kaggle等算法比赛的合奏方法Ensemble（全）
2024-04-25 11:11:29
第一种（多输出回归问题）
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from scipy.stats import mode
import pandas as pd
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
np.set_printoptions(threshold=np.inf)
import os
for dirname, _, filenames in os.walk('input'):for filename in filenames:print(os.path.join(dirname, filename))df1 = pd.read_csv("input/0.48503.csv")
df2 = pd.read_csv("input/0.48743.csv")
df3 = pd.read_csv("input/0.48748.csv")
df4 = pd.read_csv("input/0.48874.csv")
df5 = pd.read_csv("input/0.48879.csv")
df6 = pd.read_csv("input/0.48908.csv")
df7 = pd.read_csv("input/0.49608.csv")
id_col = df1[['id']]
id_col.head()
df1.drop(['id'], axis=1, inplace=True)
df2.drop(['id'], axis=1, inplace=True)
df3.drop(['id'], axis=1, inplace=True)
df4.drop(['id'], axis=1, inplace=True)
df5.drop(['id'], axis=1, inplace=True)
df6.drop(['id'], axis=1, inplace=True)
df7.drop(['id'], axis=1, inplace=True)
df1.head() # example of output
# number of datasets for ensemble
N = 5
# either divide ensemble by number of components or assign them weights that sum to 1
w1 = 1/N+0.02
w2 = 1/N-0.005
w3 = 1/N-0.005
w4 = 1/N-0.006
w5 = 1/N-0.004
# w6 = 1/N
# w7 = 1/N
ensemble = w1*df1 + w2*df2 + w3*df3 + w4*df4 + w5*df5
# ensemble = w1*df1 + w2*df2 + w3*df3
predictions = pd.concat([id_col, ensemble], axis=1)
predictions.head()
predictions.to_csv('submission5_3.csv', index=False)
print(predictions)第二种（单输出分类）
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from scipy.stats import mode
import pandas as pd
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
np.set_printoptions(threshold=np.inf)
import os
for dirname, _, filenames in os.walk('input'):for filename in filenames:print(os.path.join(dirname, filename))df1 = pd.read_csv("input/0.96523.csv")
df2 = pd.read_csv("input/0.96334.csv")
df3 = pd.read_csv("input/0.96531.csv")
df4 = pd.read_csv("input/0.96487.csv")
df5 = pd.read_csv("input/0.95937.csv")
df6 = pd.read_csv("input/0.96620.csv")
df7 = pd.read_csv("input/0.94596.csv")
df8 = pd.read_csv("input/0.96552.csv")
df9 = pd.read_csv("input/0.95489.csv")
df10 = pd.read_csv("input/0.95532.csv")
df11 = pd.read_csv("input/0.95487.csv")
df12 = pd.read_csv("input/0.95914.csv")
df13 = pd.read_csv("input/0.95330.csv")
df14 = pd.read_csv("input/0.96703.csv")
df15 = pd.read_csv("input/0.96112.csv")
df16 = pd.read_csv("input/0.96739.csv")
df17 = pd.read_csv("input/0.96671.csv")
df18 = pd.read_csv("input/0.95637.csv")
df19 = pd.read_csv("input/0.96511.csv")
df20 = pd.read_csv("input/0.95959.csv")
df21 = pd.read_csv("input/0.95554.csv")print(df1)
df1.head()
df4.head()id_col = df1[['id']]
id_col.head()df1.drop(['id'], axis=1, inplace=True)
df2.drop(['id'], axis=1, inplace=True)
df3.drop(['id'], axis=1, inplace=True)
df4.drop(['id'], axis=1, inplace=True)
df5.drop(['id'], axis=1, inplace=True)
df6.drop(['id'], axis=1, inplace=True)
df7.drop(['id'], axis=1, inplace=True)
df8.drop(['id'], axis=1, inplace=True)
df9.drop(['id'], axis=1, inplace=True)
df10.drop(['id'], axis=1, inplace=True)
df11.drop(['id'], axis=1, inplace=True)
df12.drop(['id'], axis=1, inplace=True)
df13.drop(['id'], axis=1, inplace=True)
df14.drop(['id'], axis=1, inplace=True)
df15.drop(['id'], axis=1, inplace=True)
df16.drop(['id'], axis=1, inplace=True)
df17.drop(['id'], axis=1, inplace=True)
df18.drop(['id'], axis=1, inplace=True)
df19.drop(['id'], axis=1, inplace=True)
df20.drop(['id'], axis=1, inplace=True)
df21.drop(['id'], axis=1, inplace=True)print(df1.head()) # example of outputprint(df1.iat[1,0])data = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10,df11,df12,df13,df14,df15,df16,df17,df18,df19,df20,df21], axis=1)
print(data)
print(data.iloc[0])
print(mode(data.iloc[0])[0][0])
ensemble=np.zeros([data.shape[0]])
