英雄联盟大师 Baseline

该赛事围绕英雄联盟实时对局数据预测胜负展开。提供18万训练数据与2万测试数据，含击杀、伤害等30个字段，需预测测试集“win”标签，以准确率评分。Baseline流程含环境配置、代码运行等步骤，采用简单神经网络模型，还可通过提取交叉特征、加入验证集等优化模型提升成绩。

赛事介绍

实时对战游戏是人工智能研究领域的一个热点。由于游戏复杂性、部分可观察和动态实时变化战局等游戏特点使得研究变得比较困难。我们可以在选择英雄阶段预测胜负概率，也可以在比赛期间根据比赛实时数据进行建模。那么我们英雄联盟对局进行期间，能知道自己的胜率吗？

赛事任务

比赛数据使用了英雄联盟玩家的实时游戏数据，记录下用户在游戏中对局数据（如击杀数、住物理伤害）。希望参赛选手能从数据集中挖掘出数据的规律，并预测玩家在本局游戏中的输赢情况。

赛题训练集案例如下：

import pandas as pdimport numpy as nptrain = pd.read_csv('train.csv.zip')

对于数据集中每一行为一个玩家的游戏数据，数据字段如下所示：

评审规则

选手需要提交测试集队伍排名预测，具体的提交格式如下：

win0110

本次竞赛的使用准确率进行评分，数值越高精度越高，评估代码参考：

from sklearn.metrics import accuracy_scorey_pred = [0, 2, 1, 3]y_true = [0, 1, 2, 3]accuracy_score(y_true, y_pred)

Baseline使用指导

1、点击‘fork按钮’，出现‘fork项目’弹窗
2、点击‘创建按钮’ ，出现‘运行项目’弹窗
3、点击‘运行项目’，自动跳转至新页面
4、点击‘启动环境’ ，出现‘选择运行环境’弹窗
5、选择运行环境（启动项目需要时间，请耐心等待），出现‘环境启动成功’弹窗，点击确定
6、点击进入环境，即可进入notebook环境
7、鼠标移至下方每个代码块内（代码块左侧边框会变成浅蓝色），再依次点击每个代码块左上角的‘三角形运行按钮’，待一个模块运行完以后再运行下一个模块，直至全部运行完成


8、下载页面左侧submission.zip压缩包

9、在比赛页提交submission.zip压缩包，等待系统评测结束后，即可登榜！

10、点击页面左侧‘版本-生成新版本’

11、填写‘版本名称’，点击‘生成版本按钮’，即可在个人主页查看到该项目（可选择公开此项目哦）

import pandas as pdimport paddleimport numpy as np%pylab inlineimport seaborn as snstrain_df = pd.read_csv('data/data137276/train.csv.zip')test_df = pd.read_csv('data/data137276/test.csv.zip')train_df = train_df.drop(['id', 'timecc'], axis=1)test_df = test_df.drop(['id', 'timecc'], axis=1)

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working  from collections import MutableMapping/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working  from collections import Iterable, Mapping/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working  from collections import Sized

Populating the interactive namespace from numpy and matplotlib

数据分析

train_df.isnull().mean(0)

win                       0.0kills                     0.0deaths                    0.0assists                   0.0largestkillingspree       0.0largestmultikill          0.0longesttimespentliving    0.0doublekills               0.0triplekills               0.0quadrakills               0.0pentakills                0.0totdmgdealt               0.0magicdmgdealt             0.0physicaldmgdealt          0.0truedmgdealt              0.0largestcrit               0.0totdmgtochamp             0.0magicdmgtochamp           0.0physdmgtochamp            0.0truedmgtochamp            0.0totheal                   0.0totunitshealed            0.0dmgtoturrets              0.0totdmgtaken               0.0magicdmgtaken             0.0physdmgtaken              0.0truedmgtaken              0.0wardsplaced               0.0wardskilled               0.0firstblood                0.0dtype: float64

train_df['win'].value_counts().plot(kind='bar')

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2349: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working  if isinstance(obj, collections.Iterator):/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2366: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working  return list(data) if isinstance(data, collections.MappingView) else data

sns.distplot(train_df['kills'])

sns.distplot(train_df['deaths'])

sns.boxplot(y='kills', x='win', data=train_df)

plt.scatter(train_df['kills'], train_df['deaths'])plt.xlabel('kills')plt.ylabel('deaths')

Text(0,0.5,'deaths')

for col in train_df.columns[1:]:    train_df[col] /= train_df[col].max()    test_df[col] /= test_df[col].max()

