import pandas as pd
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

data = pd.read_csv('/mnt/data/train_data.csv')


data['label'].value_counts().plot(kind='bar')
plt.show()


X = data.drop('label', axis=1)
y = data['label']


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)


dt_model = DecisionTreeClassifier()
dt_model.fit(X_train, y_train)


y_pred = dt_model.predict(X_test)


print("accuracy: ", accuracy_score(y_test, y_pred))