Added roc curve SD visualization.

workflows/decision_support/visualization.py

@@ -10,7 +10,7 @@ def sensitivity_analysis_viewer(request, input_dict, output_dict, widget):
     '''
     Computes the sensitivity analysis graph.
         
-    @author: Anze Vavpeltic, 2012
+    @author: Anze Vavpetic, 2012
     '''
     model = input_dict['model']
     attributes = [att.name for att in input_dict['model'].data.domain.features]
@@ -43,7 +43,7 @@ def ds_charts_viewer(request, input_dict, output_dict, widget):
     '''
     Decision support visualization.
         
-    @author: Anze Vavpeltic, 2012
+    @author: Anze Vavpetic, 2012
     '''
     model = input_dict['model']
     norm_data = model()

workflows/subgroup_discovery/SubgroupDiscovery/OWSubgroupROCVizualizer.py

@@ -12,6 +12,7 @@ from Beam_SD import *
 from Apriori_SD import *
 from OWSubgroupROCVizualizerGraph import *
 from PyQt4 import QtGui
+from calcHull import *
 #from qttable import *
 
 white = QColor(255,255,255)
@@ -85,11 +86,11 @@ class OWSubgroupROCVizualizer(OWWidget):
                 indx = ids.index(id)
                 subgroups.isSelected = self.subgroups[indx][1].isSelected
                 self.subgroups[indx] = (id, subgroups)
-                self.calcRates(subgroups)   ######## calc rates
+                calcRates(subgroups)   ######## calc rates
             else:       # add new subgroups
                 subgroups.isSelected = True
                 self.subgroups.append((id, subgroups))
-                self.calcRates(subgroups)   ######## calc rates
+                calcRates(subgroups)   ######## calc rates
         self.edtRules.appendPlainText("%d subgroups sets on input." % len(self.subgroups))
         self.updateclb()
 
@@ -138,95 +139,12 @@ class OWSubgroupROCVizualizer(OWWidget):
                                        symbol = QwtSymbol.Ellipse, xData =s[1].FPR, yData = s[1].TPR)
         self.graphROC.replot()
 
-
-# #############################################
-# calculations for the vizualization
-# #############################################
-
-
-    def calcRates(self, subgroups):
-        subgroups.TPR = []
-        subgroups.FPR = []
-        P = len(subgroups.targetClassRule.TP) * 1.0  # number of all positive examples as a float
-        N = len(subgroups.targetClassRule.FP) * 1.0  # number of all negative examples as a float
-        for rule in subgroups.rules:
-            subgroups.TPR.append( len(rule.TP) / P )  # true positive rate for this rule
-            subgroups.FPR.append( len(rule.FP) / N )  # false positive example for this rule
-
-      #  subgroups.TPR = [0.44,	0.34,	0.33,	0.49,	0.43,	0.49,	0.66,	0.60,	0.61,	0.78,	0.75,	0.77,	0.84,	0.82,	0.82]
-      #  subgroups.FPR = [0.01,	0.00,	0.00,	0.02,	0.00,	0.02,	0.10,	0.07,	0.07,	0.21,	0.16,	0.19,	0.31,	0.29,	0.27]
-
-        len(subgroups.TPR)
-
-        # calculate convex hull ,important: stick this 5 linet together
-        subgroups.hullTPR = [0]
-        subgroups.hullFPR = [0]
-        self.calcHull(subgroups, subgroups.TPR[:], subgroups.FPR[:] , A=(0,0), B=(1,1))
-        subgroups.hullTPR.append(1)
-        subgroups.hullFPR.append(1)
-
-    def calcRatesSubset(self, subgroups):
-        subgroups.TPR = []
-        subgroups.FPR = []
-        P = len(subgroups.targetClassRule.TP) * 1.0  # number of all positive examples as a float
-        N = len(subgroups.targetClassRule.FP) * 1.0  # number of all negative examples as a float
-        for rule in subgroups.rules:
-            TPr = len(rule.TP) / P
-            FPr = len(rule.FP) / N
-            subgroups.TPR.append( TPr )  # true positive rate for this rule
-            subgroups.FPR.append( FPr )  # false positive example for this rule
-            #self.graphROC.tooltipData(FPr, TPr, rule)
-
-
-    def calcHull(self, subgroups, Y, X, A, B):
-        #inicialization
-        C = (-1,-1)    # best new point point
-        y = -1         # best distance
-        index = -1
-        # calculate best new point
-        if (B[0]-A[0])==0:
-            self.edtRules.appendPlainText("vertical line!!!")
-        else:
-            k = (B[1]-A[1]) / (B[0]-A[0])  # coefficient of the line between A and B
-            for i in range(len(Y)):        # check every point
-                yn = Y[i] -( k * ( X[i] - A[0] ) + A[1])   # vertical distance between point i and line AB
-                if yn>0 and yn > y:        # if new distance is the greatest so far
-                    C = (X[i], Y[i])       # the new point is the best so far
-                    y = yn
-                    index = i
-
-        # if new point on the hull was found
-        if C != (-1,-1):
-            # recursivey call this function on the LEFT side of the point
-            del X[index]
-            del Y[index]
-            Xl =[]
-            Yl =[]
-            Xu =[]
-            Yu =[]
-            for i in range(len(X)):
-                if X[i]>=A[0] and X[i]<=C[0] and Y[i]>A[1]:
-                    Xl.append(X[i])
-                    Yl.append(Y[i])
-                elif X[i]>=C[0] and X[i]<=B[0] and Y[i]>C[1]:
-                    Xu.append(X[i])
-                    Yu.append(Y[i])
-
-            self.calcHull(subgroups, Yl, Xl, A,C)  # recursive call
-            # save the new point
-            subgroups.hullTPR.append(C[1])
-            subgroups.hullFPR.append(C[0])
-            # recursivey call this function on the RIGHT side of the point
-            self.calcHull(subgroups, Yu, Xu, C,B)  # recursive call
-
-
-
 ####################_______________________##### O L D
     def vizualizeSubset(self, subset):
         if subset:
             self.subset = subset
             #draw dots on the canvas
-            self.calcRatesSubset(subset)
+            calcRatesSubset(subset)
             self.graphROC.addCurve("dots", self.scolor, self.scolor, 6, style = QwtPlotCurve.NoCurve,\
                                    symbol = QwtSymbol.Ellipse, xData =self.subset.FPR, yData = self.subset.TPR)
             self.graphROC.replot()

