lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
a67ed0edccfea6a6dff8eecc4560d7da9c60dbd4
FYS-STK4155/doc/pub/LogReg/html/._LogReg-bs017.html
T
mhjensen ad8b22e3f9 minor update to logreg
2019-09-22 22:56:08 +02:00

381 lines
31 KiB
HTML
Raw Blame History

<!--
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')]}
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="#___sec16" style="font-size: 80%;">The Credit Card example</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div> <!-- end of navigation bar -->
<div class="container">
<p>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p> <!-- add vertical space -->
<a name="part0017"></a>
<!-- !split -->
<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>. More text to come.
<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">&#39;/default of credit card clients.xls&#39;</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">&quot;default payment next month&quot;</span>: <span style="color: #BA2121">&quot;defaultPaymentNextMonth&quot;</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">&#39;defaultPaymentNextMonth&#39;</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">&#39;defaultPaymentNextMonth&#39;</span>]<span style="color: #666666">.</span>values
<span style="color: #408080; font-style: italic"># Categorical variables to one-hot&#39;s</span>
onehotencoder <span style="color: #666666">=</span> OneHotEncoder(categories<span style="color: #666666">=</span><span style="color: #BA2121">&quot;auto&quot;</span>)
X <span style="color: #666666">=</span> ColumnTransformer(
[(<span style="color: #BA2121">&quot;&quot;</span>, onehotencoder, [<span style="color: #666666">3</span>]),],
remainder<span style="color: #666666">=</span><span style="color: #BA2121">&quot;passthrough&quot;</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&#39;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">&#39;&#39;&#39;</span>
<span style="color: #BA2121; font-style: italic">df = df.drop(df[(df.BILL_AMT1 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT2 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT3 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT4 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT5 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.BILL_AMT6 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT1 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT2 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT3 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT4 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT5 == 0) &amp;</span>
<span style="color: #BA2121; font-style: italic"> (df.PAY_AMT6 == 0)].index)</span>
<span style="color: #BA2121; font-style: italic">&#39;&#39;&#39;</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">&amp;</span>
(df<span style="color: #666666">.</span>BILL_AMT2 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</span>
(df<span style="color: #666666">.</span>BILL_AMT3 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</span>
(df<span style="color: #666666">.</span>BILL_AMT4 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</span>
(df<span style="color: #666666">.</span>BILL_AMT5 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</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">&amp;</span>
(df<span style="color: #666666">.</span>PAY_AMT2 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</span>
(df<span style="color: #666666">.</span>PAY_AMT3 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</span>
(df<span style="color: #666666">.</span>PAY_AMT4 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</span>
(df<span style="color: #666666">.</span>PAY_AMT5 <span style="color: #666666">==</span> <span style="color: #666666">0</span>) <span style="color: #666666">&amp;</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">&#39;C&#39;</span>: <span style="color: #666666">1./</span>lambdas, <span style="color: #BA2121">&quot;solver&quot;</span>:[<span style="color: #BA2121">&quot;lbfgs&quot;</span>]}]<span style="color: #408080; font-style: italic">#*len(parameters)}]</span>
scoring <span style="color: #666666">=</span> [<span style="color: #BA2121">&#39;accuracy&#39;</span>, <span style="color: #BA2121">&#39;roc_auc&#39;</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">&#39;roc_auc&#39;</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"># &quot;refit&quot; 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">&quot;&quot;&quot;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 &quot;&quot;&quot;</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">&#39;accuracy&#39;</span>:
mean <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;mean_test_score&#39;</span>
sd <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;std_test_score&#39;</span>
<span style="color: #008000; font-weight: bold">elif</span> scoring <span style="color: #666666">==</span> <span style="color: #BA2121">&#39;auc&#39;</span>:
mean <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;mean_test_roc_auc&#39;</span>
sd <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;std_test_roc_auc&#39;</span>
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;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">&quot;</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">&#39;params&#39;</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">&quot;</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">&quot;</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">&quot;&quot;&quot;</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"> &quot;&quot;&quot;</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">&gt;</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">&#39;</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">################### Training ###############&#39;</span>)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&#39;</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">&#39;</span>, cm)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&#39;</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">&#39;</span>, accScore)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&#39;</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">&#39;</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">&gt;</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">&#39;</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">################### Testing ###############&#39;</span>)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&#39;</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">&#39;</span>, cm)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&#39;</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">&#39;</span>, accScore)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&#39;</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">&#39;</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">&quot;white&quot;</span>, context<span style="color: #666666">=</span><span style="color: #BA2121">&quot;notebook&quot;</span>, font_scale<span style="color: #666666">=1.5</span>,
rc<span style="color: #666666">=</span>{<span style="color: #BA2121">&quot;axes.grid&quot;</span>: <span style="color: #008000">True</span>, <span style="color: #BA2121">&quot;legend.frameon&quot;</span>: <span style="color: #008000">False</span>,
<span style="color: #BA2121">&quot;lines.markeredgewidth&quot;</span>: <span style="color: #666666">1.4</span>, <span style="color: #BA2121">&quot;lines.markersize&quot;</span>: <span style="color: #666666">10</span>})
seaborn<span style="color: #666666">.</span>set_context(<span style="color: #BA2121">&quot;notebook&quot;</span>, font_scale<span style="color: #666666">=1.5</span>, rc<span style="color: #666666">=</span>{<span style="color: #BA2121">&quot;lines.linewidth&quot;</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>
<p>
<!-- navigation buttons at the bottom of the page -->
<ul class="pagination">
<li><a href="._LogReg-bs016.html">&laquo;</a></li>
<li><a href="._LogReg-bs000.html">1</a></li>
<li><a href="">...</a></li>
<li><a href="._LogReg-bs009.html">10</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 class="active"><a href="._LogReg-bs017.html">18</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>
Reference in New Issue View Git Blame Copy Permalink