{"id":4186,"date":"2024-11-11T13:21:54","date_gmt":"2024-11-11T05:21:54","guid":{"rendered":"https:\/\/fwq.ai\/blog\/4186\/"},"modified":"2024-11-11T13:21:54","modified_gmt":"2024-11-11T05:21:54","slug":"%e6%9e%84%e5%bb%ba%e5%91%bd%e5%90%8d%e5%ae%9e%e4%bd%93%e8%af%86%e5%88%ab%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f","status":"publish","type":"post","link":"https:\/\/fwq.ai\/blog\/4186\/","title":{"rendered":"\u6784\u5efa\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f"},"content":{"rendered":"<h1>\u6784\u5efa\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f<\/h1>\n<h2><\/h2>\n<p>\u672c\u6307\u5357\u5c06\u5f15\u5bfc\u60a8\u6784\u5efa\u548c\u8fd0\u884c\u547d\u540d\u5b9e\u4f53\u8bc6\u522b (NER) \u5e94\u7528\u7a0b\u5e8f\u3002\u60a8\u5c06\u4f7f\u7528 Python \u548c spaCy \u6784\u5efa\u5e94\u7528\u7a0b\u5e8f\uff0c\u7136\u540e\u8bbe\u7f6e\u73af\u5883\u5e76\u4f7f\u7528 Docker \u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\u3002<\/p>\n<p>\u8be5\u5e94\u7528\u7a0b\u5e8f\u5904\u7406\u8f93\u5165\u6587\u672c\u4ee5\u8bc6\u522b\u548c\u6253\u5370\u547d\u540d\u5b9e\u4f53\uff0c\u4f8b\u5982\u4eba\u5458\u3001\u7ec4\u7ec7\u6216\u4f4d\u7f6e\u3002<\/p>\n<h2><\/h2>\n<ul>\n<li>\u60a8\u5df2\u5b89\u88c5\u6700\u65b0\u7248\u672c\u7684 \u3002 Docker \u5b9a\u671f\u6dfb\u52a0\u65b0\u529f\u80fd\uff0c\u672c\u6307\u5357\u7684\u67d0\u4e9b\u90e8\u5206\u53ef\u80fd\u4ec5\u9002\u7528\u4e8e\u6700\u65b0\u7248\u672c\u7684 Docker Desktop\u3002<\/li>\n<li>\u60a8\u6709\u4e00\u4e2a \u3002\u672c\u8282\u4e2d\u7684\u793a\u4f8b\u4f7f\u7528\u57fa\u4e8e\u547d\u4ee4\u884c\u7684 Git \u5ba2\u6237\u7aef\uff0c\u4f46\u60a8\u53ef\u4ee5\u4f7f\u7528\u4efb\u4f55\u5ba2\u6237\u7aef\u3002<\/li>\n<\/ul>\n<h2><\/h2>\n<ol>\n<li>\n<p>\u6253\u5f00\u7ec8\u7aef\uff0c\u7136\u540e\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u514b\u9686\u793a\u4f8b\u5e94\u7528\u7a0b\u5e8f\u7684\u5b58\u50a8\u5e93\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>$<\/span> git clone https:\/\/github.com\/harsh4870\/Docker-NLP.git <\/span><\/span><\/code><\/pre>\n<\/li>\n<li>\n<p>\u9a8c\u8bc1\u60a8\u662f\u5426\u514b\u9686\u4e86\u5b58\u50a8\u5e93\u3002<\/p>\n<p>\u60a8\u5e94\u8be5\u5728\u76ee\u5f55\u4e2d\u770b\u5230\u4ee5\u4e0b\u6587\u4ef6<code>Docker-NLP<\/code>\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span>01_sentiment_analysis.py <\/span><\/span><span><span>02_name_entity_recognition.py <\/span><\/span><span><span>03_text_classification.py <\/span><\/span><span><span>04_text_summarization.py <\/span><\/span><span><span>05_language_translation.py <\/span><\/span><span><span>entrypoint.sh <\/span><\/span><span><span>requirements.txt <\/span><\/span><span><span>Dockerfile <\/span><\/span><span><span>README.md<\/span><\/span><\/code><\/pre>\n<\/li>\n<\/ol>\n<h2><\/h2>\n<p>\u540d\u79f0\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f\u7684\u6e90\u4ee3\u7801\u4f4d\u4e8e\u8be5<code>Docker-NLP\/02_name_entity_recognition.py<\/code>\u6587\u4ef6\u4e2d\u3002\u5728\u6587\u672c\u6216\u4ee3\u7801\u7f16\u8f91\u5668\u4e2d\u6253\u5f00<code>02_name_entity_recognition.py<\/code>\uff0c\u6309\u4ee5\u4e0b\u6b65\u9aa4\u63a2\u7d22\u5176\u5185\u5bb9\u3002<\/p>\n<ol>\n<li>\n<p>\u5bfc\u5165\u6240\u9700\u7684\u5e93\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>import<\/span> <span>spacy<\/span><\/span><\/span><\/code><\/pre>\n<p>\u8be5\u884c\u5bfc\u5165<code>spaCy<\/code>\u5e93\u3002<code>spaCy<\/code>\u662f Python \u4e2d\u7528\u4e8e\u81ea\u7136\u8bed\u8a00\u5904\u7406 (NLP) \u7684\u6d41\u884c\u5e93\u3002<\/p>\n<\/li>\n<li>\n<p>\u52a0\u8f7d\u8bed\u8a00\u6a21\u578b\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>nlp<\/span> <span>=<\/span> <span>spacy<\/span><span>.