workflows/subgroup_discovery/SubgroupDiscovery/SDRule.py

@@ -26,8 +26,10 @@ class SDRule :
                 distribution[int(d.getclass())]+=1
             distribution = map (lambda d: d/len(self.examples), distribution)
             self.classDistribution = orange.Distribution(distribution)  # set distribution
-            self.TP = filter(lambda e: e.getclass()==self.targetClass, self.examples)   # True positives
-            self.FP = filter(lambda e: e.getclass()!=self.targetClass, self.examples)   # flase positives
+            self.TP = self.examples.filter({self.examples.domain.classVar : self.targetClass})
+            self.FP = self.examples.filter({self.examples.domain.classVar : self.targetClass}, negate=1)
+            # self.TP = filter(lambda e: e.getclass()==self.targetClass, self.examples)   # True positives
+            # self.FP = filter(lambda e: e.getclass()!=self.targetClass, self.examples)   # flase positives
             TPlen = len(self.TP) * 1.0
             self.quality = TPlen / (len(self.FP) + self.g)   # set rule quality: generalization quocient
             self.support = 1.0* len(self.examples)/len(self.data)        # set rule support

workflows/subgroup_discovery/SubgroupDiscovery/SD_learner_classifier.py

@@ -277,10 +277,10 @@ class SD_Classifier(orange.Classifier):
 #___________________________________________________________________________________
 if __name__=="__main__":
 
-    filename = "..\\..\\doc\\datasets\\lenses.tab"
-    if 'linux' in sys.platform:
-        filename= "/usr/doc/orange/datasets/lenses.tab"
-    data = orange.ExampleTable(filename)
+    # filename = "..\\..\\doc\\datasets\\lenses.tab"
+    # if 'linux' in sys.platform:
+    #     filename= "/usr/doc/orange/datasets/lenses.tab"
+    data = orange.ExampleTable('lenses')
 
 
     learner2 = SD_learner(algorithm = "Apriori-SD", minSupport = 0.1, minConfidence= 0.6)
@@ -300,6 +300,15 @@ if __name__=="__main__":
         print d.getclass(), classifier2(d, orange.GetValue), classifier3(d, orange.GetValue), classifier4(d, orange.GetValue)
 
