{
  "schemaVersion": 1,
  "id": "1.1.3",
  "title": "金融机构信用评估系统中的业务数据审核流程设计",
  "durationMinutes": 30,
  "category": "业务数据处理与结果分析",
  "scenario": "某金融机构计划引入智能信用评估系统，通过分析客户的历史交易数据和信用记录，使用机器学习算法预测客户的信用风险等级，从而辅助贷款审批和风险控制。为了确保数据的准确性和可靠性，该机构需要设计并实现一套全面的业务数据审核流程，确保数据在进入信用评估系统之前经过严格的审核和清洗。\n\n我们提供一个客户信用数据集（credit_data.csv），包含以下字段：\n\nCustomerID: 客户ID\n\nName: 客户姓名\n\nAge: 年龄\n\nIncome: 收入\n\nLoanAmount: 贷款金额\n\nLoanTerm: 贷款期限（月）\n\nCreditScore: 信用评分\n\nDefault: 是否违约（0: 否，1: 是）\n\nTransactionHistory: 历史交易记录（JSON格式）\n\n你作为人工智能训练师，根据提供的credit_data.csv数据集和Python代码框架（1.1.3.ipynb），完成以下数据的审核和处理任务，确保数据的准确性和可靠性。请按照以下要求完成任务，确保结果准确并保存相应的截图。\n\n（1）数据完整性审核：\n\n通过运行Python代码（1.1.3.ipynb）检查数据集中的每个字段是否存在缺失值和重复值。将上述审核结果截图以JPG的格式保存，命名为“1.1.3-1”。\n\n（2）数据合理性审核：\n\n通过运行Python代码（1.1.3.ipynb）审核以下字段的合理性：\n\n年龄：应在18到70岁之间。\n\n收入：应大于2000。\n\n贷款金额：应小于收入的5倍。\n\n信用评分：应在300到850之间。\n\n对不合理的数据进行标记，并将审核结果截图以JPG的格式保存，命名为“1.1.3-2”。\n\n（3）通过运行Python代码（1.1.3.ipynb）对数据进行清洗，处理异常值。具体要求如下：\n\n将不合理的数据进行标记，并对异常值所在行进行删除；\n\n清洗后的数据保存为新文件cleaned_credit_data.csv。",
  "skillRequirements": "（1）能结合人工智能技术要求和业务特征，设计整套业务数据处理流程；\n\n（2）能结合人工智能技术要求和业务特征，设计整套业务数据审核流程",
  "qualityIndicators": "（1）完整性指标：数据集中无缺失值和重复记录。\n\n（2）合理性指标：所有数据点符合业务规则，无异常值存在。\n\n（3）清洗效果指标：清洗后的数据集完整、合理，且适于建模分析。",
  "tasks": [
    {
      "id": "code-fill",
      "type": "code-fill",
      "title": "补全代码任务",
      "instructions": "依据公开题面和附件补全代码空位；仅检查完成度与提交格式，不公开标准内容。",
      "codeBlocks": [
        "import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n# 读取数据集\ndata = pd.read_csv('credit_data.csv')",
        "# 1. 数据完整性审核\nmissing_values = data._________       #数据缺失值统计 2分\nduplicate_values = data._________     #数据重复值统计 2分\n# 输出结果\nprint(\"缺失值统计:\")\nprint(missing_values)\nprint(\"重复值统计:\")\nprint(duplicate_values)",
        "# 2. 数据合理性审核\ndata['is_age_valid'] = _________._________(18, 70)              #Age数据的合理性审核 2分\ndata['is_income_valid'] = _________ > _________                 #Income数据的合理性审核 2分\ndata['is_loan_amount_valid'] = _________ < (_________ * 5)      #LoanAmount数据的合理性审核 2分\ndata['is_credit_score_valid'] = _________._________(300, 850)   #CreditScore数据的合理性审核 2分\n# 合理性检查结果\nvalidity_checks = data[['is_age_valid', 'is_income_valid', 'is_loan_amount_valid', 'is_credit_score_valid']].all(axis=1)\ndata['is_valid'] = validity_checks\n# 输出结果\nprint(\"数据合理性检查:\")\nprint(data[['is_age_valid', 'is_income_valid', 'is_loan_amount_valid', 'is_credit_score_valid', 'is_valid']].describe())",
        "# 3. 数据清洗和异常值处理\n# 标记不合理数据\ninvalid_rows = data[~data['is_valid']]\n# 删除不合理数据行\ncleaned_data = data[data['is_valid']]\n# 删除标记列\ncleaned_data = cleaned_data.drop(columns=['is_age_valid', 'is_income_valid', 'is_loan_amount_valid', 'is_credit_score_valid', 'is_valid'])\n# 保存清洗后的数据\n_________._________(_________, index=False)\nprint(\"数据清洗完成，已保存为 'cleaned_credit_data.csv'\")"
      ],
      "blanks": [
        {
          "id": "blank-1",
          "block": 2,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-2",
          "block": 2,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-3",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-4",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-5",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-6",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-7",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-8",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-9",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-10",
