Главная

Оцените сэкономленные средства на свежих данных. Обучите модель и проверьте её качество.

# импортируем необходимые библиотеки и объявляем константы
import pandas as pd
from sklearn.svm import SVC
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
scaler = StandardScaler()

RANDOM_STATE = 77

data = pd.read_csv('orders_seafood.csv')

X = data.drop(columns=['target', 'client_id'])
y = data['target']

X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.25, random_state=RANDOM_STATE)

X_train_scalled = scaler.fit_transform(X_train)
X_test_scalled = scaler.transform(X_test)

# объявляем классификатор и обучаем модель

clf_poly = SVC(kernel = 'poly', degree = 6)
clf_poly.fit(X_train_scalled, y_train)

test_data = pd.read_csv('orders_seafood_test.csv')

test_x = test_data.drop(columns=['client_id', 'target'])
test_y = test_data['target']
test_data_scalled = scaler.transform(test_x)

y_pred_poly_test = clf_poly.predict(test_data_scalled)

r_poly = accuracy_score(test_y, y_pred_poly_test)
print(r_poly)