DRY dan "Satu Fungsi, Satu Tugas"
Menulis Function di Python
Shayne Miel
Software Architect @ Duo Security
Jangan ulangi diri sendiri (DRY)
train = pd.read_csv('train.csv')
train_y = train['labels'].values
train_X = train[col for col in train.columns if col != 'labels'].values
train_pca = PCA(n_components=2).fit_transform(train_X)
plt.scatter(train_pca[:,0], train_pca[:,1])
val = pd.read_csv('validation.csv')
val_y = val['labels'].values
val_X = val[col for col in val.columns if col != 'labels'].values
val_pca = PCA(n_components=2).fit_transform(val_X)
plt.scatter(val_pca[:,0], val_pca[:,1])
test = pd.read_csv('test.csv')
test_y = test['labels'].values
test_X = test[col for col in test.columns if col != 'labels'].values
test_pca = PCA(n_components=2).fit_transform(train_X)
plt.scatter(test_pca[:,0], test_pca[:,1])
Masalah saat mengulang kode
train = pd.read_csv('train.csv')
train_y = train['labels'].values
train_X = train[col for col in train.columns if col != 'labels'].values
train_pca = PCA(n_components=2).fit_transform(train_X)
plt.scatter(train_pca[:,0], train_pca[:,1])
val = pd.read_csv('validation.csv')
val_y = val['labels'].values
val_X = val[col for col in val.columns if col != 'labels'].values
val_pca = PCA(n_components=2).fit_transform(val_X)
plt.scatter(val_pca[:,0], val_pca[:,1])
test = pd.read_csv('test.csv')
test_y = test['labels'].values
test_X = test[col for col in test.columns if col != 'labels'].values
test_pca = PCA(n_components=2).fit_transform(train_X) ### waduh! ###
plt.scatter(test_pca[:,0], test_pca[:,1])
Masalah lain saat mengulang kode
train = pd.read_csv('train.csv')
train_y = train['labels'].values ### <- di situ dan di situ --v ###
train_X = train[col for col in train.columns if col != 'labels'].values
train_pca = PCA(n_components=2).fit_transform(train_X)
plt.scatter(train_pca[:,0], train_pca[:,1])
val = pd.read_csv('validation.csv')
val_y = val['labels'].values ### <- di situ dan di situ --v ###
val_X = val[col for col in val.columns if col != 'labels'].values
val_pca = PCA(n_components=2).fit_transform(val_X)
plt.scatter(val_pca[:,0], val_pca[:,1])
test = pd.read_csv('test.csv')
test_y = test['labels'].values ### <- di situ dan di situ --v ###
test_X = test[col for col in test.columns if col != 'labels'].values
test_pca = PCA(n_components=2).fit_transform(test_X)
plt.scatter(test_pca[:,0], test_pca[:,1])
Gunakan fungsi untuk hindari pengulangan
def load_and_plot(path):
"""Muat dataset dan plot dua komponen utama pertama.
Args:
path (str): Lokasi file CSV.
Returns:
tuple of ndarray: (features, labels)
"""
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
return X, y
train_X, train_y = load_and_plot('train.csv')val_X, val_y = load_and_plot('validation.csv')test_X, test_y = load_and_plot('test.csv')
def load_and_plot(path):
"""Muat dataset dan plot dua komponen utama pertama.
Args:
path (str): Lokasi file CSV.
Returns:
tuple of ndarray: (features, labels)
"""
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
return X, y
def load_and_plot(path):
"""Muat dataset dan plot dua komponen utama pertama.
Args:
path (str): Lokasi file CSV.
Returns:
tuple of ndarray: (features, labels)
"""
# muat data
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
return X, y
def load_and_plot(path):
"""Muat dataset dan plot dua komponen utama pertama.
Args:
path (str): Lokasi file CSV.
Returns:
tuple of ndarray: (features, labels)
"""
# muat data
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
# plot dua komponen utama pertama
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
return X, y
def load_and_plot(path):
"""Muat dataset dan plot dua komponen utama pertama.
Args:
path (str): Lokasi file CSV.
Returns:
tuple of ndarray: (features, labels)
"""
# muat data
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
# plot dua komponen utama pertama
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
# kembalikan data yang dimuat
return X, y
Satu Fungsi, Satu Tugas
def load_data(path):
"""Muat dataset.
Args:
path (str): Lokasi file CSV.
Returns:
tuple of ndarray: (features, labels)
"""
data = pd.read_csv(path)
y = data['labels'].values
X = data[col for col in data.columns
if col != 'labels'].values
return X, y
def plot_data(X):
"""Plot dua komponen utama pertama dari sebuah matriks.
Args:
X (numpy.ndarray): Data yang akan diplot.
"""
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
Keuntungan dari satu tugas
Kodenya menjadi:
- Lebih fleksibel
- Lebih mudah dipahami
- Lebih mudah diuji
- Lebih mudah di-debug
- Lebih mudah diubah
Code smell dan refactoring
"Siapa pun bisa menulis kode yang dimengerti komputer. Programmer yang baik menulis kode yang dimengerti manusia." - Martin Fowler (1999)
Ayo berlatih!
Menulis Function di Python
