import numpy as np

# 读取数据集 1分

data = ______pd.read_csv('patient_data.csv')_______

# 创建新列'RiskLevel'，根据住院天数判断风险等级 3分

_______data['RiskLevel']______ = _______np.where______(_______data['DaysInHospital'] > 7______, '高风险患者', '低风险患者')

# 统计不同风险等级的患者数量 2分

risk_counts = data______['RiskLevel']_______.______value_counts()_______

# 计算高风险患者占比 1分

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

# 计算低风险患者占比 1分

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

# 输出结果

print("高风险患者数量:", risk_counts['高风险患者'])

print("低风险患者数量:", risk_counts['低风险患者'])

print("高风险患者占比:", high_risk_ratio)

print("低风险患者占比:", low_risk_ratio)

# 定义BMI区间和标签

bmi_bins = [0, 18.5, 24, 28, np.inf]

bmi_labels = ['偏瘦', '正常', '超重', '肥胖']

# 根据BMI值划分指定区间 4分

data['BMIRange'] = ______pd.cut_______(_______data['BMI']______, _______bins = bmi_bins______, _______labels = bmi_labels______, right=False) # 使用左闭右开区间

# 计算每个BMI区间中高风险患者的比例 2分

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

# 统计每个BMI区间的患者数量 1分

bmi_patient_count = data______['BMIRange'].value_counts()_______

# 输出结果

print("BMI区间中高风险患者的比例和患者数:")

print(bmi_risk_rate)

print(bmi_patient_count)

# 定义年龄区间和标签

age_bins = [0, 26, 36, 46, 56, 66, np.inf]

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

# 根据年龄值划分指定区间 4分

data['AgeRange'] = ______pd.cut_______(______data['Age]_______, ______bins = age_bins_______, ______labels = age_labels_______, right=False) # 使用左闭右开区间

# 计算每个年龄区间中高风险患者的比例 2分

age_risk_rate = ______data.groupby_______(_______'AgeRange'______)['RiskLevel'].apply(lambda x: (x == '高风险患者').mean())

# 统计每个年龄区间的患者数量 1分

age_patient_count = data_______['AgeRange'].value_counts()______

# 输出结果

print("年龄区间中高风险患者的比例和患者数:")

print(age_risk_rate)

print(age_patient_count)

import numpy as np

import matplotlib.pyplot as plt

# 读取数据集 2分

data = ______pd.read_csv('sensor_data.csv')_______

# 对传感器类型进行分组，并计算每个组的数据数量和平均值 3分

sensor_stats = ______data.groupby______(_______'SensorType'______)['Value'].______.agg(['count','mean'])_______

# 输出结果

print("传感器数据数量和平均值:")

print(sensor_stats)

# 筛选出温度和湿度数据，然后按位置和传感器类型分组，计算每个组的平均值 2分

location_stats = data[data['SensorType']._____isin(['Temperature','Humidity'])________.______groupby(['Location','SensorType'])_______['Value'].mean().unstack()

# 输出结果

print("每个位置的温度和湿度数据平均值:")

print(location_stats)

# 标记异常值 3分

data['is_abnormal'] = ______np.where_______(

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

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

True, False

)

# 输出异常值数量 2分

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

# 填补缺失值

# 使用前向填充和后向填充的方法填补缺失值 4分

data['Value'].______fillna_______(_______method='ffill'______, inplace=True)

data['Value'].______fillna_______(_______method='ffill'______, inplace=True)

# 保存清洗后的数据

# 删除用于标记异常值的列，并将清洗后的数据保存到新的CSV文件中 4分

cleaned_data = ______data.drop_______(______columns_______=['is_abnormal'])

______cleaned_data.to_csv_______('cleaned_sensor_data.csv', ____index=False_________)

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

missing_values = data.____isnull().sum()_____ #数据缺失值统计 2分

duplicate_values = data.____duplicated().sum()_____ #数据重复值统计 2分

# 输出结果

print("缺失值统计:")

print(missing_values)

print("重复值统计:")

print(duplicate_values)

data['is_age_valid'] = _____data['Age']____.____between_____(18, 70) #Age数据的合理性审核 2分

data['is_income_valid'] = _____data['Income']____ > _____2000____ #Income数据的合理性审核 2分

data['is_loan_amount_valid'] = _____data['LoanAmount']____ < (____data['Income']_____ * 5) #LoanAmount数据的合理性审核 2分

data['is_credit_score_valid'] = ____data['CreditScore']_____._____between____(300, 850) #CreditScore数据的合理性审核 2分

