我正在使用Jupyter notebooks
创建一个ML Model with TuriCreate
。
我要执行的步骤如上所述。
我已经从https://www.kaggle.com/zynicide/wine-reviews下载了.csv和.json(相同文件)
文件大小为51 MB。
我从turienv
和建立了一个环境Anaconda Navigation
,以下步骤非常适合较小的CSV / JSON文件。
源激活turienv
pip install turicreate = 5.0
木星笔记本
----在笔记本内部----
import turicreate as tc
wine_data = tc.SFrame.read_json('winemag-data-130k-v2.json', orient='records')
wine_data.head() <-- I see that everything is loaded properly
wine_model = tc.text_classifier.create(wine_data,'title',features=['description'])
PROGRESS: Creating a validation set from 5 percent of training data. This may take a while.
You can set ``validation_set=None`` to disable validation tracking.
Logistic regression:
--------------------------------------------------------
Number of examples : 123481
Number of classes : 113404
Number of feature columns : 1
Number of unpacked features : 21030
Number of coefficients : 2384978493
Starting L-BFGS
--------------------------------------------------------
+-----------+----------+-----------+--------------+-------------------+---------------------+
| Iteration | Passes | Step size | Elapsed Time | Training Accuracy | Validation Accuracy |
+-----------+----------+-----------+--------------+-------------------+---------------------+
然后大约3-4分钟,我收到错误消息msg =内核似乎已经死亡。
有人可以帮忙吗?我是Python的新手,Jupyter仅与我合作过。如果还有其他环境,我可以在某些指导下运行相同的操作,以使我可以调试的错误消息更加可靠,请告诉我。
已编辑:我正在2018年MacBook Pro 16GB 512GB上运行以上命令。我在Activity Monitor上看到python的内存达到了130GB,CPU达到了83%
预先感谢