{"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 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# 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":"#importing library which is giong to call\nimport matplotlib.pyplot as pt#for plotting\nimport seaborn as sns\nfrom sklearn.svm import SVC #suport vector mechines for classifing data with maximum margin\nfrom sklearn.model_selection import train_test_split #for splitting data in to train and test set\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import accuracy_score\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# importing train data\ndata=pd.read_csv(\"../input/digit-recognizer/train.csv\")\n#importing test data\ndata_test=pd.read_csv(\"../input/digit-recognizer/test.csv\")\ndata.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Data=data.to_numpy()\nX=Data[:,1:]\ny=d=Data[:,0]\nnp.unique(np.isnan(X))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#splitting data for trainig and cross validation\nxtrain, xtest, ytrain, ytest= train_test_split(X, y, test_size=0.25, random_state=1)\nsns.countplot(ytrain) #ploting classes counts\n#data normalization\nsc_X = StandardScaler()\nxtrain = sc_X.fit_transform(xtrain)\nxtest = sc_X.transform(xtest)\ndata_test = sc_X.transform(data_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Training our model by using xtrain and ytrain\nclf=SVC(C=1, kernel='rbf', gamma='auto')\nclf.fit(xtrain,ytrain)\n#predetecting the output for xtest\npre=clf.predict(xtest)\nconfusion_matrix(ytest, pre)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"acuraccy=accuracy_score(ytest,pre)\nprint(acuraccy)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.Series(pre,name=\"Label\")\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),submission],axis = 1)\nsubmission.to_csv(\"final_submission_v1.csv\",index=False)\nsubmission.head()","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":1}