IIS_2023_1/ilbekov_dmitriy_lab_3/lab3.py
2023-10-22 18:42:36 +04:00

27 lines
883 B
Python

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
import pandas as pd
import numpy as np
pd.options.mode.chained_assignment = None
path = "F1DriversDataset.csv"
required = ['Pole_Positions', 'Race_Wins', 'Podiums']
target = 'Championships'
data = pd.read_csv(path)
X = data[required]
y = data[target]
X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=0.1, random_state=42)
classifier_tree = DecisionTreeClassifier(random_state=42)
classifier_tree.fit(X_train, Y_train)
feature_names = required
embarked_score = classifier_tree.feature_importances_[-3:].sum()
scores = np.append(classifier_tree.feature_importances_[:2], embarked_score)
scores = map(lambda score: round(score, 2), scores)
print(dict(zip(feature_names, scores)))
print("Оценка качества: ", classifier_tree.score(X_test, Y_test))