 
+    import cPickle
+    one= classifier2.rulesClass[0].rules.rules[0]
+    
+    for obj in dir(one):
+        try:
+            cPickle.dump(getattr(one, obj), open('foo.pkl','w'))
+            print obj, 'ok'
+        except Exception, e:
+            print obj, str(e)
 
 
     print "\n\n---> PMML model <---"

workflows/subgroup_discovery/SubgroupDiscovery/calcHull.py

+def calcRates(subgroups):
+        subgroups.TPR = []
+        subgroups.FPR = []
+        P = len(subgroups.targetClassRule.TP) * 1.0  # number of all positive examples as a float
+        N = len(subgroups.targetClassRule.FP) * 1.0  # number of all negative examples as a float
+        for rule in subgroups.rules:
+            subgroups.TPR.append( len(rule.TP) / P )  # true positive rate for this rule
+            subgroups.FPR.append( len(rule.FP) / N )  # false positive example for this rule
+
+      #  subgroups.TPR = [0.44, 0.34,   0.33,   0.49,   0.43,   0.49,   0.66,   0.60,   0.61,   0.78,   0.75,   0.77,   0.84,   0.82,   0.82]
+      #  subgroups.FPR = [0.01, 0.00,   0.00,   0.02,   0.00,   0.02,   0.10,   0.07,   0.07,   0.21,   0.16,   0.19,   0.31,   0.29,   0.27]
+
+        len(subgroups.TPR)
+
+        # calculate convex hull ,important: stick this 5 linet together
+        subgroups.hullTPR = [0]
+        subgroups.hullFPR = [0]
+        calcHull(subgroups, subgroups.TPR[:], subgroups.FPR[:] , A=(0,0), B=(1,1))
+        subgroups.hullTPR.append(1)
+        subgroups.hullFPR.append(1)
+
+def calcRatesSubset(subgroups):
+    subgroups.TPR = []
+    subgroups.FPR = []
+    P = len(subgroups.targetClassRule.TP) * 1.0  # number of all positive examples as a float
+    N = len(subgroups.targetClassRule.FP) * 1.0  # number of all negative examples as a float
+    for rule in subgroups.rules:
+        TPr = len(rule.TP) / P
+        FPr = len(rule.FP) / N
+        subgroups.TPR.append( TPr )  # true positive rate for this rule
+        subgroups.FPR.append( FPr )  # false positive example for this rule
+        #self.graphROC.tooltipData(FPr, TPr, rule)
+
+def calcHull(subgroups, Y, X, A, B):
+        #inicialization
+        C = (-1,-1)    # best new point point
+        y = -1         # best distance
+        index = -1
+        # calculate best new point
+        if (B[0]-A[0])==0:
+            #self.edtRules.appendPlainText("vertical line!!!")
+            pass
+        else:
+            k = (B[1]-A[1]) / (B[0]-A[0])  # coefficient of the line between A and B
+            for i in range(len(Y)):        # check every point
+                yn = Y[i] -( k * ( X[i] - A[0] ) + A[1])   # vertical distance between point i and line AB
+                if yn>0 and yn > y:        # if new distance is the greatest so far
+                    C = (X[i], Y[i])       # the new point is the best so far
+                    y = yn
+                    index = i
+
+        # if new point on the hull was found
+        if C != (-1,-1):
+            # recursivey call this function on the LEFT side of the point
+            del X[index]
+            del Y[index]
+            Xl =[]
+            Yl =[]
+            Xu =[]
+            Yu =[]
+            for i in range(len(X)):
+                if X[i]>=A[0] and X[i]<=C[0] and Y[i]>A[1]:
+                    Xl.append(X[i])
+                    Yl.append(Y[i])
+                elif X[i]>=C[0] and X[i]<=B[0] and Y[i]>C[1]:
+                    Xu.append(X[i])
+                    Yu.append(Y[i])
+
+            calcHull(subgroups, Yl, Xl, A,C)  # recursive call
+            # save the new point
+            subgroups.hullTPR.append(C[1])
+            subgroups.hullFPR.append(C[0])
+            # recursivey call this function on the RIGHT side of the point
+            calcHull(subgroups, Yu, Xu, C,B)  # recursive call

