irisAll.py (2802B)
1 import numpy as np 2 import pandas as pd 3 import decision_tree 4 from sklearn.model_selection import KFold 5 from sklearn.metrics import accuracy_score 6 from sklearn.datasets import load_iris 7 8 iris = load_iris() 9 df = pd.DataFrame(iris.data, columns=iris.feature_names) 10 y = iris.target 11 X = df.to_numpy() 12 13 # Define hyperparameters 14 depths = [1,2,3,4,5] 15 criteria = ["gini", "twoing", "information gain"] 16 lcs = [1,2,3,4] 17 n_splits = 5 18 n_trials = 10 19 seed = 71 20 21 # Store results 22 accuracies = {lc: {depth: [] for depth in depths} for lc in lcs} 23 treeSizes = {lc: {depth: [] for depth in depths} for lc in lcs} 24 foldSizes = [] 25 foldAccuracies = [] 26 27 # Store results 28 results = {criterion: {lc: {depth: [] for depth in depths} for lc in lcs} for criterion in criteria} 29 tree_sizes = {criterion: {lc: {depth: [] for depth in depths} for lc in lcs} for criterion in criteria} 30 31 for trial in range(n_trials): 32 kf = KFold(n_splits=n_splits, shuffle=True, random_state=(trial + seed)) 33 34 for criterion in criteria: 35 for lc in lcs: 36 for depth in depths: 37 fold_accuracies = [] 38 fold_sizes = [] 39 40 for train_index, test_index in kf.split(X): 41 X_train, X_test = X[train_index], X[test_index] 42 y_train, y_test = y[train_index], y[test_index] 43 44 clf = decision_tree.ELCClassifier(depth, lc, 100, criterion) 45 clf.fit(X_train.ravel(), y_train.shape[0], y_train, int(X_train.size / y_train.shape[0])) 46 preds = clf.predict(X_test.ravel(), y_test.shape[0], int(X_test.size / y_test.shape[0])) 47 48 fold_accuracies.append(100 * accuracy_score(y_pred=preds, y_true=y_test)) 49 fold_sizes.append(clf.getSplits() + 1) # leaves not splits 50 51 results[criterion][lc][depth].append(np.mean(fold_accuracies)) 52 tree_sizes[criterion][lc][depth].append(np.mean(fold_sizes)) 53 54 with open("resultsIris.txt", "w") as f: 55 f.write("Results:\n") 56 for criterion in criteria: 57 f.write("\n") 58 f.write(f"{criterion}:\n") 59 for lc in lcs: 60 for depth in depths: 61 avg_accuracy = np.mean(results[criterion][lc][depth]) 62 std_accuracy = np.std(results[criterion][lc][depth]) 63 avg_size = np.mean(tree_sizes[criterion][lc][depth]) 64 std_size = np.std(tree_sizes[criterion][lc][depth]) 65 66 f.write(f"LCs: {lc}, Depth: {depth} Avg Accuracy: {avg_accuracy:.1f} (Std: {std_accuracy:.1f})") 67 f.write(f", Avg # of Leaves: {avg_size:.1f} (Std: {std_size:.1f})\n")