lp3.py

dataset = raw_dataset.copy()
dataset.tail()

dataset.isna().sum()
#drop na
dataset = dataset.dropna()

dataset['Origin'] = dataset['Origin'].map({1: 'USA', 2: 'Europe', 3: 'Japan'})
#one hot encoding
dataset = pd.get_dummies(dataset, columns=['Origin'], prefix='', prefix_sep='')
dataset.tail()

train_dataset = dataset.sample(frac=0.8, random_state=0)
test_dataset = dataset.drop(train_dataset.index)

sns.pairplot(train_dataset[['MPG', 'Cylinders', 'Displacement', 'Weight']], diag_kind='kde')

train_dataset.describe().transpose()

#normalization
train_dataset.describe().transpose()[['mean', 'std']]

normalizer = tf.keras.layers.Normalization(axis=-1)
normalizer.adapt(np.array(train_features))

print(normalizer.mean.numpy())

first = np.array(train_features[:1])

with np.printoptions(precision=2, suppress=True):
  print('First example:', first)
  print()
  print('Normalized:', normalizer(first).numpy())