import tempfile import gradio as gr import pandas as pd import spaces from apriori_core import ( apriori, association_rules, default_text, format_items, parse_csv, parse_text, validate_threshold, verify_mlxtend, ) FREQUENT_COLS = [ "商品組合", "出現次數", "Support(支持度)" ] RULE_COLS = [ "前件(Antecedent)", "後件(Consequent)", "Support", "Confidence", "Lift" ] def save_csv(frame, prefix): with tempfile.NamedTemporaryFile( mode="w", encoding="utf-8-sig", newline="", suffix=".csv", prefix=prefix, delete=False ) as file: frame.to_csv(file, index=False) return file.name @spaces.GPU(duration=15) def analyze_ui( source, transaction_text, uploaded_csv, minimum_support, minimum_confidence ): try: minimum_support = validate_threshold( minimum_support, "最小支持度" ) minimum_confidence = validate_threshold( minimum_confidence, "最小信賴度" ) if source == "文字輸入": data = parse_text(transaction_text) elif source == "上傳 CSV": data = parse_csv(uploaded_csv) else: raise ValueError("請選擇有效的資料來源") counts = apriori(data, minimum_support) rules = association_rules( counts, len(data), minimum_confidence ) verification_message = verify_mlxtend( data, counts, rules, minimum_support, minimum_confidence ) except (ValueError, AssertionError, OSError, ImportError) as error: raise gr.Error(str(error)) from error frequent_rows = [] for itemset, count in sorted( counts.items(), key=lambda x: ( len(x[0]), tuple(sorted(x[0])) ) ): frequent_rows.append({ "商品組合": format_items(itemset), "出現次數": count, "Support(支持度)": f"{count / len(data):.2%}" }) rule_rows = [] for rule in rules: rule_rows.append({ "前件(Antecedent)": format_items(rule["前件"]), "後件(Consequent)": format_items(rule["後件"]), "Support": f"{rule['Support']:.2%}", "Confidence": f"{rule['Confidence']:.2%}", "Lift": f"{rule['Lift']:.4f}" }) frequent_df = pd.DataFrame( frequent_rows, columns=FREQUENT_COLS ) rules_df = pd.DataFrame( rule_rows, columns=RULE_COLS ) unique_items = len(set().union(*data)) summary = ( "### 分析完成\n" f"交易筆數:**{len(data)}**\n\n" f"商品種類:**{unique_items}**\n\n" f"頻繁項目集:**{len(counts)} 組**\n\n" f"關聯規則:**{len(rules)} 條**\n\n" f"最小支持度:**{minimum_support:.0%}**\n\n" f"最小信賴度:**{minimum_confidence:.0%}**\n\n" f"### mlxtend 交叉驗證\n{verification_message}" ) if not rules: summary += ( "\n\n目前沒有符合條件的關聯規則," "請降低支持度或信賴度。" ) return ( summary, frequent_df, rules_df, save_csv(frequent_df, "frequent_"), save_csv(rules_df, "rules_") ) def reset_defaults(): return ( "文字輸入", default_text(), None, 0.3, 0.7 ) with gr.Blocks( title="Apriori 關聯規則分析系統" ) as demo: gr.Markdown( """ # Apriori 關聯規則分析系統 Python 自行實作 Apriori 演算法 功能: - 自訂購買紀錄 - CSV 資料上傳 - 支持度與信賴度設定 - 頻繁項目集分析 - 關聯規則分析 - mlxtend 交叉驗證 - CSV 結果下載 """ ) with gr.Row(): with gr.Column(scale=3): source = gr.Radio( choices=["文字輸入", "上傳 CSV"], value="文字輸入", label="資料來源" ) transactions_input = gr.Textbox( value=default_text(), lines=15, label="購買紀錄", info="每行一筆交易,商品以逗號分隔,至少10筆" ) csv_input = gr.File( label="上傳 CSV 檔案", file_types=[".csv"], type="filepath" ) with gr.Column(scale=2): min_support = gr.Slider( minimum=0.05, maximum=1.0, value=0.3, step=0.05, label="Minimum Support(最小支持度)" ) min_confidence = gr.Slider( minimum=0.05, maximum=1.0, value=0.7, step=0.05, label="Minimum Confidence(最小信賴度)" ) run_button = gr.Button( "開始分析", variant="primary" ) reset_button = gr.Button( "恢復預設資料" ) gr.Markdown( """ ### 指標說明 **Support(支持度)** 商品組合同時出現在交易中的比例。 **Confidence(信賴度)** 購買前件商品後,也購買後件商品的比例。 **Lift(提升度)** 衡量商品間的關聯程度。 - Lift > 1:正向關聯 - Lift = 1:獨立 - Lift < 1:負向關聯 """ ) summary = gr.Markdown( "請點選開始分析" ) with gr.Tab("頻繁項目集"): frequent_table = gr.Dataframe( label="Frequent Itemsets", interactive=False ) frequent_download = gr.File( label="下載頻繁項目集 CSV", interactive=False ) with gr.Tab("關聯規則"): rule_table = gr.Dataframe( label="Association Rules", interactive=False ) rules_download = gr.File( label="下載關聯規則 CSV", interactive=False ) run_button.click( fn=analyze_ui, inputs=[ source, transactions_input, csv_input, min_support, min_confidence ], outputs=[ summary, frequent_table, rule_table, frequent_download, rules_download ] ) reset_button.click( fn=reset_defaults, outputs=[ source, transactions_input, csv_input, min_support, min_confidence ] ) if __name__ == "__main__": demo.launch()