{
  "id": 71152,
  "title": "Using Google News Embeddings",
  "url": "/competitions/quora-insincere-questions-classification/discussion/71152",
  "author_name": "",
  "post_date": "2018-11-10T18:49:04.945298Z",
  "votes": 1,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I am new with Text data. Can anyone please help on how to use GoogleNews Embeddings. It is in .bin format, I tried reading it in chunks of 11, but I fail.</p>",
  "messages": [
    {
      "id": "418862",
      "postDate": "11/10/2018 18:49:04",
      "content": "<p>I am new with Text data. Can anyone please help on how to use GoogleNews Embeddings. It is in .bin format, I tried reading it in chunks of 11, but I fail.</p>",
      "rawMarkdown": "I am new with Text data. Can anyone please help on how to use GoogleNews Embeddings. It is in .bin format, I tried reading it in chunks of 11, but I fail.",
      "votes": null
    },
    {
      "id": "418992",
      "postDate": "11/11/2018 03:22:15",
      "content": "<p>Use gensim module </p>\n\n<p>```</p>\n\n<p>import gensim</p>\n\n<p>model = gensim.models.KeyedVectors.load_word2vec_format('./data/GoogleNews-vectors-negative300.bin.gz', binary=True)</p>\n\n<p>vocab = model.vocab</p>\n\n<p>embedding = model.syn0</p>\n\n<p>```</p>\n\n<p>You might need to change the path though.</p>",
      "rawMarkdown": "Use gensim module \n\n```\n\nimport gensim\n\nmodel = gensim.models.KeyedVectors.load_word2vec_format('./data/GoogleNews-vectors-negative300.bin.gz', binary=True)\n\nvocab = model.vocab\n\nembedding = model.syn0\n\n```\n\nYou might need to change the path though.",
      "votes": null
    },
    {
      "id": "419043",
      "postDate": "11/11/2018 06:04:15",
      "content": "<p>thank you </p>",
      "rawMarkdown": "thank you",
      "votes": null
    },
    {
      "id": "420243",
      "postDate": "11/13/2018 10:34:00",
      "content": "<p>If any body is interested in specific GoogleNews preprocessing, I added a kernel on this topic <a href=\"https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings#\">https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings#</a></p>",
      "rawMarkdown": "If any body is interested in specific GoogleNews preprocessing, I added a kernel on this topic https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings#",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 418992,
      "author_name": "s4sarath",
      "author_url": "",
      "post_date": "11/11/2018 03:22:15",
      "content": "<p>Use gensim module </p>\n\n<p>```</p>\n\n<p>import gensim</p>\n\n<p>model = gensim.models.KeyedVectors.load_word2vec_format('./data/GoogleNews-vectors-negative300.bin.gz', binary=True)</p>\n\n<p>vocab = model.vocab</p>\n\n<p>embedding = model.syn0</p>\n\n<p>```</p>\n\n<p>You might need to change the path though.</p>",
      "votes": null,
      "replies": [
        {
          "id": 419043,
          "author_name": "ashishsinhaiitr",
          "author_url": "",
          "post_date": "11/11/2018 06:04:15",
          "content": "<p>thank you </p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 420243,
      "author_name": "christofhenkel",
      "author_url": "",
      "post_date": "11/13/2018 10:34:00",
      "content": "<p>If any body is interested in specific GoogleNews preprocessing, I added a kernel on this topic <a href=\"https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings#\">https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings#</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "418862": "I am new with Text data. Can anyone please help on how to use GoogleNews Embeddings. It is in .bin format, I tried reading it in chunks of 11, but I fail.",
    "418992": "Use gensim module \n\n```\n\nimport gensim\n\nmodel = gensim.models.KeyedVectors.load_word2vec_format('./data/GoogleNews-vectors-negative300.bin.gz', binary=True)\n\nvocab = model.vocab\n\nembedding = model.syn0\n\n```\n\nYou might need to change the path though.",
    "419043": "thank you",
    "420243": "If any body is interested in specific GoogleNews preprocessing, I added a kernel on this topic https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings#"
  },
  "source": "meta"
}