Description
Pandas version checks
-
I have checked that this issue has not already been reported.
-
I have confirmed this bug exists on the latest version of pandas.
-
I have confirmed this bug exists on the main branch of pandas.
Reproducible Example
import pandas as pd
import numpy as np
import sys
# Create DataFrame with datetime index and multiple columns
# This reproduces the bug with ~6 years of hourly data (2033-2038)
np.random.seed(42)
date_range = pd.date_range('2033-01-01', '2038-12-31 23:00:00', freq='H')
n_cols = 40
data = np.random.rand(len(date_range), n_cols) * 0.1 # Values between 0 and 0.1
df = pd.DataFrame(data, index=date_range, columns=range(n_cols))
# Create a Series of ones with the same index
ones_series = pd.Series(1.0, index=df.index)
print(f"DataFrame shape: {df.shape}")
print(f"Memory usage (MB): {df.memory_usage(deep=True).sum() / 1024**2:.2f}")
print(f"Original data sample (should be > 0):")
print(df.iloc[32:37, 23]) # Show some sample values
# Perform the multiplication that causes corruption
print("\nPerforming multiplication...")
result = df.mul(ones_series, axis=0)
# Check for corruption
print(f"After multiplication (should be identical):")
print(result.iloc[32:37, 23])
# Verify corruption
are_equal = df.equals(result)
print(f"\nDataFrames equal: {are_equal}")
if not are_equal:
# Count corrupted values
diff_mask = df.values != result.values
n_corrupted = diff_mask.sum()
print(f"CORRUPTION DETECTED: {n_corrupted} values corrupted!")
# Show corruption details
corrupted_rows, corrupted_cols = np.where(diff_mask)
if len(corrupted_rows) > 0:
print(f"\nCorruption sample:")
for i in range(min(5, len(corrupted_rows))):
row, col = corrupted_rows[i], corrupted_cols[i]
original = df.iloc[row, col]
corrupted = result.iloc[row, col]
date = df.index[row]
print(f" {date}, Col {col}: {original:.4f} -> {corrupted:.4f}")
# Verify that corrupted values are zeros
corrupted_values = result.values[diff_mask]
all_zeros = np.all(corrupted_values == 0.0)
print(f"\nAre all corrupted values zero? {all_zeros}")
# Show which columns are affected
unique_affected_cols = np.unique(corrupted_cols)
print(f"Number of affected columns: {len(unique_affected_cols)}")
print(f"Affected columns: {unique_affected_cols}")
# Demonstrate that numpy approach works correctly
print(f"\nTesting numpy workaround...")
numpy_result = pd.DataFrame(
df.to_numpy() * ones_series.to_numpy()[:, None],
index=df.index,
columns=df.columns
)
numpy_works = df.equals(numpy_result)
print(f"Numpy approach works correctly: {numpy_works}")Issue Description
The DataFrame.mul() method is corrupting data by setting non-zero values to zero when multiplying a DataFrame with datetime index by a Series of ones. This occurs only under specific conditions related to DataFrame size and affects data integrity.
Expected Behavior
When multiplying a DataFrame by a Series of ones using df.mul(ones_series, axis=0), all original values should be preserved (multiplied by 1.0).
Installed Versions
INSTALLED VERSIONS
commit : 0691c5c
python : 3.11.11
python-bits : 64
OS : Windows
OS-release : 10
Version : 10.0.14393
machine : AMD64
processor : Intel64 Family 6 Model 85 Stepping 4, GenuineIntel
byteorder : little
LC_ALL : None
LANG : None
LOCALE : English_United States.1252
pandas : 2.2.3
numpy : 2.3.0
pytz : 2025.2
dateutil : 2.9.0.post0
pip : 24.3.1
Cython : None
sphinx : 8.1.3
IPython : 8.31.0
adbc-driver-postgresql: None
adbc-driver-sqlite : None
bs4 : 4.12.3
blosc : None
bottleneck : None
dataframe-api-compat : None
fastparquet : None
fsspec : None
html5lib : None
hypothesis : None
gcsfs : None
jinja2 : 3.1.5
lxml.etree : 5.3.0
matplotlib : 3.10.0
numba : None
numexpr : 2.10.2
odfpy : None
openpyxl : 3.1.5
pandas_gbq : None
psycopg2 : 2.9.9
pymysql : None
pyarrow : 18.1.0
pyreadstat : None
pytest : 8.3.4
python-calamine : None
pyxlsb : 1.0.10
s3fs : None
scipy : 1.15.2
sqlalchemy : 2.0.37
tables : 3.10.2
tabulate : None
xarray : 2025.1.1
xlrd : 2.0.1
xlsxwriter : 3.2.0
zstandard : 0.23.0
tzdata : 2025.2
qtpy : 2.4.3
pyqt5 : None