starting DecisionTreeAG

mainproject/SFAnalytics/generatedgrah.gv

@@ -0,0 +1,37 @@
+digraph Tree {
+node [shape=box, style="filled, rounded", color="black", fontname=helvetica] ;
+edge [fontname=helvetica] ;
+0 [label=<petal length (cm) &le; 2.45<br/>gini = 0.6667<br/>samples = 150<br/>value = [50, 50, 50]<br/>class = setosa>, fillcolor="#e5813900"] ;
+1 [label=<gini = 0.0<br/>samples = 50<br/>value = [50, 0, 0]<br/>class = setosa>, fillcolor="#e58139ff"] ;
+0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
+2 [label=<petal width (cm) &le; 1.75<br/>gini = 0.5<br/>samples = 100<br/>value = [0, 50, 50]<br/>class = versicolor>, fillcolor="#39e58100"] ;
+0 -> 2 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
+3 [label=<petal length (cm) &le; 4.95<br/>gini = 0.168<br/>samples = 54<br/>value = [0, 49, 5]<br/>class = versicolor>, fillcolor="#39e581e5"] ;
+2 -> 3 ;
+4 [label=<petal width (cm) &le; 1.65<br/>gini = 0.0408<br/>samples = 48<br/>value = [0, 47, 1]<br/>class = versicolor>, fillcolor="#39e581fa"] ;
+3 -> 4 ;
+5 [label=<gini = 0.0<br/>samples = 47<br/>value = [0, 47, 0]<br/>class = versicolor>, fillcolor="#39e581ff"] ;
+4 -> 5 ;
+6 [label=<gini = 0.0<br/>samples = 1<br/>value = [0, 0, 1]<br/>class = virginica>, fillcolor="#8139e5ff"] ;
+4 -> 6 ;
+7 [label=<petal width (cm) &le; 1.55<br/>gini = 0.4444<br/>samples = 6<br/>value = [0, 2, 4]<br/>class = virginica>, fillcolor="#8139e57f"] ;
+3 -> 7 ;
+8 [label=<gini = 0.0<br/>samples = 3<br/>value = [0, 0, 3]<br/>class = virginica>, fillcolor="#8139e5ff"] ;
+7 -> 8 ;
+9 [label=<petal length (cm) &le; 5.45<br/>gini = 0.4444<br/>samples = 3<br/>value = [0, 2, 1]<br/>class = versicolor>, fillcolor="#39e5817f"] ;
+7 -> 9 ;
+10 [label=<gini = 0.0<br/>samples = 2<br/>value = [0, 2, 0]<br/>class = versicolor>, fillcolor="#39e581ff"] ;
+9 -> 10 ;
+11 [label=<gini = 0.0<br/>samples = 1<br/>value = [0, 0, 1]<br/>class = virginica>, fillcolor="#8139e5ff"] ;
+9 -> 11 ;
+12 [label=<petal length (cm) &le; 4.85<br/>gini = 0.0425<br/>samples = 46<br/>value = [0, 1, 45]<br/>class = virginica>, fillcolor="#8139e5f9"] ;
+2 -> 12 ;
+13 [label=<sepal length (cm) &le; 5.95<br/>gini = 0.4444<br/>samples = 3<br/>value = [0, 1, 2]<br/>class = virginica>, fillcolor="#8139e57f"] ;
+12 -> 13 ;
+14 [label=<gini = 0.0<br/>samples = 1<br/>value = [0, 1, 0]<br/>class = versicolor>, fillcolor="#39e581ff"] ;
+13 -> 14 ;
+15 [label=<gini = 0.0<br/>samples = 2<br/>value = [0, 0, 2]<br/>class = virginica>, fillcolor="#8139e5ff"] ;
+13 -> 15 ;
+16 [label=<gini = 0.0<br/>samples = 43<br/>value = [0, 0, 43]<br/>class = virginica>, fillcolor="#8139e5ff"] ;
+12 -> 16 ;
+}

mainproject/SFAnalytics/migrations/0007_auto_20170829_1215.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.11 on 2017-08-29 15:15
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('SFAnalytics', '0006_auto_20170613_1934'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='DllToEntry',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('id_dll', models.IntegerField(default=0)),
+                ('id_entry', models.IntegerField(default=0)),
+            ],
+        ),
+        migrations.CreateModel(
+            name='OpcodeToEntry',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('id_opcode', models.IntegerField(default=0)),
+                ('id_entry', models.IntegerField(default=0)),
+            ],
+        ),
+        migrations.CreateModel(
+            name='StringToEntry',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('id_string', models.IntegerField(default=0)),
+                ('id_entry', models.IntegerField(default=0)),
+            ],
+        ),
+        migrations.AlterField(
+            model_name='entryfile',
+            name='id',
+            field=models.IntegerField(primary_key=True, serialize=False),
+        ),
+    ]

mainproject/SFAnalytics/test_mining.py

@@ -0,0 +1,26 @@
+from tools import *
+from sklearn.datasets import load_iris
+from sklearn import tree
+import sys
+import numpy as np
+import graphviz
+
+def main():
+    #The secound arg is the outputfile
+    if len(sys.argv) == 2:
+        iris = load_iris()
+        decisionTree = tree.DecisionTreeClassifier()
+        decisionTree = decisionTree.fit(iris.data, iris.target)
+        sample = np.reshape(iris.data[50], (1, -1))
+        dot_data = tree.export_graphviz(decisionTree, out_file=None, feature_names=iris.feature_names, class_names=iris.target_names, filled=True, rounded=True, special_characters=True)
+        graph = graphviz.Source(dot_data)
+        graph.format = 'png'
+        graph.render(sys.argv[1])
+        print('\nGraph generated.\n')
+        a = np.array([[2, 3, 4],[5, 6, 7],[8, 9, 10]])
+        b = np.array([[11, 12, 13]])
+        #stacking arrays
+        np.vstack((a, b))
+
+if __name__ == '__main__':
+    main()