workflows/subgroup_discovery/library.py

@@ -33,19 +33,24 @@ class SubgroupDiscovery:
     }
 
 def build_subgroups(input_dict):
-    return {'rules' : None}
+    return {'rules' : None, 'classifier' : None}
 
 def build_subgroups_finished(postdata, input_dict, output_dict):
     data = input_dict['data']
     widget_id = postdata['widget_id'][0]
     alg = postdata['algorithm'+widget_id][0]
+    classValue = str(postdata['class'+widget_id][0])
     params = {'name' : alg, 'algorithm' : alg}
     for param in SubgroupDiscovery.algorithms[alg]:
         value = postdata[param+widget_id][0]
         if value != '':
             params[param] = SubgroupDiscovery.parameter_types[param](value)
-    rules = SD_learner(**params)
-    return {'rules' : rules}
+    learner = SD_learner(**params)
+    classifier = learner(data)
+    return {'rules' : classifier.getRules(classValue), 'classifier' : learner}
+
+def subgroup_bar_visualization(input_dict):
+    return {'rules' : None}
 
-def subgroup_visualization(input_dict):
-    return input_dict
+def subgroup_roc_visualization(input_dict):
+    return {'rules' : []}
\ No newline at end of file

workflows/subgroup_discovery/visualization.py

@@ -4,12 +4,43 @@ Subgroup discovery visualization views.
 @author: Anze Vavpetic <anze.vavpetic@ijs.si>
 '''
 from django.shortcuts import render
+import json
+from SubgroupDiscovery.calcHull import calcRates
 
-def subgroup_visualization(request, input_dict, output_dict, widget):
+def subgroup_bar_visualization(request, input_dict, output_dict, widget):
     '''
-    Subgroup visualizations.
+    Subgroup bar visualization.
         
-    @author: Anze Vavpeltic, 2012
+    @author: Anze Vavpetic, 2012
     '''
+    sd_rules = input_dict['rules']
+    rules = sd_rules.rules
+    P, N = float(len(sd_rules.targetClassRule.TP)), float(len(sd_rules.targetClassRule.FP))
+    fpr = [-len(rule.FP)/N for rule in rules]
+    tpr = [len(rule.TP)/P for rule in rules]
+    subgroups = [rule.ruleToString() for rule in rules]
+    return render(request, 'visualizations/subgroup_bar_visualization.html', {
+        'widget' : widget,
+        'model_name' : sd_rules.algorithmName,
+        'fpr' : json.dumps(fpr),
+        'tpr' : json.dumps(tpr),
+        'subgroups' : json.dumps(subgroups)
+        })
 
-    return render(request, 'visualizations/subgroup_visualization.html', {})
\ No newline at end of file
+def subgroup_roc_visualization(request, input_dict, output_dict, widget):
+    '''
+    Subgroup roc visualization.
+        
+    @author: Anze Vavpetic, 2012
+    '''
+    roc_data = []
+    for i, sd_rules in enumerate(input_dict['rules']):
+        P, N = float(len(sd_rules.targetClassRule.TP)), float(len(sd_rules.targetClassRule.FP))
+        calcRates(sd_rules)
+        rule_points = [{'x' : len(rule.FP)/N, 'y' : len(rule.TP)/P, 'name' : rule.ruleToString()} for rule in sd_rules.rules]
+        roc_data.append({'type': 'line', 'name' : sd_rules.algorithmName, 'data' : zip(sd_rules.hullFPR, sd_rules.hullTPR)})
+        #roc_data.append({'type': 'scatter', 'name' : sd_rules.algorithmName, 'data' : rule_points})
+    return render(request, 'visualizations/subgroup_roc_visualization.html', {
+        'widget' : widget,
+        'roc_data' : json.dumps(roc_data),
+        })
\ No newline at end of file

workflows/templates/interactions/build_subgroups.html

@@ -11,7 +11,7 @@
     {% endfor %}
     <input type="hidden" name="widget_id" value="{{widget.pk}}">
     <label for="class{{widget.pk}}">Class</label>
-    <select id="class{{widget.pk}}">
+    <select id="class{{widget.pk}}" name="class{{widget.pk}}">
     {% for class in classValues %}
         <option value="{{class}}">{{class}}</option>
     {% endfor %}

workflows/templates/visualizations/ds_charts.html

@@ -23,7 +23,7 @@
 		<script type="text/javascript">
 		$(function () {
 		
-			// Pretty radio buttons.
+			// Pretty tab buttons.
 			$("#weight_charts_tabs").tabs({
 				collapsible: true
 			});
@@ -36,14 +36,7 @@
 			$(document).ready(function(){ 
 				plot();
 			});
-		
-			// Handles radio button selection events.
-			$("form input[class=target_att]").change(function () {
-				var target_att = $("form input[class=target_att]:checked").val();
-				plot(target_att);
-			});
 
