{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Resources:\n\nhttps://machinelearningmastery.com/develop-word-embeddings-python-gensim/\n\nhttps://www.kaggle.com/chewzy/tutorial-how-to-train-your-custom-word-embedding\n\nhttps://www.geeksforgeeks.org/python-pandas-series-append/"},{"metadata":{},"cell_type":"markdown","source":"# Imports"},{"metadata":{"trusted":true},"cell_type":"code","source":"from gensim.models import Word2Vec\nimport gc","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"df1 = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv')\ndf1.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df2 = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-unintended-bias-train.csv')\ndf2.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df3 = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/validation.csv')\ndf3.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preprocessing"},{"metadata":{"trusted":true},"cell_type":"code","source":"df1['comment_text_proc'] = df1['comment_text'].apply(lambda x: x.split())\ndf2['comment_text_proc'] = df2['comment_text'].apply(lambda x: x.split())\ndf3['comment_text_proc'] = df3['comment_text'].apply(lambda x: x.split())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"text = pd.Series()\ntext = text.append(df1['comment_text_proc'])\ntext = text.append(df2['comment_text_proc'])\ntext = text.append(df3['comment_text_proc'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del df1, df2, df3\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fit Word2Vec"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Word2Vec(text)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Validate"},{"metadata":{"trusted":true},"cell_type":"code","source":"words = list(model.wv.vocab)\nprint(words[:10])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(model['embarrassing'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Save"},{"metadata":{"trusted":true},"cell_type":"code","source":"# save model\nmodel.wv.save_word2vec_format('custom_wrod2vec_100d.txt')","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}