How to get minimum of each group for each day based on hour criteria

Question

I have given two dataframes below for you to test

df = pd.DataFrame({
    \'subject_id\':[1,1,1,1,1,1,1,1,1,1,1],
    \'time_1\' :[\'2173-04-03 12:35:00\',\'         


        

Answer 1

Try this.

from datetime import timedelta

def f(x):
    dif = (x.iloc[0]-x.iloc[-1])//timedelta(minutes=1)
    return dif
df1['time_1']= pd.to_datetime(df1['time_1'])
df1['flag']= df1.val.diff().ne(0).cumsum()
df1['t_d']=df1.groupby('flag')['time_1'].transform(f)
df1['date'] = df1['time_1'].dt.date
mask= df1['t_d'].ne(0)
dfa=df1[mask].groupby(['flag','date']).first().reset_index()
dfb=df1[~mask].groupby('date').first().reset_index().dropna(how='any')
df_f = dfa.merge(dfb, how='outer')
df_f.drop_duplicates(subset='date', keep='first', inplace=True)
df_f.drop(['flag','date','t_d'], axis=1, inplace=True)
df_f

Output.

 subject_id     time_1         val
0   1   2173-04-03 12:35:00     5
1   1   2173-04-04 11:30:00     5
2   1   2173-04-05 16:00:00     5
5   1   2173-04-06 04:00:00     3