{"cells":[{"metadata":{},"cell_type":"markdown","source":"**Import Libraries**"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import RobustScaler\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.pipeline import Pipeline\nfrom sklearn import svm\nfrom sklearn.decomposition import PCA\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Import Files**"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/Kannada-MNIST/train.csv\")\ntest  = pd.read_csv(\"../input/Kannada-MNIST/test.csv\")\nsubmission  = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\nval= pd.read_csv('../input/Kannada-MNIST/Dig-MNIST.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Rename the id column of test file to label**"},{"metadata":{"trusted":true},"cell_type":"code","source":"test.rename(columns={'id':'label'}, inplace=True)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Train/Test Split**"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(train.iloc[:, 1:], train.iloc[:, 0], test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Standardize the data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"# scaler = RobustScaler()\n# X_train = scaler.fit_transform(X_train)\n# X_test = scaler.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Find Principal Components**"},{"metadata":{"trusted":true},"cell_type":"code","source":"pca = PCA(n_components=0.7,whiten=True)\nX_train_PCA = pca.fit_transform(X_train)\nX_test_PCA = pca.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Fit the train data using SVM**"},{"metadata":{"trusted":true},"cell_type":"code","source":"sv = svm.SVC(kernel='rbf', C=9, gamma='auto')\nsv.fit(X_train_PCA , y_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Predict using splitted test data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = sv.predict(X_test_PCA)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Calculate the accuary**"},{"metadata":{},"cell_type":"markdown","source":"😲"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import accuracy_score\naccuracy_score(y_pred,y_test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Submission**"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_x = test.values[:,1:]\ntest_x = pca.transform(test_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = sv.predict(test_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission['label'] = pred\nsubmission.to_csv('submission.csv', 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":1}