请使用python语言写一个使用LSTM神经网络进行混凝土强度预测的代码，要求输出预测图，求得平均绝对误差、平均绝对百分误差和均方根误差等评价指标。

好的，以下是一个使用 LSTM 神经网络进行混凝土强度预测的 Python 代码示例（使用 Keras 库）：

import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_absolute_error, mean_absolute_percentage_error, mean_squared_error
import matplotlib.pyplot as plt

# 读取数据
data = pd.read_csv('concrete_data.csv')
data = data.dropna()  # 去除缺失值

# 特征和标签
X = data.iloc[:, :-1]
y = data.iloc[:, -1]

# 归一化
scaler = MinMaxScaler(feature_range=(0, 1))
X = scaler.fit_transform(X)
y = scaler.fit_transform(y.values.reshape(-1, 1))

# 划分数据集
train_size = int(len(data) * 0.8)
X_train = X[:train_size, :]
X_test = X[train_size:, :]
y_train = y[:train_size, :]
y_test = y[train_size:, :]

# 转换为三维数据
X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1]))
X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1]))

# LSTM 模型
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(X_train.shape[1], X_train.shape[2])))
model.add(LSTM(units=50))
model.add(Dense(units=1))
model.compile(loss='mean_squared_error', optimizer='adam')

# 训练模型
history = model.fit(X_train, y_train, epochs=100, batch_size=64, validation_data=(X_test, y_test), verbose=2, shuffle=False)

# 预测
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
y_train_pred = scaler.inverse_transform(y_train_pred)
y_test_pred = scaler.inverse_transform(y_test_pred)
y_train = scaler.inverse_transform(y_train)
y_test = scaler.inverse_transform(y_test)

# 评价指标
mae_train = mean_absolute_error(y_train, y_train_pred)
mape_train = mean_absolute_percentage_error(y_train, y_train_pred)
mse_train = mean_squared_error(y_train, y_train_pred)
rmse_train = np.sqrt(mse_train)

mae_test = mean_absolute_error(y_test, y_test_pred)
mape_test = mean_absolute_percentage_error(y_test, y_test_pred)
mse_test = mean_squared_error(y_test, y_test_pred)
rmse_test = np.sqrt(mse_test)

print('训练集上的 MAE: %.2f' % mae_train)
print('训练集上的 MAPE: %.2f' % mape_train)
print('训练集上的 RMSE: %.2f' % rmse_train)
print('测试集上的 MAE: %.2f' % mae_test)
print('测试集上的 MAPE: %.2f' % mape_test)
print('测试集上的 RMSE: %.2f' % rmse_test)

# 绘制预测图
plt.plot(y_test, label='True')
plt.plot(y_test_pred, label='Predicted')
plt.legend()
plt.show()

其中，`concrete_data.csv` 是包含混凝土强度数据的 CSV 文件，需要根据实际情况进行修改。在代码中使用了 LSTM 神经网络进行预测，并使用了 MinMaxScaler 进行数据归一化。最后计算了训练集和测试集上的 MAE、MAPE、RMSE 等评价指标，并绘制了预测图。