Combination of CNN and LSTM for time series data - time-series

Question

I'm trying to run a combination of CNN (Convolutional Neural Network) and LSTM (Long Short Term Memory), and didn't find the right reshaping for the data the fits for both. I thought LSTM needs [samples, timesteps, features], but it doesn't work here as input.
I'm receiving an error:
ValueError: Negative dimension size caused by subtracting 3 from 1 for '{{node conv1d/conv1d/Conv2D}} = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], explicit_paddings=[], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](conv1d/conv1d/Reshape, conv1d/conv1d/ExpandDims_1)' with input shapes: [?,1,1,24], [1,3,24,64].
The data is taken from:
https://www.kaggle.com/berkeleyearth/climate-change-earth-surface-temperature-data
It has the shape of:
date
LandAverageTemperature
1750-01-01
1.2
etc..
The full code is:
import tensorflow as tf
def preprocessing(data,n_in=1, n_out=1):
from sklearn.model_selection import train_test_split
def series_to_supervised(df, n_in=1, n_out=1,
dropnan=True):
cols = list()
# input sequence (t-n, ... t-1)
for i in range(n_in, 0, -1):
cols.append(df.shift(i))
# forecast sequence (t, t+1, ... t+n)
for i in range(0, n_out):
cols.append(df.shift(-i))
# put it all together
agg = pd.concat(cols, axis=1)
# drop rows with NaN values
if dropnan:
agg.dropna(inplace=True)
return agg.values
land_temp = pd.DataFrame(data['LandAverageTemperature'].values)
ma_vals = data['LandAverageTemperature'].expanding(min_periods=12).mean()
ma_vals_inter = ma_vals.interpolate(limit_direction='both')
df = series_to_supervised(ma_vals_inter, n_in=n_in, n_out=n_out, dropnan=True)
df = pd.DataFrame(df)
X, y = df.iloc[:, :-n_out], df.iloc[:, -n_out:]
percent = 0.8
if n_out == 1:
y = y.iloc[:, 0]
lim = int(percent * X.shape[0])
X_train, X_test, y_train, y_test = X[:lim], X[lim:], y[:lim], y[ lim:] # train_test_split( X, y, test_size=0.4, random_state=0)
return X_train, X_test, y_train, y_test
def lstm_cnn2(X_train,y_train,config,n_in,n_out=1,batch_size=1,epochs=1000,verbose=0,n_features=1):
input_y = y_train.values.reshape(y_train.shape[0], 1)
n_timesteps, n_features, n_outputs = X_train.shape[0],
X_train.shape[1], input_y.shape[1]
# reshape output into [samples, timesteps, features]
input_x = X_train.values.reshape((X_train.shape[0], 1,
n_features))
# define model
model = Sequential()
model.add(Conv1D(64, 3, activation='relu', input_shape=(n_timesteps,1,n_features)))
model.add(Conv1D(64, 3, activation='relu'))
model.add(MaxPooling1D())
model.add(Flatten())
model.add(RepeatVector(n_outputs))
model.add(LSTM(200, activation='relu',
return_sequences=True))
model.add(TimeDistributed(Dense(100,
activation='relu')))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mse', optimizer='adam')
# fit network
model.fit(input_x, input_y, epochs=epochs,
batch_size=batch_size, verbose=verbose)
return model
if __name__ == '__main__':
file_location='./GlobalTemperatures.csv'
data = pd.read_csv(file_location)
data['dt'] = pd.to_datetime(data['dt'])
n_out = 1
n_in = 12 * 2
X_train, X_test, y_train, y_test =
preprocessing(data,n_in,n_out)
config = 128, 64, 32, 3 * 48, 48, 24, 100, 20 # lstm
model configuration
verbose, epochs, batch_size = 0, 1, 16
model_lstm = lstm_cnn2(X_train, y_train, config,
n_in,batch_size=batch_size)