src/experiments/decision_tree/decision_tree.py

@@ -1,16 +1,15 @@
-from enum import Enum
 from sklearn import tree
 from sklearn import metrics
 from sklearn import preprocessing
-import sklearn
+from sklearn.ensemble import RandomForestClassifier
-from matplotlib import pyplot as plt
+# from ...helpers.treenum import Tree
-import pandas as pd
+from enum import Enum
-import numpy as np
-import random
 import csv
+import random
+from matplotlib import pyplot as plt
+import numpy as np
 
 SIFT_PATH = "..\\algorithms\\data\\sift.csv"
-# SIFT_PATH = "C:\\Users\\Tom\\Desktop\\Files\\Repositories\\EV5_Beeldherk_Bomen\datacsv\\result-2023-10-13T14.46.23.csv"
 
 class Tree(Enum):
     ACCASIA = 0
@@ -25,27 +24,6 @@ class Tree(Enum):
 # [[tree1_data],[tree2_data]]
 # [tree1_label, tree2_label]
 
-def roc_auc_score_multiclass(actual_class, pred_class, average = "macro"):
-    
-    #creating a set of all the unique classes using the actual class list
-    unique_class = set(actual_class)
-    roc_auc_dict = {}
-    for per_class in unique_class:
-        
-        #creating a list of all the classes except the current class 
-        other_class = [x for x in unique_class if x != per_class]
-
-        #marking the current class as 1 and all other classes as 0
-        new_actual_class = [0 if x in other_class else 1 for x in actual_class]
-        new_pred_class = [0 if x in other_class else 1 for x in pred_class]
-
-        #using the sklearn metrics method to calculate the roc_auc_score
-        roc_auc = metrics.roc_auc_score(new_actual_class, new_pred_class, average = average)
-        roc_auc_dict[per_class] = roc_auc
-
-    return roc_auc_dict
-
-
 labels = []
 i = 0
 done = False
@@ -66,65 +44,30 @@ with open(SIFT_PATH, 'r') as file:
     normalized = preprocessing.normalize(data, axis=0, norm='max')
     norm = list(normalized.tolist())
 
-steps = np.linspace(2, 20, 10, dtype=np.int64)
+actual = []
-accuracy = []
+predicted = []
-precision = []
+for i in range(75):
-recall = []
+    test_index = random.randint(1, 101)
-roc = []
+    temp_data = data.pop(test_index)
+    temp_label = labels.pop(test_index)
 
-for step in steps:
+    # dec_tree = tree.DecisionTreeClassifier(
-    actual = []
+    #     criterion='entropy', 
-    predicted = []
+    #     splitter='best')
+    dec_tree = RandomForestClassifier(max_depth=None)
+    dec_tree = dec_tree.fit(data, labels)
+    result = dec_tree.predict([matrix[test_index][1:]])
 
-    for i in range(100):
+    # normalized_list.append(temp_data)
-        test_index = random.randint(1, 101)
+    data.append(temp_data)
-        temp_data = data.pop(test_index)
+    labels.append(temp_label)
-        temp_label = labels.pop(test_index)
-        del dec_tree
 
-        dec_tree = tree.DecisionTreeClassifier(
+    actual.append(temp_label)
-            min_samples_leaf=2,
+    predicted.append(result[0])
-            max_depth=None,
-            random_state=False,
-            criterion='gini', 
-            splitter='best')
-        dec_tree = dec_tree.fit(data, labels)
-        result = dec_tree.predict([matrix[test_index][1:]])
 
-        # normalized_list.append(temp_data)
-        data.append(temp_data)
-        labels.append(temp_label)
-
-        actual.append(temp_label)
-        predicted.append(result[0])
-
-    accuracy.append(metrics.accuracy_score(actual, predicted))
-    precision.append(metrics.precision_score(actual, predicted, average='macro'))
-    recall.append(metrics.recall_score(actual, predicted, average='macro'))
-    roc.append(roc_auc_score_multiclass(actual, predicted))
-
-    print(step)
-
-# Scores
-# https://www.evidentlyai.com/classification-metrics/multi-class-metrics
-plt.plot(accuracy)
-plt.title("Accuracy")
-plt.show()
-plt.plot(precision)
-plt.title("Precision")
-plt.show()
-plt.plot(recall)
-plt.title("Recall")
-plt.show()
-df = pd.DataFrame(roc)
-plt.figure()
-for i in range(7):
-    plt.plot(df[i], label=Tree(i).name)
-plt.legend()
-plt.show()
-
-# Confusion matrix
 c_matrix = metrics.confusion_matrix(actual, predicted)
 cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix=c_matrix)
 cm_display.plot()
 plt.show(block=False)
+# print("Testdata: \t" + Tree[matrix[test_index][0].upper()].name)
+# print("Predicted: \t" + Tree(result[0]).name)