From f11a5a82e23d025090b725b5ddc81453fb2f6f70 Mon Sep 17 00:00:00 2001
From: Tom Selier <tbj.selier@gmail.com>
Date: Sat, 21 Oct 2023 20:38:07 +0200
Subject: [PATCH] the worky version

---
 .../decision_tree/decision_tree.py            | 15 +++---
 src/helpers/test/decision_tree.py             | 54 ++++++++++---------
 src/suite.py                                  |  6 ++-
 3 files changed, 42 insertions(+), 33 deletions(-)

diff --git a/src/experiments/decision_tree/decision_tree.py b/src/experiments/decision_tree/decision_tree.py
index fef2b00..398bed9 100644
--- a/src/experiments/decision_tree/decision_tree.py
+++ b/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='max')
+    normalized = preprocessing.normalize(data, axis=0, norm='')
     norm = list(normalized.tolist())
 
-steps = np.linspace(1e-4, 1, 20, dtype=np.float64)
+steps = np.linspace(1, 12, 4, dtype=np.int64)
 
 print("Step \t seconds/step")
 for step in steps:
@@ -78,11 +78,12 @@ 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,
diff --git a/src/helpers/test/decision_tree.py b/src/helpers/test/decision_tree.py
index 9cbd08d..4bede1d 100644
--- a/src/helpers/test/decision_tree.py
+++ b/src/helpers/test/decision_tree.py
@@ -1,15 +1,22 @@
 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 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)
 
 class Tree(Enum):
     ACCASIA = 0
@@ -52,19 +59,18 @@ class CVSuiteTestTree:
                 i += 1
         
         # normalize data
-        if self.scaler is not None:
-            norm = self.scaler.fit(data)
-            for row in norm:
-                print(len(row))
-        else:
-            raise EnvironmentError("No scaler found")
+        #TODO: Arne help
 
         # train model
-        self.train(norm, labels, output)
+        self.train(data, 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")
 
@@ -75,7 +81,7 @@ 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
 
@@ -110,18 +116,16 @@ class CVSuiteTestExtraTrees(CVSuiteTestTree):
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    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))
\ No newline at end of file
+    
+    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)
\ No newline at end of file
diff --git a/src/suite.py b/src/suite.py
index c6f0939..c2b2629 100644
--- a/src/suite.py
+++ b/src/suite.py
@@ -347,8 +347,12 @@ class CVSuite:
             print(C_WARN, "KNN Model not configured!")
 
         if self.test_dectree is not None:
-            print(self.test_dectree.predict(data))
+            result = 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!")