Predict stock price

[VitolLub]

hi Daniel and every one who read this message. Please help me improve my code to predicting stock market price.
`

df = pd.DataFrame({'y': close, 'h':close_high_o,'o':open_arr_o,'l':close_low_o})

df = df[['y','h','o','l']]
df2 = df.values

print(len(df))
training = int(np.ceil(len(df) * .95))
print(training)  

# MinMaxScaler expecting like 1 feature
scaler = MinMaxScaler()
scaled_data = scaler.fit_transform(df)

# How many past days of data we want to use to predict the next day price
prediction_days = 500

# Preparing the Training data
X_train = []
y_train = []

for x in range(prediction_days, len(scaled_data)):
    X_train.append(scaled_data[x - prediction_days:x, 0])
    y_train.append(scaled_data[x, 0])

X_train, y_train = np.array(X_train), np.array(y_train)
# Reshaping so that it will work in Neural net
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
print(X_train.shape)
print(y_train.shape)
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(X_train.shape[1], 1)))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50))
model.add(Dropout(0.2))
model.add(Dense(units=500))

model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X_train, y_train, epochs=500, batch_size=32)

model.save('model.h5')

model = load_model('model.h5')

# show me examples hot to train my model
company = "Crypo price"
test_data = 60 

total_dataset = df.values
model_inputs = total_dataset[len(total_dataset) - test_data - prediction_days:]
print(model_inputs)
print(len(model_inputs))
model_inputs = model_inputs.reshape(-1, 1)
print(model_inputs)
print(len(model_inputs)) 

model_inputs = scaler.fit_transform(model_inputs) # ValueError: X has 1 features, but MinMaxScaler is expecting 4 features as input.

print(f"model_inputs len{len(model_inputs)}")
print(f"prediction_days {prediction_days}")

real_data = [model_inputs[len(model_inputs) - prediction_days : len(model_inputs)+1, 0]]
print(f"prediction_days")
print(real_data)
print(len(real_data[0])) 
real_data = np.array(real_data)
real_data = np.reshape(real_data, (real_data.shape[0], real_data.shape[1], 1)) 

prediction = model.predict(real_data)
prediction = scaler.inverse_transform(prediction)
prediction = prediction.reshape(-1, 1) 
plt.plot(prediction, color='green')
plt.legend()
plt.show() 

`
This code must predict LTC coin price.
I have a problem what can't to fix. Code work good, but if get from my DB 800 records(every records is 1 minute price) for example, then I receive predicttion like on follow graph:
https://prnt.sc/2GFx9K7ujxa4

But if I take much more data(for example - 20000 records) for prediction with the same predicting step, then receive next graph.
https://prnt.sc/JobzJmR0RGxE

Meybe some one try to make the same code or working in this way.
Please help me figure out with this problem.