DeepChem | Windows 10下anaconda3环境从源码构建并安装deepchem

环境依赖

• 微软构建工具2015年更新3

      https://visualstudio.microsoft.com/ja/downloads/

• Anaconda3 

      Python 3.7.9

编译安装

创建deepchem虚拟环境

conda create -n deepchem python=3.7

激活虚拟环境并安装依赖包

conda activate deepchem (deepchem) >conda install tensorflow (deepchem) >conda install tensorflow-probability (deepchem) >conda install pandas joblib scikit-learn numpy

安装Git

(deepchem) >conda install git

克隆deepchem (deepchem) >git clone https://github.com/deepchem/deepchem.git

编译安装deepchem

(deepchem) >cd deepchem (deepchem) >python setup.py install

# Name                    Version                   Build  Channel deepchem                  2.4.0rc1.dev20210105175316          pypi_0    pypi

基于DeepChem的多任务学习

Columns of dataset: ['MUV-466' 'MUV-548' 'MUV-600' 'MUV-644' 'MUV-652' 'MUV-689' 'MUV-692' 'MUV-712' 'MUV-713' 'MUV-733' 'MUV-737' 'MUV-810' 'MUV-832' 'MUV-846' 'MUV-852' 'MUV-858' 'MUV-859' 'mol_id' 'smiles']Number of examples in dataset: 10000

Loading raw samples now.shard_size: 8192About to start loading CSV from medium_muv.csv.gzLoading shard 1 of size 8192.Featurizing sample 0Featurizing sample 1000Featurizing sample 2000Featurizing sample 3000Featurizing sample 4000Featurizing sample 5000Featurizing sample 6000Featurizing sample 7000Featurizing sample 8000TIMING: featurizing shard 0 took 25.886 sLoading shard 2 of size 8192.Featurizing sample 0Featurizing sample 1000TIMING: featurizing shard 1 took 5.656 sTIMING: dataset construction took 31.964 sLoading dataset from disk.

Computing train/valid/test indicesTIMING: dataset construction took 0.639 sLoading dataset from disk.TIMING: dataset construction took 0.371 sLoading dataset from disk.TIMING: dataset construction took 0.263 sLoading dataset from disk.