python:基于索引事件将时间间隔数据排序为两天的chuck

您可以使用:

# Compute the delta
days = df['date_medication'].sub(df['index_date']).dt.days

# Create desired bins and labels
bins = np.arange(days.min() - days.min() % 2, days.max() + days.max() % 2 + 1, 2)
lbls = bins[bins != 0]  # Exclude 0
df['interval'] = pd.cut(days, bins, labels=lbls, include_lowest=True, right=False)

# Reshape your dataframe
out = (df.pivot(index='id', columns='interval', values='medication')
         .reindex(bins, fill_value='IE', axis=1).fillna(0)
         .rename_axis(columns=None).reset_index())

输出:

>>> out
   id -4 -2   0  2  4  6
0   1  A  A  IE  B  B  0
1   2  A  B  IE  A  0  B

使用:

#convert columns to datetimes
df['date_medication'] = pd.to_datetime(df['date_medication'])
df['index_date'] = pd.to_datetime(df['index_date'])

#get 2 days chunks
s = df['date_medication'].sub(df['index_date']).dt.days // 2 * 2
#add 2 days for greater/equal values 0 
s.loc[s.ge(0)] += 2

#pivoting columns
df1 = df.assign(g = s).pivot(index='id', columns='g', values='medication')
#added 0 column
df1.loc[:, 0] = 'IE'
#added 0 column
df1 = (df1.rename_axis(columns=None)
         .reindex(columns=range(df1.columns.min(), df1.columns.max() + 2, 2), fill_value=0)
         .fillna(0)
         .reset_index())
   id -4 -2   0  2  4  6
0   1  A  A  IE  B  B  0
1   2  A  B  IE  A  0  B

细节 :

print (s)
0   -4
1   -2
2    2
3    4
4   -4
5   -2
6    2
7    6
dtype: int64