{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"4af8a1f0-8975-82a7-a72b-649436132718"},"outputs":[],"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 the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d438b223-3a82-d9f1-0814-94cd9b7f62b9"},"outputs":[],"source":"/from sklearn import datasets, ensemble, metrics, neighbors, cross_validation, grid_search, learning_curve"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"8f4d87ae-e4f9-a221-4e52-3d2d02627fac"},"outputs":[],"source":"data = pd.read_csv('../input/train.csv')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b41a21d5-3b7a-d34c-b505-6e964f10bf97"},"outputs":[],"source":"X = data.iloc[:,1:].as_matrix()\ny = data.label.as_matrix()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"599cee77-9166-d760-6d4d-aef301fe3d82"},"outputs":[],"source":"nnclassifier = neighbors.KNeighborsClassifier(3)\nnnclassifier.fit(X, y)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"8dec2902-82bd-1f4a-324e-1838416d9cdb"},"outputs":[],"source":"cross_validation.cross_val_score(nnclassifier, X, y, scoring='accuracy').mean()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"6310e401-6cbf-88da-9e83-2c6762e9c721"},"outputs":[],"source":"test_data = pd.read_csv('../input/test.csv')\ntest_result = nnclassifier.predict(test_data)\nresult_df = pd.DataFrame(data=test_result, columns=['Label'])\nresult_df.index += 1\nresult_df.index.name='ImageID'\nresult_df.to_csv('rfc2_test.csv', sep=',')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"1bdea9cc-8023-3521-71f1-84113c82e915"},"outputs":[],"source":"centroid = neighbors.NearestCentroid()\ncross_validation.cross_val_score(centroid, X, y, scoring='accuracy').mean()\n#centroid.fit(X, y)\n#predictions = centroid.predict(test_data)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"26463373-e2a6-dbf8-28f0-94d8c538d8ad"},"outputs":[],"source":"with open(\"centroid_test.csv\", \"w\") as out_file:\n    out_file.write(\"ImageId,Label\\n\")\n    for i in range(len(predictions)):\n        out_file.write(str(i+1) + \",\" + str(int(predictions[i])) + \"\\n\")"}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.5.2"}},"nbformat":4,"nbformat_minor":0}