DataStore 查询构建

使用 DataStore 通过流畅的方法链式调用构建 SQL 风格的查询

DataStore 提供 SQL 风格的查询构建方法，可编译为优化后的 SQL 查询。所有操作都会延迟执行，直到需要结果时才会真正运行。

​

查询方法概览

方法	SQL 对应项	说明
select(*cols)	SELECT cols	选择列
filter(cond)	WHERE cond	使用过滤器筛选行
where(cond)	WHERE cond	filter 的别名
sort(*cols)	ORDER BY cols	对行排序
orderby(*cols)	ORDER BY cols	sort 的别名
limit(n)	LIMIT n	限制行数
offset(n)	OFFSET n	跳过若干行
distinct()	DISTINCT	去重
groupby(*cols)	GROUP BY cols	对行分组
having(cond)	HAVING cond	过滤分组
join(right, ...)	JOIN	连接 DataStore
union(other)	UNION	合并结果

---

​

选区

​

select

从 DataStore 中选择指定列。

select(*fields: Union[str, Expression]) -> DataStore

示例：

from chdb.datastore import DataStore
from pathlib import Path
Path("employees.csv").write_text("""\
name,age,city,salary,department,dept_id,status,email,manager_id,bonus
Alice,28,NYC,75000,Engineering,1,active,[e-mail],3,5000
Bob,35,LA,85000,Engineering,1,active,[e-mail],3,
Charlie,52,NYC,95000,Product,2,active,[e-mail],,10000
Diana,32,SF,70000,Design,3,active,[e-mail],3,3000
Eve,23,LA,48000,Product,2,inactive,[e-mail],2,
""")

ds = DataStore.from_file("employees.csv")

# 按列名选择
result = ds.select('name', 'age', 'salary')

# 选择所有列
result = ds.select('*')

# 使用表达式选择
result = ds.select(
    'name',
    (ds['salary'] * 12).as_('annual_salary'),
    ds['age'].as_('employee_age')
)

# 等效的 pandas 风格
result = ds[['name', 'age', 'salary']]

---

​

过滤器

​

filter / where

根据条件使用过滤器筛选行。两种方法等价。

filter(condition) -> DataStore
where(condition) -> DataStore  # 别名

示例：

ds = DataStore.from_file("employees.csv")

# 单一条件
result = ds.filter(ds['age'] > 30)
result = ds.where(ds['salary'] >= 50000)

# 多个条件（与）
result = ds.filter((ds['age'] > 30) & (ds['department'] == 'Engineering'))

# 多个条件（或）
result = ds.filter((ds['city'] == 'NYC') | (ds['city'] == 'LA'))

# NOT 条件
result = ds.filter(~(ds['status'] == 'inactive'))

# 字符串条件
result = ds.filter(ds['name'].str.contains('John'))
result = ds.filter(ds['email'].str.endswith('@company.com'))

# NULL 检查
result = ds.filter(ds['manager_id'].notnull())
result = ds.filter(ds['bonus'].isnull())

# IN 条件
result = ds.filter(ds['department'].isin(['Engineering', 'Product', 'Design']))

# BETWEEN 条件
result = ds.filter(ds['salary'].between(50000, 100000))

# 链式过滤器（与）
result = (ds
    .filter(ds['age'] > 25)
    .filter(ds['salary'] > 50000)
    .filter(ds['city'] == 'NYC')
)

​

Pandas 风格筛选

# 布尔索引（等同于过滤器）
result = ds[ds['age'] > 30]
result = ds[(ds['age'] > 30) & (ds['salary'] > 50000)]

# 查询方法
result = ds.query('age > 30 and salary > 50000')

---

​

排序

​

sort / orderby

按一个或多个列对行排序。

sort(*fields, ascending=True) -> DataStore
orderby(*fields, ascending=True) -> DataStore  # 别名

示例：

ds = DataStore.from_file("employees.csv")

# 单列升序
result = ds.sort('name')

# 单列降序
result = ds.sort('salary', ascending=False)

# 多列
result = ds.sort('department', 'salary')

# 混合排序（ascending 参数使用列表）
result = ds.sort('department', 'salary', ascending=[True, False])

# Pandas 风格
result = ds.sort_values('salary', ascending=False)
result = ds.sort_values(['department', 'salary'], ascending=[True, False])