<\/span><span>load<\/span><span>(<\/span><span>\"en_core_web_sm\"<\/span><span>)<\/span><\/span><\/span><\/code><\/pre>\n<p>\u5728\u8fd9\u91cc\uff0c\u8be5<code>spacy.load<\/code>\u51fd\u6570\u52a0\u8f7d\u4e00\u4e2a\u8bed\u8a00\u6a21\u578b\u3002\u8be5<code>en_core_web_sm<\/code> \u6a21\u578b\u662f\u4e00\u4e2a\u5c0f\u578b\u7684\u82f1\u8bed\u8bed\u8a00\u6a21\u578b\u3002\u60a8\u53ef\u4ee5\u5c06\u6b64\u6a21\u578b\u7528\u4e8e\u5404\u79cd NLP \u4efb\u52a1\uff0c\u5305\u62ec\u6807\u8bb0\u5316\u3001\u8bcd\u6027\u6807\u8bb0\u548c\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u3002<\/p>\n<\/li>\n<li>\n<p>\u6307\u5b9a\u4e3b\u8981\u6267\u884c\u5757\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>if<\/span> <span>__name__<\/span> <span>==<\/span> <span>\"__main__\"<\/span><span>:<\/span><\/span><\/span><\/code><\/pre>\n<p>\u8fd9\u4e2a Python \u4e60\u60ef\u7528\u6cd5\u786e\u4fdd\u4ec5\u5f53\u8be5\u811a\u672c\u662f\u4e3b\u7a0b\u5e8f\u65f6\u4ee5\u4e0b\u4ee3\u7801\u5757\u624d\u8fd0\u884c\u3002\u5b83\u63d0\u4f9b\u4e86\u7075\u6d3b\u6027\uff0c\u5141\u8bb8\u811a\u672c\u65e2\u4f5c\u4e3a\u72ec\u7acb\u7a0b\u5e8f\u53c8\u4f5c\u4e3a\u5bfc\u5165\u6a21\u5757\u8fd0\u884c\u3002<\/p>\n<\/li>\n<li>\n<p>\u521b\u5efa\u65e0\u9650\u5faa\u73af\u4ee5\u8fdb\u884c\u8fde\u7eed\u8f93\u5165\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span> <span>while<\/span> <span>True<\/span><span>:<\/span><\/span><\/span><\/code><\/pre>\n<p>\u8fd9\u4e2a while \u5faa\u73af\u65e0\u9650\u671f\u5730\u8fd0\u884c\uff0c\u76f4\u5230\u5b83\u88ab\u660e\u786e\u7834\u574f\u4e3a\u6b62\u3002\u5b83\u5141\u8bb8\u7528\u6237\u8fde\u7eed\u8f93\u5165\u6587\u672c\u4ee5\u8fdb\u884c\u5b9e\u4f53\u8bc6\u522b\uff0c\u76f4\u5230\u4ed6\u4eec\u51b3\u5b9a\u9000\u51fa\u3002<\/p>\n<\/li>\n<li>\n<p>\u83b7\u53d6\u7528\u6237\u8f93\u5165\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>input_text<\/span> <span>=<\/span> <span>input<\/span><span>(<\/span><span>\"Enter the text for entity recognition (type 'exit' to end): \"<\/span><span>)<\/span><\/span><\/span><\/code><\/pre>\n<p>\u8be5\u884c\u63d0\u793a\u7528\u6237\u8f93\u5165\u6587\u672c\u3002\u7136\u540e\u7a0b\u5e8f\u5c06\u5bf9\u6b64\u6587\u672c\u6267\u884c\u5b9e\u4f53\u8bc6\u522b\u3002<\/p>\n<\/li>\n<li>\n<p>\u5b9a\u4e49\u9000\u51fa\u6761\u4ef6\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>if<\/span> <span>input_text<\/span><span>.<\/span><span>lower<\/span><span>()<\/span> <span>==<\/span> <span>'exit'<\/span><span>:<\/span> <\/span><\/span><span><span> <span>print<\/span><span>(<\/span><span>\"Exiting...