DRY 与"只做一件事"
Python 函数编写
Shayne Miel
Software Architect @ Duo Security
不要重复自己（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])
重复的风险
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(test_X) ### yikes! ###
plt.scatter(test_pca[:,0], test_pca[:,1])
重复的另一问题
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])
用函数避免重复
def load_and_plot(path):
"""加载数据集并绘制前两个主成分。
Args:
path (str): CSV 文件路径。
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):
"""加载数据集并绘制前两个主成分。
Args:
path (str): CSV 文件路径。
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):
"""加载数据集并绘制前两个主成分。
Args:
path (str): CSV 文件路径。
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):
"""加载数据集并绘制前两个主成分。
Args:
path (str): CSV 文件路径。
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):
"""加载数据集并绘制前两个主成分。
Args:
path (str): CSV 文件路径。
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
只做一件事（Do One Thing）
def load_data(path):
"""加载数据集。
Args:
path (str): CSV 文件路径。
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):
"""绘制矩阵的前两个主成分。
Args:
X (numpy.ndarray): 要绘制的数据。
"""
pca = PCA(n_components=2).fit_transform(X)
plt.scatter(pca[:,0], pca[:,1])
只做一件事的优势
代码将变得：
- 更灵活
- 更易理解
- 更易测试
- 更易调试
- 更易修改
代码异味与重构
"任何傻瓜都能写出计算机能看懂的代码。优秀的程序员写的是人能看懂的代码。"——Martin Fowler（1999）
Ayo berlatih!
Python 函数编写