---

​

限制与分页

​

limit

限制返回结果的行数。

limit(n: int) -> DataStore

​

offset

跳过前 n 行。

offset(n: int) -> DataStore

示例：

ds = DataStore.from_file("employees.csv")

# 前 10 行
result = ds.limit(10)

# 跳过前 100 行，取接下来的 50 行
result = ds.offset(100).limit(50)

# Pandas 风格
result = ds.head(10)
result = ds.tail(10)
result = ds.iloc[100:150]

---

​

DISTINCT

​

distinct

去除重复行。

distinct(subset=None, keep='first') -> DataStore

示例：

from pathlib import Path
Path("events.csv").write_text("""\
user_id,event_type,timestamp
1,click,2024-01-15 10:30:00
2,view,2024-01-15 11:00:00
1,purchase,2024-01-15 11:30:00
3,click,2024-01-16 09:00:00
2,click,2024-01-16 10:00:00
""")

ds = DataStore.from_file("events.csv")

# 删除所有重复行
result = ds.distinct()

# 根据特定列删除重复项
result = ds.distinct(subset=['user_id', 'event_type'])

# Pandas 风格
result = ds.drop_duplicates()
result = ds.drop_duplicates(subset=['user_id'])

---

​

分组

​

groupby

按一个或多个列对行分组。返回一个 LazyGroupBy 对象。

groupby(*fields, sort=True, as_index=True, dropna=True) -> LazyGroupBy

示例：

from pathlib import Path
Path("sales.csv").write_text("""\
region,product,category,amount,quantity,price,date,order_id
East,Widget,Electronics,5200,10,120,2024-01-15,1001
West,Gadget,Electronics,800,5,160,2024-02-20,1002
East,Gizmo,Home,6500,3,100,2024-03-10,1003
North,Widget,Electronics,4500,6,150,2024-06-18,1004
West,Gadget,Electronics,2000,8,250,2024-09-14,1005
""")

ds = DataStore.from_file("sales.csv")

# 按单列分组
by_region = ds.groupby('region')

# 按多列分组
by_region_product = ds.groupby('region', 'product')

# groupby 后聚合
result = ds.groupby('region')['amount'].sum()
result = ds.groupby('region').agg({'amount': 'sum', 'quantity': 'mean'})

# 多重聚合
result = ds.groupby('category').agg({
    'price': ['min', 'max', 'mean'],
    'quantity': 'sum'
})

# 命名聚合
result = ds.groupby('region').agg(
    total_amount=('amount', 'sum'),
    avg_quantity=('quantity', 'mean'),
    order_count=('order_id', 'count')
)

​

having

对聚合后的分组进行过滤。

having(condition: Union[Condition, str]) -> DataStore

示例：

# 过滤 total > 10000 的分组
result = (ds
    .groupby('region')
    .agg({'amount': 'sum'})
    .having(ds['sum'] > 10000)
)

# 使用 SQL 风格的 having
result = (ds
    .select('region', 'SUM(amount) as total')
    .groupby('region')
    .having('total > 10000')
)

---

​

连接

​

join

连接两个 DataStore。

join(right, on=None, how='inner', left_on=None, right_on=None) -> DataStore

参数：

参数	类型	默认值	描述
right	DataStore	必填	要连接的右侧 DataStore
on	str/list	None	用于连接的列
how	str	'inner'	连接类型：‘inner’、‘left’、‘right’、‘outer’
left_on	str/list	None	左侧用于连接的列
right_on	str/list	None	右侧用于连接的列

示例：

from pathlib import Path
Path("departments.csv").write_text("""\
dept_id,department_name
1,Engineering
2,Product
3,Design
""")

employees = DataStore.from_file("employees.csv")
departments = DataStore.from_file("departments.csv")

