All Projects → ChuanyuXue → The-Purchase-and-Redemption-Forecast-Challenge-baseline

ChuanyuXue / The-Purchase-and-Redemption-Forecast-Challenge-baseline

Licence: other
天池“资金流入流出预测——挑战baseline”的解决方案,线上效果143.5

Programming Languages

Jupyter Notebook
11667 projects

Projects that are alternatives of or similar to The-Purchase-and-Redemption-Forecast-Challenge-baseline

Sktime
A unified framework for machine learning with time series
Stars: ✭ 4,741 (+5978.21%)
Mutual labels:  data-mining, time-series
Awesome Ts Anomaly Detection
List of tools & datasets for anomaly detection on time-series data.
Stars: ✭ 2,027 (+2498.72%)
Mutual labels:  data-mining, time-series
Elki
ELKI Data Mining Toolkit
Stars: ✭ 613 (+685.9%)
Mutual labels:  data-mining, time-series
Btctrading
Time Series Forecast with Bitcoin value, to detect upward/down trends with Machine Learning Algorithms
Stars: ✭ 99 (+26.92%)
Mutual labels:  time-series, prediction
sentometrics
An integrated framework in R for textual sentiment time series aggregation and prediction
Stars: ✭ 77 (-1.28%)
Mutual labels:  time-series, prediction
Sweep
Extending broom for time series forecasting
Stars: ✭ 143 (+83.33%)
Mutual labels:  time-series, prediction
Openhistorian
The Open Source Time-Series Data Historian
Stars: ✭ 120 (+53.85%)
Mutual labels:  data-mining, time-series
COVID19
Using Kalman Filter to Predict Corona Virus Spread
Stars: ✭ 78 (+0%)
Mutual labels:  time-series, prediction
Open Solution Toxic Comments
Open solution to the Toxic Comment Classification Challenge
Stars: ✭ 154 (+97.44%)
Mutual labels:  competition, prediction
Hefei ECG TOP1
“合肥高新杯”心电人机智能大赛 —— 心电异常事件预测 TOP1 Solution
Stars: ✭ 109 (+39.74%)
Mutual labels:  competition, data-mining
Neural prophet
NeuralProphet - A simple forecasting model based on Neural Networks in PyTorch
Stars: ✭ 1,125 (+1342.31%)
Mutual labels:  time-series, prediction
timemachines
Predict time-series with one line of code.
Stars: ✭ 342 (+338.46%)
Mutual labels:  time-series, prediction
Deep Learning Time Series
List of papers, code and experiments using deep learning for time series forecasting
Stars: ✭ 796 (+920.51%)
Mutual labels:  time-series, prediction
Timetk
A toolkit for working with time series in R
Stars: ✭ 371 (+375.64%)
Mutual labels:  data-mining, time-series
Rnn Time Series Anomaly Detection
RNN based Time-series Anomaly detector model implemented in Pytorch.
Stars: ✭ 718 (+820.51%)
Mutual labels:  time-series, prediction
Tsrepr
TSrepr: R package for time series representations
Stars: ✭ 75 (-3.85%)
Mutual labels:  data-mining, time-series
Matrixprofile
A Python 3 library making time series data mining tasks, utilizing matrix profile algorithms, accessible to everyone.
Stars: ✭ 141 (+80.77%)
Mutual labels:  data-mining, time-series
awesome-Python-data-science-books
Probably the best curated list of data science books in Python
Stars: ✭ 331 (+324.36%)
Mutual labels:  data-mining, time-series
PyDREAM
Python Implementation of Decay Replay Mining (DREAM)
Stars: ✭ 22 (-71.79%)
Mutual labels:  data-mining, prediction
Start maja
To process a Sentinel-2 time series with MAJA cloud detection and atmospheric correction processor
Stars: ✭ 47 (-39.74%)
Mutual labels:  time-series

The-Purchase-and-Redemption-Forecast-Challenge-baseline

天池“资金流入流出预测——挑战baseline”的解决方案,线上效果143.5

项目结构

  1. 数据探索与分析 对于赛题的理解与对数据的分析
  2. 数据探索与分析 对于赛题的理解与对数据的分析
  3. 时间序列规则 采用简单时间序列规则进行预测
  4. 时间序列 采用时间序列模型进行预测(本章节未上传,但不影响继续后面几个章节)
  5. 特征工程 面向机器学习模型进行时间序列特征工程
  6. 建模预测 采用机器学习模型进行建模预测

/slide 文件夹存放了代码对应的课件

Q&A

Q: 我在运行您的第6个文件时发现缺少数据,请问是否缺少文件,遇到这个问题可以怎么 处理?
A: 首先您需要先运行05.特征工程生成特征文件保存在./Feature目录下。其次06.建模预测中对Purchase以及Redeem分别建模,因此您需要将05.特征工程中的Purchase替换成Redeem再次运行一遍,以生成Redeem特征。

Q: 您好!在天池竞赛——资金流入流出预测中,在训练模型的时候发现某个文件不存在feature0522.csv,请问是否存在其他脚本,如果有可以发一下吗?
A: feature0522并没有实际生成,您可以读取05.特征工程中生成的purchase_feature_droped_0614.csv文件,在建模时删除特征名中不带有"is"的特征,与feature0522建模效果是等价的。

声明

本项目库专门存放阿里天池在线课程《资金流入流出预测-挑战Baseline》的相关代码文件,所有代码仅供各位同学学习参考使用,未经许可不得用于商业用途。如有任何对代码的问题请邮箱联系:[email protected]

知乎ID:小雨姑娘

天池ID:小雨姑娘 & BruceQD

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].