Construcción de consultas con DataStore

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

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,alice@company.com,3,5000
Bob,35,LA,85000,Engineering,1,active,bob@company.com,3,
Charlie,52,NYC,95000,Product,2,active,charlie@company.com,,10000
Diana,32,SF,70000,Design,3,active,diana@company.com,3,3000
Eve,23,LA,48000,Product,2,inactive,eve@company.com,2,
""")

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

# Seleccionar por nombres de columna
result = ds.select('name', 'age', 'salary')

# Seleccionar todas las columnas
result = ds.select('*')

# Seleccionar con expresiones
result = ds.select(
    'name',
    (ds['salary'] * 12).as_('annual_salary'),
    ds['age'].as_('employee_age')
)

# Estilo equivalente en pandas
result = ds[['name', 'age', 'salary']]

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

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

# Condición única
result = ds.filter(ds['age'] > 30)
result = ds.where(ds['salary'] >= 50000)

# Múltiples condiciones (AND)
result = ds.filter((ds['age'] > 30) & (ds['department'] == 'Engineering'))

# Múltiples condiciones (OR)
result = ds.filter((ds['city'] == 'NYC') | (ds['city'] == 'LA'))

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

# Condiciones de cadena de texto
result = ds.filter(ds['name'].str.contains('John'))
result = ds.filter(ds['email'].str.endswith('@company.com'))

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

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

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

# Filtros encadenados (AND)
result = (ds
    .filter(ds['age'] > 25)
    .filter(ds['salary'] > 50000)
    .filter(ds['city'] == 'NYC')
)

# Indexación booleana (equivalente a filter)
result = ds[ds['age'] > 30]
result = ds[(ds['age'] > 30) & (ds['salary'] > 50000)]

# Método query
result = ds.query('age > 30 and salary > 50000')

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

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

# Columna única ascendente
result = ds.sort('name')

# Columna única descendente
result = ds.sort('salary', ascending=False)

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

# Orden mixto (usar lista para el parámetro ascending)
result = ds.sort('department', 'salary', ascending=[True, False])

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

limit(n: int) -> DataStore

offset(n: int) -> DataStore

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

# Primeras 10 filas
result = ds.limit(10)

# Omitir las primeras 100, tomar las siguientes 50
result = ds.offset(100).limit(50)

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

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

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")

# Eliminar todas las filas duplicadas
result = ds.distinct()

# Eliminar duplicados basándose en columnas específicas
result = ds.distinct(subset=['user_id', 'event_type'])

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

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

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")

# Agrupar por una sola columna
by_region = ds.groupby('region')

# Agrupar por múltiples columnas
by_region_product = ds.groupby('region', 'product')

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

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

# Agregación con nombre
result = ds.groupby('region').agg(
    total_amount=('amount', 'sum'),
    avg_quantity=('quantity', 'mean'),
    order_count=('order_id', 'count')
)

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

# Filtrar grupos con total > 10000
result = (ds
    .groupby('region')
    .agg({'amount': 'sum'})
    .having(ds['sum'] > 10000)
)

# Usando having al estilo SQL
result = (ds
    .select('region', 'SUM(amount) as total')
    .groupby('region')
    .having('total > 10000')
)

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

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")

# Inner join en una sola columna
result = employees.join(departments, on='dept_id')

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

# Join con nombres de columna distintos
result = employees.join(
    departments,
    left_on='department_id',
    right_on='id',
    how='inner'
)

# Merge al estilo Pandas
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(other, all=False) -> DataStore

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 (elimina duplicados)
result = ds1.union(ds2)

# UNION ALL (conserva duplicados)
result = ds1.union(ds2, all=True)

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

when(condition, value) -> CaseWhenBuilder

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

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

# Con asignación de columna
ds['salary_tier'] = (
    ds.when(ds['salary'] > 100000, 'High')
      .when(ds['salary'] > 50000, 'Medium')
      .otherwise('Low')
)

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

from chdb.datastore import DataStore

# Ejecutar Raw 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
""")

# SQL sobre un DataStore existente
ds = DataStore.from_file("employees.csv")
result = ds.sql("SELECT * FROM __table__ WHERE age > 30")

to_sql(**kwargs) -> str

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

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)
)

# Ver SQL
print(result.to_sql())

# Ejecutar
df = result.to_df()

as_(alias: str) -> DataStore

# Alias de columna
result = ds.select(
    ds['name'].as_('employee_name'),
    (ds['salary'] * 12).as_('annual_salary')
)

# Alias de subconsulta
subquery = ds.filter(ds['age'] > 30).as_('senior_employees')