{"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)\nimport matplotlib.pyplot as plt\nimport sklearn\nimport tensorflow as tf\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\nfrom sklearn.model_selection import train_test_split\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#convert first row into 1-D numpy array \n#matrix_nw = train.iloc[0].as_matrix()   //// as_matrix() can be removed in future so not using this\nmatrix_new = train.iloc[0].values\nmatrix_new = matrix_new[1:]\n#matrix_new\n#now reshape array in image size that is 28*28\nmatrix_new = matrix_new.reshape(28,28)\n#visualize image\nplt.imshow(matrix_new,cmap = 'gray')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# now split features and label for training purpose\ny_train = train[\"label\"]\nx_train = train.drop(columns = {'label'})\ntraining, validating,training_labels, validating_labels = train_test_split(x_train, y_train, train_size=0.8, random_state=0)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training_labels.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nfrom sklearn.svm import SVC\nfrom sklearn.metrics import accuracy_score\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nclassifiers = [\n                \n                SVC(),\n               # LogisticRegression()\n             ]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf = SVC()\nclf.fit(training, training_labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_prdiction = clf.predict(validating)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"acc = accuracy_score(validating_labels, val_prdiction)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"acc","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predicted = clf.predict(test_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"type(predicted)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data[\"Label\"] = predicted\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = [ i + 1 for i in range(len(test_data))]\ntest_data[\"ImageId\"] = x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"answer = test_data[[\"ImageId\", \"Label\"]]\nanswer\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"answer.to_csv(\"result.csv\",header=True,index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}