What I want to achieve

I am working on two data sets. Dataset #1 shows Natural Gas Futures for different months starting most current till 100 rows and Dataset #2 is Natural Gas storage data which is refreshed every week. I have included both datasets below.

Dataset#2

Dataset#1

The prices in dataset#1, for eg. NGLast, NGOpen,NGHigh fluctuate every 10 minutes while active trading continues.However, during every week data from dataset#2 is published which indicates Natural Gas storage and the prices in dataset#1 can fluctuate based on how much storage was reported.

Code

 import pandas as pd

 import numpy as np

 import matplotlib.pyplot as plt

 from keras.layers import Dense

 from keras.models import Sequential

 from keras.layers import LSTM

 import datetime

 from keras import metrics

 from sklearn.preprocessing import MinMaxScaler



 data = pd.read_excel("C:FuturesFutures.xls")



 data['Contract'] = pd.to_datetime(data['Contract'],unit='s').dt.date

 data['NG Last'] = data['NG Last'].str.rstrip('s')

 data['CO Last'] = data['CO Last'].str.rstrip('s')



 L=len(data)



 COHigh =  np.array([data.iloc[:,8]])

 COLow  =  np.array([data.iloc[:,9]])

 NGLast =  np.array([data.iloc[:,1]])

 NGOpen =  np.array([data.iloc[:,2]])

 NGLow  =  np.array([data.iloc[:,4]])

 COOpen =  np.array([data.iloc[:,7]])

 NGHigh =  np.array([data.iloc[:,3]])

 COLast =  np.array([data.iloc[:,10]])

 NGP     = np.array([data.iloc[:,5]])

 NGVolumes = np.array([data.iloc[:,6]])

 COVolumes = np.array([data.iloc[:,12]])

 COP       = np.array([data.iloc[:,11]])





 X = np.concatenate([COHigh,COLow, NGLast,NGOpen,COOpen,COLast,  NGHigh,NGVolumes,COVolumes, COP,NGP], axis =0)

 X = np.transpose(X)



 Y = NGLow

 Y = np.transpose(Y)





 scaler = MinMaxScaler()



 scaler.fit(X)

 X = scaler.transform(X)

 scaler.fit(Y)

 Y = scaler.transform(Y)



 X = np.reshape(X,(X.shape[0],1,X.shape[1]))

 print(X.shape)



 model = Sequential()

 model.add(LSTM(100,activation='tanh',input_shape=(1,11),   recurrent_activation='hard_sigmoid'))

 model.add(Dense(1))



 model.compile(loss='mean_squared_error', optimizer='rmsprop', metrics = ['accuracy'])

 model.fit(X,Y,epochs = 100,batch_size=1,verbose=2)



 Predict = model.predict(X,verbose=1)



 inversed = scaler.inverse_transform(Predict)

 loss, accuracy = model.evaluate(X, Y, verbose=2)

What has been done thus far

The code above predicts "NG Low" data based on 10 input parameters from dataset#1 and its accurate.
However, I am not following how to include parameters from dataset#2 which has data that is released on weekly basis.
Dataset#1 updates every 10 minutes
Dataset#2 updates every week.

What additional information that I need to include.

I intend to bring in weekly weather data as well just to make my model more reliable.