quick analysis and dataanalysis pipleline
Project description
#a pipeline for quick data analysis and machine learning
##file_operate:
123
- read file and do base operate like auto asdtype etc.
- it support multi type files operates together.
##preprocess:
create a preprocessor to preprocessing(dropna,fillna,dropoutlyers...)
you can select the file and cols by passing dict-type args.
##analysis: base on the previous manipulations,we get clean datas,we can now acutally start the analysis tasks: correlation: get correlations between value-type features and labels. compare the correlation between class-type features and labels.
##modeling: we provide base ml models to complete classification or regression tasks listing: gbdt:xgboost,light gbm,radom forests norm:svc,linear,logistic,bayes timesequence:ARMA,ARIMA nn: DeepLearning:\
statistic_test:
normality test
correlation test
significance test
parametric test
nonparametric test
表头 | 表头 |
---|---|
单元格 | 单元格 |
单元格 | 单元格 |
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
quickpanda_aidroid-0.0.1.tar.gz
(18.5 kB
view hashes)
Built Distribution
Close
Hashes for quickpanda_aidroid-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8a97c3cc23b742467af338895a2a45abeffbe3b6e154e48e0c0e9fd7d9b30938 |
|
MD5 | f46c4e831b7423641585a8e0074e8d0e |
|
BLAKE2b-256 | fc343e04e71c69f9675d1c4182a4fbd0f35e796391689b6de33e9bae8152511a |