我如何预测未来几天的温度值？

Question

希望你没事，我基本上是机器学习的新手，我需要你们的帮助。我想每小时预测接下来 3 天的温度值，我该怎么做？谁能帮忙....？？

import pandas as pd
import numpy as np
import datetime as dt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestRegressor
from sklearn import metrics
dataset = pd.read_csv(r"C:\Users\saadh\Desktop\The Weather Forecast\Rawalpindi.csv")
#print(dataset.head)
X = dataset[['moon_illumination','sunHour','date_time','mintempC','uvIndex','DewPointC','humidity','cloudcover','pressure','windspeedKmph']].values
Y = dataset['maxtempC'].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.20, random_state=0)
regressor = RandomForestRegressor(n_estimators=300, random_state=0)
regressor.fit(X_train, Y_train)
predictData = regressor.predict(X_test)
#df = pd.DataFrame({'Actual': Y_test, 'Predicted': predictData})
#res = df.head()
#print(df)
print(predictData.astype(int))
print('Mean Absolute Error:', metrics.mean_absolute_error(Y_test, predictData))
print('Mean Squared Error:', metrics.mean_squared_error(Y_test, predictData))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(Y_test, predictData)))

输出： [43 40 41 41 40 40 39]

平均绝对误差：0.5561904761904758
均方误差：1.0668126984126995
均方根误差：1.0328662538841606

Answer 1

您需要获取要预测的值的功能，并将其馈送到培训的模型。 就像在您的代码中，您对测试数据集X_test的预测，这是存储在X的一部分的一部分。

因此，对代码中的功能类似于此行的功能进行预测

X = dataset[['mintempC','moon_illumination','date_time','uvIndex','sunHour','DewPointC','pressure','humidity','cloudcover']].values

然后做这样的预测

predictData = regressor.predict(X)