{"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)\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import metrics\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"1) Import de training set y val set "},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')\ntrain.isnull().sum()\nprint(train.shape)\nprint(test.shape)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"2) Revision training y test sets "},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Valores null en train set\")\nprint(train.isnull().sum())\nprint(\"Valores null en test set\")\nprint(test.isnull().sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"3) Split train dev y test "},{"metadata":{"trusted":true},"cell_type":"code","source":"train, dev = train_test_split(train, test_size=0.1) \n\n#configuration values \n\n\n#Extract X. Values transforms it into array\nX_train = train['question_text'].values\nX_dev = dev['question_text'].values\nx_test = test['question_text'].values\n#Extract Y\nY_train = train['target'].values\nY_dev = dev['target'].values","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}