{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"raw","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\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 read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom sklearn import feature_extraction, linear_model, model_selection, preprocessing\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.naive_bayes import MultinomialNB\nimport spacy\n\ntrain_df = pd.read_csv(\"/kaggle/input/quora-insincere-questions-classification/train.csv\")\ntest_df = pd.read_csv(\"/kaggle/input/quora-insincere-questions-classification/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:03:55.853715Z","iopub.execute_input":"2021-10-16T02:03:55.854743Z","iopub.status.idle":"2021-10-16T02:04:00.235889Z","shell.execute_reply.started":"2021-10-16T02:03:55.854667Z","shell.execute_reply":"2021-10-16T02:04:00.234829Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:00.237572Z","iopub.execute_input":"2021-10-16T02:04:00.238811Z","iopub.status.idle":"2021-10-16T02:04:00.251297Z","shell.execute_reply.started":"2021-10-16T02:04:00.238757Z","shell.execute_reply":"2021-10-16T02:04:00.250455Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df.head()","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:00.253399Z","iopub.execute_input":"2021-10-16T02:04:00.254065Z","iopub.status.idle":"2021-10-16T02:04:00.272362Z","shell.execute_reply.started":"2021-10-16T02:04:00.254010Z","shell.execute_reply":"2021-10-16T02:04:00.270963Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"count_vectorizer = feature_extraction.text.CountVectorizer()\n\nexample_train_vectors = count_vectorizer.fit_transform(train_df[\"question_text\"][0:5])","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:00.275142Z","iopub.execute_input":"2021-10-16T02:04:00.275528Z","iopub.status.idle":"2021-10-16T02:04:00.307184Z","shell.execute_reply.started":"2021-10-16T02:04:00.275485Z","shell.execute_reply":"2021-10-16T02:04:00.306003Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(example_train_vectors[0].todense().shape)\nprint(example_train_vectors[0].todense())","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:00.308411Z","iopub.execute_input":"2021-10-16T02:04:00.309035Z","iopub.status.idle":"2021-10-16T02:04:00.321856Z","shell.execute_reply.started":"2021-10-16T02:04:00.308999Z","shell.execute_reply":"2021-10-16T02:04:00.320993Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_vectors = count_vectorizer.fit_transform(train_df[\"question_text\"])\n\ntest_vectors = count_vectorizer.transform(test_df[\"question_text\"])","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:00.323328Z","iopub.execute_input":"2021-10-16T02:04:00.323970Z","iopub.status.idle":"2021-10-16T02:04:38.169224Z","shell.execute_reply.started":"2021-10-16T02:04:00.323927Z","shell.execute_reply":"2021-10-16T02:04:38.168175Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"clf = MultinomialNB()","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:38.170856Z","iopub.execute_input":"2021-10-16T02:04:38.171341Z","iopub.status.idle":"2021-10-16T02:04:38.176810Z","shell.execute_reply.started":"2021-10-16T02:04:38.171289Z","shell.execute_reply":"2021-10-16T02:04:38.175580Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"clf.fit(train_vectors, train_df[\"target\"])\n\npredicts = clf.predict(test_vectors)\n\nresult = pd.read_csv('../input/quora-insincere-questions-classification/sample_submission.csv')\nresult['prediction'] = pd.Series(predicts)\nresult.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2021-10-16T02:04:38.178699Z","iopub.execute_input":"2021-10-16T02:04:38.179078Z","iopub.status.idle":"2021-10-16T02:04:39.995542Z","shell.execute_reply.started":"2021-10-16T02:04:38.179030Z","shell.execute_reply":"2021-10-16T02:04:39.994263Z"},"trusted":true},"execution_count":null,"outputs":[]}]}