          "block": 3,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-11",
          "block": 4,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-12",
          "block": 4,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        },
        {
          "id": "blank-13",
          "block": 4,
          "placeholder": "_________",
          "gradingMode": "completion-and-format-only"
        }
      ]
    },
    {
      "id": "1-1-response",
      "type": "rubric-response",
      "title": "数据处理结果分析",
      "instructions": "说明处理过程、结果证据和质量判断。",
      "sections": [
        {
          "id": "response",
          "label": "作答内容"
        }
      ],
      "rubric": [
        {
          "id": "criterion-1",
          "label": "处理流程完整且逻辑清晰",
          "weight": 25
        },
        {
          "id": "criterion-2",
          "label": "关键结果有附件或数据证据",
          "weight": 25
        },
        {
          "id": "criterion-3",
          "label": "结果符合技能要求与质量指标",
          "weight": 25
        },
        {
          "id": "criterion-4",
          "label": "能够解释异常、限制和改进方向",
          "weight": 25
        }
      ]
    },
    {
      "id": "artifact-submission",
      "type": "artifact-submission",
      "title": "选择结果文件",
      "instructions": "文件仅在本机选择并校验，不上传，也不持久化文件内容。",
      "items": [
        {
          "id": "artifact-1",
          "label": "提交文件：cleaned_credit_data.csv",
          "filename": "cleaned_credit_data.csv",
          "extensions": [
            ".csv"
          ],
          "minCount": 1,
          "maxCount": 1,
          "maxSize": 104857600
        },
        {
          "id": "artifact-2",
          "label": "提交文件：1.1.3-1.jpg",
          "filename": "1.1.3-1.jpg",
          "extensions": [
            ".jpg"
          ],
          "minCount": 1,
          "maxCount": 1,
          "maxSize": 104857600
        },
        {
          "id": "artifact-3",
          "label": "提交文件：1.1.3-2.jpg",
          "filename": "1.1.3-2.jpg",
          "extensions": [
            ".jpg"
          ],
          "minCount": 1,
          "maxCount": 1,
          "maxSize": 104857600
        }
      ]
    }
  ],
  "attachments": [
    {
      "name": "1.1.3.ipynb",
      "url": "assets/1.1.3/1.1.3.ipynb",
      "size": 2747,
      "sha256": "591f6655d11499b477f6beecc71cfaa3746e905c2ac53e9e50982bcbbed8aa5f",
      "mime": "application/x-ipynb+json"
    },
    {
      "name": "1.1.3.md",
      "url": "assets/1.1.3/1.1.3.md",
      "size": 2851,
      "sha256": "c0fff90a1a36551b468b1f2a8d2d66f63711d74bc212cbb7bb4520a28808f180",
      "mime": "text/markdown"
    },
    {
      "name": "credit_data.csv",
      "url": "assets/1.1.3/credit_data.csv",
      "size": 583251,
      "sha256": "2d040de2559c987043fec64aa5fc4ef1805f3bb1bc518bbb54989f3e15af9fe5",
      "mime": "text/csv"
    }
  ],
  "grading": {
    "mode": "completion-and-format-only"
  },
  "review": {
    "status": "approved",
    "notice": "由公开题面通用生成，未使用答案树。",
    "conflicts": []
  },
  "contentVersion": "f2f7a4e28dbc8055"
}