt\n",
|
||||
"\n",
|
||||
"seaborn.set(style=\"white\", context=\"notebook\", font_scale=1.5, \n",
|
||||
" rc={\"axes.grid\": True, \"legend.frameon\": False,\n",
|
||||
"\"lines.markeredgewidth\": 1.4, \"lines.markersize\": 10})\n",
|
||||
"seaborn.set_context(\"notebook\", font_scale=1.5, rc={\"lines.linewidth\": 4.5})\n",
|
||||
"\n",
|
||||
"yPred = gridSearch.predict_proba(XTest) \n",
|
||||
"print(yTest.ravel().shape, yPred.shape)\n",
|
||||
"\n",
|
||||
"#skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred_onehot)\n",
|
||||
"skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred)\n",
|
||||
"\n",
|
||||
"defaults = sum(yTest == 1)\n",
|
||||
"total = len(yTest)\n",
|
||||
"defaultRate = defaults/total\n",
|
||||
"def bestCurve(defaults, total, defaultRate):\n",
|
||||
" x = np.linspace(0, 1, total)\n",
|
||||
" \n",
|
||||
" y1 = np.linspace(0, 1, defaults)\n",
|
||||
" y2 = np.ones(total-defaults)\n",
|
||||
" y3 = np.concatenate([y1,y2])\n",
|
||||
" return x, y3\n",
|
||||
"\n",
|
||||
"x, best = bestCurve(defaults=defaults, total=total, defaultRate=defaultRate) \n",
|
||||
"plt.plot(x, best) \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Analysis of the credi card example"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {},
|
||||
|
||||
Binary file not shown.
Binary file not shown.
@@ -451,7 +451,19 @@ if __name__ == "__main__":
|
||||
!split
|
||||
===== The Credit Card example =====
|
||||
Here we use the the "credit card data":"https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients".
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors. More text and clean up of code will be added.
|
||||
The data are from an extensive database from Taiwan and include more than ten predictors.
|
||||
|
||||
For categorical data -Scikit-Learn- provides a so-called _one-hot encoder_.
|
||||
This is called one-hot
|
||||
encoding, because only one attribute will be equal to 1 (hot), while the others will be 0 (cold).
|
||||
_Scikit-Learn_ provides a OneHotEncoder encoder to convert integer categorical values into one-hot
|
||||
!bc pycod
|
||||
from sklearn.preprocessing import OneHotEncoder
|
||||
encoder = OneHotEncoder()
|
||||
!ec
|
||||
|
||||
!split
|
||||
===== How to read the Credit Card data =====
|
||||
|
||||
!bc pycod
|
||||
import pandas as pd
|
||||
@@ -546,116 +558,3 @@ logReg = LogisticRegression()
|
||||
gridSearch = GridSearchCV(logReg, parameters, cv=5, scoring=scoring, refit='roc_auc')