\"<\/span><span>)<\/span> <\/span><\/span><span><span> <span>break<\/span><\/span><\/span><\/code><\/pre>\n<p>\u5982\u679c\u7528\u6237\u952e\u5165\u67d0\u4e9b\u5185\u5bb9\uff0c\u7a0b\u5e8f\u4f1a\u5c06\u8f93\u5165\u8f6c\u6362\u4e3a\u5c0f\u5199\u5e76\u5c06\u5176\u4e0e \u8fdb\u884c\u6bd4\u8f83<code>exit<\/code>\u3002\u5982\u679c\u5b83\u4eec\u5339\u914d\uff0c\u7a0b\u5e8f\u5c06\u6253\u5370<strong>Exiting&#8230;<\/strong>\u5e76\u8df3\u51fa while \u5faa\u73af\uff0c\u4ece\u800c\u6709\u6548\u5730\u7ed3\u675f\u7a0b\u5e8f\u3002<\/p>\n<\/li>\n<li>\n<p>\u6267\u884c\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>doc<\/span> <span>=<\/span> <span>nlp<\/span><span>(<\/span><span>input_text<\/span><span>)<\/span> <\/span><\/span><span><span> <\/span><\/span><span><span><span>for<\/span> <span>ent<\/span> <span>in<\/span> <span>doc<\/span><span>.<\/span><span>ents<\/span><span>:<\/span> <\/span><\/span><span><span> <span>print<\/span><span>(<\/span><span>f<\/span><span>\"Entity: <\/span><span>{<\/span><span>ent<\/span><span>.<\/span><span>text<\/span><span>}<\/span><span>, Type: <\/span><span>{<\/span><span>ent<\/span><span>.<\/span><span>label_<\/span><span>}<\/span><span>\"<\/span><span>)<\/span><\/span><\/span><\/code><\/pre>\n<ul>\n<li><code>doc = nlp(input_text)<\/code>\uff1a\u8fd9\u91cc\uff0cnlp \u6a21\u578b\u5904\u7406\u7528\u6237\u8f93\u5165\u7684\u6587\u672c\u3002\u8fd9\u5c06\u521b\u5efa\u4e00\u4e2a Doc \u5bf9\u8c61\uff0c\u5176\u4e2d\u5305\u542b\u5404\u79cd NLP \u5c5e\u6027\uff0c\u5305\u62ec\u8bc6\u522b\u7684\u5b9e\u4f53\u3002<\/li>\n<li><code>for ent in doc.ents:<\/code>\uff1a\u6b64\u5faa\u73af\u8fed\u4ee3\u6587\u672c\u4e2d\u627e\u5230\u7684\u5b9e\u4f53\u3002<\/li>\n<li><code>print(f\"Entity: {ent.text}, Type: {ent.label_}\")<\/code>\uff1a\u5bf9\u4e8e\u6bcf\u4e2a\u5b9e\u4f53\uff0c\u5b83\u6253\u5370\u5b9e\u4f53\u6587\u672c\u53ca\u5176\u7c7b\u578b\uff08\u5982 PERSON\u3001ORG \u6216 GPE\uff09\u3002<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u521b\u9020<code>requirements.txt<\/code>\u3002<\/p>\n<p>\u793a\u4f8b\u5e94\u7528\u7a0b\u5e8f\u5df2\u5305\u542b<code>requirements.txt<\/code>\u7528\u4e8e\u6307\u5b9a\u5e94\u7528\u7a0b\u5e8f\u5bfc\u5165\u7684\u5fc5\u8981\u5305\u7684\u6587\u4ef6\u3002<code>requirements.txt<\/code>\u5728\u4ee3\u7801\u6216\u6587\u672c\u7f16\u8f91\u5668\u4e2d\u6253\u5f00\u4ee5\u63a2\u7d22\u5176\u5185\u5bb9\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span># 02 named_entity_recognition <\/span><\/span><span><span>spacy==3.7.2 <\/span><\/span><span><span> <\/span><\/span><span><span>...<\/span><\/span><\/code><\/pre>\n<p>\u547d\u540d\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f\u53ea<code>spacy<\/code>\u9700\u8981\u8be5\u5305\u3002<\/p>\n<\/li>\n<\/ol>\n<h2><\/h2>\n<p>\u60a8\u5c06\u4f7f\u7528 Docker \u5728\u5bb9\u5668\u4e2d\u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\u3002 Docker \u5141\u8bb8\u60a8\u5bf9\u5e94\u7528\u7a0b\u5e8f\u8fdb\u884c\u5bb9\u5668\u5316\uff0c\u4e3a\u8fd0\u884c\u5b83\u63d0\u4f9b\u4e00\u81f4\u4e14\u9694\u79bb\u7684\u73af\u5883\u3002\u8fd9\u610f\u5473\u7740\u5e94\u7528\u7a0b\u5e8f\u5c06\u5728\u5176 Docker \u5bb9\u5668\u5185\u6309\u9884\u671f\u8fd0\u884c\uff0c\u65e0\u8bba\u5e95\u5c42\u7cfb\u7edf\u6709\u4f55\u5dee\u5f02\u3002<\/p>\n<p>\u8981\u5728\u5bb9\u5668\u4e2d\u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\uff0c\u9700\u8981 Dockerfile\u3002 Dockerfile \u662f\u4e00\u4e2a\u6587\u672c\u6587\u6863\uff0c\u5176\u4e2d\u5305\u542b\u60a8\u5728\u547d\u4ee4\u884c\u4e0a\u8c03\u7528\u4ee5\u7ec4\u88c5\u6620\u50cf\u7684\u6240\u6709\u547d\u4ee4\u3002\u955c\u50cf\u662f\u4e00\u4e2a\u53ea\u8bfb\u6a21\u677f\uff0c\u5305\u542b\u521b\u5efa Docker \u5bb9\u5668\u7684\u8bf4\u660e\u3002<\/p>\n<p>\u793a\u4f8b\u5e94\u7528\u7a0b\u5e8f\u5df2\u5305\u542b\u4e00\u4e2a<code>Dockerfile<\/code>.