DRY และ "Do One Thing"
การเขียนฟังก์ชันใน Python
Shayne Miel
Software Architect @ Duo Security
อย่าเขียนโค้ดซ้ำ (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])
ปัญหาของการเขียนโค้ดซ้ำ
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) ### yikes! ###
plt.scatter(test_pca[:,0], test_pca[:,1])
อีกปัญหาของการเขียนโค้ดซ้ำ
train = pd.read_csv('train.csv')
train_y = train['labels'].values ### <- there and there --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 ### <- there and there --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 ### <- there and there --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])
ใช้ฟังก์ชันเพื่อหลีกเลี่ยงการเขียนซ้ำ
def load_and_plot(path):
"""Load a dataset and plot the first two principal components.
Args:
path (str): The location of a CSV file.
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):
"""Load a dataset and plot the first two principal components.
Args:
path (str): The location of a CSV file.
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):
"""Load a dataset and plot the first two principal components.
Args:
path (str): The location of a CSV file.
Returns:
tuple of ndarray: (features, labels)
"""
# load the 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):
"""Load a dataset and plot the first two principal components.
Args:
path (str): The location of a CSV file.
Returns:
tuple of ndarray: (features, labels)
"""
# load the data
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
# plot the first two principal components
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
return X, y
def load_and_plot(path):
"""Load a dataset and plot the first two principal components.
Args:
path (str): The location of a CSV file.
Returns:
tuple of ndarray: (features, labels)
"""
# load the data
data = pd.read_csv(path)
y = data['label'].values
X = data[col for col in data.columns if col != 'label'].values
# plot the first two principle components
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
# return loaded data
return X, y
Do One Thing
def load_data(path):
"""Load a dataset.
Args:
path (str): The location of a CSV file.
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 the first two principal components of a matrix.
Args:
X (numpy.ndarray): The data to plot.
"""
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
ข้อดีของการทำสิ่งเดียว
โค้ดจะ:
- ยืดหยุ่นมากขึ้น
- เข้าใจได้ง่ายขึ้น
- ทดสอบได้ง่ายขึ้น
- ดีบักได้ง่ายขึ้น
- แก้ไขได้สะดวกขึ้น
Code smell และการ Refactor
"คนโง่ก็เขียนโค้ดที่คอมพิวเตอร์เข้าใจได้ แต่โปรแกรมเมอร์ที่ดีเขียนโค้ดที่มนุษย์เข้าใจได้" - Martin Fowler (1999)
มาฝึกกันเถอะ!
การเขียนฟังก์ชันใน Python