# 合理性检查结果

validity_checks = data[['is_age_valid', 'is_income_valid', 'is_loan_amount_valid', 'is_credit_score_valid']].all(axis=1)

data['is_valid'] = validity_checks

# 输出结果

print("数据合理性检查:")

print(data[['is_age_valid', 'is_income_valid', 'is_loan_amount_valid', 'is_credit_score_valid', 'is_valid']].describe())

# 标记不合理数据

invalid_rows = data[~data['is_valid']]

# 删除不合理数据行

cleaned_data = data[data['is_valid']]

# 删除标记列

cleaned_data = cleaned_data.drop(columns=['is_age_valid', 'is_income_valid', 'is_loan_amount_valid', 'is_credit_score_valid', 'is_valid'])

# 保存清洗后的数据

____cleaned_data_____.____to_csv_____(_____'cleaned_credit_data.csv'____, index=False)

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

import numpy as np

import matplotlib.pyplot as plt

# 1. 数据采集

# 从本地文件中读取数据 2分

data = _____________pandas.read_csv('user_behavior_data.csv')__________________

print("数据采集完成，已加载到DataFrame中")

# 打印数据的前5条记录 2分

print(_____________data.head()__________________)

# 处理缺失值（删除） 2分

data = _______________data.dropna()_________________

# 数据类型转换

data________['Age']________ = _________data['Age'].astype_______(int) # Age数据类型转换为int 2分

data________['PurchaseAmount']________ = ________data['purchaseAmount'].astype________(float) # PurchaseAmount数据类型转换为float 2分

data________['ReviewScore']________ = ________data['ReviewSource'].astype________(int) # ReviewScore数据类型转换为int 2分

# 处理异常值 2分

data = data[(________data['Age']________.________between________(18, 70)) &

(data['PurchaseAmount'] > 0) &

(_______data['ReviewScore']_________.________between________(1, 5))]

# 数据标准化

data['PurchaseAmount'] = (data['PurchaseAmount'] - ________data['PurchaseAmount'].mean()________) / _________data['PurchaseAmount'].std()_______ # PurchaseAmount数据标准化 2分

data['ReviewScore'] = (data['ReviewScore'] - ________data['ReviesScore'].mean()________) / ________data['ReviewScore'].std()________ # ReviewScore数据标准化 2分

# 保存清洗后的数据 1分

________data.to_csv________('cleaned_user_behavior_data.csv', index=False)

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

# 统计每个购买类别的用户数 2分

purchase_category_counts = _______data['PurchaseCategory']_________._________value_counts()_______

print("每个购买类别的用户数:\n", purchase_category_counts)

# 统计不同性别的平均购买金额 2分

gender_purchase_amount_mean = _______data.groupby_________(________'Gender'________)['PurchaseAmount'].mean()

print("不同性别的平均购买金额:\n", gender_purchase_amount_mean)

# 统计不同年龄段的用户数 2分

bins = [18, 26, 36, 46, 56, 66, np.inf]

labels = ['18-25', '26-35', '36-45', '46-55', '56-65', '65+']

data['AgeGroup'] = pandas.________cut________(________data['Age'],bins = bins, labels = labesl________, right=False)

age_group_counts = data['AgeGroup'].value_counts().sort_index()

print("不同年龄段的用户数:\n", age_group_counts)

import numpy as np

import matplotlib.pyplot as plt

# 1. 数据采集

# 从本地文件中读取数据 2分

data = ______pd.read_csv('vehicle_traffic_data.csv')_______

print("数据采集完成，已加载到DataFrame中")

# 打印数据的前5条记录 2分

print(______data.head()_______)

