Dimension issue in LSTM python

0
votes

I am getting the below value due to dimension issue. My input features are ColA and ColB and I want to predict the ColC. When i try to fit the model i am getting the below issue.

ValueError: Input 0 of layer sequential_6 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 2]

import pandas as pd
from numpy import array
from numpy import hstack
from tensorflow.keras.layers import *
from tensorflow.keras import Sequential
from sklearn.model_selection import train_test_split

df = pd.read_csv('input_file.csv')
df.head()
    ColA    ColB    ColC
0   10  15  25
1   20  25  45
2   30  35  65
3   40  45  85
4   50  55  105

X = df.drop(columns =['ColC'])
y = df['ColC']

n_features = X.shape[1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=2)

# define model
n_steps = 5
model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(3, 2)))
model.add(Dense(1))

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

# fit model
model.fit(X, y, epochs=20)

Error message: C:\Users\Amy\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\input_spec.py:180 assert_input_compatibility str(x.shape.as_list()))

ValueError: Input 0 of layer sequential_6 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 2]

pythonlstm