# 单列内连接
result = employees.join(departments, on='dept_id')

# 左连接
result = employees.join(departments, on='dept_id', how='left')

# 使用不同列名进行连接
result = employees.join(
    departments,
    left_on='department_id',
    right_on='id',
    how='inner'
)

# Pandas 风格的合并
from chdb import datastore as pd
result = pd.merge(employees, departments, on='dept_id')
result = pd.merge(employees, departments, left_on='department_id', right_on='id')

​

union

将两个 DataStore 的结果合并。

union(other, all=False) -> DataStore

示例：

from pathlib import Path
Path("sales_2023.csv").write_text("""\
region,product,amount,date
East,Widget,1200,2023-06-15
West,Gadget,800,2023-09-20
North,Gizmo,600,2023-11-10
""")
Path("sales_2024.csv").write_text("""\
region,product,amount,date
East,Widget,1500,2024-03-10
North,Gizmo,900,2024-07-22
West,Gadget,1100,2024-05-05
""")

ds1 = DataStore.from_file("sales_2023.csv")
ds2 = DataStore.from_file("sales_2024.csv")

# UNION（去除重复项）
result = ds1.union(ds2)

# UNION ALL（保留重复项）
result = ds1.union(ds2, all=True)

# Pandas 风格
from chdb import datastore as pd
result = pd.concat([ds1, ds2])

---

​

条件表达式

​

when

创建 CASE WHEN 表达式。

when(condition, value) -> CaseWhenBuilder

示例：

ds = DataStore.from_file("employees.csv")

# 简单的 case-when
result = ds.select(
    'name',
    ds.when(ds['salary'] > 100000, 'High')
      .when(ds['salary'] > 50000, 'Medium')
      .otherwise('Low')
      .as_('salary_tier')
)

# 带列赋值
ds['salary_tier'] = (
    ds.when(ds['salary'] > 100000, 'High')
      .when(ds['salary'] > 50000, 'Medium')
      .otherwise('Low')
)

---

​

原生 SQL

​

run_sql / sql

执行原生 SQL 查询。

run_sql(query: str) -> DataStore
sql(query: str) -> DataStore  # 别名

示例：

from chdb.datastore import DataStore

# 执行原生 SQL
result = DataStore().sql("""
    SELECT 
        department,
        COUNT(*) as count,
        AVG(salary) as avg_salary
    FROM file('employees.csv', 'CSVWithNames')
    WHERE status = 'active'
    GROUP BY department
    HAVING count > 5
    ORDER BY avg_salary DESC
    LIMIT 10
""")

# 在已有 DataStore 上执行 SQL
ds = DataStore.from_file("employees.csv")
result = ds.sql("SELECT * FROM __table__ WHERE age > 30")

​

to_sql

查看生成的 SQL，但不执行。

to_sql(**kwargs) -> str

示例：

ds = DataStore.from_file("employees.csv")

query = (ds
    .filter(ds['age'] > 30)
    .groupby('department')
    .agg({'salary': 'mean'})
    .sort('mean', ascending=False)
)

print(query.to_sql())
# 输出：
# SELECT department, AVG(salary) AS mean
# FROM file('employees.csv', 'CSVWithNames')
# WHERE age > 30
# GROUP BY department
# ORDER BY mean DESC

---

​

方法链式调用

所有查询方法都支持链式调用：

from chdb.datastore import DataStore

ds = DataStore.from_file("sales.csv")

result = (ds
    .select('region', 'product', 'amount', 'date')
    .filter(ds['date'] >= '2024-01-01')
    .filter(ds['amount'] > 100)
    .groupby('region', 'product')
    .agg({
        'amount': ['sum', 'mean'],
        'date': 'count'
    })
    .having(ds['sum'] > 10000)
    .sort('sum', ascending=False)
    .limit(20)
)

# 查看 SQL
print(result.to_sql())

# 执行
df = result.to_df()

---

​

别名

​

as_

为列或子查询指定别名。

as_(alias: str) -> DataStore

示例：

# 列别名
result = ds.select(
    ds['name'].as_('employee_name'),
    (ds['salary'] * 12).as_('annual_salary')
)

# 子查询别名
subquery = ds.filter(ds['age'] > 30).as_('senior_employees')