文章目录
1. 项目综述
本文基于英特尔 oneAPI AI分析工具套件，对汽车工人打胶数据进行分析建模，构建汽车工人打胶评价体系，给出高精度胶质流体模拟预测方案。并基于模型训练结果给出调整建议，规范打胶手工操作流程。该项目可作为汽车涂胶车间新员工的技能培训的重要参考，同时构建的评价体系针对手工操作培训场景具有很强的延伸性与扩展性。
1.1 项目背景
在现代汽车制造业中，胶水在车辆组装过程中起着至关重要的作用，用于连接各种零部件和确保车辆的质量和安全性。然而，正确打胶是一项技术活，需要工人具备一定的经验和技能，以确保打胶的质量和一致性。传统的打胶手工培训通常依赖于经验丰富的员工进行传帮带，这种培训方法存在一些问题，如培训时间长、培训成本高、一致性差等。
-
为了解决这些问题，我们提出了基于英特尔 OneAPI AI 分析工具套件的汽车工人打胶数据分析建模项目。这个项目不仅可以帮助评估工人的打胶技能，还可以提供实时的速度和角度调整建议，以确保打胶的质量和效率。同时，这个项目还将建立一个全面的打胶评价体系，以便针对不同的打胶任务和技能水平提供培训解决方案。
-
本项目基于 AI 分析工具套件提供了技术驱动的培训模式，基于该项目，我们团队开发员工打胶培训系统，记录并分析员工学习情况，借助虚拟协同技术对员工进行上岗前培训，提供实时反馈与调整建议，在提供生产质量的同时降低企业生产成本，实现技术驱动生产。
-
建立的评价体系不仅适用于新员工的技能培训，还可以用于现有员工的技能提升和评估。此外，这个体系还可以扩展到其他手工操作场景，如焊接、组装等，为制造业提供更广泛的解决方案，具有很强的扩展性与易用性
1.3 项目具体任务
经过团队成员讨论，本次建模任务有以下内容：
- 根据提供的数据信息判断工人一条打胶数据是否合格
- 给出各点位速度、角度调整建议
- 建立工人打胶训练评价标准，结合虚拟协同技术提供员工培训解决方案
2. 系统环境配置
本项目基于Ubuntu 20.04系统开发，在conda中创建python虚拟环境，并安装相关依赖，附录1是本次开发环境中库版本信息.
2.1 虚拟环境安装
本项目中基于conda进行各依赖库的安装与版本控制，conda安装与基本使用方法很多教程中有讲解，有需要的小伙伴可参考进行虚拟环境的安装与配置，在项目开始前系统中需具备python编程环境
下面是一些参考文档链接：
2.2 OneAPI AI分析工具安装
Intel官网提供OneAPI相关的安装教程，下面是本团队安装过程的记录，仅供参考。
- Step1 Download the Toolkit
下载链接: https://www.intel.com/content/www/us/en/developer/tools/oneapi/ai-analytics-toolkit-download.html?operatingsystem=linux&distributions=aptpackagemanager
该下载链接提供在线、离线、命令行等多种下载方式，在该页面中选择系统版本linux/windows后，选择合适的下载方式，考虑到网速问题，我选择离线安装的方式，将安装包下载到本地，解压后安装。
- 离线安装方式
# 注意，安装时可能需要sudo权限
wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/af4bc50d-898e-45a4-8f7d-378448ba294a/l_AIKit_p_2023.2.0.48997_offline.sh
./l_AIKit_p_2023.2.0.48997_offline.sh
- Step2 Configure the System
- 配置系统环境变量
下面这种方法，每次打开新的终端都要执行一遍，使其在当前终端有效，这样方可使用自带的虚拟环境
----- method -------
cd <安装目录>
sh setvars.sh
----- example ------
. ~/intel/oneapi/setvars.sh
或者修改系统配置文件，这种方法配置一次即可永久生效，具体操作请参考官方文档
step1:打开.bashrc文件
vim ~/.bashrc
step2:在文档末尾追加命令
source <install_dir>/setvars.sh
step3:保存文件后退出
- step3: Conda使用
安装包中提供以下基本虚拟环境供用户使用，我们可以使用conda相关命令查看、创建、进入虚拟环境，进行项目的开发
--- 查看系统中已有环境
conda env list
--- 激活某个虚拟环境
conda activate <env_name>
2.3 Jupyter安装与使用
项目开发中使用notebook，需要在环境中安装
- 安装notebook
pip install notebook
- 启动notebook
jupyter notebook --notebook-dir=./ --ip=* --no-browser
启动后浏览器自动打开，工作区为当前目录
3. 数据分析
3.1 数据结构
汽车后备箱前盖部位结构复杂，无法实现机器打胶，需要工人师傅手持胶枪完成打胶操作，整个过程中胶枪的角度、速度将直接影响涂胶质量。
-
数据集中提供打胶过程中17个点位速度、角度信息，具体数据格式如下图所示：
3.2 数据特征
我们团队进行数据清洗、特征值分析等预处理工作，分析后发现，工人打胶数据属于小规模、弱特征数据，需要基于实际场景进行深入特征工程和模型调优
4.建模与分析
4.1 模型建立过程
考虑到工业数据小规模、弱特征的特点，在建模过程中采用规则与算法模型相结合的策略，利用OneAPi官方提供的相关api接口做训练，采用RandomForest对打胶数据是否合格做分类，利用XGBboost算法对数据做回归，两者结合给出调整建议，提高模型的泛化能力，借助英特尔 Intel® AI Analytics Toolkit做模型优化与加速，试验结果表明 Intel® AI Analytics Toolkit 实现接近2倍的性能加速。
4.3 使用oneMKL进行流体仿真计算模型构建
为了进一步还原真实打胶过程，考虑到胶体黏合速度、流动方向对打胶效果的影响，我们团队进行流体动力学建模与仿真，借助oneMKL构建流体仿真计算模型
oneMKL作为Intel高性能数学函数库，提供跨各种CPU和加速器的最高性能。该高度优化和广泛并行化的例程提供到FFT、随机数、稀疏和稠密线性代数等数据分析工具，极大便利打胶模拟过程
4.2 使用Intel® AI Analytics Toolkit加速
Intel® AI Analytics Toolkit一个显著的优点是可以在基本不改动原有代码基础上对算法进行优化加速，表现出优异的模型推理能力，下面代码是源程序中使用方式，详细过程请参考源文件。
from sklearnex import patch_sklearn
patch_sklearn()
#随机森林构建与训练