|
||||
!ec
|
||||
|
||||
!bc pycod
|
||||
|
||||
# "refit" gives the metric used deciding best model.
|
||||
# See more http://scikit-learn.org/stable/auto_examples/model_selection/plot_multi_metric_evaluation.html
|
||||
gridSearch.fit(XTrain, yTrain.ravel())
|
||||
|
||||
def gridSearchSummary(method, scoring):
|
||||
"""Prints best parameters from Grid search
|
||||
and AUC with standard deviation for all
|
||||
parameter combos """
|
||||
|
||||
method = eval(method)
|
||||
if scoring == 'accuracy':
|
||||
mean = 'mean_test_score'
|
||||
sd = 'std_test_score'
|
||||
elif scoring == 'auc':
|
||||
mean = 'mean_test_roc_auc'
|
||||
sd = 'std_test_roc_auc'
|
||||
print("Best: %f using %s" % (method.best_score_, method.best_params_))
|
||||
means = method.cv_results_[mean]
|
||||
stds = method.cv_results_[sd]
|
||||
params = method.cv_results_['params']
|
||||
for mean, stdev, param in zip(means, stds, params):
|
||||
print("%f (%f) with: %r" % (mean, stdev, param))
|
||||
|
||||
def createConfusionMatrix(method, printOut=True):
|
||||
"""
|
||||
Computes and prints confusion matrices, accuracy scores,
|
||||
and AUC for test and training sets
|
||||
"""
|
||||
confusionArray = np.zeros(6, dtype=object)
|
||||
method = eval(method)
|
||||
|
||||
# Train
|
||||
yPredTrain = method.predict(XTrain)
|
||||
yPredTrain = (yPredTrain > 0.5)
|
||||
cm = confusion_matrix(
|
||||
yTrain, yPredTrain)
|
||||
cm = np.around(cm/cm.sum(axis=1)[:,None], 2)
|
||||
confusionArray[0] = cm
|
||||
|
||||
accScore = accuracy_score(yTrain, yPredTrain)
|
||||
confusionArray[1] = accScore
|
||||
|
||||
AUC = roc_auc_score(yTrain, yPredTrain)
|
||||
confusionArray[2] = AUC
|
||||
|
||||
if printOut:
|
||||
print('\n################### Training ###############')
|
||||
print('\nTraining Confusion matrix: \n', cm)
|
||||
print('\nTraining Accuracy score: \n', accScore)
|
||||
print('\nTrain AUC: \n', AUC)
|
||||
|
||||
# Test
|
||||
yPred = method.predict(XTest)
|
||||
yPred = (yPred > 0.5)
|
||||
cm = confusion_matrix(
|
||||
yTest, yPred)
|
||||
cm = np.around(cm/cm.sum(axis=1)[:,None], 2)
|
||||
confusionArray[3] = cm
|
||||
|
||||
accScore = accuracy_score(yTest, yPred)
|
||||
confusionArray[4] = accScore
|
||||
|
||||
AUC = roc_auc_score(yTest, yPred)
|
||||
confusionArray[5] = AUC
|
||||
|
||||
if printOut:
|
||||
print('\n################### Testing ###############')
|
||||
print('\nTest Confusion matrix: \n', cm)
|
||||
print('\nTest Accuracy score: \n', accScore)
|
||||
print('\nTestAUC: \n', AUC)
|
||||
|
||||
return confusionArray
|
||||
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
import seaborn
|
||||
import scikitplot as skplt
|
||||
|
||||
seaborn.set(style="white", context="notebook", font_scale=1.5,
|
||||
rc={"axes.grid": True, "legend.frameon": False,
|
||||
"lines.markeredgewidth": 1.4, "lines.markersize": 10})
|
||||
seaborn.set_context("notebook", font_scale=1.5, rc={"lines.linewidth": 4.5})
|
||||
|
||||
yPred = gridSearch.predict_proba(XTest)
|
||||
print(yTest.ravel().shape, yPred.shape)
|
||||
|
||||
#skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred_onehot)
|
||||
skplt.metrics.plot_cumulative_gain(yTest.ravel(), yPred)
|
||||
|
||||
defaults = sum(yTest == 1)
|
||||
total = len(yTest)
|
||||
defaultRate = defaults/total
|
||||
def bestCurve(defaults, total, defaultRate):
|
||||
x = np.linspace(0, 1, total)
|
||||
|
||||
y1 = np.linspace(0, 1, defaults)
|
||||
y2 = np.ones(total-defaults)
|
||||
y3 = np.concatenate([y1,y2])
|
||||
return x, y3
|
||||
|
||||
x, best = bestCurve(defaults=defaults, total=total, defaultRate=defaultRate)
|
||||
plt.plot(x, best)
|
||||
|
||||
|
||||
plt.show()
|
||||
|
||||
!ec
|
||||
|
||||
|
||||
!split
|
||||
===== Analysis of the credi card example =====
|
||||
|
||||
Reference in New Issue
Block a user