{"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 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_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train=pd.read_csv('../input/train.csv')\nprint(train.shape)\nprint(train.head())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.decomposition import PCA\nfrom sklearn.neighbors import KNeighborsClassifier\nimport csv","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=pd.read_csv('../input/train.csv')\ntest=pd.read_csv('../input/test.csv')\ntrain_data=train.values[:,1:]\ntrain_label=train.values[:,0]\n# PCA\ntrainData = np.array(train_data)\ntestData = np.array(test)\n'''\nn_components>=1\n  n_components=NUM  \b 设置\b占特征数量比\n0 < n_components < 1\n  n_components=0.99  \b设置阈值总方差占比\n2）whiten ：判断是否进行白化。所谓白化，就是对降维后的数据的每个特征进行归一化，让方差都为1.对于PCA降维本身来说，一般不需要白化。\n'''\npca = PCA(n_components=0.7,whiten=False)\npca.fit(trainData)\npcaTrainData = pca.transform(trainData)\npcaTestData = pca.transform(testData)\nprint(pca.n_components_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf = KNeighborsClassifier(n_neighbors=15)\nclf.fit(pcaTrainData, np.ravel(train_label))\ntestLabel = clf.predict(pcaTestData)\nwith open('result.csv', 'w') as myFile:\n    myWriter = csv.writer(myFile)\n    myWriter.writerow([\"ImageId\", \"Label\"])\n    index = 0\n    for r in testLabel:\n        index += 1\n        myWriter.writerow([index, int(r)])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pwd","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls -a","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}