import pandas as pd

df=pd.read_csv('data/review.csv')
review_data= df.drop(['이름', '성별'], axis=1)


x_train=df[['나이', '학점', '키']]
y_train = df['토익점수']

from sklearn.linear_model import LinearRegression

lr = LinearRegression().fit(x_train, y_train)

print('train set accuracy', lr.score(x_train, y_train))

df_test = pd.read_csv('data/review_test.csv')

x_test = df_test[['나이', '학점', '키']]
prediction = lr.predict(x_test)
prediction

lr.predict([(24,3.7,170)])

comparison = pd.DataFrame(y_train)
y_test = lr.predict(x_train)

comparison['나의 예측']=y_test
comparison