arima时间序列预测代码

Sure! Here's an example code for ARIMA time series forecasting using the statsmodels library in Python:

import pandas as pd
import numpy as np
from statsmodels.tsa.arima.model import ARIMA

# Read the time series data
data = pd.read_csv('data.csv', parse_dates=['date'], index_col='date')

# Fit the ARIMA model
model = ARIMA(data, order=(p, d, q))  # Replace p, d, q with your desired values
model_fit = model.fit()

# Forecast future values
forecast = model_fit.predict(start=start_date, end=end_date)  # Replace start_date and end_date with your desired range

# Print the forecasted values
print(forecast)

Make sure to replace `'data.csv'` with the path to your actual data file. Set the appropriate values for `p`, `d`, and `q` in the `order` parameter of the `ARIMA` model. Also, replace `start_date` and `end_date` with the desired range for forecasting.

Remember to preprocess your data if necessary, such as removing outliers or handling missing values, before fitting the ARIMA model.