Thanks to visit codestin.com
Credit goes to github.com

Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions bigframes/dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -1086,19 +1086,19 @@ def head(self, n: int = 5) -> DataFrame:
def tail(self, n: int = 5) -> DataFrame:
return typing.cast(DataFrame, self.iloc[-n:])

def peek(self, n: int = 5, *, force: bool = False) -> pandas.DataFrame:
def peek(self, n: int = 5, *, force: bool = True) -> pandas.DataFrame:
"""
Preview n arbitrary rows from the dataframe. No guarantees about row selection or ordering.
DataFrame.peek(force=False) will always be very fast, but will not succeed if data requires
full data scanning. Using force=True will always succeed, but may be perform expensive
computations.
``DataFrame.peek(force=False)`` will always be very fast, but will not succeed if data requires
full data scanning. Using ``force=True`` will always succeed, but may be perform queries.
Query results will be cached so that future steps will benefit from these queries.

Args:
n (int, default 5):
The number of rows to select from the dataframe. Which N rows are returned is non-deterministic.
force (bool, default False):
force (bool, default True):
If the data cannot be peeked efficiently, the dataframe will instead be fully materialized as part
of the operation if force=True. If force=False, the operation will throw a ValueError.
of the operation if ``force=True``. If ``force=False``, the operation will throw a ValueError.
Returns:
pandas.DataFrame: A pandas DataFrame with n rows.

Expand Down
8 changes: 4 additions & 4 deletions tests/system/small/test_dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -429,14 +429,14 @@ def test_rename(scalars_dfs):

def test_df_peek(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
peek_result = scalars_df.peek(n=3)
peek_result = scalars_df.peek(n=3, force=False)
pd.testing.assert_index_equal(scalars_pandas_df.columns, peek_result.columns)
assert len(peek_result) == 3


def test_df_peek_filtered(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
peek_result = scalars_df[scalars_df.int64_col != 0].peek(n=3)
peek_result = scalars_df[scalars_df.int64_col != 0].peek(n=3, force=False)
pd.testing.assert_index_equal(scalars_pandas_df.columns, peek_result.columns)
assert len(peek_result) == 3

Expand All @@ -449,9 +449,9 @@ def test_df_peek_exception(scalars_dfs):
scalars_df[["int64_col", "int64_too"]].cumsum().peek(n=3, force=False)


def test_df_peek_force(scalars_dfs):
def test_df_peek_force_default(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
peek_result = scalars_df[["int64_col", "int64_too"]].cumsum().peek(n=3, force=True)
peek_result = scalars_df[["int64_col", "int64_too"]].cumsum().peek(n=3)
pd.testing.assert_index_equal(
scalars_pandas_df[["int64_col", "int64_too"]].columns, peek_result.columns
)
Expand Down