PUBG数据集分析报告
数据集分为两个部分
数据集1：
agg数据： 15 字段
date: 时间game_size:队伍数量match_id:比赛match_mode: 对局模式（第一人称还是第三人称）party_size：组队模式（单人赛、双人赛、四人赛）player_assists：助攻次数player_dbno：击倒人数player_dist_ride：载具移动距离player_dist_walk：行走距离player_dmg：伤害数值player_kills：击杀人数player_name：玩家名称player_survive_time：玩家生存时间team_id：队伍idteam_placement：队伍排名
数据集2:
kill dataset12 字段
killed_by：死亡方式killer_name：击杀者名字killer_placement：击杀者排名killer_position_x：击杀者位置x坐标killer_position_y：击杀者位置y坐标,map：地图match_id：比赛time：存活时间,victim_name：被击杀者名字victim_placement：被击杀者排名ictim_position_x：被击杀者位置x坐标victim_position_y：被击杀者位置y坐标
我们可以自由探索数据间的关系，发现一些有意思的现象
我想完成的目标:
击杀人数的分布情况单变量分析: 击杀人数与排名， 组队模式与吃鸡多变量间分析落地成盒热点区域（存活时间小于180s）最好用的枪械战斗发生的距离分布不同战斗距离中最好用的枪械训练一个SVM预测是否能够吃鸡
及杀人数的分布情况
部分代码
导入数据 并处理丢失数据
agg = './pubg/agg0.csv'kill = './pubg/kill0.csv'agg_df = pd.read_csv(agg) # shape (13849287, 15)kill_df = pd.read_csv(kill) # shape(13426348, 12)agg_sub_df = agg_df[:1000000]kill_sub_df = kill_df[:1000000]agg_sub_deleted = agg_sub_df.dropna(axis=0)kill_sub_deleted = kill_sub_df.dropna(axis=0)
agg_sub_deleted['player_kills'].describe() # 大部分人的击杀人数都是在1人和0人
count 998580.000000
mean 0.887166
std 1.555946
min 0.000000
25% 0.000000
50% 0.000000
75% 1.000000
max 62.000000
Name: player_kills, dtype: float64
单变量分析: 击杀人数与排名， 组队模式与吃鸡
# 查看击杀人数与排名的关系; 整体看，击杀人数超过10人可以排到前5名概率比较大， 40左右时有异常发生。data = agg_sub_deleted[['player_kills', 'team_placement']]sns.set(style="darkgrid")g = sns.relplot(x="player_kills", y="team_placement",height=4,linewidth=2,aspect=1.3, kind="line", data=data)g.fig.autofmt_xdate() # Rotate coordinates
agg_sub_1 = agg_sub_deleted[agg_sub_deleted['team_placement']==1.0] # 筛选第一名数据party_size_data = agg_sub_1.groupby('party_size') # 2 , 4, 1三种组队模式, 分别获胜率old = agg_sub_deleted.groupby('party_size')# 查看每种组队模式的获胜概率, 4 人组队获胜概率最大： 4%, num = []for i in range(1,5):if i==3:continuesize = old.get_group(i)size2 = party_size_data.get_group(i)num.append(round(size2.shape[0]/size.shape[0], 2)) name = ['solo', 'double', 'four-people']f, ax = plt.subplots(figsize=(7, 3))plt.bar(range(len(num)), num, color=sns.color_palette("cubehelix",3), tick_label=name)plt.title('ranking 1 percentage by party_size')
多变量间分析
# 相关性分析, date, match_id, ,match_mode, pary_size, player_name, team_id 这些字段不需要not_use = ['date', 'match_id', 'match_mode', 'party_size', 'player_name', 'team_id']all_columns = agg_sub_deleted.columns.valuesagg_sub_corr = agg_sub_deleted[[column for column in all_columns if column not in not_use]] #筛选不在not use中的字段corr_data = agg_sub_corr.corr(method='spearman')plt.subplots(figsize=(9, 9)) sns.heatmap(corr_data, annot=True, vmax=1, square=True, cmap="Blues")plt.show()
关注’team_placement’列发现队伍排名除了与存活时间有强烈的负相关以外，与载具移动距离和行走距离也有较强负相关（排名越小越好所以是负相关）
详细查看 获胜率 和 载具移动距离的关系
df_ride = agg_sub_deleted.loc[agg_sub_deleted['player_dist_ride']<10000, ['player_dist_ride', 'champion']]labels=["0k-1k", "1k-2k", "2k-3k", "3k-4k","4k-5k", "5k-6k", "6k-7k", "7k-8k"]df_ride['drive'] = pd.cut(df_ride['player_dist_ride'], 8, labels=labels) # pd.cut , 分割pandas 为10个等距子表df_ride.groupby('drive').champion.mean().plot.bar(rot=30, figsize=(10, 6), color=sns.color_palette("cubehelix",8))plt.xlabel("drive distance")plt.ylabel("prop of Champion")
落地成盒热点区域（存活时间小于180s）
部分代码
