machine4life / recommenderSystem

for recommenderSystem
0 stars 0 forks source link

newbie #3

Open machine4life opened 6 years ago

machine4life commented 6 years ago
  1. python2 and python3 https://www.cnblogs.com/thunderLL/p/6643022.html
  2. pip3 install xgboost报错,在这里下载了whl,然后D:\Program Files\Python\common>pip install xgboost-0.7-cp36-cp36m-win_amd64.whl,更新(还是没解决,无法import) https://www.lfd.uci.edu/~gohlke/pythonlibs/#xgboost
    1. 解决了第二个问题。将Windows XP/WIN7系统,将dll复制到C:\Windows\System32目录下。 下载地址为: http://www.jb51.net/dll/vcomp140.dll.html
  3. python xgboost (备注python36) https://xgboost.readthedocs.io/en/latest/get_started/ 没有('demo/data/agaricus.txt.train') github克隆下来之后就有了 Administrator@SZ-20171205CSVD MINGW64 /d/code/xgboost (master) $ git clone https://github.com/dmlc/xgboost --recursive^C 报错feature_names mismatch XGBoost,其实是测试集整体没有覆盖全126个特征,不是指某一条。 http://blog.csdn.net/lujiandong1/article/details/52743396
  4. python sklearn logistic regression (备注python27) http://scikit-learn.org/stable/auto_examples/linear_model/plot_logistic_path.html#sphx-glr-auto-examples-linear-model-plot-logistic-path-py
  5. tensorflow无法访问 https://www.jianshu.com/p/3976adc80fc3 在hosts文件中添加 64.233.188.121 www.tensorflow.org 即可. ##且不要问64.233.188.121是什么
  6. TensorFlow自带wdl pip3 intall tensorflow python代码在这里还可以找到并成功运行 来自这篇博客http://www.cnblogs.com/zhanxiage1994/p/7489537.html https://github.com/tensorflow/tensorflow/edit/r1.3/tensorflow/examples/learn/wide_n_deep_tutorial.py python3 wide_n_deep_tutorial.py
machine4life commented 6 years ago

2.1 D:\Program Files\Python>cd common D:\Program Files\Python\common>pip install xgboost-0.7-cp36-cp36m-win_amd64.whl Processing d:\program files\python\common\xgboost-0.7-cp36-cp36m-win_amd64.whl Requirement already satisfied: scipy in d:\program files\python\python36\lib\sit e-packages (from xgboost==0.7) Requirement already satisfied: numpy in d:\program files\python\python36\lib\sit e-packages (from xgboost==0.7) Installing collected packages: xgboost Successfully installed xgboost-0.7 2.2 D:\Program Files\Python\common> image

machine4life commented 6 years ago

脚本之家下载-dll下载频道,帮您搞定文件丢失问题

www.jb51.net/dll/部分dll文件中有多个目录分别表示多个系统专用文件

X86表示32位系统 x64表示64位系统

dll控件常规安装方法(仅供参考):

一、如果在运行某软件或编译程序时提示缺少、找不到dll等类似提示,您可将从脚本之家下载来的dll拷贝到指定目录即可(一般是system系统目录或放到软件同级目录里面),或者重新添加文件引用。 二、直接拷贝该文件到系统目录里:    1、Windows 95/98/Me系统,将dll复制到C:\Windows\System目录下。    2、Windows NT/2000系统,将dll复制到C:\WINNT\System32目录下。    3、Windows XP/WIN7系统,将dll复制到C:\Windows\System32目录下。 三、打开"开始-运行-输入regsvr32 dll",回车即可解决。希望脚本之家为您提供的dll对您有所帮助。

通过脚本之家下载dll的朋友,可将下面的代码保存为“注册.bat“,放到dll目录,就会自动完成dll注册(win98不支持)。

@echo 开始注册 copy dll %windir%\system32\ regsvr32 %windir%\system32\dll /s @echo dll注册成功 @pause

machine4life commented 6 years ago
  1. Microsoft Windows [版本 6.1.7601] 版权所有 (c) 2009 Microsoft Corporation。保留所有权利。

C:\Users\Administrator>d:

D:>cd code

D:\code>cd web

D:\code\web>dir 驱动器 D 中的卷没有标签。 卷的序列号是 6C26-3BD2

D:\code\web 的目录

2018/02/05 11:15

. 2018/02/05 11:15 .. 2018/02/03 09:10 1,195 plot_logistic_path.py 2018/02/05 11:15 8,225 wide_n_deep_tutorial.py 2 个文件 9,420 字节 2 个目录 276,871,376,896 可用字节

D:\code\web>python3 wide_n_deep_tutorial.py Training data is downloaded to C:\Users\ADMINI~1\AppData\Local\Temp\tmp0ymc3xqo Test data is downloaded to C:\Users\ADMINI~1\AppData\Local\Temp\tmpfivq1p8j 2018-02-05 11:16:08.997030: I C:\tf_jenkins\workspace\rel-win\M\windows\PY\36\te nsorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2 WARNING:tensorflow:enqueue_data was called with num_epochs and num_threads > 1. num_epochs is applied per thread, so this will produce more epochs than you prob ably intend. If you want to limit epochs, use one thread. WARNING:tensorflow:enqueue_data was called with shuffle=False and num_threads >

  1. This will create multiple threads, all reading the array/dataframe in order. If you want examples read in order, use one thread; if you want multiple threads , enable shuffling. model directory = C:\Users\ADMINI~1\AppData\Local\Temp\tmpte27hivh accuracy: 0.8353909 accuracy_baseline: 0.76377374 auc: 0.8745185 auc_precision_recall: 0.7114024 average_loss: 0.37545654 global_step: 2000 label/mean: 0.23622628 loss: 37.50189 prediction/mean: 0.26989672

D:\code\web>