# 处理缺失值（删除） 2分

data = ______data.dropna()_______

# 数据类型转换

data______['Age']_______ = ______data['Age'].astype_______(int) #Age数据类型转换为int 1分

data______['Speed']_______ = _______data['Speed'].astype______(float) #Speed数据类型转换为float 1分

data_______['TravelDistance']______ = _______data['TravelDistance'].astype______(float) #TravelDistance数据类型转换为float 1分

data______['TravelTime']_______ = _______data['TravelTime'].astype______(float) #TravelTime数据类型转换为float 1分

# 处理异常值 2分

data = data[(_______data['Age'].between______(18, 70)) &

(______data['Speed'].between_______(0, 200)) &

(_______data['TravelDistance'].between______(1, 1000)) &

(_______data['TravelTime'].between______(1, 1440))]

# 保存清洗后的数据 1分

_______data.to_csv______('cleaned_vehicle_traffic_data.csv', index=False)

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

# 审核字段合理性 1分

unreasonable_data = data[~((_______data['Age'].between______(18, 70)) &

(______data['Speed'].between_______(0, 200)) &

(______data['TravelDistance'].between_______(1, 1000)) &

(______data['TravelTime'].between_______(1, 1440)))]

print("不合理的数据:\n", unreasonable_data)

# 4. 数据统计

# 统计每种交通事件的发生次数 2分

traffic_event_counts = ______data['TrafficEvent'].value_counts()_______

print("每种交通事件的发生次数:\n", traffic_event_counts)

# 统计不同性别的平均车速、行驶距离和行驶时间 2分

gender_stats = data.______groupby('Gender')_______.______agg({'Speed':'mean','TravelDistance':'mean','TravelTime':'mean'})_______

print("不同性别的平均车速、行驶距离和行驶时间:\n", gender_stats)

# 统计不同年龄段的驾驶员数 5分

age_bins = [18, 26, 36, 46, 56, 66, np.inf]

age_labels = ['18-25', '26-35', '36-45', '46-55', '56-65', '65+']

data['AgeGroup'] = ______pd.cut_______(_______data['Age']______,______bins = age_bins_______,_______labels = age_labels______, right=False)

age_group_counts = ______data['AgeGroup'].value_counts()_______

print("不同年龄段的驾驶员数:\n", age_group_counts)

# 加载数据集并显示数据集的前五行 1分

data = _____pd.read_csv('auto-mpg.csv')_____

print("数据集的前五行:")

print(_____data.head()_____)

# 显示每一列的数据类型

print(data.dtypes)

# 检查缺失值并删除缺失值所在的行 2分

print("\n检查缺失值:")

print(_____data_____._____isnull()_____._____sum()_____)

data = _____data.dropna()_____

# 将 'horsepower' 列转换为数值类型，并（删除）处理转换中的异常值 1分

data['horsepower'] = _____pd.to_numeric_____(data['horsepower'], errors='coerce')

data = _____data.dropna(subset=['horsepower'])_____

# 显示每一列的数据类型

print(data.horsepower.dtypes)

# 检查清洗后的缺失值

print("\n检查清洗后的缺失值:")

print(data.isnull().sum())

from sklearn.preprocessing import StandardScaler

# 对数值型数据进行标准化处理 1分

numerical_features = ['displacement', 'horsepower', 'weight', 'acceleration']

scaler = StandardScaler()

data[numerical_features] = _____scaler.fit_transform(data[numerical_features])_____

from sklearn.model_selection import train_test_split

# 选择特征、自变量和目标变量 2分

selected_features = _____['cylinders','displacement','horsepower','weight',acceleration],'model year','origin'_____

X = _____data[Selected_features]_____

y = _____data['mpg']_____

# 划分数据集为训练集和测试集（训练集占8成） 1分

X_train, X_test, y_train, y_test = _____train_test_split_____(_____X,y,test_size=0.2_____, random_state=42)

# 将特征和目标变量合并到一个数据框中

cleaned_data = X.copy()

cleaned_data['mpg'] = y

# 保存清洗和处理后的数据（不存储额外的索引号） 1分

_____cleaned_data.to_csv_____('2.1.1_cleaned_data.csv', _____index=False_____)

# 打印消息指示文件已保存

print("\n清洗后的数据已保存到 2.1.1_cleaned_data.csv")