from scipy.ndimage.filters import gaussian_filterimport matplotlib.cm as cmfrom matplotlib.colors import Normalizekill_sub_df_die_map1 = kill_sub_df.loc[(kill_sub_df['map'] == 'ERANGEL')&(kill_sub_df['time'] < 180)&(kill_sub_df['victim_position_x']>0), :].dropna()bg = imread('erangel.jpg')hmap, extent = heatmap(plot_data_ev[:,0], plot_data_ev[:,1], 1.5, bins =200)alphas = np.clip(Normalize(0, hmap.max()/100, clip=True)(hmap)*1.5,0.0,1.)colors = Normalize(hmap.max()/100, hmap.max()/20, clip=True)(hmap)colors = cm.bwr(colors)colors[..., -1] = alphasfig, ax = plt.subplots(figsize = (8,8))ax.set_xlim(0, 4096);ax.set_ylim(0, 4096)ax.imshow(bg)ax.imshow(colors, extent = extent, origin = 'lower', cmap = cm.cool, alpha = 1)plt.gca().invert_yaxis()plt.title('erangel killed pepole Distribution')
最好用的枪械
部分代码
gun_category = kill_sub_df['killed_by'].unique()MIRAMAR = kill_sub_df[kill_sub_df['map']=='MIRAMAR']ERANGEL = kill_sub_df[kill_sub_df['map']=='ERANGEL']kill_sub_df_gun_M = MIRAMAR.groupby('killed_by')kill_sub_df_gun_E = ERANGEL.groupby('killed_by')# 统计各重武器击杀人数M_data = {}E_data = {}for name in gun_category: try:sub = kill_sub_df_gun_M.get_group(name)if sub.shape[0]>100:M_data[name]=sub.shape[0]except Exception as e:continuefor name in gun_category: try:sub = kill_sub_df_gun_E.get_group(name)if sub.shape[0]>100:E_data[name]=sub.shape[0]except Exception as e:continue
统计发现无论在艾伦格还是米拉马， M416, SCAR-L, M16A4 都是击杀人数前三名的武器
战斗发生的距离分布
部分代码
vec1 = np.array([93091.37, 722236.4])vec2 = np.array([92238.68, 723375.1])dist = np.linalg.norm(vec1 - vec2) vec1 =kill_sub_df[['killer_position_x', 'killer_position_y']].valuesvec2 = kill_sub_df[['victim_position_x', 'victim_position_y']].valuesdist = []for i in range(len(vec1)):dis = np.linalg.norm(vec1[i]-vec2[i])dist.append(dis//100)#增加一列击杀距离kill_sub_df['kill_dist'] = distshort_dis = kill_sub_df[kill_sub_df['kill_dist']<=50]mid_dis = kill_sub_df[(kill_sub_df['kill_dist']>50) & (kill_sub_df['kill_dist']<=300)] # 多条件筛选()&()long_dis = kill_sub_df[(kill_sub_df['kill_dist']>300) & (kill_sub_df['kill_dist']<800)]super_dis = kill_sub_df[kill_sub_df['kill_dist']>=800]
绝大部分人在50米以内近距离被击杀
不同战斗距离中最好用的枪械
部分代码
shor_gun = short_dis.groupby('killed_by')mid_gun = mid_dis.groupby('killed_by') long_gun = long_dis.groupby('killed_by')super_gun = super_dis.groupby('killed_by')def count_gun(df, category):data = {}for name in category: try:sub = df.get_group(name)if sub.shape[0]>100:data[name]=sub.shape[0]except Exception as e:continuedata = sorted(data.items(), key=lambda x:x[1],reverse=True)return data[1:4]shor_data = count_gun(shor_gun, gun_category)mid_data = count_gun(mid_gun, gun_category)long_data = count_gun(long_gun, gun_category)super_data = count_gun(super_gun, gun_category)
近距离战斗，中距离战斗，M416, SCAR-L, AKM 表现最好
远距离战斗, Kar98k, M416, Mini 14 三种武器表现最好
超过800米的战斗数据可能有问题
训练一个SVM预测是否能够吃鸡
部分代码
# 不要的字段all_colum = agg_sub_deleted.columns no_use = ['match_id', 'match_mode', 'player_name', 'team_id', 'team_placement', 'date']agg_svm = agg_sub_deleted[[colum for colum in all_colum if colum not in no_use]]df_dataset = pd.concat([agg_negative_sub, agg_positive],axis=0) # 合并两个df，竖向拼接df_dataset = shuffle(df_dataset)y = df_dataset['champion'].valuesX = df_dataset.drop(columns=['champion']).valuesX_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3)clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))clf.fit(X_train, y_train)print('mean accuracy:', clf.score(X_test, y_test))
mean accuracy: 0.940930317181151
手动检测
test = agg_negative.iloc[0][:-1].values # 删除标签列clf.predict([test]) == agg_negative.iloc[0][-1]
array([ True])
总结
大部分人的击杀人数都是在1人和0人, 平均击杀数0.88击杀人数超过7人可以排到前5名概率很大跳伞时应该避开图中标注热点区域队伍排名除了与存活时间有强烈的负相关以外，与载具移动距离和行走距离也有较强负相关（排名越小越好所以是负相关统计发现无论在艾伦格还是米拉马， M416, SCAR-L, M16A4 都是击杀人数前三名的武器绝大部分人在50米以内近距离被击杀近距离战斗，中距离战斗，M416, SCAR-L, AKM 表现最好远距离战斗, Kar98k, M416, Mini 14 三种武器表现最好选取合适的特征，SVM准确率达到了0.94イケイケ！
如果觉得《Kaggle PUBG吃鸡数据集--数据分析可视化》对你有帮助，请点赞、收藏，并留下你的观点哦！
