{"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 areavailable 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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport nltk\n#nltk.download('stopwords')\nfrom nltk.stem import WordNetLemmatizer \nfrom nltk.tokenize import RegexpTokenizer\nfrom nltk.corpus import stopwords\nfrom nltk import word_tokenize\nfrom sklearn.model_selection import train_test_split\nfrom gensim import models\n\nimport re\nfrom collections import Counter\nimport gensim\nimport heapq\nfrom operator import itemgetter\nfrom multiprocessing import Pool","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = pd.read_csv('../input/quora-insincere-questions-classification/train.csv')\ntest_data = pd.read_csv('../input/quora-insincere-questions-classification/test.csv')\ndisplay(data.head())\ndata.target.value_counts","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"stop_words = set(stopwords.words('english'))\ntokenizer = RegexpTokenizer(r'\\w+')\nlemmatizer = WordNetLemmatizer() \n\ndef lower_token(tokens): \n    return [w.lower() for w in tokens]   \n\ndef lemmatize_words(tokens):\n    return [lemmatizer.lemmatize(word) for word in tokens]\n\ndef remove_stop_words(tokens): \n    return [word for word in tokens if word not in stop_words]\n\n#https://towardsdatascience.com/nlp-learning-series-part-1-text-preprocessing-methods-for-deep-learning-20085601684b \n\ndef clean_numbers(sen):\n    res = []\n    for word in sen:\n        if bool(re.search(r'\\d', word)):\n            word = re.sub('[0-9]{5,}', '#####', word)\n            word = re.sub('[0-9]{4}', '####', word)\n            word = re.sub('[0-9]{3}', '###', word)\n            word = re.sub('[0-9]{2}', '##', word)\n            word = re.sub('[0-9]{1}', '#', word)\n        res.append(word)\n    return res\n\n\nword2vec_path = '../input/quora-insincere-questions-classification/embeddings/\\\nGoogleNews-vectors-negative300/GoogleNews-vectors-negative300.bin'\nword2vec = models.KeyedVectors.load_word2vec_format(word2vec_path, binary=True)\nwords = word2vec.index2word","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import time\nfrom tqdm import tqdm_notebook\n\ndef process_basic(data):\n    tokens = [tokenizer.tokenize(sen) for sen in data['question_text']]\n    lower_tokens = [lower_token(token) for token in tokens]\n    lemmatized_tokens = [lemmatize_words(token) for token in lower_tokens]\n    filtered_nums = [clean_numbers(sen) for sen in lemmatized_tokens]\n    no_stopwords = [remove_stop_words(sen) for sen in filtered_nums]\n    data['basic'] = [' '.join(sen) for sen in no_stopwords]\n    return data\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = process_basic(data)\ndisplay(data.head())\ntest_data = process_basic(test_data)\ndisplay(test_data.head())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lemmatizer.lemmatize('do')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display(test_data.head(50))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.to_csv('processed_train_lemmatized.csv')\ntest_data.to_csv('processed_test_lemmatized.csv')","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":1}