33 lines
1.1 KiB
Python
33 lines
1.1 KiB
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
|
|
|
|
FILE_PATH = "boston.csv"
|
|
REQUIRED_COLUMNS = ['CRIM', 'DIS', 'TAX']
|
|
TARGET_COLUMN = 'RAD'
|
|
|
|
|
|
def print_classifier_info(feature_importance):
|
|
feature_names = REQUIRED_COLUMNS
|
|
embarked_score = feature_importance[-3:].sum()
|
|
scores = np.append(feature_importance[:2], embarked_score)
|
|
scores = map(lambda score: round(score, 2), scores)
|
|
print(dict(zip(feature_names, scores)))
|
|
|
|
|
|
if __name__ == '__main__':
|
|
data = pd.read_csv(FILE_PATH)
|
|
|
|
X = data[REQUIRED_COLUMNS]
|
|
y = data[TARGET_COLUMN]
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
|
|
|
classifier_tree = DecisionTreeClassifier(random_state=42)
|
|
classifier_tree.fit(X_train, y_train)
|
|
|
|
print_classifier_info(classifier_tree.feature_importances_)
|
|
print("Оценка качества (задача классификации) - ", classifier_tree.score(X_test, y_test)) |