性能模式 (compat_mode)

from chdb.datastore.config import config

# Enable performance mode
config.use_performance_mode()

# Back to pandas compatibility
config.use_pandas_compat()

# Check current mode
print(config.compat_mode)  # 'pandas' or 'performance'

from chdb.datastore.config import set_compat_mode, CompatMode, is_performance_mode

# Enable performance mode
set_compat_mode(CompatMode.PERFORMANCE)

# Check
print(is_performance_mode())  # True

# Back to default
set_compat_mode(CompatMode.PANDAS)

from chdb import use_performance_mode, use_pandas_compat

use_performance_mode()
# ... high-performance operations ...
use_pandas_compat()

config.use_performance_mode()

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

# Unordered (fast)
result = ds.groupby("region")["revenue"].sum()

# Ordered (still fast, just adds ORDER BY)
result = ds.groupby("region")["revenue"].sum().sort_values()

config.use_performance_mode()

# Sum of all-NaN group returns NULL (not 0)
# Count returns native uint64 (not forced int64)
# No -If wrappers: sum() instead of sumIf()
result = ds.groupby("cat")["val"].sum()

config.use_performance_mode()

# Pandas mode: two SQL queries (filter → materialize → groupby)
# Performance mode: one SQL query (WHERE + GROUP BY in same query)
result = ds[ds["rating"] > 3.5].groupby("category")["revenue"].sum()

# Generated SQL (single query):
# SELECT category, sum(revenue) FROM data WHERE rating > 3.5 GROUP BY category

from chdb.datastore.config import config

# These are independent
config.use_chdb()              # Force chDB engine, keep pandas compat
config.use_performance_mode()  # Force chDB + remove pandas overhead

# Sort both sides by the same columns before comparing
ds_result = ds.groupby("cat")["val"].sum()
pd_result = pd_df.groupby("cat")["val"].sum()

ds_sorted = ds_result.sort_index()
pd_sorted = pd_result.sort_index()
np.testing.assert_array_equal(ds_sorted.values, pd_sorted.values)

# first() with any() returns an arbitrary element from the group
result = ds.groupby("cat")["val"].first()
for group_key in groups:
    assert result.loc[group_key] in group_values[group_key]

# head() without sort_values: row set is non-deterministic
result = ds.head(5)
assert len(result) == 5
assert set(result.columns) == expected_columns

from chdb.datastore.config import config

config.use_performance_mode()

# All subsequent operations benefit
ds = pd.read_parquet("data.parquet")
result = ds[ds["amount"] > 100].groupby("region")["amount"].sum()

# For display or downstream processing that expects order
result = (ds
    .groupby("region")["revenue"].sum()
    .sort_values(ascending=False)
)

config.use_performance_mode()

# ETL pipeline — order doesn't matter, throughput does
summary = (ds
    .filter(ds["date"] >= "2024-01-01")
    .groupby(["region", "product"])
    .agg({"revenue": "sum", "quantity": "sum", "rating": "mean"})
)
summary.to_df().to_parquet("summary.parquet")

# Performance mode for heavy computation
config.use_performance_mode()
aggregated = ds.groupby("cat")["val"].sum()

# Back to pandas mode for exact-match comparison
config.use_pandas_compat()
detailed = ds[ds["val"] > 100].head(10)