tensorflow2用DPCNN和GNN预测数据，输入绝对路径下的一列的csv数据作为训练集数据，训练集95%作为测试集，并将预测值和实际值画曲线显示，最后把loss和acc结果按epochs可视化

非常抱歉，我的回答有误。GNN是图神经网络，而非GCN。以下是使用DPCNN和GNN的代码：

1. 加载数据：

import pandas as pd
import numpy as np

# 读取csv文件
data = pd.read_csv('path/to/your/csv/file.csv', header=None)

# 将数据分为输入和输出
X = data.iloc[:, :-1].values
y = data.iloc[:, -1].values

# 将输出转换为one-hot编码（如果是分类问题）
from tensorflow.keras.utils import to_categorical
y = to_categorical(y)

2. 划分数据集：

from sklearn.model_selection import train_test_split

# 划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.05, random_state=42)

3. 构建模型：

import tensorflow as tf
from spektral.layers import GraphConv, GlobalAvgPool

# 构建DPCNN模型
inputs = tf.keras.layers.Input(shape=(X_train.shape[1],))
x = inputs
for i in range(3):
    x = tf.keras.layers.Conv1D(64, kernel_size=3, activation='relu', padding='same')(x)
    x = tf.keras.layers.Conv1D(64, kernel_size=3, activation='relu', padding='same')(x)
    if i < 2:
        x = tf.keras.layers.MaxPooling1D(pool_size=2)(x)
dpcnn_output = tf.keras.layers.GlobalMaxPooling1D()(x)

# 构建GNN模型
A = tf.keras.layers.Input(shape=(None,), sparse=True)
X_in = tf.keras.layers.Input(shape=(X_train.shape[1],))
X = GraphConv(32, activation='relu')([X_in, A])
X = GraphConv(32, activation='relu')([X, A])
gnn_output = GlobalAvgPool()(X)

# 连接DPCNN和GNN的输出
concat = tf.keras.layers.concatenate([dpcnn_output, gnn_output])

# 构建输出层
outputs = tf.keras.layers.Dense(units=y.shape[1], activation='softmax')(concat)

# 定义模型
model = tf.keras.Model(inputs=[inputs, X_in, A], outputs=outputs)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

4. 训练模型：

# 构建邻接矩阵
from spektral.utils import normalized_adjacency

A_train = normalized_adjacency(X_train)

history = model.fit([X_train, X_train, A_train], y_train, validation_split=0.05, epochs=100, batch_size=32)

5. 可视化结果：

import matplotlib.pyplot as plt

# 绘制训练集和验证集的loss曲线
plt.plot(history.history['loss'], label='train_loss')
plt.plot(history.history['val_loss'], label='val_loss')
plt.legend()
plt.show()

# 绘制训练集和验证集的accuracy曲线
plt.plot(history.history['accuracy'], label='train_acc')
plt.plot(history.history['val_accuracy'], label='val_acc')
plt.legend()
plt.show()

# 在测试集上评估模型
A_test = normalized_adjacency(X_test)
test_loss, test_acc = model.evaluate([X_test, X_test, A_test], y_test)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)

希望这些代码可以帮到您！