{"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 seaborn as sns\n\nimport warnings\nwarnings.filterwarnings('ignore')\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\")\ntest = pd.read_csv(\"../input/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = (train['label'])\ntrain.drop(labels='label' , inplace=True , axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X =  train.values.tolist()\n#train.drop(train.columns[:-1] , inplace=True , axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = test.values.tolist()\n#test.drop(labels=test.columns[0:-1],inplace=True , axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"some_digit = np.reshape(X[1000], (28,28))\nplt.imshow(some_digit)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import SGDClassifier\nsgd = SGDClassifier(random_state=42)\nsgd.fit(X , labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sgd.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import StratifiedKFold\nfrom sklearn.base import clone\nskfolds = StratifiedKFold(n_splits=3 , shuffle=True , random_state=42)\n\n\nfor train_index  , test_index in skfolds.split(X , labels):\n    clone_clf = clone(sgd)\n    #print(\"Train Index :\", train_index , \"Test Index\", test_index)\n    \n    X_train_folds = train.iloc[train_index]      #using .iloc for selecting indexes\n    Y_train_folds = labels.iloc[train_index]      #using .iloc for selecting indexes\n    X_test_folds = train.iloc[test_index]        #using .iloc for selecting indexes\n    Y_test_folds = labels.iloc[test_index]        #using .iloc for selecting indexes\n    \n    clone_clf.fit(X_train_folds , Y_train_folds)\n    y_pred = (clone_clf.predict(X_test_folds))\n    n_correct = sum(y_pred == Y_test_folds)\n    print(\"Accuracy:\" , n_correct/len(y_pred))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import cross_val_score\ncross_val_score(sgd , train  , labels , cv=3 , scoring='accuracy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import cross_val_predict\npred = cross_val_predict(sgd , train , labels, cv=3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\nconfusion_matrix(labels , pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import precision_score , recall_score\nprint(precision_score(labels, pred , average=\"macro\"))\nprint(recall_score(labels, pred , average='macro'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}