Use:
#convert columns to datetimes
df["Start"] = pd.to_datetime(df["Start"])
df["End"] = pd.to_datetime(df["End"])
#subtract values and convert to days
s = df["End"].sub(df["Start"]).dt.days
#repeat index
df = df.loc[df.index.repeat(s)].copy()
#add days by timedeltas, add 1 day for End column
add = pd.to_timedelta(df.groupby(level=0).cumcount(), unit='d')
df['Start'] = df["Start"].add(add)
df['End'] = df["Start"] + pd.Timedelta(1, 'd')
#default index
df = df.reset_index(drop=True)
print (df)
A B Start End
0 A1 B1 2021-05-15 2021-05-16
1 A1 B1 2021-05-16 2021-05-17
2 A1 B2 2021-05-30 2021-05-31
3 A1 B2 2021-05-31 2021-06-01
4 A1 B2 2021-06-01 2021-06-02
5 A2 B3 2021-05-10 2021-05-11
6 A2 B3 2021-05-11 2021-05-12
7 A2 B4 2021-06-02 2021-06-03
8 A2 B4 2021-06-03 2021-06-04
Performance:
#4k rows
df = pd.concat([df] * 1000, ignore_index=True)
In [136]: %timeit jez(df)
16.9 ms ± 3.94 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
In [137]: %timeit andreas(df)
888 ms ± 136 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
#800 rows
df = pd.concat([df] * 200, ignore_index=True)
In [139]: %timeit jez(df)
6.25 ms ± 46.3 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
In [140]: %timeit andreas(df)
170 ms ± 28.1 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
def andreas(df):
df['d_range'] = df.apply(lambda row: list(pd.date_range(start=row['Start'], end=row['End'])), axis=1)
return df.explode('d_range')
def jez(df):
df["Start"] = pd.to_datetime(df["Start"])
df["End"] = pd.to_datetime(df["End"])
#subtract values and convert to days
s = df["End"].sub(df["Start"]).dt.days
#repeat index
df = df.loc[df.index.repeat(s)].copy()
#add days by timedeltas, add 1 day for End column
add = pd.to_timedelta(df.groupby(level=0).cumcount(), unit='d')
df['Start'] = df["Start"].add(add)
df['End'] = df["Start"] + pd.Timedelta(1, 'd')
#default index
return df.reset_index(drop=True)