from sklearn.ensemble import RandomForestClassifier
start = timer()
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
train_patched = timer() - start
f"Intel® extension for Scikit-learn time: {train_patched:.2f} s"
下面的结果可以看出 ，在模型训练准确率相同的情况下，使用OneAPI AI分析工具可提高模型训练速度2倍以上，表现出更优的性能。
- 使用Analytics Toolkit加速
- 未使用Analytics Toolkit加速
4.3 Intel® Extension for Scikit-learn使用过程
- 英特尔 Scikit-learn 扩展 * 无缝地加速了英特尔 CPU 和 GPU 跨单节点和多节点配置的 Scikit-learn 应用程序，在机器学习、数据分析领域表现出优异的性能。
- 作为AI分析工具中的一部分，本项目主要基于Scikit-learn库提供的api进行模型的训练与推理
- 下面给出代码源代码的一部分，使用XGBboost库中的接口对模型进行训练和推理
import pandas as pd
import numpy as np
from timeit import default_timer as timer
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
from sklearn.linear_model import LogisticRegression
import csv
import json
# 读取qualified 数据
with open('./dataset/vgra_qualified_round_train_202308.txt', 'r', encoding='utf-8', errors='ignore') as f:
json_string = f.read()
# 将文件内容转换为Python对象
json_data = json.loads(json_string)
# 创建CSV文件并写入数据
with open('vgra_qualified_round_train_202308.csv', 'w', newline='') as csvfile:
fieldnames = ['areaName', 'allisQualified', 'pointName', 'pointisQualified', 'speed', 'angle', 'isValid']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for track_result in json_data['trackResults']:
for area in track_result['trackArea']:
allisQualified = area['isQualified']
for point in area['trackPoints']:
row = {
'areaName': area['areaName'],
'allisQualified': allisQualified,
'pointName': point['pointName'],
'pointisQualified': point['isQualified'],
'speed': point['speed'],
'angle': point['angle'],
'isValid': True
}
writer.writerow(row)
print("结果已保存到 vgra_qualified_round_train_202308.csv 文件中。")
true_data=pd.read_csv('vgra_qualified_round_train_202308.csv')
true_data
# 读取unqualified 数据
# 读取文件内容
with open('./BMWtest/vgra_unqualified_round_train_202308.txt', 'r', encoding='utf-8', errors='ignore') as f:
json_string = f.read()
# 将文件内容转换为Python对象
json_data = json.loads(json_string)
# 创建CSV文件并写入数据
with open('vgra_unqualified_round_train_202308.csv', 'w', newline='') as csvfile:
fieldnames = ['areaName', 'allisQualified','pointName', 'pointisQualified', 'speed', 'angle', 'isValid']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for track_result in json_data['trackResults']:
for area in track_result['trackArea']:
allisQualified = area['isQualified']
for point in area['trackPoints']:
row = {
'areaName': area['areaName'],
'allisQualified': allisQualified,
'pointName': point['pointName'],
'pointisQualified': point['isQualified'],
'speed': point['speed'],
'angle': point['angle'],
'isValid': point['isValid']
}
writer.writerow(row)
print("结果已保存到 vgra_unqualified_round_train_202308.csv 文件中。")
# 读取文件内容
with open('./BMWtest/vgra_qualified_round_test_202308.txt', 'r', encoding='utf-8', errors='ignore') as f:
json_string = f.read()
# 将文件内容转换为Python对象
json_data = json.loads(json_string)
# 创建CSV文件并写入数据
with open('vgra_qualified_round_test_202308.csv', 'w', newline='') as csvfile:
fieldnames = ['areaName', 'allisQualified','pointName', 'pointisQualified', 'speed', 'angle']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for track_result in json_data['trackResults']:
for area in track_result['trackArea']:
allisQualified = area['isQualified']
for point in area['trackPoints']:
row = {
'areaName': area['areaName'],
'allisQualified': allisQualified,
'pointName': point['pointName'],
'pointisQualified': point['isQualified'],
'speed': point['speed'],
'angle': point['angle']
}
writer.writerow(row)
print("结果已保存到 vgra_qualified_round_test_202308.csv 文件中。")
#导入随机森林
from sklearn.ensemble import RandomForestClassifier
项目最终展示
附录1
# packages in environment at /home/hanbingq/intel/oneapi/intelpython/latest/envs/usr_intelpython:
#
# Name Version Build Channel
_libgcc_mutex 0.1 main file:///home/hanbingq/intel/oneapi/conda_channel
_openmp_mutex 5.1 1_gnu file:///home/hanbingq/intel/oneapi/conda_channel
anyio 3.7.1 pypi_0 pypi
argon2-cffi 23.1.0 pypi_0 pypi
argon2-cffi-bindings 21.2.0 pypi_0 pypi
arrow 1.2.3 pypi_0 pypi
asn1crypto 1.5.1 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
asttokens 2.2.1 pypi_0 py39h27cfd23_1003 file:///home/hanbingq/intel/oneapi/conda_channel
bzip2 1.0.8 hb9a14ef_9 file:///home/hanbingq/intel/oneapi/conda_channel
c-ares 1.18.1 h7f8727e_0 file:///home/hanbingq/intel/oneapi/conda_channel
ca-certificates 2023.01.10 h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
certifi 2022.12.7 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
cffi 1.15.1 py39h74dc2b5_0 file:///home/hanbingq/intel/oneapi/conda_channel
chardet 4.0.0 py39h06a4308_1003 file:///home/hanbingq/intel/oneapi/conda_channel
charset-normalizer 2.0.4 pyhd3eb1b0_0 file:///home/hanbingq/intel/oneapi/conda_channel
comm 0.1.4 pypi_0 pypi
common_cmplr_lib_rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
common_cmplr_lic_rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
conda-package-handling 2.0.2 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
conda-package-streaming 0.7.0 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
contourpy 1.1.0 pypi_0 pypi
cryptography 39.0.1 py39h9ce1e76_0 file:///home/hanbingq/intel/oneapi/conda_channel
cycler 0.11.0 pyhd3eb1b0_0 file:///home/hanbingq/intel/oneapi/conda_channel
cython 0.29.33 py39ha718fea_0 file:///home/hanbingq/intel/oneapi/conda_channel
daal4py 2023.1.0 py39_intel_46349 file:///home/hanbingq/intel/oneapi/conda_channel
dal 2023.1.0 intel_46349 file:///home/hanbingq/intel/oneapi/conda_channel
debugpy 1.6.7.post1 pypi_0 pypi
decorator 5.1.1 pypi_0 pypi
defusedxml 0.7.1 pypi_0 pypi
dpcpp-cpp-rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
dpcpp-llvm-spirv 2023.0.0 py39h065f59b_25370 file:///home/hanbingq/intel/oneapi/conda_channel
dpcpp_cpp_rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
dpctl 0.14.2 py39ha23a21d_9 file:///home/hanbingq/intel/oneapi/conda_channel
dpnp 0.11.1 py39h193dc20_12 file:///home/hanbingq/intel/oneapi/conda_channel
exceptiongroup 1.1.3 pypi_0 pypi
executing 1.2.0 pypi_0 pypi
fastjsonschema 2.18.0 pypi_0 pypi