-		
 			// Plots for the selected attribute.
 			function plot() {
 				

workflows/templates/visualizations/subgroup_bar_visualization.html

+<div id="widgetvisualization-{{widget.pk}}" rel="{{widget.pk}}" class="widgetvisualizationdialog" title="{{widget.name}} visualization" width="700px" height="670px">
+    <div style="width:620px; margin: 0 auto;">
+        <form>
+        <div id="bar_chart{{widget.pk}}" style="margin-bottom: 10px;">
+        </div>
+        <input type="hidden" name="widget_id" value="{{widget.pk}}"/>
+        </form>
+        <script type="text/javascript">
+        $(function () {
+            $(document).ready(function(){ 
+                plot();
+            });
+            // Plots for the selected attribute.
+            function plot() {
+                // Weights barchart
+                new Highcharts.Chart({
+                    chart: {
+                        renderTo: 'bar_chart{{widget.pk}}',
+                        type: 'bar'
+                    },
+                    title: {
+                        text: 'Subgroup BAR visualization'
+                    },
+                    subtitle: {
+                        text: 'Model: {{ model_name }}'
+                    },
+                    xAxis: [{
+                        categories: {{subgroups|safe}},
+                        reversed: false
+                    }],
+                    yAxis: {
+                        title: {
+                            text: null
+                        },
+                        labels: {
+                            formatter: function(){
+                                return Math.abs(this.value);
+                            }
+                        },
+                        min: -1.0,
+                        max: 1.0
+                    },
+                    plotOptions: {
+                        series: {
+                            stacking: 'normal'
+                        }
+                    },
+                    tooltip: {
+                        formatter: function() {
+                            return ''+
+                                this.series.name +': '+ Math.abs(this.y.toFixed(3));
+                        }
+                    },
+                    series: [{
+                        name: 'False positive rate',
+                        data: {{fpr|safe}}
+                    }, {
+                        name: 'True positive rate',
+                        data: {{tpr|safe}}
+                    }],
+                    credits: {
+                        enabled: false
+                    }
+                });
+            }
+        });
+        </script>
+    </div>
+</div>
\ No newline at end of file

workflows/templates/visualizations/subgroup_roc_visualization.html

+<div id="widgetvisualization-{{widget.pk}}" rel="{{widget.pk}}" class="widgetvisualizationdialog" title="{{widget.name}} visualization" width="700px" height="670px">
+    <div style="width:620px; margin: 0 auto;">
+        <form>
+        <div id="roc_curve{{widget.pk}}" style="margin-bottom: 10px;">
+        </div>
+        <input type="hidden" name="widget_id" value="{{widget.pk}}"/>
+        </form>
+        <script type="text/javascript">
+        $(function () {
+            $(document).ready(function(){ 
+                plot();
+            });
+        
+            // Plots for the selected attribute.
+            function plot() {
+                // Weights barchart
+                new Highcharts.Chart({
+                    chart: {
+                        renderTo: 'roc_curve{{widget.pk}}',
+                    },
+                    title: {
+                        text: 'Subgroup ROC visualization'
+                    },
+                    xAxis: [{
+                        title: {
+                            text: 'FP rate (1-specificity)'
+                        },
+                        min: -0.01,
+                        max: 1.0
+                    }],
+                    yAxis: {
+                        title: {
+                            text: 'TP rate (sensitivity)'
+                        },
+                        min: 0.0,
+                        max: 1.0
+                    },
+                    series: {{roc_data|safe}},
+                    credits: {
+                        enabled: false
+                    }
+                });
+            }
+        });
+        </script>
+    </div>
+</div>
\ No newline at end of file

workflows/visualization_views.py

@@ -2,6 +2,7 @@ from django.shortcuts import render
 from django.http import Http404, HttpResponse
 import nlp
 from decision_support.visualization import *
+from subgroup_discovery.visualization import *
 
 def odt_to_tab(request,input_dict,output_dict,widget):
     import Orange