for i in range(data.shape[0]):ensemble[i] = int(mode(data.iloc[i])[0][0])ensemble[i] = ensemble[i].astype(np.int64)
print(pd.DataFrame(ensemble),type((ensemble[9])))ensemble=pd.DataFrame(ensemble,dtype=np.int64)
predictions = pd.concat([id_col, ensemble], axis=1)# predictions.head()
print(type(predictions.iat[1,1]))predictions.rename(columns={0:'label'},inplace=True)
print(predictions)predictions.to_csv('submission.csv', index=False)第三种（单变量回归）
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
# from scipy import stats
import pandas as pd
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
np.set_printoptions(threshold=np.inf)
import os
for dirname, _, filenames in os.walk('input'):for filename in filenames:print(os.path.join(dirname, filename))df1 = pd.read_csv("input/0.9240_submission.csv")
df2 = pd.read_csv("input/0.9240.csv")
df3 = pd.read_csv("input/0.9247.csv")
df4 = pd.read_csv("input/0.9344.csv")
df5 = pd.read_csv("input/0.9383.csv")
df6 = pd.read_csv("input/0.9354.csv")
df7 = pd.read_csv("input/0.9404_submission.csv")print(df1)
df1.head()
df4.head()id_col = df1[['id']]
id_col.head()df1.drop(['id'], axis=1, inplace=True)
df2.drop(['id'], axis=1, inplace=True)
df3.drop(['id'], axis=1, inplace=True)
df4.drop(['id'], axis=1, inplace=True)
df5.drop(['id'], axis=1, inplace=True)
df6.drop(['id'], axis=1, inplace=True)
df7.drop(['id'], axis=1, inplace=True)print(df1.head()) # example of outputprint(df1.iat[1,0])data = pd.concat([df1,df2,df3,df4,df5,df6,df7], axis=1)
print(data)
print(data.iloc[0])
# print(mode(data.iloc[0])[0][0])
ensemble=np.zeros([data.shape[0]])
for i in range(data.shape[0]):ensemble[i] = (np.mean(data.iloc[i]))ensemble[i] = ensemble[i].astype(np.float64)
print(pd.DataFrame(ensemble),type((ensemble[9])))ensemble=pd.DataFrame(ensemble,dtype=np.float64)
predictions = pd.concat([id_col, ensemble], axis=1)# predictions.head()
print(type(predictions.iat[1,1]))predictions.rename(columns={0:'toxic'},inplace=True)
print(predictions)predictions.to_csv('submission.csv', index=False)kaggle等算法比赛的合奏方法Ensemble（全）相关推荐
- Kaggle获奖者自述比赛求生指南：我们如何“穿越”亚马逊热带雨林
本文来自AI新媒体量子位(QbitAI) 大家好,我是思聪 · 格里尔斯,我将向您展示如何从世界上某些竞争最激烈的比赛中拿到金牌.我将面临一个月的比赛挑战,在这些比赛中缺乏正确的求生技巧,你甚至拿不到 ...
- Ai关于目标检测类算法比赛的经验总结
内容来源于 宅码,作者Ai. 附一张作者签名--艾宏峰! 导读: 本文为作者自己参加的三个目标检测类算法比赛的经验总结,分为五个部分:数据研究和准备.参数调节.模型验证以及模型融合,作者还给出了一些关 ...
- Kaggle新上比赛：Google AI发起地域包容性图像识别竞赛
(欢迎关注"我爱计算机视觉"公众号,一个有价值有深度的公众号~) 昨天Kaggle新上了一个关于图像识别的比赛,Google AI发起了地域包容性图像识别竞赛(Inclusive ...
- Kaggle新上比赛：胸部X光片肺炎检测
(欢迎关注"我爱计算机视觉"公众号,一个有价值有深度的公众号~) 今天北美放射学会(RSNA®)联合Kaggle发起了医学图像肺炎检测的比赛.医学图像中的肺炎视觉信号,表现为胸部X ...
- Kaggle新上比赛：空客公司卫星图像船体分割
今天Kaggle新上了一个计算机视觉目标分割方面的比赛(Airbus Ship Detection Challenge, Find ships on satellite images as quick ...
- Paddle打比赛-古籍文档图像识别与分析算法比赛
一.粤港澳大湾区(黄埔)国际算法算例大赛-古籍文档图像识别与分析算法比赛简介 1.背景及意义 中国几千年辉煌的华夏文明,留下了海量的古籍文献资料,这些文字记录承载着丰富的历史信息和文化传承.为响应古籍 ...
- 参加了个算法比赛，真是一言难尽啊
hello大家好呀,我是小楼. 上周参加了一个区的程序员技能比赛的初赛,其实就是算法比赛,虽然最后结果是过了初赛,但过程真是一言难尽啊. 这次的算法比赛和ACM非常类似,虽然我大学是数学专业,虽然大学 ...
- 【机器学习实战】第7章 集成方法 ensemble method
第7章 集成方法 ensemble method 集成方法: ensemble method(元算法: meta algorithm) 概述 概念:是对其他算法进行组合的一种形式. 通俗来说: 当做重 ...
- 你与ACM MM的距离只差一场算法比赛
你与ACM MM的距离只差一场算法比赛 伴随5G时代来临,视频广告迎来爆发式增长,在广告创意/投放/策略等广告系统的关键环节中,对视频广告内容的深度理解越发显得重要且迫切. 因此,2021腾讯广告算法 ...
最新文章
- flash，sdram 和 cpu 是 T形连接（类似于争的板子上flash和sdram的拓扑结构） --- FLASH搭上SDRAM，并不是你想象的那样不用布等长！...
- c语言的适当大小的子集,编译原理上机实验报告
- Oracle DML
- 电子发现与统一归档库
- 中国最难考的大学共有31所，分6大梯度，考上毕业很抢手
- linux系统适合电脑小白吗,linux小白说说用linux的感受
- 阿里云96页报告详解《云上转型》（10个案例、10大趋势/完整版PPT）
- 如何在水晶报表显示上下标
- 导入项目时中文乱码的消除
- 2021-06-26JS基本语法 入门
- UNIX环境高级编程(第三版)--开发环境搭建和第一个案例
- 混合线性模型如何检测固定因子和随机因子的显著性以及计算R2
- vue-JsMind思维导图实现（包含鼠标右键自定义菜单）
- 如何取消服务器自动关机,XP系统怎么取消自动关机？
- 晶体二极管 三极管 MOS原理
- Java for循环的几种用法详解（转载）
- 什么是二极管钳位电路
- 【pion】ice-single-port解析
- html网页组织结构,使用HTML和CSS编码创建组织结构图
- 五 根据用户名和手机号进行查询操作