Description
Pandas version checks
-
I have checked that this issue has not already been reported.
-
I have confirmed this issue exists on the latest version of pandas.
-
I have confirmed this issue exists on the main branch of pandas.
Reproducible Example
See test below where we see that agg operation min (same for other aggregation functions mean, max, first, last ...) on Timestamp[pyArrow] is extremely slow.
import timeit
import numpy as np
import pandas as pd
import pyarrow as pa
def create_sample_dataframe(rows=2000, columns=5):
data = {
'int_col1': np.random.randint(1, 10000000, size=rows),
'int_col2': np.random.randint(1, 10000000, size=rows),
'int_col3': np.random.randint(1, 10000000, size=rows),
'int_col4': np.random.randint(1, 10000000, size=rows),
'start_time': pd.to_datetime(np.random.randint(1_000_000_000, 2_000_000_000, size=rows), unit='s')
}
return pd.DataFrame(data)
# Function to perform aggregation and measure execution time
def measure_execution_time(df, use_pyarrow=False):
if use_pyarrow:
# Convert the 'start_time' column to Timestamp[pyArrow]
df['start_time'] = df['start_time'].astype(pd.ArrowDtype(pa.timestamp(unit="ns")))
else:
# Convert the 'start_time' column to Timestamp[pandas]
df['start_time'] = pd.to_datetime(df['start_time'], unit='ns')
# Group by four int64 columns and aggregate the 'start_time' column using min
start_time = timeit.default_timer()
result = df.groupby(['int_col1', 'int_col2', 'int_col3', 'int_col4'])['start_time'].min()
end_time = timeit.default_timer()
return end_time - start_time
# Create a sample dataframe
df = create_sample_dataframe(100000)
# In the case of datetime64[ns] dtype:
print(measure_execution_time(df, use_pyarrow=False))
# 0.1226182999998855 sec
# In the case of timestamp[ns][pyarrow] dtype
print(measure_execution_time(df, use_pyarrow=True))
# 8.103240000000369 sec
Installed Versions
INSTALLED VERSIONS
commit : ba1cccd
python : 3.10.12.final.0
python-bits : 64
OS : Linux
OS-release : 5.15.90.1-microsoft-standard-WSL2
Version : #1 SMP Fri Jan 27 02:56:13 UTC 2023
machine : x86_64
processor : x86_64
byteorder : little
LC_ALL : None
LANG : C.UTF-8
LOCALE : en_US.UTF-8
pandas : 2.1.0
numpy : 1.24.3
pytz : 2022.7
dateutil : 2.8.2
setuptools : 68.0.0
pip : 23.2.1
Cython : None
pytest : 7.4.0
hypothesis : 6.82.0
sphinx : None
blosc : None
feather : None
xlsxwriter : None
lxml.etree : 4.9.2
html5lib : None
pymysql : None
psycopg2 : 2.8.6
jinja2 : 3.1.2
IPython : 8.12.2
pandas_datareader : None
bs4 : None
bottleneck : 1.3.5
dataframe-api-compat: None
fastparquet : None
fsspec : 2023.4.0
gcsfs : 2023.4.0
matplotlib : None
numba : 0.57.1
numexpr : 2.8.4
odfpy : None
openpyxl : 3.1.2
pandas_gbq : None
pyarrow : 12.0.1
pyreadstat : None
pyxlsb : None
s3fs : None
scipy : None
sqlalchemy : 1.4.39
tables : None
tabulate : None
xarray : None
xlrd : 2.0.1
zstandard : None
tzdata : 2023.3
qtpy : None
pyqt5 : None
None
Prior Performance
No response