搭建模型

class Classifier(paddle.nn.Layer):    # self代表类的实例自身    def __init__(self):        # 初始化父类中的一些参数        super(Classifier, self).__init__()                self.fc1 = paddle.nn.Linear(in_features=29, out_features=40)        self.fc2 = paddle.nn.Linear(in_features=40, out_features=1)        self.relu = paddle.nn.ReLU()        # 网络的前向计算    def forward(self, inputs):        x = self.relu(self.fc1(inputs))        x = self.fc2(x)        return x

model = Classifier()model.train()opt = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())loss_fn = paddle.nn.BCEWithLogitsLoss()

W0427 14:43:44.334179   103 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 8.0, Driver API Version: 11.2, Runtime API Version: 11.2W0427 14:43:44.338698   103 device_context.cc:465] device: 0, cuDNN Version: 8.2.

EPOCH_NUM = 2   # 设置外层循环次数BATCH_SIZE = 100  # 设置batch大小training_data = train_df.iloc[:-1000,].values.astype(np.float32)val_data = train_df.iloc[-1000:, ].values.astype(np.float32)# 定义外层循环for epoch_id in range(EPOCH_NUM):    # 在每轮迭代开始之前，将训练数据的顺序随机的打乱        np.random.shuffle(training_data)        # 将训练数据进行拆分，每个batch包含10条数据    mini_batches = [training_data[k:k+BATCH_SIZE] for k in range(0, len(training_data), BATCH_SIZE)]        # 定义内层循环    for iter_id, mini_batch in enumerate(mini_batches):        x = np.array(mini_batch[:, 1:]) # 获得当前批次训练数据        y = np.array(mini_batch[:, :1]) # 获得当前批次训练标签                # 将numpy数据转为飞桨动态图tensor的格式        features = paddle.to_tensor(x)        y = paddle.to_tensor(y)                # 前向计算        predicts = model(features)                # 计算损失        loss = loss_fn(predicts, y, )        avg_loss = paddle.mean(loss)        if iter_id%200==0:            acc = (predicts > 0).astype(int).flatten() == y.flatten().astype(int)            acc = acc.astype(float).mean()            print("epoch: {}, iter: {}, loss is: {}, acc is {}".format(epoch_id, iter_id, avg_loss.numpy(), acc.numpy()))                # 反向传播，计算每层参数的梯度值        avg_loss.backward()        # 更新参数，根据设置好的学习率迭代一步        opt.step()        # 清空梯度变量，以备下一轮计算        opt.clear_grad()

epoch: 0, iter: 0, loss is: [0.6994627], acc is [0.49]epoch: 0, iter: 200, loss is: [0.7009081], acc is [0.36]epoch: 0, iter: 400, loss is: [0.6921266], acc is [0.57]epoch: 0, iter: 600, loss is: [0.6839013], acc is [0.64]epoch: 0, iter: 800, loss is: [0.6739801], acc is [0.75]epoch: 0, iter: 1000, loss is: [0.65885824], acc is [0.83]epoch: 0, iter: 1200, loss is: [0.66508365], acc is [0.71]epoch: 0, iter: 1400, loss is: [0.6578212], acc is [0.74]epoch: 0, iter: 1600, loss is: [0.6562445], acc is [0.72]epoch: 1, iter: 0, loss is: [0.6200185], acc is [0.85]epoch: 1, iter: 200, loss is: [0.62804365], acc is [0.79]epoch: 1, iter: 400, loss is: [0.6358215], acc is [0.75]epoch: 1, iter: 600, loss is: [0.6242084], acc is [0.76]epoch: 1, iter: 800, loss is: [0.6128205], acc is [0.78]epoch: 1, iter: 1000, loss is: [0.6186602], acc is [0.68]epoch: 1, iter: 1200, loss is: [0.57297456], acc is [0.79]epoch: 1, iter: 1400, loss is: [0.57423747], acc is [0.78]epoch: 1, iter: 1600, loss is: [0.58428985], acc is [0.75]

model.eval()test_data = paddle.to_tensor(test_df.values.astype(np.float32))test_predict = model(test_data)test_predict = (test_predict > 0).astype(int).flatten()

pd.DataFrame({'win':              test_predict.numpy()             }).to_csv('submission.csv', index=None)!zip submission.zip submission.csv

updating: submission.csv (deflated 90%)

总结与上分点

你是一名 AI 行业编辑，请围绕下面这条热点输出一份资讯解读：
热点：英雄联盟大师 Baseline要求：
1. 先用一句话解释这条热点在讲什么
2. 再总结它为什么重要
3. 说明会影响哪些 AI 产品或内容方向
4. 最后给出 3 个适合资讯站使用的标题