Справочник по классам DataStore

from chdb.datastore import DataStore

DataStore(data=None, columns=None, index=None, dtype=None, copy=None)

# From dictionary
ds = DataStore({'a': [1, 2, 3], 'b': ['x', 'y', 'z']})

# From pandas DataFrame
import pandas as pd
ds = DataStore(pd.DataFrame({'a': [1, 2, 3]}))

# Empty DataStore
ds = DataStore()

# ColumnExpr is returned automatically
col = ds['name']  # Returns ColumnExpr

ds['total'] = ds['price'] * ds['quantity']
ds['profit'] = ds['revenue'] - ds['cost']
ds['ratio'] = ds['a'] / ds['b']
ds['squared'] = ds['value'] ** 2
ds['remainder'] = ds['value'] % 10

ds[ds['age'] > 25]           # Greater than
ds[ds['age'] >= 25]          # Greater or equal
ds[ds['age'] < 25]           # Less than
ds[ds['age'] <= 25]          # Less or equal
ds[ds['name'] == 'Alice']    # Equal
ds[ds['name'] != 'Bob']      # Not equal

ds[(ds['age'] > 25) & (ds['city'] == 'NYC')]    # AND
ds[(ds['age'] > 25) | (ds['city'] == 'NYC')]    # OR
ds[~(ds['status'] == 'inactive')]               # NOT

# LazyGroupBy is returned automatically
grouped = ds.groupby('category')  # Returns LazyGroupBy

# Select column after groupby
grouped['amount'].sum()     # Returns DataStore
grouped[['a', 'b']].sum()   # Returns DataStore

# Single aggregation
grouped.agg({'amount': 'sum'})

# Multiple aggregations per column
grouped.agg({'amount': ['sum', 'mean', 'count']})

# Named aggregations
grouped.agg(
    total=('amount', 'sum'),
    average=('amount', 'mean'),
    count=('id', 'count')
)

from chdb.datastore import F, Field

# Aggregations
F.sum(Field('amount'))
F.avg(Field('price'))
F.count(Field('id'))
F.quantile(Field('value'), 0.95)

# Conditional
F.sum_if(Field('amount'), Field('status') == 'completed')
F.count_if(Field('active'))

# Window
F.row_number().over(order_by='date')
F.lag('price', 1).over(partition_by='product', order_by='date')

from chdb.datastore import Field

# Create field reference
amount = Field('amount')
price = Field('price')

# Use in expressions
F.sum(Field('amount'))
F.avg(Field('price'))

# Create case-when expression
result = (ds
    .when(ds['score'] >= 90, 'A')
    .when(ds['score'] >= 80, 'B')
    .when(ds['score'] >= 70, 'C')
    .otherwise('F')
)

# Assign to column
ds['grade'] = result

from chdb.datastore import F

# Create window
window = F.window(
    partition_by='category',
    order_by='date',
    rows_between=(-7, 0)
)

# Use with aggregation
ds['rolling_avg'] = F.avg('price').over(window)