<code>Dockerfile<\/code>\u5728\u4ee3\u7801\u6216\u6587\u672c\u7f16\u8f91\u5668\u4e2d\u6253\u5f00\u4ee5\u6d4f\u89c8\u5176\u5185\u5bb9\u3002<\/p>\n<p>\u4ee5\u4e0b\u6b65\u9aa4\u89e3\u91ca\u4e86 \u7684\u6bcf\u4e2a\u90e8\u5206<code>Dockerfile<\/code>\u3002\u6709\u5173\u66f4\u591a\u8be6\u7ec6\u4fe1\u606f\uff0c\u8bf7\u53c2\u9605 \u3002<\/p>\n<ol>\n<li>\n<p>\u6307\u5b9a\u57fa\u7840\u56fe\u50cf\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>FROM<\/span><span> python:3.8-slim<\/span><\/span><\/span><\/code><\/pre>\n<p>\u8be5\u547d\u4ee4\u4e3a\u6784\u5efa\u5960\u5b9a\u4e86\u57fa\u7840\u3002<code>python:3.8-slim<\/code>\u662f Python 3.8 \u6620\u50cf\u7684\u8f7b\u91cf\u7ea7\u7248\u672c\uff0c\u9488\u5bf9\u5927\u5c0f\u548c\u901f\u5ea6\u8fdb\u884c\u4e86\u4f18\u5316\u3002\u4f7f\u7528\u8fd9\u4e2a\u7ea4\u8584\u7684\u955c\u50cf\u53ef\u4ee5\u51cf\u5c11 Docker \u955c\u50cf\u7684\u6574\u4f53\u5927\u5c0f\uff0c\u4ece\u800c\u52a0\u5feb\u4e0b\u8f7d\u901f\u5ea6\u5e76\u51cf\u5c11\u5b89\u5168\u6f0f\u6d1e\u7684\u8868\u9762\u79ef\u3002\u8fd9\u5bf9\u4e8e\u57fa\u4e8e Python \u7684\u5e94\u7528\u7a0b\u5e8f\u7279\u522b\u6709\u7528\uff0c\u60a8\u53ef\u80fd\u4e0d\u9700\u8981\u5b8c\u6574\u7684\u6807\u51c6 Python \u6620\u50cf\u3002<\/p>\n<\/li>\n<li>\n<p>\u8bbe\u7f6e\u5de5\u4f5c\u76ee\u5f55\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>WORKDIR<\/span><span> \/app<\/span><\/span><\/span><\/code><\/pre>\n<p><code>WORKDIR<\/code>\u8bbe\u7f6e Docker \u6620\u50cf\u4e2d\u7684\u5f53\u524d\u5de5\u4f5c\u76ee\u5f55\u3002\u901a\u8fc7\u5c06\u5176\u8bbe\u7f6e\u4e3a<code>\/app<\/code>\uff0c\u53ef\u4ee5\u786e\u4fdd Dockerfile \u4e2d\u7684\u6240\u6709\u540e\u7eed\u547d\u4ee4\uff08\u4f8b\u5982<code>COPY<\/code>\u548c<code>RUN<\/code>\uff09\u90fd\u5728\u6b64\u76ee\u5f55\u4e2d\u6267\u884c\u3002\u8fd9\u4e5f\u6709\u52a9\u4e8e\u7ec4\u7ec7 Docker \u6620\u50cf\uff0c\u56e0\u4e3a\u6240\u6709\u4e0e\u5e94\u7528\u7a0b\u5e8f\u76f8\u5173\u7684\u6587\u4ef6\u90fd\u5305\u542b\u5728\u7279\u5b9a\u76ee\u5f55\u4e2d\u3002<\/p>\n<\/li>\n<li>\n<p>\u5c06\u9700\u6c42\u6587\u4ef6\u590d\u5236\u5230\u6620\u50cf\u4e2d\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>COPY<\/span> requirements.txt \/app<\/span><\/span><\/code><\/pre>\n<p>\u8be5<code>COPY<\/code>\u547d\u4ee4\u5c06<code>requirements.txt<\/code>\u6587\u4ef6\u4ece\u672c\u5730\u8ba1\u7b97\u673a\u4f20\u8f93\u5230 Docker \u6620\u50cf\u4e2d\u3002\u8be5\u6587\u4ef6\u5217\u51fa\u4e86\u5e94\u7528\u7a0b\u5e8f\u6240\u9700\u7684\u6240\u6709 Python \u4f9d\u8d56\u9879\u3002\u5c06\u5176\u590d\u5236\u5230\u5bb9\u5668\u4e2d\u53ef\u4ee5\u8ba9\u4e0b\u4e00\u4e2a\u547d\u4ee4 ( <code>RUN pip install<\/code>) \u5728\u6620\u50cf\u73af\u5883\u4e2d\u5b89\u88c5\u8fd9\u4e9b\u4f9d\u8d56\u9879\u3002<\/p>\n<\/li>\n<li>\n<p>\u5728\u6620\u50cf\u4e2d\u5b89\u88c5 Python \u4f9d\u8d56\u9879\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>RUN<\/span> pip install --no-cache-dir -r requirements.txt<\/span><\/span><\/code><\/pre>\n<p>\u6b64\u884c\u4f7f\u7528<code>pip<\/code>Python \u7684\u8f6f\u4ef6\u5305\u5b89\u88c5\u7a0b\u5e8f\u6765\u5b89\u88c5 \u4e2d\u5217\u51fa\u7684\u8f6f\u4ef6\u5305<code>requirements.txt<\/code>\u3002\u8be5<code>--no-cache-dir<\/code>\u9009\u9879\u7981\u7528\u7f13\u5b58\uff0c\u4ece\u800c\u901a\u8fc7\u4e0d\u5b58\u50a8\u4e0d\u5fc5\u8981\u7684\u7f13\u5b58\u6570\u636e\u6765\u51cf\u5c0f Docker \u6620\u50cf\u7684\u5927\u5c0f\u3002<\/p>\n<\/li>\n<li>\n<p>\u8fd0\u884c\u9644\u52a0\u547d\u4ee4\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>RUN<\/span> python -m spacy download en_core_web_sm<\/span><\/span><\/code><\/pre>\n<p>\u6b64\u6b65\u9aa4\u7279\u5b9a\u4e8e\u9700\u8981 spaCy \u5e93\u7684 NLP \u5e94\u7528\u7a0b\u5e8f\u3002\u5b83\u4e0b\u8f7d<code>en_core_web_sm<\/code>\u6a21\u578b\uff0c\u8fd9\u662f spaCy \u7684\u5c0f\u578b\u82f1\u8bed\u6a21\u578b\u3002<\/p>\n<\/li>\n<li>\n<p>\u5c06\u5e94\u7528\u7a0b\u5e8f\u4ee3\u7801\u590d\u5236\u5230\u56fe\u50cf\u4e2d\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>COPY<\/span> *.py \/app<span> <\/span><\/span><\/span><span><span><span><\/span><span>COPY<\/span> entrypoint.sh \/app<\/span><\/span><\/code><\/pre>\n<p>\u8fd9\u4e9b\u547d\u4ee4\u5c06\u60a8\u7684 Python \u811a\u672c\u548c<code>entrypoint.sh<\/code>\u811a\u672c\u590d\u5236\u5230\u56fe\u50cf\u7684<code>\/app<\/code>\u76ee\u5f55\u4e2d\u3002\u8fd9\u5f88\u91cd\u8981\uff0c\u56e0\u4e3a\u5bb9\u5668\u9700\u8981\u8fd9\u4e9b\u811a\u672c\u6765\u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\u3002\u8be5<code>entrypoint.sh<\/code>\u811a\u672c\u7279\u522b\u91cd\u8981\uff0c\u56e0\u4e3a\u5b83\u6307\u793a\u5e94\u7528\u7a0b\u5e8f\u5982\u4f55\u5728\u5bb9\u5668\u5185\u542f\u52a8\u3002<\/p>\n<\/li>\n<li>\n<p>\u8bbe\u7f6e<code>entrypoint.sh<\/code>\u811a\u672c\u7684\u6743\u9650\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>RUN<\/span> chmod +x \/app\/entrypoint.sh<\/span><\/span><\/code><\/pre>\n<p>\u6b64\u547d\u4ee4\u4fee\u6539 \u7684\u6587\u4ef6\u6743\u9650<code>entrypoint.sh<\/code>\uff0c\u4f7f\u5176\u53ef\u6267\u884c\u3002\u6b64\u6b65\u9aa4\u662f\u786e\u4fdd Docker \u5bb9\u5668\u53ef\u4ee5\u8fd0\u884c\u6b64\u811a\u672c\u6765\u542f\u52a8\u5e94\u7528\u7a0b\u5e8f\u6240\u5fc5\u9700\u7684\u3002<\/p>\n<\/li>\n<li>\n<p>\u8bbe\u7f6e\u5165\u53e3\u70b9\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>ENTRYPOINT<\/span> <span>[<\/span><span>\"\/app\/entrypoint.sh\"<\/span><span>]<\/span><\/span><\/span><\/code><\/pre>\n<p>\u8be5<code>ENTRYPOINT<\/code>\u6307\u4ee4\u5c06\u5bb9\u5668\u914d\u7f6e<code>entrypoint.sh<\/code> \u4e3a\u4f5c\u4e3a\u9ed8\u8ba4\u53ef\u6267\u884c\u6587\u4ef6\u8fd0\u884c\u3002\u8fd9\u610f\u5473\u7740\u5f53\u5bb9\u5668\u542f\u52a8\u65f6\uff0c\u5b83\u4f1a\u81ea\u52a8\u6267\u884c\u811a\u672c\u3002<\/p>\n<p>\u60a8\u53ef\u4ee5<code>entrypoint.sh<\/code>\u901a\u8fc7\u5728\u4ee3\u7801\u6216\u6587\u672c\u7f16\u8f91\u5668\u4e2d\u6253\u5f00\u811a\u672c\u6765\u63a2\u7d22\u8be5\u811a\u672c\u3002\u7531\u4e8e\u793a\u4f8b\u5305\u542b\u591a\u4e2a\u5e94\u7528\u7a0b\u5e8f\uff0c\u56e0\u6b64\u8be5\u811a\u672c\u5141\u8bb8\u60a8\u6307\u5b9a\u5728\u5bb9\u5668\u542f\u52a8\u65f6\u8fd0\u884c\u54ea\u4e2a\u5e94\u7528\u7a0b\u5e8f\u3002<\/p>\n<\/li>\n<\/ol>\n<h2><\/h2>\n<p>\u8981\u4f7f\u7528 Docker \u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\uff1a<\/p>\n<ol>\n<li>\n<p>\u5efa\u7acb\u5f62\u8c61\u3002<\/p>\n<p>\u5728\u7ec8\u7aef\u4e2d\uff0c\u5728\u6240\u5728\u76ee\u5f55\u4e2d\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4<code>Dockerfile<\/code>\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>$<\/span> docker