在先知中测量模型准确性

时间:2019-11-11 14:41:52

标签: python forecast facebook-prophet

我正在运行这段代码。用先知预测多个时间序列,但不知道如何评估模型。

import pandas as pd
from fbprophet import Prophet
data = pd.read_csv(r'C:\Users\XXX.csv')
ids = data['id'].unique()
series = []
for id in ids:
   f = data[data['id'] == id]
   series.append(f)

def run_prophet(timeserie):
    model = Prophet(yearly_seasonality=False,daily_seasonality=False)
    model.fit(timeserie)
    forecast = model.make_future_dataframe(periods=90, include_history=False)
    forecast = model.predict(forecast)
    return forecast

results = list(map(lambda timeserie: run_prophet(timeserie), series))

results[0] 
results[1]

数据的结构是这样的:

id       ds         y
id1   2017-01-01    12
id2   2017-01-01    15
id3   2017-01-01    16

1 个答案:

答案 0 :(得分:1)

您可以通过导入以下代码来做到这一点: from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error 然后 r2_score(original price,predicted price) 其余的都一样 注意:两个数组的样本长度应相等。