mhjensen
273 lines
18 KiB
HTML
273 lines
18 KiB
HTML
<!--
|
|
Automatically generated HTML file from DocOnce source
|
|
(https://github.com/hplgit/doconce/)
|
|
-->
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
|
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="description" content="Data Analysis and Machine Learning: Logistic Regression">
|
|
|
|
<title>Data Analysis and Machine Learning: Logistic Regression</title>
|
|
|
|
<!-- Bootstrap style: bootstrap -->
|
|
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
|
<!-- not necessary
|
|
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
|
-->
|
|
|
|
<style type="text/css">
|
|
|
|
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
|
.dropdown-menu {
|
|
height: auto;
|
|
max-height: 400px;
|
|
overflow-x: hidden;
|
|
}
|
|
|
|
/* Adds an invisible element before each target to offset for the navigation
|
|
bar */
|
|
.anchor::before {
|
|
content:"";
|
|
display:block;
|
|
height:50px; /* fixed header height for style bootstrap */
|
|
margin:-50px 0 0; /* negative fixed header height */
|
|
}
|
|
</style>
|
|
|
|
|
|
</head>
|
|
|
|
<!-- tocinfo
|
|
{'highest level': 2,
|
|
'sections': [('Logistic Regression', 2, None, '___sec0'),
|
|
('Optimization and Deep learning', 2, None, '___sec1'),
|
|
('Basics', 2, None, '___sec2'),
|
|
('Linear classifier', 2, None, '___sec3'),
|
|
('Some selected properties', 2, None, '___sec4'),
|
|
('The logistic function', 2, None, '___sec5'),
|
|
('Examples of likelihood functions used in logistic regression '
|
|
'and nueral networks',
|
|
2,
|
|
None,
|
|
'___sec6'),
|
|
('Two parameters', 2, None, '___sec7'),
|
|
('Maximum likelihood', 2, None, '___sec8'),
|
|
('The cost function rewritten', 2, None, '___sec9'),
|
|
('Minimizing the cross entropy', 2, None, '___sec10'),
|
|
('A more compact expression', 2, None, '___sec11'),
|
|
('Extending to more predictors', 2, None, '___sec12'),
|
|
('Including more classes', 2, None, '___sec13'),
|
|
('More classes', 2, None, '___sec14'),
|
|
('A simple classification problem', 2, None, '___sec15'),
|
|
('The Credit Card example', 2, None, '___sec16'),
|
|
('How to read the Credit Card data', 2, None, '___sec17')]}
|
|
end of tocinfo -->
|
|
|
|
<body>
|
|
|
|
|
|
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
TeX: {
|
|
equationNumbers: { autoNumber: "none" },
|
|
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
|
}
|
|
});
|
|
</script>
|
|
<script type="text/javascript" async
|
|
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
|
</script>
|
|
|
|
|
|
|
|
|
|
<!-- Bootstrap navigation bar -->
|
|
<div class="navbar navbar-default navbar-fixed-top">
|
|
<div class="navbar-header">
|
|
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
|
<span class="icon-bar"></span>
|
|
<span class="icon-bar"></span>
|
|
<span class="icon-bar"></span>
|
|
</button>
|
|
<a class="navbar-brand" href="LogReg-bs.html">Data Analysis and Machine Learning: Logistic Regression</a>
|
|
</div>
|
|
|
|
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
|
<ul class="nav navbar-nav navbar-right">
|
|
<li class="dropdown">
|
|
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
|
<ul class="dropdown-menu">
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs001.html#___sec0" style="font-size: 80%;">Logistic Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs002.html#___sec1" style="font-size: 80%;">Optimization and Deep learning</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs003.html#___sec2" style="font-size: 80%;">Basics</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs004.html#___sec3" style="font-size: 80%;">Linear classifier</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs005.html#___sec4" style="font-size: 80%;">Some selected properties</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs006.html#___sec5" style="font-size: 80%;">The logistic function</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs007.html#___sec6" style="font-size: 80%;">Examples of likelihood functions used in logistic regression and nueral networks</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs008.html#___sec7" style="font-size: 80%;">Two parameters</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs009.html#___sec8" style="font-size: 80%;">Maximum likelihood</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs010.html#___sec9" style="font-size: 80%;">The cost function rewritten</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs011.html#___sec10" style="font-size: 80%;">Minimizing the cross entropy</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs012.html#___sec11" style="font-size: 80%;">A more compact expression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs013.html#___sec12" style="font-size: 80%;">Extending to more predictors</a></li>
|
|
<!-- navigation toc: --> <li><a href="._LogReg-bs014.html#___sec13" style="font-size: 80%;">Including more classes</a></li>
|
|
<!-- 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%;">How to read the Credit Card data</a></li>
|
|
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
</div> <!-- end of navigation bar -->
|
|
|
|
<div class="container">
|
|
|
|
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
|
|
|
<a name="part0018"></a>
|
|
<!-- !split -->
|
|
|
|
<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 -->
|
|
<ul class="pagination">
|
|
<li><a href="._LogReg-bs017.html">«</a></li>
|
|
<li><a href="._LogReg-bs000.html">1</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._LogReg-bs010.html">11</a></li>
|
|
<li><a href="._LogReg-bs011.html">12</a></li>
|
|
<li><a href="._LogReg-bs012.html">13</a></li>
|
|
<li><a href="._LogReg-bs013.html">14</a></li>
|
|
<li><a href="._LogReg-bs014.html">15</a></li>
|
|
<li><a href="._LogReg-bs015.html">16</a></li>
|
|
<li><a href="._LogReg-bs016.html">17</a></li>
|
|
<li><a href="._LogReg-bs017.html">18</a></li>
|
|
<li class="active"><a href="._LogReg-bs018.html">19</a></li>
|
|
</ul>
|
|
<!-- ------------------- end of main content --------------- -->
|
|
|
|
</div> <!-- end container -->
|
|
<!-- include javascript, jQuery *first* -->
|
|
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
|
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
|
|
|
<!-- Bootstrap footer
|
|
<footer>
|
|
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
|
</footer>
|
|
-->
|
|
|
|
|
|
<center style="font-size:80%">
|
|
<!-- copyright only on the titlepage -->
|
|
</center>
|
|
|
|
|
|
</body>
|
|
</html>
|
|
|
|
|