{"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":"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\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","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"teste = pd.read_csv('../input/kddbr-2020/201701.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#data_in = teste[teste['input_1'] == 0]\ndata_in = teste[teste.columns[2:7748]]\ndata_in.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_out = teste[teste.columns[7748:7860]]\ndata_out.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_in_train = data_in[:80]\ndata_out_train = data_out[:80]\n\ndata_in_test = data_in[80:]\ndata_out_test = data_out[80:]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# k-nearest neighbors for multioutput regression\nfrom sklearn.datasets import make_regression\nfrom sklearn.neighbors import KNeighborsRegressor\n\n# define model\nmodel = KNeighborsRegressor()\n# fit model\nmodel.fit(data_in_train, data_out_train)\n# make a prediction\nyhat = model.predict(data_in_test)\n# summarize prediction\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"a = teste[(teste['input_0'] == 278) & (teste['input_1'] == 3) & (teste['input_2'] == 126) & (teste['input_3'] == 117)]\na.count()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}