ML - Lab 2 - xtest, ytest, xtrain, ytrain in tree classificator

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets, tree
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score

# Load an iris dataset
iris = datasets.load_iris()
data = iris.data[:, [0, 1]]         # Select only the 2 first columns (0, 1)
# print("Dataset: ")                  # Length = 150
# print(data)
# print()
target = iris.target                # Like the class column
# print("Target: ")
# print(target)
# print()
target[100:125] = 0
target[125:150] = 1
# print("Target: ")
# print(target)
# print()


# Split into training and testing data
# Select 120/150 entries for training
xtrain = np.concatenate((data[0:40], data[50:90], data[100:140]))
ytrain = np.concatenate((target[0:40], target[50:90], target[100:140]))
# Select 30/150 entries for testing
xtest = np.concatenate((data[40:50], data[90:100], data[140:150]))
ytest = np.concatenate((target[40:50], target[90:100], target[140:150]))
print(str(len(xtrain)) + " training entries, " + str(len(xtest)) + " testing entries")

# Classifier - Prediction
clf = tree.DecisionTreeClassifier(min_samples_split=20)
clf = clf.fit(xtrain, ytrain)
pred = clf.predict(xtest)
# Plot
fig = plt.figure(figsize=(10, 9))
tree.plot_tree(clf, class_names=['No', 'Yes'], filled=True)
plt.show()
# Metrics
print("Confusion Matrix = ")
print(confusion_matrix(ytest, pred))
print("Accuracy = " + str(accuracy_score(ytest, pred)))
print("Precision = " + str(precision_score(ytest, pred, pos_label=1)))
print("Recall = " + str(recall_score(ytest, pred, pos_label=1)))
print("F1 score = " + str(f1_score(ytest, pred, pos_label=1)))