写一段python代码，读取一个csv文件，该文件没有表头，第一列为时间编号,编号以1,2,3……这样自然数的形式出现，第二列为充电量数值，将该数据集的前90%划分为训练集，其余部分设置为测试集，利用L1正则化方法改进的lstm模型预测该时间序列，并打印rmse作为评价指标，并分别绘制训练集的真实值和预测值图片以及测试集的真实值和预测值图片，两张图片的横坐标单位为time/h，纵坐标单位为kwh

以下是读取csv文件、划分数据集、构建LSTM模型、训练和预测、打印rmse、绘制训练集和测试集的真实值和预测值图片的代码。需要安装的包有：pandas、numpy、scikit-learn、Keras、matplotlib。

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

# 读取CSV文件
data = pd.read_csv('data.csv', header=None, index_col=0)

# 将数据集划分为训练集和测试集
train_size = int(len(data) * 0.9)
train, test = data.values[0:train_size,:], data.values[train_size:len(data),:]

# 将数据集缩放到0到1之间
scaler = MinMaxScaler(feature_range=(0, 1))
train = scaler.fit_transform(train)
test = scaler.transform(test)

# 将数据集转换为有监督的学习问题
def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back), 0]
        dataX.append(a)
        dataY.append(dataset[i + look_back, 0])
    return np.array(dataX), np.array(dataY)

look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

# 将输入数据重塑为 [样本数，时间步长，特征] 的形状
trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = np.reshape(testX, (testX.shape[0], testX.shape[1], 1))

# 构建LSTM模型
model = Sequential()
model.add(LSTM(50, input_shape=(look_back, 1), kernel_regularizer='l1'))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')

# 训练模型
model.fit(trainX, trainY, epochs=100, batch_size=10, verbose=2)

# 预测
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

# 将预测结果缩放回原始范围
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])

# 计算rmse
trainScore = np.sqrt(np.mean(np.square(trainY[0] - trainPredict[:,0])))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = np.sqrt(np.mean(np.square(testY[0] - testPredict[:,0])))
print('Test Score: %.2f RMSE' % (testScore))

# 绘制训练集真实值和预测值
trainPredictPlot = np.empty_like(data.values)
trainPredictPlot[:, :] = np.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
plt.figure(figsize=(10,5))
plt.plot(data.values, label='True Data')
plt.plot(trainPredictPlot, label='Predicted Data')
plt.title('Training Set')
plt.xlabel('Time/h')
plt.ylabel('kwh')
plt.legend()
plt.show()

# 绘制测试集真实值和预测值
testPredictPlot = np.empty_like(data.values)
testPredictPlot[:, :] = np.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(data)-1, :] = testPredict
plt.figure(figsize=(10,5))
plt.plot(data.values, label='True Data')
plt.plot(testPredictPlot, label='Predicted Data')
plt.title('Testing Set')
plt.xlabel('Time/h')
plt.ylabel('kwh')
plt.legend()
plt.show()

其中，假设数据文件名为"data.csv"，LSTM模型中使用了L1正则化方法。可以根据需要调整LSTM模型的参数、数据集划分比例、look_back参数等。