Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / evaluate /main /en /custom_evaluator.html
HuggingFaceDocBuilder
about 22 hours ago
download
raw
27.6 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Using the evaluator with custom pipelines&quot;,&quot;local&quot;:&quot;using-the-evaluator-with-custom-pipelines&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Scikit-Learn&quot;,&quot;local&quot;:&quot;scikit-learn&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Spacy&quot;,&quot;local&quot;:&quot;spacy&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/evaluate/main/en/_app/immutable/entry/start.BR5Aqcvb.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/DqHwGgZ9.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/DfHjNWj2.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/entry/app.DmLJnaQj.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/Ba1drWuH.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/B9F8bIy5.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/PGLvW8OU.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/nodes/0.DDTih1_y.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/CFswWuIO.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/nodes/7.DO3e7wn0.js" rel="modulepreload">
		<link href="/docs/evaluate/main/en/_app/immutable/chunks/-IybLn_I.js" rel="modulepreload">
		<!--mcymhu--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Using the evaluator with custom pipelines&quot;,&quot;local&quot;:&quot;using-the-evaluator-with-custom-pipelines&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Scikit-Learn&quot;,&quot;local&quot;:&quot;scikit-learn&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Spacy&quot;,&quot;local&quot;:&quot;spacy&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/evaluate/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----></span> <span dir="auto">Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="using-the-evaluator-with-custom-pipelines" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#using-the-evaluator-with-custom-pipelines"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->Using the evaluator with custom pipelines<!----></span></h1><!--]--><!----> <p>The evaluator is designed to work with <code>transformer</code> pipelines out-of-the-box. However, in many cases you might have a model or pipeline that’s not part of the <code>transformer</code> ecosystem. You can still use <code>evaluator</code> to easily compute metrics for them. In this guide we show how to do this for a Scikit-Learn <a href="https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html#sklearn.pipeline.Pipeline" rel="nofollow">pipeline</a> and a Spacy <a href="https://spacy.io" rel="nofollow">pipeline</a>. Let’s start with the Scikit-Learn case.</p> <!--[1--><h2 class="relative group"><a id="scikit-learn" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#scikit-learn"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->Scikit-Learn<!----></span></h2><!--]--><!----> <p>First we need to train a model. We’ll train a simple text classifier on the <a href="https://huggingface.co/datasets/imdb" rel="nofollow">IMDb dataset</a>, so let’s start by downloading the dataset:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset

ds = load_dataset(<span class="hljs-string">&quot;imdb&quot;</span>)<!----></pre></div><!----> <p>Then we can build a simple TF-IDF preprocessor and Naive Bayes classifier wrapped in a <code>Pipeline</code>:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">from</span> sklearn.pipeline <span class="hljs-keyword">import</span> Pipeline
<span class="hljs-keyword">from</span> sklearn.naive_bayes <span class="hljs-keyword">import</span> MultinomialNB
<span class="hljs-keyword">from</span> sklearn.feature_extraction.text <span class="hljs-keyword">import</span> TfidfTransformer
<span class="hljs-keyword">from</span> sklearn.feature_extraction.text <span class="hljs-keyword">import</span> CountVectorizer

text_clf = Pipeline([
        (<span class="hljs-string">&#x27;vect&#x27;</span>, CountVectorizer()),
        (<span class="hljs-string">&#x27;tfidf&#x27;</span>, TfidfTransformer()),
        (<span class="hljs-string">&#x27;clf&#x27;</span>, MultinomialNB()),
])

text_clf.fit(ds[<span class="hljs-string">&quot;train&quot;</span>][<span class="hljs-string">&quot;text&quot;</span>], ds[<span class="hljs-string">&quot;train&quot;</span>][<span class="hljs-string">&quot;label&quot;</span>])<!----></pre></div><!----> <p>Following the convention in the <code>TextClassificationPipeline</code> of <code>transformers</code> our pipeline should be callable and return a list of dictionaries. In addition we use the <code>task</code> attribute to check if the pipeline is compatible with the <code>evaluator</code>. We can write a small wrapper class for that purpose:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">class</span> <span class="hljs-title class_">ScikitEvalPipeline</span>:
    <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self, pipeline</span>):
        <span class="hljs-variable language_">self</span>.pipeline = pipeline
        <span class="hljs-variable language_">self</span>.task = <span class="hljs-string">&quot;text-classification&quot;</span>

    <span class="hljs-keyword">def</span> <span class="hljs-title function_">__call__</span>(<span class="hljs-params">self, input_texts, **kwargs</span>):
        <span class="hljs-keyword">return</span> [{<span class="hljs-string">&quot;label&quot;</span>: p} <span class="hljs-keyword">for</span> p <span class="hljs-keyword">in</span> <span class="hljs-variable language_">self</span>.pipeline.predict(input_texts)]

pipe = ScikitEvalPipeline(text_clf)<!----></pre></div><!----> <p>We can now pass this <code>pipeline</code> to the <code>evaluator</code>:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">from</span> evaluate <span class="hljs-keyword">import</span> evaluator

task_evaluator = evaluator(<span class="hljs-string">&quot;text-classification&quot;</span>)
task_evaluator.compute(pipe, ds[<span class="hljs-string">&quot;test&quot;</span>], <span class="hljs-string">&quot;accuracy&quot;</span>)