fonttools 4.42.1 pypi_0 pypi
fortran_rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
fqdn 1.5.1 pypi_0 pypi
freetype 2.12.1 hb267b13_2 file:///home/hanbingq/intel/oneapi/conda_channel
funcsigs 1.0.2 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
future 0.18.3 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
icc_rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
idna 3.4 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
impi_rt 2021.9.0 intel_43482 file:///home/hanbingq/intel/oneapi/conda_channel
importlib-metadata 6.8.0 pypi_0 pypi
importlib-resources 6.0.1 pypi_0 pypi
intel-cmplr-lib-rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
intel-cmplr-lic-rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
intel-fortran-rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
intel-opencl-rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
intel-openmp 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
intelpython 2023.1.0 1 file:///home/hanbingq/intel/oneapi/conda_channel
ipp 2021.8.0 intel_46345 file:///home/hanbingq/intel/oneapi/conda_channel
ipykernel 6.25.1 pypi_0 pypi
ipython 8.14.0 pypi_0 pypi
ipython-genutils 0.2.0 pypi_0 pypi
isoduration 20.11.0 pypi_0 pypi
jedi 0.19.0 pypi_0 pypi
jinja2 3.1.2 pypi_0 pypi
joblib 1.2.0 pyh3f38642_0 file:///home/hanbingq/intel/oneapi/conda_channel
json5 0.9.14 pypi_0 pypi
jsonpointer 2.4 pypi_0 pypi
jsonschema 4.19.0 pypi_0 pypi
jsonschema-specifications 2023.7.1 pypi_0 pypi
jupyter-client 8.3.0 pypi_0 pypi
jupyter-contrib-core 0.4.2 pypi_0 pypi
jupyter-contrib-nbextensions 0.7.0 pypi_0 pypi
jupyter-core 5.3.1 pypi_0 pypi
jupyter-events 0.7.0 pypi_0 pypi
jupyter-highlight-selected-word 0.2.0 pypi_0 pypi
jupyter-lsp 2.2.0 pypi_0 pypi
jupyter-nbextensions-configurator 0.6.3 pypi_0 pypi
jupyter-server 2.7.2 pypi_0 pypi
jupyter-server-terminals 0.4.4 pypi_0 pypi
jupyterlab 4.0.5 pypi_0 pypi
jupyterlab-pygments 0.2.2 pypi_0 pypi
jupyterlab-server 2.24.0 pypi_0 pypi
kiwisolver 1.4.2 py39h295c915_0 file:///home/hanbingq/intel/oneapi/conda_channel
libarchive 3.6.2 hb7eea22_0 file:///home/hanbingq/intel/oneapi/conda_channel
libevent 2.1.12 h8f2d780_0 file:///home/hanbingq/intel/oneapi/conda_channel
libffi 3.3 he6710b0_2 file:///home/hanbingq/intel/oneapi/conda_channel
libgcc-ng 11.2.0 h1234567_1 file:///home/hanbingq/intel/oneapi/conda_channel
libgfortran-ng 11.2.0 h00389a5_1 file:///home/hanbingq/intel/oneapi/conda_channel
libgfortran5 11.2.0 h1234567_1 file:///home/hanbingq/intel/oneapi/conda_channel
libgomp 11.2.0 h1234567_1 file:///home/hanbingq/intel/oneapi/conda_channel
libllvm11 11.0.0 h3826bc1_1 file:///home/hanbingq/intel/oneapi/conda_channel
libpng 1.6.39 h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
libprotobuf 3.20.3 he621ea3_0 file:///home/hanbingq/intel/oneapi/conda_channel
libstdcxx-ng 11.2.0 h1234567_1 file:///home/hanbingq/intel/oneapi/conda_channel
libxml2 2.10.3 h6b0140f_0 file:///home/hanbingq/intel/oneapi/conda_channel
llvm 11.0.0 h06a4308_1 file:///home/hanbingq/intel/oneapi/conda_channel
