data = pd.___('patient_data.csv')

data['RiskLevel'] = np._____(data['DaysInHospital'] > 7, '高风险患者', '低风险患者')

risk_counts = data['RiskLevel']._____( )

high_risk_ratio = risk_counts['高风险患者'] / ______ (data)

low_risk_ratio = risk_counts['低风险患者'] / ______(data)

bmi_bins = [0, 18.5, 24.9, 29.9, np.inf]

bmi_labels = ['低于18.5', '18.5～24.9', '25.0～29.9', '高于30.0']

data['BMIRange'] = pd.______(data['BMI'], bins=bmi_bins, labels=bmi_labels)

bmi_risk_rate = data.______('BMIRange')['RiskLevel'].apply(lambda x: (x == '高风险患者').mean())

bmi_patient_count = data['BMIRange']._______()

age_bins = [0, 25, 35, 45, 55, 65, np.inf]

age_labels = ['低于25岁', '26岁-35岁', '36岁-45岁', '46岁-55岁', '56岁-65岁', '高于65岁']

data['AgeRange'] = pd.________(data['Age'], bins=age_bins, labels=age_labels)

age_risk_rate = data.________('AgeRange')['RiskLevel'].apply(lambda x: (x == '高风险患者').mean())

age_patient_count = data['AgeRange'].________()

data = pd.______('sensor_data.csv')

sensor_stats = data.________('SensorType')['Value'].agg(['count', 'mean'])

# 输出结果

print(传感器数据数量和平均值:)

print(________)

# 标记异常值

data['is_abnormal'] = np._________(

((data['SensorType'] == 'Temperature') ＆ ((data['Value'] ＜ -10) | (data['Value'] > 50))) |

((data['SensorType'] == 'Humidity') ＆ ((data['Value'] ＜ 0) | (data['Value'] > 100))),

True, False

)

print(异常值数量:, data['is_abnormal']._______())

data['Value'].________(method='ffill', inplace=True)

data['Value'].________(method='bfill', inplace=True)

cleaned_data = data._______(columns=['is_abnormal'])

cleaned_data.________('cleaned_sensor_data.csv', index=False)

missing_values = data._______().______() # 数据缺失值统计

duplicate_values = data.________().______() # 数据重复值统计

________['is_age_valid'] = _______['Age'].between(18, 70) # Age数据的合理性审核

________['is_income_valid'] = _______['Income'] > 2000 # Income数据的合理性审核

________['is_loan_amount_valid'] = _______['LoanAmount'] ＜ (data['Income'] * 5) # LoanAmount数据的合理性审核

________['is_credit_score_valid'] = _______['CreditScore'].between(300, 850) # CreditScore数据的合理性审核

# 从本地文件中读取数据

data = pd._________('user_behavior_data.csv')

print(data.________())

data = data.______()

data['Age'] = ______['Age']._______(int) # Age转整型

data = data[

(data['Age'].________(18, 70)) ＆

(data['PurchaseAmount'] > 0) ＆

(data['ReviewScore']._________(1, 5))

]

data['PurchaseAmount'] = (data['PurchaseAmount'] - data['PurchaseAmount']._________()) / data['PurchaseAmount'].________()

data['ReviewScore'] = (data['ReviewScore'] - data['ReviewScore']._______()) / data['ReviewScore']._____________()

data.__________('cleaned_user_behavior_data.csv', index=False)

print(数据清洗完成，已保存为 'cleaned_user_behavior_data.csv')