python-LSTM Timeseriesgenerator错误：ValueError:无法将NumPy数组转换为张量（不支持的对象类型NumPy.float64）

我正在创建一个LSTM模型，所以我试图用Timeseriesgenerator设置数据，但我得到了这个值错误：

ValueError:无法将NumPy数组转换为张量（不支持的对象类型NumPy.float64）。

以下是所有相关代码，不确定哪里出了问题，我下面就是一些在线示例：

# Create Timeseries data
n_future = 1   # Number of days we want to look into the future based on the past days.
n_past = 5  # Number of past days we want to use to predict the future.

data_gen = TimeseriesGenerator(clean_df.iloc[:,2:], clean_df.iloc[:,8],
                               length=n_past, sampling_rate=n_future,
                               batch_size=1)

model=Sequential()
model.add(LSTM(100, activation='relu', input_shape=(5,7), return_sequences=True))
model.add(LSTM(50, activation='relu', return_sequences=True))
model.add(LSTM(10, activation='relu'))
model.add(Dense(1))

model.compile(optimizer='adam',loss='mse')
model.summary()

# Train our model
history = model.fit(data_gen,epochs=30)