Files
airflow/dags/train/office/rent/train.py
T
2025-01-17 18:40:44 +08:00

47 lines
1.4 KiB
Python

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import pandas as pd
import numpy as np
# 读取数据
data = pd.read_csv('train.csv')
test_data = pd.read_csv('test.csv')
# 分离特征和目标变量
X = data.drop('rent_price', axis=1)
y = data['rent_price']
X_test = test_data.drop('rent_price', axis=1)
y_test = test_data['rent_price']
# 数据标准化
scaler = StandardScaler()
X = scaler.fit_transform(X)
X_test = scaler.transform(X_test)
# 创建模型
model = Sequential([
Dense(50, activation='relu', input_shape=(15,)), # 输入层和第一隐藏层
Dense(50, activation='relu'), # 第二隐藏层
Dense(50, activation='relu'), # 第三隐藏层
Dense(1) # 输出层
])
# 编译模型
model.compile(optimizer=Adam(learning_rate=0.01), loss='mse')
# 训练模型
model.fit(X, y, epochs=500, batch_size=32, verbose=1)
# 评估模型
predictions = model.predict(X_test)
for i in range(len(predictions)):
print(f"Predicted vs Actual: {predictions[i][0]} vs {y_test.iloc[i]}")
# 保存模型为SavedModel格式,以便Java可以加载
model.save('office_rent_model')
print("模型已保存为 office_rent_model,可以由Java加载。")