Machine learning keras fitting sine function

1.dataset

from random import random
import numpy as np


def f(x):
    a = -1
    b = 1
    c = 1
    return a * (x ** 2) + b * x + c

def g(x):
    k = 1
    b = 1
    return k * x + b

def h(x):
    return np.sin(x)


def get_data(num):

    cnt = (np.random.random(100) - 0.5) * 20
    cnt = np.sort(cnt)
    X = cnt
    Y = h(cnt)
    return X, Y


if __name__ == '__main__':
    X, Y = get_data(100)
    print(X)
    print(Y)

2.keras

from turtle import color
import matplotlib.pyplot as plt
import numpy as np
import get_data
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD

X, Y = get_data.get_data(500)
model = Sequential()

#  Number of neurons in the current layer ：1  Activate function type ：sigmoid  Input data characteristic latitude ：1
model.add(Dense(units=200, input_dim=1))
model.add(Dense(units=100))
model.add(Dense(units=100))
model.add(Dense(units=100, activation='sigmoid'))
# model.add(Dense(units=100, activation='sigmoid'))
# model.add(Dense(units=100, activation='sigmoid'))
# model.add(Dense(units=100, activation='sigmoid'))
# model.add(Dense(units=100, activation='sigmoid'))
# model.add(Dense(units=100, activation='sigmoid'))
# model.add(Dense(units=100, activation='sigmoid'))
model.add(Dense(units=1))

#  Loss function （ Mean square error ）  Optimizer （sgd： Stochastic gradient descent algorithm ）  Evaluation criteria （accuracy： Accuracy ）
model.compile(loss='mse', optimizer=SGD(lr=0.01), metrics=['accuracy'])

model.summary()

model.fit(X, Y, epochs=10000, batch_size=20)

pres = model.predict(X)

plt.scatter(X, Y)
plt.plot(X, pres, color='red')
plt.show()