src/experiments/decision_tree/decision_tree.py

@@ -46,10 +46,10 @@ with open(PATH, 'r') as file:
         i += 1
 
     # Werkt niet met genormaliseerde data
-    normalized = preprocessing.normalize(data, axis=0, norm='')
+    normalized = preprocessing.normalize(data, axis=0, norm='max')
     norm = list(normalized.tolist())
 
-steps = np.linspace(1, 12, 4, dtype=np.int64)
+steps = np.linspace(1e-4, 1, 20, dtype=np.float64)
 
 print("Step \t seconds/step")
 for step in steps:
@@ -78,12 +78,11 @@ for step in steps:
             # model = ensemble.ExtraTreesClassifier(
             #     n_estimators=step # higher is better, but slower (def: 100)
             # )
-            model = neighbors.KNeighborsClassifier(
-                algorithm='auto',
-                leaf_size=2,
-                n_neighbors=step,
-            )
-
+            # model = neighbors.KNeighborsClassifier(
+            #     algorithm='auto',
+            #     leaf_size=2,
+            #     n_neighbors=step,
+            # )
             # model = ensemble.BaggingClassifier(
             #     n_estimators=5,
             #     max_samples=.5,

src/helpers/test/decision_tree.py

@@ -1,22 +1,15 @@
 from enum import Enum
+from sklearn.preprocessing import maxabs_scale, MaxAbsScaler
 from sklearn.ensemble import RandomForestClassifier
 from joblib import dump, load
 from sklearn import tree
-import numpy as np
 import csv
 import argparse
 import os
 
 parser = argparse.ArgumentParser(prog='DecisionTree CLI')
 parser.add_argument('-i', '--input', help='Input CSV file', required=True)
-parser.add_argument('-o', '--output', help='Output model folder', required=True)
-parser.add_argument(
-    '-m', 
-    '--model', 
-    help='Chosen model (\'dectree\', \'randforest\' or \'extratree\')', 
-    required=True
-    )
-parser.add_argument('-s', '--scaler', help='Scaler preprocesser', required=True)
+parser.add_argument('-o', '--output', help='Output model file', required=True)
 
 class Tree(Enum):
     ACCASIA = 0
@@ -59,18 +52,19 @@ class CVSuiteTestTree:
                 i += 1
         
         # normalize data
-        #TODO: Arne help
+        if self.scaler is not None:
+            norm = self.scaler.fit(data)
+            for row in norm:
+                print(len(row))
+        else:
+            raise EnvironmentError("No scaler found")
 
         # train model
-        self.train(data, labels, output)
+        self.train(norm, labels, output)
 
     def addScaler(self, path) -> None:
         self.scaler = load(path)
 
-        if self.scaler is None:
-            print("Scaler failed to load!")
-            exit()
-
     def train(self, data, labels, output) -> None:
         print("You called the parent class, doofus")
 
@@ -81,7 +75,7 @@ class CVSuiteTestTree:
 
     def predict(self, data) -> None | int:
         if self.model is not None:
-            return self.model.predict(data)
+            return self.model.predict([data])
         else:
             return None
 
@@ -116,16 +110,18 @@ class CVSuiteTestExtraTrees(CVSuiteTestTree):
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    
-    if args.model == 'dectree':
-        test = CVSuiteTestDecisionTree()
-    elif args.model == 'randforest':
-        test = CVSuiteTestRandomForest()
-    elif args.model == 'extratree':
-        test = CVSuiteTestExtraTrees()
-    else:
-        print("Model not found!")
-        exit()
-    
-    test.addScaler(args.scaler)
-    test.trainCSV(args.input, args.output)
+    test = CVSuiteTestRandomForest()
+    test.trainCSV(args.input, args.output)
+    test = CVSuiteTestDecisionTree(
+        "C:\\Users\\Tom\\Desktop\\Files\\Repositories\\EV5_Beeldherk_Bomen\\models\\randomforest.joblib"
+    )
+    path = "C:\\Users\\Tom\\Desktop\\Files\\Repositories\\EV5_Beeldherk_Bomen\\dataset\\csv\\result-2023-10-21T09.59.24.csv"
+    file = open(path, 'r')
+    reader = csv.reader(file, delimiter=',')
+    matrix = list(reader)
+    file.close()
+
+    data = [float(x) for x in matrix[2][2:]]
+    norm = maxabs_scale(data)
+
+    print(test.predict(norm))

src/suite.py

@@ -347,12 +347,8 @@ class CVSuite:
             print(C_WARN, "KNN Model not configured!")
 
         if self.test_dectree is not None:
-            result = self.test_dectree.predict(data)
+            print(self.test_dectree.predict(data))
             output.insert("end", "Decision Tree Result:\n")
-            output.insert("end", f"\t{Tree(result).name}\n")
-
-            print(C_DBUG, "Decision Tree Result:")
-            print("\t\t result: \t{}".format(result))
         else:
             print(C_WARN, "Decison Tree Model not configured!")