Skip to content

Add incremental improvements of classier.#3

Merged
owlas merged 5 commits into
masterfrom
fea-incremental-classifier-improvements
May 4, 2017
Merged

Add incremental improvements of classier.#3
owlas merged 5 commits into
masterfrom
fea-incremental-classifier-improvements

Conversation

@andrazhribernik

@andrazhribernik andrazhribernik commented May 4, 2017

Copy link
Copy Markdown
Contributor

I added @matichorvat changes from #2 as well.

@owlas owlas self-requested a review May 4, 2017 16:35

@owlas owlas left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Additional steps are great. Thanks for spell check too

Comment thread tutorial.ipynb
"outputs": [],
"source": [
"pipeline.predict([\"Literally just 8 incredible dog videos.\"])"
"pipeline.predict([\"10 things you need to do...\"])"

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is the benefit of this? Maybe it wasn't intentional.

@andrazhribernik andrazhribernik May 4, 2017

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The original sentence was labeled as 0 when I switched from title + description into title only :)

Comment thread tutorial.ipynb Outdated
"source": [
"df['full_content'] = (df.description + df.title)\n",
"# df['full_content'] = (df.description + df.title)\n",
"df['full_content'] = (df.title)\n",

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is quite confusing. We can just use df.title in the notebook and then switch to df.full_content later to show the incremental benefit.

Comment thread tutorial.ipynb
},
{
"cell_type": "markdown",
"metadata": {},

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is model selection based on the testing data!

Comment thread tutorial.ipynb Outdated
"source": [
"from sklearn.metrics import accuracy_score\n",
"from sklearn.metrics import confusion_matrix\n",
"from utils.plotting import plot_confusion_matrix\n",

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The notebook would be tidier if this was moved into a separate file.

Comment thread tutorial.ipynb
" ('vectorizer', CountVectorizer()),\n",
" ('vectorizer', TfidfVectorizer()),\n",
" ('classifier', LinearSVC())\n",
")\n",

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice incremental addition

@owlas owlas reopened this May 4, 2017
@owlas owlas merged commit 01ea891 into master May 4, 2017
@owlas owlas deleted the fea-incremental-classifier-improvements branch May 4, 2017 20:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants