def predict(x, y):
    ex = sum(x) / len(x)
    ey = sum(y) / len(y)
    numerator = sum([(xi - ex) * (yi - ey) for xi, yi in zip(x, y)])
    denominator = sum([(xi - ex)**2 for xi in x])
    slope = numerator / denominator
    intercept = ey - (slope * ex)
    predict = slope * 10 + intercept
    return predict

if __name__ == '__main__':
    feature_1 = "Physics Scores  15  12  8   8   7   7   7   6   5   3"
    feature_2 = "History Scores  10  25  17  11  13  17  20  13  9   15"
    feature_1 = [int(x) for x in feature_1.split() if x.isnumeric()]
    feature_2 = [int(x) for x in feature_2.split() if x.isnumeric()]
    result = predict(feature_1, feature_2)
    print(f'{result:.3f}')

class LR:
    def __init__(self):
        self.slope = None
        self.intercept = None
        
    def fit(self, x, y):
        x_avg = sum(x)/x.__len__()
        y_avg = sum(y)/y.__len__()
        numerator = sum([(a - x_avg)*(b - y_avg) for a,b in zip(x,y)])
        denominator = sum([(a - x_avg)**2 for a in x])
        self.slope = round(numerator/denominator, 3)
        self.intercept = y_avg - self.slope*x_avg
    def predict(self, x):
        if self.slope and self.intercept:
            return self.slope*x + self.intercept
        else:
            raise ModuleNotFoundError('predict is not found, call fit() before predict()')
        

if __name__ == '__main__':
    if __name__ == '__main__':
        feature_1 = "Physics Scores  15  12  8   8   7   7   7   6   5   3"
        feature_2 = "History Scores  10  25  17  11  13  17  20  13  9   15"
        feature_1 = [int(x) for x in input().split() if x.isnumeric()]
        feature_2 = [int(x) for x in input().split() if x.isnumeric()]
        model = LR()
        model.fit(feature_1, feature_2)
        out = str(model.predict(10))
        out = out.split('.')
        print(float(out[0] + '.' + out[1][0]))

physics = [15 , 12 , 8 , 8 , 7 , 7 , 7 , 6 , 5 , 3]
history = [10 , 25 , 17 , 11 , 13 , 17 , 20 , 13 , 9 , 15]
xy = sum([x*y for x,y in zip(physics , history)])
xmean = sum(physics) / len(physics)
ymean = sum(history) / len(history)
x_2 = sum([x*x for x in physics])
numerator = xy - ymean*(sum(physics))
denominator = x_2 - xmean*(sum(physics))
slope = numerator/denominator
intercept = ymean - slope*xmean

prediction = slope*10 + intercept

print("%.2f" %prediction)

import numpy as np

P = np.array([15, 12, 8, 8, 7, 7, 7, 6, 5, 3])
H = np.array([10, 25, 17, 11, 13, 17, 20, 13, 9, 15])

fit = np.polyfit(P, H, deg=1)
a = fit[0]
b = fit[1]

pred = a * 10 + b
print(round(pred, 1))

x <- c(15, 12, 8, 8, 7, 7, 7, 6, 5, 3)
y <- c(10, 25, 17, 11, 13, 17, 20, 13, 9, 15) 
linearMod <- lm(y ~ x)
pred <- as.vector(linearMod$coefficients)[1] + as.vector(linearMod$coefficients)[2]*10
round(pred,1)