数据集名称Electric Car Performance and Battery Dataset电动汽车性能与电池数据集源地址https://www.kaggle.com/datasets/afnansaifafnan/electric-car-performance-and-battery-dataset发布平台与作者平台Kaggle全球知名数据科学社区作者afnansaifafnanKaggle 用户核心定位聚焦电动汽车的 “性能表现” 与 “电池特性”提供结构化、多维度的数据集用于替代敏感的真实车辆数据支持安全的数据分析与建模。数据属性信息范围无任何个人隐私信息如车主信息、行驶轨迹仅包含车辆公开规格与性能参数。完整性覆盖多品牌、多车型特征维度连贯从电池到性能再到车身规格无重大数据缺失。授权范围开放授权https://opendatacommons.org/licenses/pddl/1-0/。文件下载链接https://pan.quark.cn/s/bd8a050c2d08通过网盘分享的文件电车性能和电池链接: https://pan.baidu.com/s/1YgqQzy0ahbVsSqJpW51tYg?pwd3n6k 提取码: 3n6k查看基本信息importpandasaspd# 加载数据集dfpd.read_csv(/mnt/electric_vehicles_spec_2025.csv.csv)print(数据基本信息)df.info()# 查看数据集行数和列数rows,columnsdf.shapeifrows100andcolumns20:# 短表数据行数少于100且列数少于20查看全量数据信息print(数据全部内容信息)print(df.to_csv(sep\t,na_repnan))else:# 长表数据查看数据前几行信息print(数据前几行内容信息)print(df.head().to_csv(sep\t,na_repnan))本数据集中有 478 行22 列数据集包含如下字段brand品牌model型号top_speed_kmh最高时速公里/小时battery_capacity_kWh电池容量千瓦时battery_type电池类型number_of_cells电池的电芯数量torque_nm扭矩牛米efficiency_wh_per_km每公里耗电量瓦时/公里range_km续航里程公里acceleration_0_100_s0 - 100 公里/小时加速时间秒fast_charging_power_kw_dc直流快充功率千瓦fast_charge_port快充接口towing_capacity_kg牵引能力公斤cargo_volume_l载货容积升seats座位数drivetrain传动系统segment细分市场length_mm长度毫米width_mm宽度毫米height_mm高度毫米car_body_type车身类型source_url数据来源网址一、数据概况总结# 一、数据概况# 数值型特征的描述性统计保留两位小数print(数值型特征的描述性统计)print(df[[top_speed_kmh,battery_capacity_kWh,number_of_cells,torque_nm,efficiency_wh_per_km,range_km,acceleration_0_100_s,fast_charging_power_kw_dc,towing_capacity_kg,seats,length_mm,width_mm,height_mm]].describe().round(2))# 分类型特征的描述性统计forcolin[brand,model,battery_type,fast_charge_port,cargo_volume_l,drivetrain,segment,car_body_type]:print(f\n{col}的类别分布)print(df[col].value_counts())1. 数值型特征特征计数均值标准差最小值25%分位数50%分位数75%分位数最大值top_speed_kmh478.00185.4934.25125.00160.00180.00201.00325.00battery_capacity_kWh478.0074.0420.3321.3060.0076.1590.60118.00number_of_cells276.00485.291210.8272.00150.00216.00324.007920.00torque_nm471.00498.01241.46113.00305.00430.00679.001350.00efficiency_wh_per_km478.00162.9034.32109.00143.00155.00177.75370.00range_km478.00393.18103.29135.00320.00397.50470.00685.00acceleration_0_100_s478.006.882.732.204.806.608.2019.10fast_charging_power_kw_dc477.00125.0158.2129.0080.00113.00150.00281.00towing_capacity_kg452.001052.26737.850.00500.001000.001600.002500.00seats478.005.261.002.005.005.005.009.00length_mm478.004678.51369.213620.004440.004720.004961.005908.00width_mm478.001887.3673.661610.001849.001890.001939.002080.00height_mm478.001601.13130.751329.001514.001596.001665.001986.00二、特征相关性分析# 二、特征相关性分析importmatplotlib.pyplotaspltimportseabornassns# 剔除source_url列dfdf.drop(columnssource_url)# 将分类型变量进行编码df_encodedpd.get_dummies(df,columns[brand,model,battery_type,fast_charge_port,cargo_volume_l,drivetrain,segment,car_body_type])# 计算相关系数矩阵保留两位小数correlation_matrixdf_encoded.corr().round(2)# 查看与range_km相关性较高的前10个特征top_10_featurescorrelation_matrix[range_km].sort_values(ascendingFalse)[1:11]print(top_10_features)# 设置图片清晰度plt.rcParams[figure.dpi]300# 设置中文字体plt.rcParams[font.sans-serif][WenQuanYi Zen Hei]# 显示负号plt.rcParams[axes.unicode_minus]False# 绘制热力图plt.figure(figsize(12,8))sns.heatmap(correlation_matrix,annotFalse,cmapcoolwarm)plt.title(特征相关性热力图)plt.show()与续航里程range_km相关性较高的前 10 个特征特征与range_km的相关性系数battery_capacity_kWh0.88top_speed_kmh0.73fast_charging_power_kw_dc0.72torque_nm0.65width_mm0.52length_mm0.50drivetrain_AWD0.48segment_F - Luxury0.44car_body_type_Sedan0.39towing_capacity_kg0.33