記述のカテゴリ分け

もとの詳細な記述を分析して、下位のカテゴリに分類し、下位のカテゴリをさらに上位カテゴリに再分類する。
2階層のブレイクダウンの逆。

ルールは辞書で作成。keyにあたる部分がカテゴリ名、valueにはlistを設定する。
そのリストにある記述が、もとの詳細な記述の中にあれば、そのカテゴリであると判断する。

下位カテゴリが複数のカテゴリに該当する場合、もとの詳細な記述の最初に書いてあるカテゴリとする。

結果の見方は、「もとの詳細な記述 下位カテゴリ 上位カテゴリ」

結果

AA123 A1 A
AA123B22 A1 A
B22AA123 B2 B
asdf None None
asC12df C1 None

ソース

def classify_category(source_descripton,rule_dic):
    category_found = False
    found_key= ""
    find_pos=100 # 十分な長さ

    for category_key in rule_dic.keys():
        for category_value in rule_dic[category_key]:
            if category_value in source_descripton:
                category_found = True
                tmp_pos=source_descripton.find(category_value)
                if tmp_pos < find_pos:
                    found_key = category_key
                    find_pos=tmp_pos

    if category_found is False:
        found_key="None"

    return found_key

if __name__ == '__main__':
    top_category={}
    second_category={}

    top_category["A"]=["A1","A2"]
    top_category["B"]=["B1","B2"]

    second_category["A1"]=["A11","A12"]
    second_category["A2"]=["A21","A22"]
    second_category["B1"]=["B11","B12"]
    second_category["B2"]=["B21","B22"]
    second_category["C1"]=["C11","C12"]

    source_descripton="AA123"
    second_category_description = classify_category(source_descripton,second_category)
    top_category_description = classify_category(second_category_description,top_category)
    print(source_descripton,second_category_description,top_category_description)

    source_descripton="AA123B22"
    second_category_description = classify_category(source_descripton,second_category)
    top_category_description = classify_category(second_category_description,top_category)
    print(source_descripton,second_category_description,top_category_description)
    
    source_descripton="B22AA123"
    second_category_description = classify_category(source_descripton,second_category)
    top_category_description = classify_category(second_category_description,top_category)
    print(source_descripton,second_category_description,top_category_description)

    source_descripton="asdf"
    second_category_description = classify_category(source_descripton,second_category)
    top_category_description = classify_category(second_category_description,top_category)
    print(source_descripton,second_category_description,top_category_description)

    source_descripton="asC12df"
    second_category_description = classify_category(source_descripton,second_category)
    top_category_description = classify_category(second_category_description,top_category)
    print(source_descripton,second_category_description,top_category_description)