import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error as rmse

reg = LinearRegression()

alldata = pd.read_csv(
    'country_vaccinations.csv', header=0, skipinitialspace=True,
     usecols=['total_vaccinations', 'people_vaccinated', 'daily_vaccinations' ,'daily_vaccinations_per_million']).dropna()

X = alldata[[c for c in alldata.columns if c != 'daily_vaccinations']]
y = alldata['daily_vaccinations']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 6)
lin_reg = reg.fit(X_train, y_train)
score = lin_reg.score(X_test, y_test)
prediction = lin_reg.predict(X_test)
print("RMSE:", rmse(y_test, prediction, squared=False))
print("Score:", score)