import pandas as pd
import sys
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(
    'test.csv', header=0,
     usecols=['total_vaccinations', 'daily_vaccinations', 'people_fully_vaccinated']).dropna()

X = alldata['total_vaccinations'].to_numpy().ravel().reshape(-1, 1)
y = alldata['daily_vaccinations'].to_numpy().ravel().reshape(-1, 1)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
lin_reg = reg.fit(X_train, y_train)
score = lin_reg.score(X_test, y_test)
prediction = lin_reg.predict(X_test)

build_no = sys.argv[1] if len(sys.argv) > 1 else 0
rmse = rmse(y_test, prediction, squared=False)
data = {"rmse": [round(rmse, 2)], "build": [build_no]}
df = pd.DataFrame(data=data)

with open("evaluation.csv", "a") as f:
    df.to_csv(f, header=f.tell() == 0, index=False)

print("RMSE:", rmse)
print("Score:", score)