.2 procent

src/experiments/knn/knn.py

@@ -3,7 +3,7 @@ import numpy as np
 import matplotlib.pyplot as plt
 import seaborn as sns
 import csv
-from sklearn.preprocessing import MinMaxScaler
+from sklearn.preprocessing import MinMaxScaler, StandardScaler, RobustScaler, MaxAbsScaler
 from enum import Enum
 import random
 from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, matthews_corrcoef
@@ -19,7 +19,7 @@ class Tree(Enum):
     PLATAAN = 7
 
 # Open file
-file = open('./out/result-2023-10-10T15.08.36.csv', "r")
+file = open('dataset\\csv\\result-2023-10-14T16.13.30.csv', "r")
 data = list(csv.reader(file, delimiter=","))
 file.close()
 
@@ -32,6 +32,7 @@ tags_int = []
 
 for row in data:
     tree = row.pop(0)
+    row.pop(1) # TODO: Doe dit niet
     id = Tree[tree.upper()]
     
     # print("Tree name =", tree, " id =", id.value)
@@ -52,14 +53,16 @@ for idx, col in enumerate(data[0]):
     column = np.array(column).reshape(-1, 1)
     
     # Perform Min - Max scaling
-    scaler = MinMaxScaler()
+    # scaler = MinMaxScaler()
+    scaler = MaxAbsScaler()
+
     column = scaler.fit_transform(column)
     
     # Reshape it back cus scaler is dumb af
     column = np.array(column).reshape(len(column))
     
     # DEBUG Print resulting column
-    # print("NORM", header[idx + 1], "\n", column)
+    print("NORM", header[idx + 1], "\n", column)
     
     # Replace original data array
     data[:, idx] = column