max_p=3,
max_q=3,
m=12,
start_P=0,
seasonal=True,
d=1,
D=1,
trace=True,
error_action='ignore',
suppress_warnings=True)
# fitting the model
model.fit(training)
# using the model to make predictions
forecast = model.predict(n_periods=248)
forecast = pd.DataFrame(forecast, index=test.index, columns=['Prediction'])
# RMSE
rms = np.sqrt(
np.mean(
np.power((np.array(test['Close']) - np.array(forecast['Prediction'])),
2)))
print(rms)
# plot
plt.plot(train['Close'])
plt.plot(test['Close'])
plt.plot(forecast['Prediction'])
plt.show()
# importing data_processing
from data_processing import train, test, np, plt
# moving average
# create predictions for test set
# check RMSE using the actual values
preds = []
for i in range(0, test.shape[0]):
a = train['Close'][len(train) - 248 + i:].sum() + sum(preds)
b = a / 248
preds.append(b)
# checking RMSE value
rms = np.sqrt(np.mean(np.power((np.array(test['Close']) - preds), 2)))
print('\n RMSE value on test set:')
print(rms)
# plot
test['Predictions'] = preds
plt.plot(train['Close'])
plt.plot(test[['Close', 'Predictions']])
plt.show()
new_data['Date'] = pd.to_datetime(new_data.Date, format='%Y-%m-%d')
new_data.index = new_data['Date']
# preparing data
new_data.rename(columns={'Close': 'y', 'Date': 'ds'}, inplace=True)
# splitting into training and testing data
train = new_data[:987]
test = new_data[987:]
# Creating and fitting the model
model = Prophet()
model.fit(train)
# predictions
close_prices = model.make_future_dataframe(periods=len(test))
forecast = model.predict(close_prices)
# RMSE
forecast_test = forecast['yhat'][987:]
rms = np.sqrt(
np.mean(np.power((np.array(test['y']) - np.array(forecast_test)), 2)))
print(rms)
# plot
test['Predictions'] = forecast_test.values
plt.plot(train['y'])
plt.plot(test[['y', 'Predictions']])
plt.show()