大佬们，这个程序没法运行，该怎么改啊

data = pd.read_excel('Qidata.xlsx') # 读取流量表
Qi_train1 = data[0:5507].copy().reset_index(drop=True) # 第一段数据
Qi_train2 = data[5507:14275].copy().reset_index(drop=True) # 第二段数据
Qi_test1 = data[14275:].copy().reset_index(drop=True) # 测试数据

# 降雨数据
Raindata = pd.read_excel('Raindata.xlsx')
raindata_new = pd.DataFrame()
raindata_new['TimeStample'] = Raindata['TimeStample'].copy()
Raindata.drop('TimeStample',axis=1,inplace=True)
# 将所有测点的数据求和作为总降雨
raindata_new['Rain_sum'] = Raindata.apply(lambda x: x.sum(), axis=1)
Rain_train = raindata_new[0:43824].copy().reset_index(drop=True)
Rain_test1 = raindata_new[43824:].copy().reset_index(drop=True)
Rain_train.set_index('TimeStample', inplace=True)

# 流量的采样频率为（每3个小时），而降雨为每1个小时
Rain_train = Rain_train.resample('3H').sum()
Qi_train1['Rain_sum'] = Rain_train['Rain_sum'].values[0:5507]
Qi_train2['Rain_sum'] = Rain_train['Rain_sum'].values[5507+333:]
Rain_test1.set_index('TimeStample', inplace=True)
a1 = Rain_test1[0:31*24].resample('3H').sum()
a2 = Rain_test1[31*24:2*31*24].resample('3H').sum()
a3 = Rain_test1[2*31*24:3*31*24].resample('3H').sum()
Qi_test1['Rain_sum'] = pd.concat([a1,a2,a3],axis=0,ignore_index=True)
Environmentdata = pd.read_excel('Environmentdata.xlsx')
# 填充缺失
Environmentdata['T'].fillna(method='ffill',inplace=True)
Environmentdata['w'].fillna(method='ffill',inplace=True)
# wd需要归一化
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
Environmentdata['wd'] = ss.fit_transform(Environmentdata['wd'].values.reshape(-1,1))
Environment = pd.DataFrame()
Environment['T'] = np.zeros(len(Environmentdata)*8)
Environment['w'] = np.zeros(len(Environmentdata)*8)
Environment['wd'] = np.zeros(len(Environmentdata)*8)
for i in range(len(Environment)):
Environment['T'][i] = Environmentdata['T'][int(i/8)]
Environment['w'][i] = Environmentdata['w'][int(i/8)]
Environment['wd'][i] = Environmentdata['wd'][int(i/8)]
Qi_train1['T'] = Environment['T'][0:len(Qi_train1)].values
Qi_train1['w'] = Environment['w'][0:len(Qi_train1)].values
Qi_train1['wd'] = Environment['wd'][0:len(Qi_train1)].values
Qi_train2['T'] = Environment['T'][5840:(5840 + len(Qi_train2))].values
Qi_train2['w'] = Environment['w'][5840:(5840 + len(Qi_train2))].values
Qi_train2['wd'] = Environment['wd'][5840:(5840 + len(Qi_train2))].values
Qi_test1['T'] = Environment['T'][(5840 + len(Qi_train2)):(5840 + len(Qi_train2) + len(Qi_test1))].values
Qi_test1['w'] = Environment['w'][(5840 + len(Qi_train2)):(5840 + len(Qi_train2) + len(Qi_test1))].values
Qi_test1['wd'] = Environment['wd'][(5840 + len(Qi_train2)):(5840 + len(Qi_train2) + len(Qi_test1))].values

# train为数据，多维的时间序列；n_input为输入的维数，n_out为预测的步数，n_features为要使用前几个时间序列
def to_supervised(train, n_input, n_out, n_features):
data = train
X, y = list(), list()
in_start = 0
for _ in range(len(data)):
in_end = in_start + n_input
out_end = in_end + n_out
if out_end <= len(data):
X.append(data[in_start:in_end, 0:n_features]) # 使用几个特征
y.append(data[in_end:out_end, 0])
in_start += 1
return array(X), array(y)
# baseline中只用了2个feature
trainData2 = read_csv('trainData2.csv', usecols=['Qi', 'Rain_sum']).values
# 验证数据为2017年的数据
validData = read_csv('validData.csv', usecols=['Qi', 'Rain_sum']).values
testData1 = read_csv('testData1.csv', usecols=['Qi', 'Rain_sum']).values
n_weeks = 4 # 可调
n_input = n_weeks * 7 * 8
n_out = 7 * 8
n_features = 2
train_x1, train_y1 = to_supervised(trainData1, n_input, n_out, n_features)
train_x2, train_y2 = to_supervised(trainData2, n_input, n_out, n_features)
valid_x, valid_y = to_supervised(validData, n_input, n_out, n_features)
model = Sequential()