{"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":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom pandas import DataFrame\nimport plotly.offline as py\npy.init_notebook_mode(connected=True)\nimport plotly.graph_objs as go\nimport plotly.tools as tls\nimport seaborn as sns\nimport matplotlib.image as mpimg\nimport matplotlib.pyplot as plt\nimport matplotlib\n%matplotlib inline\n\nfrom sklearn.manifold import TSNE\nfrom sklearn.decomposition import PCA\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA\n\nfrom sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# reading training data"},{"metadata":{"trusted":true},"cell_type":"code","source":"# save the labels to a Pandas series target\ntrain = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"target = train['label']\n# Drop the label feature\ntrain = train.drop(\"label\",axis=1)\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Some good models"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import SGDClassifier\nfrom sklearn.linear_model import SGDRegressor\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.svm import SVC","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_using_pca(n_comp):\n    \n    # spliting\n    \n    x_train, x_test, y_train, y_test = train_test_split( train, target, test_size=0.25, random_state=42)\n    \n    # doing pca\n    \n    n_components = n_comp\n    print(x_train.values.shape)\n    pca = PCA(n_components=n_components).fit(x_train.values)\n    eigenvalues = pca.components_.reshape(n_components, 28, 28)\n    eigenvalues = pca.components_\n    \n    # making a new data frame with fewer dimensions\n    x_train = DataFrame(pca.transform(x_train), index=x_train.index)\n    \n    # scaling \n    scaler = StandardScaler()\n    x_train = DataFrame(scaler.fit_transform(x_train))\n    \n    \n    #training\n    \n    model = SVC(kernel='rbf')\n    model.fit(x_train, y_train)\n    \n    #seeing results\n    x_test = pca.transform(x_test)\n    x_test = DataFrame(scaler.transform(x_test))\n    \n    print(\"On train: \", accuracy_score(y_train, model.predict(x_train), normalize=True) )\n    print(\"On test: \", accuracy_score(y_test, model.predict(x_test), normalize=True))\n    \n    return pca, scaler, model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pca, scaler, model = train_using_pca(20)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Predicting on actual test data"},{"metadata":{"trusted":true},"cell_type":"code","source":"ids = test['id']\ntest = test.drop('id', axis=1)\ntest_pca = DataFrame(pca.transform(test))\ntest_pca = DataFrame(scaler.transform(test_pca))\npreds = model.predict(test_pca)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Making CSV file"},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.DataFrame({'id': ids, 'label': preds})\noutput.to_csv('submission.csv', index=False)","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}