build -t basic-nlp . <\/span><\/span><\/code><\/pre>\n<p>\u4ee5\u4e0b\u662f\u8be5\u547d\u4ee4\u7684\u7ec6\u5206\uff1a<\/p>\n<ul>\n<li><code>docker build<\/code>\uff1a\u8fd9\u662f\u7528\u4e8e\u4ece Dockerfile \u548c\u4e0a\u4e0b\u6587\u6784\u5efa Docker \u6620\u50cf\u7684\u4e3b\u8981\u547d\u4ee4\u3002\u4e0a\u4e0b\u6587\u901a\u5e38\u662f\u6307\u5b9a\u4f4d\u7f6e\u7684\u4e00\u7ec4\u6587\u4ef6\uff0c\u901a\u5e38\u662f\u5305\u542b Dockerfile \u7684\u76ee\u5f55\u3002<\/li>\n<li><code>-t basic-nlp<\/code>\uff1a\u8fd9\u662f\u4e00\u4e2a\u7528\u4e8e\u6807\u8bb0\u56fe\u50cf\u7684\u9009\u9879\u3002\u65d7\u5e1c<code>-t<\/code>\u4ee3\u8868\u6807\u7b7e\u3002\u5b83\u4e3a\u56fe\u50cf\u5206\u914d\u4e00\u4e2a\u540d\u79f0\uff0c\u5728\u672c\u4f8b\u4e2d\u4e3a <code>basic-nlp<\/code>.\u6807\u7b7e\u662f\u7a0d\u540e\u5f15\u7528\u56fe\u50cf\u7684\u4fbf\u6377\u65b9\u6cd5\uff0c\u5c24\u5176\u662f\u5728\u5c06\u5b83\u4eec\u63a8\u9001\u5230\u6ce8\u518c\u8868\u6216\u8fd0\u884c\u5bb9\u5668\u65f6\u3002<\/li>\n<li><code>.<\/code>\uff1a\u8fd9\u662f\u547d\u4ee4\u7684\u6700\u540e\u4e00\u90e8\u5206\uff0c\u6307\u5b9a\u6784\u5efa\u4e0a\u4e0b\u6587\u3002\u53e5\u70b9 ( <code>.<\/code>) \u8868\u793a\u5f53\u524d\u76ee\u5f55\u3002 Docker \u5c06\u5728\u6b64\u76ee\u5f55\u4e2d\u67e5\u627e Dockerfile\u3002\u6784\u5efa\u4e0a\u4e0b\u6587\uff08\u5728\u672c\u4f8b\u4e2d\u4e3a\u5f53\u524d\u76ee\u5f55\uff09\u88ab\u53d1\u9001\u5230 Docker \u5b88\u62a4\u8fdb\u7a0b\u4ee5\u542f\u7528\u6784\u5efa\u3002\u5b83\u5305\u62ec\u6307\u5b9a\u76ee\u5f55\u4e2d\u7684\u6240\u6709\u6587\u4ef6\u548c\u5b50\u76ee\u5f55\u3002<\/li>\n<\/ul>\n<p>\u6709\u5173\u66f4\u591a\u8be6\u7ec6\u4fe1\u606f\uff0c\u8bf7\u53c2\u9605 \u3002<\/p>\n<p>Docker \u5728\u6784\u5efa\u955c\u50cf\u65f6\u4f1a\u5411\u63a7\u5236\u53f0\u8f93\u51fa\u591a\u4e2a\u65e5\u5fd7\u3002\u60a8\u5c06\u770b\u5230\u5b83\u4e0b\u8f7d\u5e76\u5b89\u88c5\u4f9d\u8d56\u9879\u3002\u6839\u636e\u60a8\u7684\u7f51\u7edc\u8fde\u63a5\uff0c\u8fd9\u53ef\u80fd\u9700\u8981\u51e0\u5206\u949f\u7684\u65f6\u95f4\u3002 Docker \u786e\u5b9e\u5177\u6709\u7f13\u5b58\u529f\u80fd\uff0c\u56e0\u6b64\u540e\u7eed\u6784\u5efa\u53ef\u4ee5\u66f4\u5feb\u3002\u5b8c\u6210\u540e\u63a7\u5236\u53f0\u5c06\u8fd4\u56de\u5230\u63d0\u793a\u7b26\u3002<\/p>\n<\/li>\n<li>\n<p>\u5c06\u56fe\u50cf\u4f5c\u4e3a\u5bb9\u5668\u8fd0\u884c\u3002<\/p>\n<p>\u5728\u7ec8\u7aef\u4e2d\uff0c\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>$<\/span> docker run -it basic-nlp 02_name_entity_recognition.py <\/span><\/span><\/code><\/pre>\n<p>\u4ee5\u4e0b\u662f\u8be5\u547d\u4ee4\u7684\u7ec6\u5206\uff1a<\/p>\n<ul>\n<li><code>docker run<\/code>\uff1a\u8fd9\u662f\u7528\u4e8e\u4ece Docker \u6620\u50cf\u8fd0\u884c\u65b0\u5bb9\u5668\u7684\u4e3b\u8981\u547d\u4ee4\u3002<\/li>\n<li><code>-it<\/code>\uff1a\u8fd9\u662f\u4e24\u4e2a\u9009\u9879\u7684\u7ec4\u5408\uff1a\n<ul>\n<li><code>-i<\/code>\u6216<code>--interactive<\/code>\uff1a\u5373\u4f7f\u672a\u8fde\u63a5\uff0c\u8fd9\u4e5f\u4f1a\u4f7f\u6807\u51c6\u8f93\u5165 (STDIN) \u4fdd\u6301\u6253\u5f00\u72b6\u6001\u3002\u5b83\u8ba9\u5bb9\u5668\u4fdd\u6301\u5728\u524d\u53f0\u8fd0\u884c\u5e76\u5177\u6709\u4ea4\u4e92\u6027\u3002<\/li>\n<li><code>-t<\/code>or <code>--tty<\/code>\uff1a\u8fd9\u4f1a\u5206\u914d\u4e00\u4e2a\u4f2a TTY\uff0c\u672c\u8d28\u4e0a\u662f\u6a21\u62df\u7ec8\u7aef\uff0c\u5982\u547d\u4ee4\u63d0\u793a\u7b26\u6216 shell\u3002\u5b83\u53ef\u4ee5\u8ba9\u60a8\u4e0e\u5bb9\u5668\u5185\u7684\u5e94\u7528\u7a0b\u5e8f\u8fdb\u884c\u4ea4\u4e92\u3002<\/li>\n<\/ul>\n<\/li>\n<li><code>basic-nlp<\/code>\uff1a\u6307\u5b9a\u7528\u4e8e\u521b\u5efa\u5bb9\u5668\u7684 Docker \u6620\u50cf\u7684\u540d\u79f0\u3002\u5728\u672c\u4f8b\u4e2d\uff0c\u5b83\u662f<code>basic-nlp<\/code>\u60a8\u4f7f\u7528\u547d\u4ee4\u521b\u5efa\u7684\u540d\u4e3a\u7684\u56fe\u50cf<code>docker build<\/code>\u3002<\/li>\n<li><code>02_name_entity_recognition.py<\/code>\uff1a\u8fd9\u662f\u60a8\u8981\u5728 Docker \u5bb9\u5668\u5185\u8fd0\u884c\u7684\u811a\u672c\u3002\u5b83\u88ab\u4f20\u9012\u7ed9<code>entrypoint.sh<\/code>\u811a\u672c\uff0c\u811a\u672c\u5728\u5bb9\u5668\u542f\u52a8\u65f6\u8fd0\u884c\u5b83\u3002<\/li>\n<\/ul>\n<p>\u6709\u5173\u66f4\u591a\u8be6\u7ec6\u4fe1\u606f\uff0c\u8bf7\u53c2\u9605 \u3002<\/p>\n<blockquote>\n<p><strong>\u7b14\u8bb0<\/strong><\/p>\n<p>\u5bf9\u4e8e Windows \u7528\u6237\uff0c\u8fd0\u884c\u5bb9\u5668\u65f6\u53ef\u80fd\u4f1a\u51fa\u73b0\u9519\u8bef\u3002\u9a8c\u8bc1\u884c\u7ed3\u5c3e\u662f<code>entrypoint.sh<\/code>( <code>LF<\/code>)<code>\\n<\/code>\u800c\u4e0d\u662f<code>CRLF<\/code>( <code>\\r\\n<\/code>)\uff0c\u7136\u540e\u91cd\u5efa\u56fe\u50cf\u3002\u6709\u5173\u66f4\u591a\u8be6\u7ec6\u4fe1\u606f\uff0c\u8bf7\u53c2\u9605 \u3002<\/p>\n<\/blockquote>\n<p>\u5bb9\u5668\u542f\u52a8\u540e\uff0c\u60a8\u5c06\u5728\u63a7\u5236\u53f0\u4e2d\u770b\u5230\u4ee5\u4e0b\u5185\u5bb9\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>Enter the text for entity recognition (type 'exit' to end): <\/span><\/span><\/span><\/code><\/pre>\n<\/li>\n<li>\n<p>\u6d4b\u8bd5\u5e94\u7528\u7a0b\u5e8f\u3002<\/p>\n<p>\u8f93\u5165\u4e00\u4e9b\u4fe1\u606f\u4ee5\u83b7\u5f97\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u3002<\/p>\n<p> <span> <\/span> <span> <\/span> <\/p>\n<pre><code><span><span><span>Enter the text for entity recognition (type 'exit' to end): Apple Inc. is planning to open a new store in San Francisco. Tim Cook is the CEO of Apple. <\/span><\/span><\/span><span><span><span><\/span><span> <\/span><\/span><\/span><span><span><span><\/span><span>Entity: Apple Inc., Type: ORG <\/span><\/span><\/span><span><span><span>Entity: San Francisco, Type: GPE <\/span><\/span><\/span><span><span><span>Entity: Tim Cook, Type: PERSON <\/span><\/span><\/span><span><span><span>Entity: Apple, Type: ORG <\/span><\/span><\/span><\/code><\/pre>\n<\/li>\n<\/ol>\n<h2><\/h2>\n<p>\u672c\u6307\u5357\u6f14\u793a\u4e86\u5982\u4f55\u6784\u5efa\u548c\u8fd0\u884c\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f\u3002\u60a8\u5b66\u4e60\u4e86\u5982\u4f55\u4f7f\u7528 Python \u548c spaCy \u6784\u5efa\u5e94\u7528\u7a0b\u5e8f\uff0c\u7136\u540e\u8bbe\u7f6e\u73af\u5883\u5e76\u4f7f\u7528 Docker \u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\u3002<\/p>\n<p>\u76f8\u5173\u4fe1\u606f\uff1a<\/p>\n<ul>\n<li><\/li>\n<li><\/li>\n<li><\/li>\n<li><\/li>\n<\/ul>\n<h2><\/h2>\n<p>\u63a2\u7d22\u66f4\u591a \u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6784\u5efa\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f \u672c\u6307\u5357\u5c06\u5f15\u5bfc\u60a8\u6784\u5efa\u548c\u8fd0\u884c\u547d\u540d\u5b9e\u4f53\u8bc6\u522b (NER) \u5e94\u7528\u7a0b\u5e8f\u3002\u60a8\u5c06\u4f7f\u7528 Python \u548c spaCy \u6784\u5efa\u5e94\u7528\u7a0b\u5e8f\uff0c\u7136\u540e\u8bbe\u7f6e\u73af\u5883\u5e76\u4f7f\u7528 Docker \u8fd0\u884c\u5e94\u7528\u7a0b\u5e8f\u3002 \u8be5\u5e94\u7528\u7a0b\u5e8f\u5904\u7406\u8f93\u5165\u6587\u672c\u4ee5\u8bc6\u522b\u548c\u6253\u5370\u547d\u540d\u5b9e\u4f53\uff0c\u4f8b\u5982\u4eba\u5458\u3001\u7ec4\u7ec7\u6216\u4f4d\u7f6e\u3002 \u60a8\u5df2\u5b89\u88c5\u6700\u65b0\u7248\u672c\u7684 \u3002 Docker \u5b9a\u671f\u6dfb\u52a0\u65b0\u529f\u80fd\uff0c\u672c\u6307\u5357\u7684\u67d0\u4e9b\u90e8\u5206\u53ef\u80fd\u4ec5\u9002\u7528\u4e8e\u6700\u65b0\u7248\u672c\u7684 Docker Desktop\u3002 \u60a8\u6709\u4e00\u4e2a \u3002\u672c\u8282\u4e2d\u7684\u793a\u4f8b\u4f7f\u7528\u57fa\u4e8e\u547d\u4ee4\u884c\u7684 Git \u5ba2\u6237\u7aef\uff0c\u4f46\u60a8\u53ef\u4ee5\u4f7f\u7528\u4efb\u4f55\u5ba2\u6237\u7aef\u3002 \u6253\u5f00\u7ec8\u7aef\uff0c\u7136\u540e\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u514b\u9686\u793a\u4f8b\u5e94\u7528\u7a0b\u5e8f\u7684\u5b58\u50a8\u5e93\u3002 $ git clone https:\/\/github.com\/harsh4870\/Docker-NLP.git \u9a8c\u8bc1\u60a8\u662f\u5426\u514b\u9686\u4e86\u5b58\u50a8\u5e93\u3002 \u60a8\u5e94\u8be5\u5728\u76ee\u5f55\u4e2d\u770b\u5230\u4ee5\u4e0b\u6587\u4ef6Docker-NLP\u3002 01_sentiment_analysis.py 02_name_entity_recognition.py 03_text_classification.py 04_text_summarization.py 05_language_translation.py entrypoint.sh requirements.txt Dockerfile README.md \u540d\u79f0\u8bc6\u522b\u5e94\u7528\u7a0b\u5e8f\u7684\u6e90\u4ee3\u7801\u4f4d\u4e8e\u8be5Docker-NLP\/02_name_entity_recognition.py\u6587\u4ef6\u4e2d\u3002\u5728\u6587\u672c\u6216\u4ee3\u7801\u7f16\u8f91\u5668\u4e2d\u6253\u5f0002_name_entity_recognition.py\uff0c\u6309\u4ee5\u4e0b\u6b65\u9aa4\u63a2\u7d22\u5176\u5185\u5bb9\u3002 \u5bfc\u5165\u6240\u9700\u7684\u5e93\u3002 import spacy \u8be5\u884c\u5bfc\u5165spaCy\u5e93\u3002spaCy\u662f Python \u4e2d\u7528\u4e8e\u81ea\u7136\u8bed\u8a00\u5904\u7406 (NLP) \u7684\u6d41\u884c\u5e93\u3002 \u52a0\u8f7d\u8bed\u8a00\u6a21\u578b\u3002 nlp = spacy.load(&#8220;en_core_web_sm&#8221;) \u5728\u8fd9\u91cc\uff0c\u8be5spacy.load\u51fd\u6570\u52a0\u8f7d\u4e00\u4e2a\u8bed\u8a00\u6a21\u578b\u3002\u8be5en_core_web_sm \u6a21\u578b\u662f\u4e00\u4e2a\u5c0f\u578b\u7684\u82f1\u8bed\u8bed\u8a00\u6a21\u578b\u3002\u60a8\u53ef\u4ee5\u5c06\u6b64\u6a21\u578b\u7528\u4e8e\u5404\u79cd NLP \u4efb\u52a1\uff0c\u5305\u62ec\u6807\u8bb0\u5316\u3001\u8bcd\u6027\u6807\u8bb0\u548c\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u3002 \u6307\u5b9a\u4e3b\u8981\u6267\u884c\u5757\u3002 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[17],"tags":[],"class_list":["post-4186","post","type-post","status-publish","format-standard","hentry","category-docker"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/4186","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=4186"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/4186\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=4186"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=4186"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=4186"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}