# Split the data into train and test sets
train_size = int(len(df)*0.7)
train, test = df.iloc[:train_size],df.iloc[train_size:]

# Split train and test sets into predictors (X) and outcome (y) variables
X_train = train.drop('Activity', axis = 1)
y_train = train.loc[:,['Activity']]
X_test = test.drop('Activity', axis = 1)
y_test = test.loc[:,['Activity']]

# Scale the X data 
scaler_x = MinMaxScaler(feature_range = (0,1))
input_scaler = scaler_x.fit(X_train)
train_x_norm = input_scaler.transform(X_train)
test_x_norm = input_scaler.transform(X_test)

# One-hot encode y data
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)