Machine_learning_2023/decisionTree/prepare.py

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import metrics
import joblib

pima = pd.read_csv("data.csv", header=1, delimiter=';')

feature_cols = ['Size', 'Color', 'Sound', 'Sharp','Smell', 'Length','Temperature', 'Weight']
X = pima[feature_cols]
y = pima.ToRemove

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)
clf = DecisionTreeClassifier()
clf = clf.fit(X_train.values, y_train)

joblib.dump(clf, 'decision_tree_model.pkl')

y_pred = clf.predict(X_test)

print("Accuracy:",metrics.accuracy_score(y_test, y_pred))