Creating pandas columns with for loop - pandas

Question

I have the following dataframe created through the following chunk of code:
df = pd.DataFrame(
[
(13412339, '07/03/2022', '08/03/2022', '10/03/2022', 1),
(13412343, '07/03/2022', '07/03/2022', '09/03/2022', 0),
(13412489, '07/02/2022', '08/02/2022', '07/03/2022', 0),
],
columns=['task_id', 'start_date', 'end_date', 'end_period', 'status']
)
df = df.astype(dtype={'status' : bool})
df.start_date = pd.to_datetime(df.start_date)
df.end_date = pd.to_datetime(df.end_date)
df.end_period = pd.to_datetime(df.end_period)
What I need to do here is to calculate the difference in days between the start_date and end_date columns if the status column is False, else it should do the same but between start_date and end_period columns.
The code that I have implemented to calculate the days differences between the start_date and end_date columns is as follows:
new_frame = pd.DataFrame()
for row in range(df.shape[0]):
#extract the row
extracted_row = df.loc[row,:]
#Calculates the date difference in days for each row in the loop
diff = extracted_row['end_date'] - extracted_row['start_date']
diff_days = diff.days
#Iterate over these date differences and repeat the row for each full day
for i in range(diff_days+1):
new_row = extracted_row.copy()
new_row['date'] = new_row['start_date'] + dt.timedelta(days=i)
new_row = new_row[['task_id','start_date','end_date',
'end_period','date','status']]
#appends the rows created to new dataframe
new_frame = new_frame.append(new_row)
#Rearranges columns in the desired order
new_frame = new_frame[['task_id','start_date','end_date','end_period','date','status']]
#Changes data types
new_frame = new_frame.astype(dtype={'task_id' : int,'status' : bool})
Then in order to calculate the differences if the status column is False, I did the following one:
new_frame1 = pd.DataFrame()
new_frame2 = pd.DataFrame()
for row in range(df.shape[0]):
#In this iteration, status column should be equals True
if df['status'] == False:
#extract the row
extracted_row_end = df.loc[row,:]
#Calculates the date difference in days for each row in the loop
diff1 = extracted_row_end['end_date'] - extracted_row_end['start_date']
diff_days_end = diff1.days
#Iterate over these date differences and repeat the row for each full day
for i in range(diff_days_end+1):
new_row_end = extracted_row_end.copy()
new_row_end['date'] = new_row_end['start_date'] + dt.timedelta(days=i)
new_row_end = new_row_end[['task_id','start_date','end_date',
'end_period','date','status']]
#appends the rows created to new dataframe
new_frame1 = new_frame1.append(new_row_end)
#Rearranges columns in the desired order
new_frame = new_frame[['task_id','start_date','end_date','end_period','date','status']]
#Changes data types
new_frame = new_frame.astype(dtype={'task_id' : int,'status' : bool})
#In this iteration, status column should be equals False
else:
#extract the row
extracted_row_period = df.loc[row,:]
#Calculates the date difference in days for each row in the loop
diff2 = extracted_row_period['end_period'] - extracted_row_period['start_date']
diff_days_period = diff2.days
#Iterate over these date differences and repeat the row for each full day
for i in range(diff_days_period+1):
new_row_period = extracted_row_end.copy()
new_row_period['date'] = new_row_period['start_date'] + dt.timedelta(days=i)
new_row_period = new_row_period[['task_id','start_date','end_date',
'end_period','date','status']]
#appends the rows created to new dataframe
new_frame2 = new_frame2.append(new_row_period)
#Rearranges columns in the desired order
new_frame = new_frame[['task_id','start_date','end_date','end_period','date','status']]
#Changes data types
new_frame = new_frame.astype(dtype={'task_id' : int,'status' : bool})
#Merges both dataframes
frames = [new_frame1,new_frame2]
df = pd.concat(frames)
Then it throws an error when starts the first for loop, here is where I should be asking help on how to calculate the difference in days between the start_date and end_date columns if the status column is False, else calculate it between start_date and end_period columns.
The complete error is as follows:

Answer 1

Some part of your code did not work on my machine (so I just took the initial df from your first cell) - but when reading what you need, this is what I would do
import numpy as np
df['dayDiff']=np.where(df['status'],(df['end_period']-df['start_date']).dt.days,(df['end_date']-df['start_date']).dt.days)
df
As you already have booleand on df['status'], I would use that to the np.where condition , then either calculate the day difference df['end_period']-df['start_date']).dt.days when True either day difference (df['end_date']-df['start_date']).dt.days when False