用python #11.根据2015-2016年用水量数据，预测编号1-200的用户，2017年每个月用水量，并对预测值进行评价。

好的，具体实现如下：

首先，读取数据，进行预处理：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from statsmodels.tsa.arima_model import ARIMA
from sklearn.metrics import mean_squared_error

# 读取数据
data = pd.read_csv('water_usage.csv', index_col='id')
# 将缺失值填充为前一个值
data.fillna(method='ffill', inplace=True)
# 去除异常值
data = data[(data >= 0) & (data <= 500)]
# 平稳性检验
from statsmodels.tsa.stattools import adfuller
def test_stationarity(timeseries):
    # Determing rolling statistics
    rolmean = timeseries.rolling(12).mean()
    rolstd = timeseries.rolling(12).std()

    # Plot rolling statistics:
    plt.plot(timeseries, color='blue', label='Original')
    plt.plot(rolmean, color='red', label='Rolling Mean')
    plt.plot(rolstd, color='black', label='Rolling Std')
    plt.legend(loc='best')
    plt.title('Rolling Mean & Standard Deviation')
    plt.show()

    # Perform Dickey-Fuller test:
    print('Results of Dickey-Fuller Test:')
    dftest = adfuller(timeseries, autolag='AIC')
    dfoutput = pd.Series(dftest[0:4], index=['Test Statistic','p-value','#Lags Used','Number of Observations Used'])
    for key,value in dftest[4].items():
        dfoutput['Critical Value (%s)'%key] = value
    print(dfoutput)

test_stationarity(data.loc[1:200, '2016-12-31'])

然后，使用ARIMA模型进行预测：

# 构建ARIMA模型
model = ARIMA(data.loc[1:200, '2015-01-31':'2016-12-31'], order=(2,1,2))
model_fit = model.fit(disp=0)
# 预测2017年每个月的用水量
forecast = model_fit.forecast(steps=12)[0]
# 输出预测结果
print(forecast)

最后，使用评价指标对预测结果进行评价：

# 计算均方根误差
mse = mean_squared_error(data.loc[1:200, '2017-01-31':'2017-12-31'], forecast)
rmse = np.sqrt(mse)
print('RMSE: %.2f' % rmse)
# 可视化预测结果
plt.plot(data.loc[1:200, '2017-01-31':'2017-12-31'].values.flatten(), label='Actual')
plt.plot(forecast, label='Predicted')
plt.legend()
plt.show()

完整代码如下：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from statsmodels.tsa.arima_model import ARIMA
from sklearn.metrics import mean_squared_error

# 读取数据
data = pd.read_csv('water_usage.csv', index_col='id')
# 将缺失值填充为前一个值
data.fillna(method='ffill', inplace=True)
# 去除异常值
data = data[(data >= 0) & (data <= 500)]
# 平稳性检验
from statsmodels.tsa.stattools import adfuller
def test_stationarity(timeseries):
    # Determing rolling statistics
    rolmean = timeseries.rolling(12).mean()
    rolstd = timeseries.rolling(12).std()

    # Plot rolling statistics:
    plt.plot(timeseries, color='blue', label='Original')
    plt.plot(rolmean, color='red', label='Rolling Mean')
    plt.plot(rolstd, color='black', label='Rolling Std')
    plt.legend(loc='best')
    plt.title('Rolling Mean & Standard Deviation')
    plt.show()

    # Perform Dickey-Fuller test:
    print('Results of Dickey-Fuller Test:')
    dftest = adfuller(timeseries, autolag='AIC')
    dfoutput = pd.Series(dftest[0:4], index=['Test Statistic','p-value','#Lags Used','Number of Observations Used'])
    for key,value in dftest[4].items():
        dfoutput['Critical Value (%s)'%key] = value
    print(dfoutput)

test_stationarity(data.loc[1:200, '2016-12-31'])

# 构建ARIMA模型
model = ARIMA(data.loc[1:200, '2015-01-31':'2016-12-31'], order=(2,1,2))
model_fit = model.fit(disp=0)
# 预测2017年每个月的用水量
forecast = model_fit.forecast(steps=12)[0]
# 输出预测结果
print(forecast)

# 计算均方根误差
mse = mean_squared_error(data.loc[1:200, '2017-01-31':'2017-12-31'], forecast)
rmse = np.sqrt(mse)
print('RMSE: %.2f' % rmse)
# 可视化预测结果
plt.plot(data.loc[1:200, '2017-01-31':'2017-12-31'].values.flatten(), label='Actual')
plt.plot(forecast, label='Predicted')
plt.legend()
plt.show()