实践示例
Python 测试入门
Alexander Levin
Data Scientist
数据与流水线
数据：数据科学薪资。
每行包含一名数据从业者的薪资、职位等信息。
流水线：计算平均薪资：
- 读取数据
- 按雇佣类型筛选
- 计算平均薪资
- 保存结果
流水线代码
import pandas as pd
# 获取数据的 fixture
@pytest.fixture
def read_df():
return pd.read_csv('ds_salaries.csv')
# 过滤函数
def filter_df(df):
return df[df['employment_type'] == 'FT']
# 计算均值
def get_mean(df):
return df['salary_in_usd'].mean()
集成测试
测试用例：
- 读取数据
- 写入文件
代码：
def test_read_df(read_df):
# Check the type of the dataframe
assert isinstance(read_df, pd.DataFrame)
# Check that df contains rows
assert read_df.shape[0] > 0
集成测试
示例：检查 Python 能否创建文件。
def test_write():
# 以写入模式打开文件
with open('temp.txt', 'w') as wfile:
# 写入文本
wfile.write('Testing stuff is awesome')
# 检查文件是否存在
assert os.path.exists('temp.txt')
# 别忘了清理
os.remove('temp.txt')
单元测试
测试用例：
- 过滤后数据集仅含"FT"雇佣类型
get_mean()函数返回数值
代码：
def test_units(read_df):
filtered = filter_df(read_df)
assert filtered['employment_type'].unique() == ['FT']
assert isinstance(get_mean(filtered), float)
特性测试
测试用例：
- 均值大于 0
- 均值不大于数据集中的最高薪资
代码：
def test_feature(read_df):
# 过滤数据
filtered = filter_df(read_df)
# 用例：均值大于 0
assert get_mean(filtered) > 0
# 用例：均值不大于最大值
assert get_mean(filtered) <= read_df['salary_in_usd'].max()
性能测试
测试用例：
- 从开始到结束的流水线执行时间
代码：
def test_performance(benchmark, read_df):
# 基准装饰器
@benchmark
# 待测函数
def get_result():
filtered = filter_df(read_df)
return get_mean(filtered)
最终测试套件
import pytest
## Integration Tests
def test_read_df(read_df):
# Check the type of the dataframe
assert isinstance(read_df, pd.DataFrame)
# Check that df contains rows
assert read_df.shape[0] > 0
def test_write():
with open('temp.txt', 'w') as wfile:
wfile.write('12345')
assert os.path.exists('temp.txt')
os.remove('temp.txt')
## Unit Tests
def test_units(read_df):
filtered = filter_df(read_df)
assert filtered['employment_type'].unique() == ['FT']
assert isinstance(get_mean(filtered), float)
## Feature Tests
def test_feature(read_df):
# Filtering the data
filtered = filter_df(read_df)
# Test case: mean is greater than zero
assert get_mean(filtered) > 0
# Test case: mean is not bigger than the maximum
assert get_mean(filtered) <= read_df['salary_in_usd'].max()
## Performance Tests
def test_performance(benchmark, read_df):
# Benchmark decorator
@benchmark
# Function to measure
def pipeline():
filtered = filter_df(read_df)
return get_mean(filtered)
Passons à la pratique !
Python 测试入门