llvm-spirv 11.0.0 h4616538_1 file:///home/hanbingq/intel/oneapi/conda_channel
llvmlite 0.39.1 py39he188f65_0 file:///home/hanbingq/intel/oneapi/conda_channel
lxml 4.9.3 pypi_0 pypi
lz4-c 1.9.4 h6a678d5_0 file:///home/hanbingq/intel/oneapi/conda_channel
lzo 2.10 h7b6447c_2 file:///home/hanbingq/intel/oneapi/conda_channel
markupsafe 2.1.3 pypi_0 pypi
matplotlib 3.7.2 pypi_0 pypi
matplotlib-inline 0.1.6 pypi_0 pypi
mistune 3.0.1 pypi_0 pypi
mkl 2023.1.0 intel_46342 file:///home/hanbingq/intel/oneapi/conda_channel
mkl-dpcpp 2023.1.0 intel_46342 file:///home/hanbingq/intel/oneapi/conda_channel
mkl-service 2.4.0 py39h75d02e3_15 file:///home/hanbingq/intel/oneapi/conda_channel
mkl_fft 1.3.5 py39ha5a625c_11 file:///home/hanbingq/intel/oneapi/conda_channel
mkl_random 1.2.2 py39h0b06908_51 file:///home/hanbingq/intel/oneapi/conda_channel
mkl_umath 0.1.1 py39h450dca2_61 file:///home/hanbingq/intel/oneapi/conda_channel
mpi4py 3.1.4 py39h618b5fa_0 file:///home/hanbingq/intel/oneapi/conda_channel
nbclient 0.8.0 pypi_0 pypi
nbconvert 7.7.4 pypi_0 pypi
nbformat 5.9.2 pypi_0 pypi
ncurses 6.4 h6a678d5_0 file:///home/hanbingq/intel/oneapi/conda_channel
nest-asyncio 1.5.7 pypi_0 pypi
notebook 7.0.2 pypi_0 pypi
notebook-shim 0.2.3 pypi_0 pypi
numba 0.56.4 py39h7826fa9_1 file:///home/hanbingq/intel/oneapi/conda_channel
numba-dpex 0.20.0 py39h5027c17_16 file:///home/hanbingq/intel/oneapi/conda_channel
numpy 1.23.5 py39h52df89b_7 file:///home/hanbingq/intel/oneapi/conda_channel
numpy-base 1.23.5 py39ha03f565_7 file:///home/hanbingq/intel/oneapi/conda_channel
opencl_rt 2023.1.0 intel_46305 file:///home/hanbingq/intel/oneapi/conda_channel
openssl 1.1.1t h7f8727e_0 file:///home/hanbingq/intel/oneapi/conda_channel
overrides 7.4.0 pypi_0 pypi
packaging 22.0 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
pandas 1.5.2 py39h385cf95_0 file:///home/hanbingq/intel/oneapi/conda_channel
pandocfilters 1.5.0 pypi_0 pypi
parso 0.8.3 pypi_0 pypi
pexpect 4.8.0 pypi_0 pypi
pickleshare 0.7.5 pypi_0 pypi
pillow 10.0.0 pypi_0 pypi
pip 23.0.1 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
platformdirs 3.10.0 pypi_0 pypi
pluggy 1.0.0 py39h06a4308_1 file:///home/hanbingq/intel/oneapi/conda_channel
prometheus-client 0.17.1 pypi_0 pypi
prompt-toolkit 3.0.39 pypi_0 pypi
psutil 5.9.5 pypi_0 pypi
ptyprocess 0.7.0 pypi_0 pypi
pure-eval 0.2.2 pypi_0 pypi
pycosat 0.6.4 py39h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
pycparser 2.21 pyhd3eb1b0_0 file:///home/hanbingq/intel/oneapi/conda_channel
pygments 2.16.1 pypi_0 pypi
pyopenssl 23.0.0 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
pyparsing 3.0.9 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
pysocks 1.7.1 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
python 3.9.16 h2722d68_1 file:///home/hanbingq/intel/oneapi/conda_channel
python-dateutil 2.8.2 pyhd3eb1b0_0 file:///home/hanbingq/intel/oneapi/conda_channel
python-json-logger 2.0.7 pypi_0 pypi
python-libarchive-c 2.9 pyhd3eb1b0_1 file:///home/hanbingq/intel/oneapi/conda_channel
