DataStore: واجهة برمجة تطبيقات متوافقة مع pandas مع تحسينات SQL

# Before (pandas)
import pandas as pd
df = pd.read_csv("data.csv")
result = df[df['age'] > 25].groupby('city')['salary'].mean()

# After (DataStore) - just change the import!
from chdb import datastore as pd
df = pd.read_csv("data.csv")
result = df[df['age'] > 25].groupby('city')['salary'].mean()

from chdb import datastore as pd

# Read data from various sources
ds = pd.read_csv("sales.csv")
# or: ds = pd.DataStore.uri("s3://bucket/sales.parquet")
# or: ds = pd.DataStore.from_mysql("mysql://user:pass@host/db/table")

# Familiar pandas operations - automatically optimized to SQL
result = (ds
    .filter(ds['amount'] > 1000)           # WHERE amount > 1000
    .groupby('region')                      # GROUP BY region
    .agg({'amount': ['sum', 'mean']})       # SUM(amount), AVG(amount)
    .sort_values('sum', ascending=False)    # ORDER BY sum DESC
    .head(10)                               # LIMIT 10
)

# View the generated SQL
print(result.to_sql())

# Execute and get results
df = result.to_df()  # Returns pandas DataFrame