{ "cells": [ { "cell_type": "code", "execution_count": 20, "id": "21cfc41f-637c-4154-b177-5c3bfad84a8a", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from mlxtend.preprocessing import TransactionEncoder\n", "\n", "df = pd.read_csv('D:/이강성/Retail_Transactions_Dataset.csv')" ] }, { "cell_type": "code", "execution_count": 40, "id": "2b8c94c7-682f-43cd-88d1-dacea5ef4491", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from mlxtend.preprocessing import TransactionEncoder\n", "from ast import literal_eval\n", "\n", "# 데이터 타입이 문자열(str)인 경우에만 실제 리스트로 변환하는 함수\n", "def to_list(x):\n", " if isinstance(x, str):\n", " try:\n", " return literal_eval(x)\n", " except (ValueError, SyntaxError):\n", " # 문자열이지만 리스트 형태가 아닌 예외 상황 처리\n", " return [x]\n", " elif isinstance(x, list):\n", " return x\n", " else:\n", " # 그 외의 타입(예: NaN 등) 처리\n", " return []\n", "\n", "# 1. Product 열의 데이터를 안전하게 리스트 형식으로 일괄 변환\n", "df1 = df[df['Store_Type'] == 'Warehouse Club']\n", "df1['Product_List'] = df1['Product'].apply(to_list)\n", "\n", "# 2. TransactionEncoder 객체 생성 및 변환\n", "te = TransactionEncoder()\n", "te_ary = te.fit(df1['Product_List']).transform(df1['Product_List'])\n", "\n", "# 3. 변환된 데이터를 1과 0 형식의 데이터프레임으로 변환\n", "df_encoded = pd.DataFrame(te_ary, columns=te.columns_)" ] }, { "cell_type": "code", "execution_count": 41, "id": "9c91787a-2980-48ec-b680-e1cad02f96a2", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Air FreshenerAppleBBQ SauceBaby WipesBananaBath TowelsBeefBreadBroomButter...TomatoesToothbrushToothpasteTrash BagsTrash CansTunaVacuum CleanerVinegarWaterYogurt
0FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse...FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
1FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse...FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
2FalseTrueFalseFalseFalseFalseFalseFalseFalseFalse...FalseFalseFalseTrueFalseFalseFalseFalseFalseFalse
3FalseFalseFalseFalseFalseFalseTrueFalseFalseFalse...FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
4FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse...FalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
\n", "

5 rows × 81 columns

\n", "
" ], "text/plain": [ " Air Freshener Apple BBQ Sauce Baby Wipes Banana Bath Towels Beef \\\n", "0 False False False False False False False \n", "1 False False False False False False False \n", "2 False True False False False False False \n", "3 False False False False False False True \n", "4 False False False False False False False \n", "\n", " Bread Broom Butter ... Tomatoes Toothbrush Toothpaste Trash Bags \\\n", "0 False False False ... False False False False \n", "1 False False False ... False False False False \n", "2 False False False ... False False False True \n", "3 False False False ... False False False False \n", "4 False False False ... False False False False \n", "\n", " Trash Cans Tuna Vacuum Cleaner Vinegar Water Yogurt \n", "0 False False False False False False \n", "1 False False False False False False \n", "2 False False False False False False \n", "3 False False False False False False \n", "4 False False False False False False \n", "\n", "[5 rows x 81 columns]" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_encoded.head()" ] }, { "cell_type": "code", "execution_count": 42, "id": "ccc4c504-0de7-4453-a922-959fa1151200", "metadata": {}, "outputs": [], "source": [ "from mlxtend.frequent_patterns import apriori, association_rules\n", "\n", "frequent_itemsets = apriori(df_encoded, min_support=0.002, use_colnames=True)\n" ] }, { "cell_type": "code", "execution_count": 43, "id": "3a3ea342-a0bb-48b6-b312-e5e4a327c1b8", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
supportitemsets
00.035702frozenset({Air Freshener})
10.035918frozenset({Apple})
20.036242frozenset({BBQ Sauce})
30.036464frozenset({Baby Wipes})
40.036602frozenset({Banana})
.........
1560.002352frozenset({Toothpaste, Tuna})
1570.002262frozenset({Toothpaste, Vacuum Cleaner})
1580.002124frozenset({Toothpaste, Vinegar})
1590.002220frozenset({Water, Toothpaste})
1600.002238frozenset({Toothpaste, Yogurt})
\n", "

161 rows × 2 columns

\n", "
" ], "text/plain": [ " support itemsets\n", "0 0.035702 frozenset({Air Freshener})\n", "1 0.035918 frozenset({Apple})\n", "2 0.036242 frozenset({BBQ Sauce})\n", "3 0.036464 frozenset({Baby Wipes})\n", "4 0.036602 frozenset({Banana})\n", ".. ... ...\n", "156 0.002352 frozenset({Toothpaste, Tuna})\n", "157 0.002262 frozenset({Toothpaste, Vacuum Cleaner})\n", "158 0.002124 frozenset({Toothpaste, Vinegar})\n", "159 0.002220 frozenset({Water, Toothpaste})\n", "160 0.002238 frozenset({Toothpaste, Yogurt})\n", "\n", "[161 rows x 2 columns]" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" } ], "source": [ "frequent_itemsets" ] }, { "cell_type": "code", "execution_count": 47, "id": "538b2d8b-349b-4e73-b1c8-9d2f9c2403af", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " antecedents consequents support \\\n", "20 frozenset({Deodorant}) frozenset({Toothpaste}) 0.002574 \n", "37 frozenset({Ketchup}) frozenset({Toothpaste}) 0.002550 \n", "71 frozenset({Tomatoes}) frozenset({Toothpaste}) 0.002550 \n", "21 frozenset({Diapers}) frozenset({Toothpaste}) 0.002568 \n", "34 frozenset({Iron}) frozenset({Toothpaste}) 0.002490 \n", ".. ... ... ... \n", "38 frozenset({Laundry Detergent}) frozenset({Toothpaste}) 0.002130 \n", "23 frozenset({Dishware}) frozenset({Toothpaste}) 0.002112 \n", "77 frozenset({Vinegar}) frozenset({Toothpaste}) 0.002124 \n", "53 frozenset({Plant Fertilizer}) frozenset({Toothpaste}) 0.002094 \n", "5 frozenset({Bath Towels}) frozenset({Toothpaste}) 0.002094 \n", "\n", " confidence lift \n", "20 0.071074 0.993951 \n", "37 0.070493 0.985826 \n", "71 0.070190 0.981593 \n", "21 0.069958 0.978343 \n", "34 0.068788 0.961992 \n", ".. ... ... \n", "38 0.058833 0.822772 \n", "23 0.058794 0.822224 \n", "77 0.058745 0.821544 \n", "53 0.058725 0.821252 \n", "5 0.058312 0.815489 \n", "\n", "[80 rows x 5 columns]\n" ] } ], "source": [ "rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=0.05)\n", "# 결과 확인을 위해 필요한 컬럼만 선택해서 출력\n", "print(rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']]\n", " .sort_values(by='confidence', ascending=False))" ] }, { "cell_type": "code", "execution_count": 31, "id": "0861bf21-5e3d-4d1b-81f2-4237d11156ab", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "166685" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(df1)" ] }, { "cell_type": "code", "execution_count": null, "id": "6b3fa60f-d125-412e-9a76-f1ff0e343e39", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }