Certainly! You can achieve this using the dt accessor in pandas, which allows you to access the datetime components of a Series. Here’s an example:

Assuming your DataFrame df has a datetime index, you can create new binary columns for each day of the week as follows:

import pandas as pd

# Assuming df has a datetime index
# If not, you can convert the index to datetime using df.index = pd.to_datetime(df.index)
# df.index = pd.to_datetime(df.index)

# Create binary columns for each day of the week
df['Monday'] = (df.index.dayofweek == 0).astype(int)
df['Tuesday'] = (df.index.dayofweek == 1).astype(int)
df['Wednesday'] = (df.index.dayofweek == 2).astype(int)
df['Thursday'] = (df.index.dayofweek == 3).astype(int)
df['Friday'] = (df.index.dayofweek == 4).astype(int)
df['Saturday'] = (df.index.dayofweek == 5).astype(int)
df['Sunday'] = (df.index.dayofweek == 6).astype(int)

This code uses the dayofweek property of the datetime index, which returns the day of the week where Monday is 0 and Sunday is 6. It then compares this with the day number corresponding to each day of the week, and the result is converted to binary using astype(int).

This should give you a DataFrame with new binary columns indicating the day of the week for each datetime index.