Time series association analysis using pandas

Question

I have the below example dataframe of products purchased between 8AM and 6PM and I want to perform association analysis per hourly time interval.

date,08:00:00,09:00:00,10:00:00,11:00:00,12:00:00,13:00:00,14:00:00,15:00:00,16:00:00,17:00:00,18:00:00
2021-02-01,item2,item2,item2,item3,item1,item1,item1,item1,item1,item1,item1
2021-02-02,item3,item1,item1,item2,item2,item3,item1,item1,item1,item1,item1
2021-02-03,item2,item3,item1,item1,item1,item1,item3,item1,item1,item1,item3
2021-02-04,item2,item2,item2,item3,item1,item1,item1,item1,item1,item1,item1
2021-02-05,item2,item2,item2,item3,item1,item1,item1,item1,item1,item1,item1
2021-02-06,item2,item3,item1,item1,item1,item1,item1,item1,item1,item1,item1
2021-02-07,item2,item2,item1,item1,item1,item1,item1,item1,item1,item1,item1
2021-02-08,item2,item2,item3,item1,item1,item1,item1,item1,item1,item1,item1
2021-02-09,item2,item2,item3,item1,item1,item1,item1,item1,item1,item1,item1
2021-02-10,item2,item2,item2,item1,item1,item1,item1,item1,item1,item1,item1

I have tried the example given here https://medium.com/analytics-vidhya/association-analysis-in-python-2b955d0180c. However, the solution does not consider association of items per each time interval.

import pandas as pd
from datetime import datetime
from mlxtend.frequent_patterns import apriori, association_rules

df = pd.read_csv('df.csv')

items = set()
for col in df:
    items.update(df[col].unique())
items

itemset = set(items)
encoded_vals = []
for index, row in df.iterrows():
    rowset = set(row) 
    labels = {}
    uncommons = list(itemset - rowset)
    commons = list(itemset.intersection(rowset))
    for uc in uncommons:
        labels[uc] = 0
    for com in commons:
        labels[com] = 1
    encoded_vals.append(labels)
encoded_vals[0]
ohe_df = pd.DataFrame(encoded_vals)

freq_items = apriori(ohe_df, min_support=0.2, use_colnames=True)
freq_items = freq_items.sort_values('support', ascending=False)

rules = association_rules(freq_items, metric="confidence", min_threshold=0.2)
rules = rules.sort_values('support', ascending=False)
rules = rules[['antecedents','consequents','antecedent support','consequent support','support','confidence']]
print(rules)

I want to extend the above solution to include association of items per each time interval (T) to extract information such as at T1(item3 => item2 i.e., item3 is followed by item 2). I want to repeat this for each time interval T1, T2, T3, ....T10 (where each T can be an hourly interval e.g., T1=8AM-9AM, T2=9AM-10AM,...,T10=5PM-6PM). How can I enhance the solution to extract association rules per each time interval to achieve an output similar to my example output here.

Example output