Trying to run an LSTM model where the data is separated into few columns in csv and i'm trying to prepare date from such csv's.
Getting the error of
ValueError: Failed to convert a NumPy array to a Tensor
(Unsupported object type numpy.ndarray)
# Load CSV data # 3 features (1, 2, 3), 1 label (5) columns
# All data is in float and 1,0 in Labels
data = pd.read_csv("data_1.csv", usecols=["Column_1","Column_2","Column_3","Column_5"])
data2 = pd.read_csv("data_2.csv", usecols=["Column_1","Column_2","Column_3","Column_5"])
window_size = 1 # For timesteps
# Function to create sequences
def create_sequences(data, window_size, label_col):
sequences = []
labels = []
for i in range(len(data) - window_size + 1):
window = data.loc[i:i+window_size,["Column_1","Column_2","Column_3"]].astype('float64')
label = data.loc[i + window_size - 1, label_col] # Label at the end of window
sequences.append(window.to_numpy())
labels.append(label)
return np.array(sequences), np.array(labels)
# Create sequences and labels
sequences2, labels2 = create_sequences(data, window_size, "Column_5")
sequences2 = sequences2.reshape(-1, 1) # (samples, timesteps, features)
print("Data 1 preparation is done")
sequences3, labels3 = create_sequences(data2, window_size, "Column_5")
sequences3 = sequences3.reshape(-1, 1) # (samples, timesteps, features)
print("Data 2 preparation is done")
sequences = np.concatenate((sequences2, sequences3))
labels = np.concatenate((labels2, labels3), axis=0)
# Define LSTM model
model = keras.Sequential([
keras.layers.LSTM(64, return_sequences=True, input_shape=(window_size, sequences.shape[2])),
keras.layers.LSTM(32),
keras.layers.Dense(len(np.unique(labels)), activation='softmax') # Multi-class output
])
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(sequences, keras.utils.to_categorical(labels), epochs=1)
I can also replicate it by running the code,
sequences=tf.convert_to_tensor(sequences)
Expecting the dataset taken properly in the LSTM Layer.
