{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input//quora-insincere-questions-classification/train.csv')\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"docs = train['question_text']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['target'].value_counts()/train.shape[0]*100","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import nltk\nstemmer = nltk.stem.PorterStemmer()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"stemmer.stem('organization')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# test cleaning process for text classification \n- convert to lower case\n- regular expression to remove non alphabets \n- apply stemming to get root form of a word \n- apply stop word removel "},{"metadata":{"trusted":true},"cell_type":"code","source":"docs.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"docs_clean = docs.str.lower().str.replace('[^a-z ]','')\ndocs_clean.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"stopwords = nltk.corpus.stopwords.words('english')\nstopwords.extend([])\ndef clean_sentence(doc):\n    words = nltk.word_tokenize(doc)\n    words_clean = [stemmer.stem(word) for word in words if word not in stopwords]\n    return ' '.join(words_clean)\ndocs_clean = docs_clean.apply(clean_sentence)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"docs_clean.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#DTM\nfrom sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train,x_validate,y_train,y_validate = train_test_split(docs_clean,train['target'],test_size= 0.3,random_state = 1)\nx_train.shape,x_validate.shape,y_train.shape,y_validate.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vectorizer = CountVectorizer(min_df=10).fit(x_train)\ntrain_dtm = vectorizer.transform(x_train)\nvalidate_dtm = vectorizer.transform(x_validate)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.naive_bayes import MultinomialNB\nmodel = MultinomialNB().fit(train_dtm,y_train)\nvalidate_pred = model.predict(validate_dtm)\n\nfrom sklearn.metrics import f1_score\nf1_score(y_validate,validate_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/test.csv')\ntest_data.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_doc = test_data['question_text']\ntest_doc.head(2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import gensim \npath = '/kaggle/input/quora-insincere-questions-classification/embeddings/GoogleNews-vectors-negative300/GoogleNews-vectors-negative300.bin'\nembendings = gensim.models.KeyedVectors.load_word2vec_format(path,binary= True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"embendings.most_similar(['romance'],topn=10) # using cosine similarity ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"embendings.most_similar(positive=['king','woman'],negative=['man'],topn=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}