pytz 2022.7 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
pyyaml 6.0 py39h5eee18b_1 file:///home/hanbingq/intel/oneapi/conda_channel
pyzmq 25.1.1 pypi_0 pypi
readline 8.2 h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
referencing 0.30.2 pypi_0 pypi
requests 2.28.1 py39h06a4308_1 file:///home/hanbingq/intel/oneapi/conda_channel
rfc3339-validator 0.1.4 pypi_0 pypi
rfc3986-validator 0.1.1 pypi_0 pypi
rpds-py 0.9.2 pypi_0 pypi
ruamel.yaml 0.17.21 py39h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
ruamel.yaml.clib 0.2.6 py39h5eee18b_1 file:///home/hanbingq/intel/oneapi/conda_channel
scikit-learn 1.2.1 py39h6a678d5_0 file:///home/hanbingq/intel/oneapi/conda_channel
scikit-learn-intelex 2023.1.0 py39_intel_46349 file:///home/hanbingq/intel/oneapi/conda_channel
scipy 1.7.3 py39h4ca98da_8 file:///home/hanbingq/intel/oneapi/conda_channel
seaborn 0.12.2 pypi_0 pypi
send2trash 1.8.2 pypi_0 pypi
setuptools 65.6.3 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
six 1.16.0 pyhd3eb1b0_1 file:///home/hanbingq/intel/oneapi/conda_channel
smp 0.1.5 py39h4ba20aa_0 file:///home/hanbingq/intel/oneapi/conda_channel
snappy 1.1.9 h295c915_0 file:///home/hanbingq/intel/oneapi/conda_channel
sniffio 1.3.0 pypi_0 pypi
soupsieve 2.4.1 pypi_0 pypi
spirv-tools 2021.4 h6bb024c_0 file:///home/hanbingq/intel/oneapi/conda_channel
sqlite 3.40.1 h5082296_0 file:///home/hanbingq/intel/oneapi/conda_channel
stack-data 0.6.2 pypi_0 pypi
tbb 2021.9.0 intel_43484 file:///home/hanbingq/intel/oneapi/conda_channel
tbb4py 2021.9.0 py39_intel_43484 file:///home/hanbingq/intel/oneapi/conda_channel
tcl 8.6.10 2 file:///home/hanbingq/intel/oneapi/conda_channel
terminado 0.17.1 pypi_0 pypi
threadpoolctl 2.2.0 pyh0d69192_0 file:///home/hanbingq/intel/oneapi/conda_channel
tinycss2 1.2.1 pypi_0 pypi
tk 8.6.12 h1ccaba5_0 file:///home/hanbingq/intel/oneapi/conda_channel
tomli 2.0.1 pypi_0 pypi
toolz 0.12.0 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
tornado 6.3.3 pypi_0 pypi
tqdm 4.64.0 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
traitlets 5.9.0 pypi_0 pypi
typing-extensions 4.7.1 pypi_0 pypi
uri-template 1.3.0 pypi_0 pypi
urllib3 1.26.14 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
wcwidth 0.2.6 pypi_0 pypi
webcolors 1.13 pypi_0 pypi
webencodings 0.5.1 pypi_0 pypi
websocket-client 1.6.2 pypi_0 pypi
wheel 0.38.4 py39h06a4308_0 file:///home/hanbingq/intel/oneapi/conda_channel
xgboost 1.7.3 0_gfed039py39_0 file:///home/hanbingq/intel/oneapi/conda_channel
xz 5.2.8 h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
yaml 0.2.5 h7b6447c_0 file:///home/hanbingq/intel/oneapi/conda_channel
zipp 3.16.2 pypi_0 pypi
zlib 1.2.13 h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
zstandard 0.19.0 py39h5eee18b_0 file:///home/hanbingq/intel/oneapi/conda_channel
zstd 1.4.5 h9ceee32_0 file:///home/hanbingq/intel/oneapi/conda_channel
(usr_intelpython) hanbingq@hanbingq-RESCUER-R720-15IKBN:~/intelopenai$
9589
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