<span class="hljs-meta">&gt;&gt;&gt; </span>{<span class="hljs-string">&#x27;accuracy&#x27;</span>: <span class="hljs-number">0.82956</span>}<!----></pre></div><!----> <p>Implementing that simple wrapper is all that’s needed to use any model from any framework with the <code>evaluator</code>. In the <code>__call__</code> you can implement all logic necessary for efficient forward passes through your model.</p> <!--[1--><h2 class="relative group"><a id="spacy" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#spacy"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->Spacy<!----></span></h2><!--]--><!----> <p>We’ll use the <code>polarity</code> feature of the <code>spacytextblob</code> project to get a simple sentiment analyzer. First you’ll need to install the project and download the resources:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-bash "><!---->pip install spacytextblob
python -m textblob.download_corpora
python -m spacy download en_core_web_sm<!----></pre></div><!----> <p>Then we can simply load the <code>nlp</code> pipeline and add the <code>spacytextblob</code> pipeline:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> spacy

nlp = spacy.load(<span class="hljs-string">&#x27;en_core_web_sm&#x27;</span>)
nlp.add_pipe(<span class="hljs-string">&#x27;spacytextblob&#x27;</span>)<!----></pre></div><!----> <p>This snippet shows how we can use the <code>polarity</code> feature added with <code>spacytextblob</code> to get the sentiment of a text:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!---->texts = [<span class="hljs-string">&quot;This movie is horrible&quot;</span>, <span class="hljs-string">&quot;This movie is awesome&quot;</span>]
results = nlp.pipe(texts)

<span class="hljs-keyword">for</span> txt, res <span class="hljs-keyword">in</span> <span class="hljs-built_in">zip</span>(texts, results):
    <span class="hljs-built_in">print</span>(<span class="hljs-string">f&quot;<span class="hljs-subst">{text}</span> | Polarity: <span class="hljs-subst">{res._.blob.polarity}</span>&quot;</span>)<!----></pre></div><!----> <p>Now we can wrap it in a simple wrapper class like in the Scikit-Learn example before. It just has to return a list of dictionaries with the predicted lables. If the polarity is larger than 0 we’ll predict positive sentiment and negative otherwise:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">class</span> <span class="hljs-title class_">SpacyEvalPipeline</span>:
    <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self, nlp</span>):
        <span class="hljs-variable language_">self</span>.nlp = nlp
        <span class="hljs-variable language_">self</span>.task = <span class="hljs-string">&quot;text-classification&quot;</span>

    <span class="hljs-keyword">def</span> <span class="hljs-title function_">__call__</span>(<span class="hljs-params">self, input_texts, **kwargs</span>):
        results =[]
        <span class="hljs-keyword">for</span> p <span class="hljs-keyword">in</span> <span class="hljs-variable language_">self</span>.nlp.pipe(input_texts):
            <span class="hljs-keyword">if</span> p._.blob.polarity&gt;=<span class="hljs-number">0</span>:
                results.append({<span class="hljs-string">&quot;label&quot;</span>: <span class="hljs-number">1</span>})
            <span class="hljs-keyword">else</span>:
                results.append({<span class="hljs-string">&quot;label&quot;</span>: <span class="hljs-number">0</span>})
        <span class="hljs-keyword">return</span> results

pipe = SpacyEvalPipeline(nlp)<!----></pre></div><!----> <p>That class is compatible with the <code>evaluator</code> and we can use the same instance from the previous examlpe along with the IMDb test set:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-built_in">eval</span>.compute(pipe, ds[<span class="hljs-string">&quot;test&quot;</span>], <span class="hljs-string">&quot;accuracy&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>{<span class="hljs-string">&#x27;accuracy&#x27;</span>: <span class="hljs-number">0.6914</span>}<!----></pre></div><!----> <p>This will take a little longer than the Scikit-Learn example but after roughly 10-15min you will have the evaluation results!</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/evaluate/blob/main/docs/source/custom_evaluator.mdx" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_1qnqef1 = {
						base: "/docs/evaluate/main/en",
						assets: "/docs/evaluate/main/en"
					};
					const element = document.currentScript.parentElement;
					Promise.all([
						import("/docs/evaluate/main/en/_app/immutable/entry/start.BR5Aqcvb.js"),
						import("/docs/evaluate/main/en/_app/immutable/entry/app.DmLJnaQj.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 7],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 27.6 kB
Xet hash:: 808cf1182ef3de81941ae6fda977f27f3a52fcfb228daba13d7ac0f882ba5f99
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.