Метод explain()

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
""")

from chdb import datastore as pd

ds = pd.read_csv("sales.csv")

query = (ds
    .filter(ds['amount'] > 1000)
    .groupby('region')
    .agg({'amount': ['sum', 'mean']})
    .sort('sum', ascending=False)
)

# Просмотр плана выполнения
query.explain()

explain(verbose=False) -> None

================================================================================
Execution Plan (in execution order)
================================================================================

 [1] 📊 Data Source: file('sales.csv', 'csv')

Operations:
────────────────────────────────────────────────────────────────────────────────
    ️  Segment 1 [chDB] (from source): Operations 2-5
    ️  Note: SQL operations after Pandas ops use Python() table function

 [2] 🚀 [chDB] WHERE: "amount" > 1000
 [3] 🚀 [chDB] GROUP BY: region
 [4] 🚀 [chDB] AGGREGATE: sum(amount), avg(amount)
 [5] 🚀 [chDB] ORDER BY: sum DESC

────────────────────────────────────────────────────────────────────────────────
Final State: 📊 Pending (lazy, not yet executed)
             └─> Will execute when print(), .to_df(), .execute() is called

────────────────────────────────────────────────────────────────────────────────
Generated SQL Query:
────────────────────────────────────────────────────────────────────────────────

SELECT region, SUM(amount) AS sum, AVG(amount) AS mean
FROM file('sales.csv', 'csv')
WHERE "amount" > 1000
GROUP BY region
ORDER BY sum DESC

================================================================================

query.explain(verbose=True)

  1. Source: file('sales.csv', 'CSVWithNames')
  2. Filter: amount > 1000      
  3. GroupBy: region
  4. Aggregate: sum(amount)

  5. Execute SQL -> DataFrame
     Trigger: to_df() called

  6. [pandas] pivot_table(...)
  7. [pandas] apply(custom_func)

Source: file('sales.csv', 'CSVWithNames')

Source: s3('bucket/data.parquet', ...)
Source: mysql('host', 'db', 'table', ...)
Source: __dataframe__  (pandas DataFrame input)

Filter: amount > 1000 AND status = 'active'

GroupBy: region, category
Aggregate: sum(amount), avg(amount), count(id)

Sort: sum DESC, region ASC

Limit: 10
Offset: 100

Filter: amount > 1000
  - Engine: chdb
  - Pushdown: Yes

Apply: custom_function
  - Engine: pandas
  - Pushdown: No

from pathlib import Path
Path("data.csv").write_text("""\
name,age,city,salary,department
Alice,25,NYC,55000,Engineering
Bob,30,LA,65000,Product
Charlie,35,NYC,80000,Engineering
Diana,28,SF,70000,Design
Eve,42,NYC,95000,Product
""")

ds = pd.read_csv("data.csv")
ds.filter(ds['age'] > 25).explain()

================================================================================
Execution Plan (in execution order)
================================================================================

 [1] 📊 Data Source: file('data.csv', 'csv')

Operations:
────────────────────────────────────────────────────────────────────────────────
    ️  Segment 1 [chDB] (from source): Operations 2-2

 [2] 🚀 [chDB] WHERE: "age" > 25

────────────────────────────────────────────────────────────────────────────────
Generated SQL Query:
────────────────────────────────────────────────────────────────────────────────

SELECT * FROM file('data.csv', 'csv') WHERE "age" > 25

================================================================================

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

================================================================================
Execution Plan (in execution order)
================================================================================

 [1] 📊 Data Source: file('sales.csv', 'csv')

Operations:
────────────────────────────────────────────────────────────────────────────────
    ️  Segment 1 [chDB] (from source): Operations 2-8

 [2] 🚀 [chDB] WHERE: "date" >= '2024-01-01'
 [3] 🚀 [chDB] WHERE: "amount" > 100
 [4] 🚀 [chDB] SELECT: region, category, amount
 [5] 🚀 [chDB] GROUP BY: region, category
 [6] 🚀 [chDB] AGGREGATE: sum(amount), avg(amount), count(amount)
 [7] 🚀 [chDB] ORDER BY: sum DESC
 [8] 🚀 [chDB] LIMIT: 20

────────────────────────────────────────────────────────────────────────────────
Generated SQL Query:
────────────────────────────────────────────────────────────────────────────────

SELECT region, category, 
       SUM(amount) AS sum, 
       AVG(amount) AS mean, 
       COUNT(amount) AS count
FROM file('sales.csv', 'csv')
WHERE "date" >= '2024-01-01' AND "amount" > 100
GROUP BY region, category
ORDER BY sum DESC
LIMIT 20

================================================================================

query = (ds
    .filter(ds['age'] > 25)           # SQL
    .groupby('city')                   # SQL
    .agg({'salary': 'mean'})           # SQL
    .apply(lambda x: x * 1.1)          # pandas (вызывает разбиение на сегменты)
    .filter(ds['mean'] > 50000)        # SQL (новый сегмент)
)
query.explain()

================================================================================
Execution Plan (в порядке исполнения)
================================================================================

 [1] 📊 Data Source: file('data.csv', 'csv')

Operations:
────────────────────────────────────────────────────────────────────────────────
    ️  Segment 1 [chDB] (из источника): Операции 2–4
    ️  Segment 2 [Pandas] (на DataFrame): Операция 5
    ️  Segment 3 [chDB] (на DataFrame): Операция 6
    ️  Note: SQL-операции после операций Pandas используют табличную функцию Python()

 [2] 🚀 [chDB] WHERE: "age" > 25
 [3] 🚀 [chDB] GROUP BY: city
 [4] 🚀 [chDB] AGGREGATE: avg(salary)
 [5] 🐼 [Pandas] APPLY: lambda
 [6] 🚀 [chDB] WHERE: "mean" > 50000

================================================================================

# Проверьте правильность фильтра
query = ds.filter((ds['age'] > 25) & (ds['city'] == 'NYC'))
query.explain()
# Вывод: Filter: age > 25 AND city = 'NYC'

# Проверка отсечения столбцов
query = ds.select('name', 'age').filter(ds['age'] > 25)
query.explain()
# Вывод: SELECT name, age FROM ... WHERE age > 25

# Проверка функций агрегации
query = ds.groupby('dept').agg({'salary': ['sum', 'mean', 'std']})
query.explain()
# Вывод: SELECT dept, SUM(salary), AVG(salary), stddevPop(salary)

# Всегда сначала используйте explain для больших данных
query = ds.complex_pipeline()
query.explain()  # Проверить план

# Если план выглядит корректным
result = query.to_df()  # Выполнить

# Когда что-то идёт не так
query.explain(verbose=True)
# Показывает выбор движка и информацию о pushdown

# explain() показывает план
query.explain()

# to_sql() показывает только SQL
print(query.to_sql())

# Оба метода полезны для разных целей

# Подробный режим показывает, выполняется ли pushdown операций
query.explain(verbose=True)

# Если Pushdown: No, операция выполняется в pandas
# Рассмотрите возможность переструктурирования запроса для повышения производительности