当前位置：首页 > news >正文

对采集到的温湿度数据，使用python进行数据清洗，并使用预测模型进行预测未来一段时间的温湿度数据。

news 2025/9/12 5:11:32

使用Python对传感器采集到的数据进行数据清洗和预测未来一段时间的温湿度数据，您可以按照以下步骤进行操作：

导入必要的库

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

读取数据

data = pd.read_csv('data.csv')  # 替换为您的数据文件路径

数据清洗

# 处理缺失值或异常值
data = data.dropna()  # 删除包含缺失值的行
data = data[(data['Temperature'] > -50) & (data['Temperature'] < 100)]  # 温度异常值范围
data = data[(data['Humidity'] >= 0) & (data['Humidity'] <= 100)]  # 湿度异常值范围# 处理重复值
data = data.drop_duplicates()# 处理时间列
data['Timestamp'] = pd.to_datetime(data['Timestamp'])
data = data.set_index('Timestamp')

特征工程

# 提取日期和时间特征
data['Year'] = data.index.year
data['Month'] = data.index.month
data['Day'] = data.index.day
data['Hour'] = data.index.hour
data['Minute'] = data.index.minute

划分训练集和测试集

X = data[['Year', 'Month', 'Day', 'Hour', 'Minute']]
y_temperature = data['Temperature']
y_humidity = data['Humidity']X_train, X_test, y_temperature_train, y_temperature_test = train_test_split(X, y_temperature, test_size=0.2, random_state=42)
X_train, X_test, y_humidity_train, y_humidity_test = train_test_split(X, y_humidity, test_size=0.2, random_state=42)

构建模型并训练

# 温度预测模型
temperature_model = LinearRegression()
temperature_model.fit(X_train, y_temperature_train)# 湿度预测模型
humidity_model = LinearRegression()
humidity_model.fit(X_train, y_humidity_train)

预测未来一段时间的温湿度数据

# 构造待预测的时间特征
future_time = pd.date_range(start=data.index[-1], periods=10, freq='H')
future_data = pd.DataFrame({'Year': future_time.year,'Month': future_time.month,'Day': future_time.day,'Hour': future_time.hour,'Minute': future_time.minute})# 预测温度
future_temperature = temperature_model.predict(future_data)# 预测湿度
future_humidity = humidity_model.predict(future_data)

打印预测结果

for i in range(len(future_time)):print('Time: {}, Predicted Temperature: {:.2f}°C, Predicted Humidity: {:.2f}%'.format(future_time[i], future_temperature[i], future_humidity[i]))