{"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":"#Thanks to rahuldshetty for data preprocessing steps.\n#CNN model needs to be finetuned\n#https://www.kaggle.com/rahuldshetty/kannada-digits-mnist-using-cnn-0-97\n\nimport numpy as np\nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport os\nimport gc\nfrom datetime import datetime\n\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils import to_categorical \nfrom keras import backend as K\nfrom keras.layers import Dense, Dropout,Flatten\nfrom keras.layers.convolutional import Conv2D, MaxPooling2D\nfrom keras.models import Sequential\nfrom keras.layers import Dropout\nfrom keras.layers.core import Activation\nfrom keras.layers.normalization import BatchNormalization","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('../input/Kannada-MNIST/test.csv')\nvalid = pd.read_csv('../input/Kannada-MNIST/Dig-MNIST.csv')\nsub = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_arr = train.values[0:,1:]\nlabels = train.values[0:,0]\nlabels = to_categorical(labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(train_arr[0].reshape((28,28)))\nprint(f'this is a {labels[0][0]}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_arr = train_arr/255.0\ntrain_arr = train_arr.reshape(train_arr.shape[0], 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_arr = valid.values\nvalid_arrx = valid_arr[0:,1:]\nvalid_arry = valid_arr[0:,0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_arrx = valid_arrx/255.0\nvalid_arrx = valid_arrx.reshape(valid_arr.shape[0], 28, 28, 1)\nvalid_arry = to_categorical(valid_arry)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32,(3,3),input_shape=train_arr.shape[1:], activation='relu', padding='same'))\n# model.add(Conv2D(32,(3,3), activation='relu'))\nmodel.add(MaxPooling2D((2,2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Conv2D(64,(3,3), activation='relu', padding='same'))\n# model.add(Conv2D(64,(3,3), activation='relu'))\nmodel.add(MaxPooling2D((2,2)))\nmodel.add(Dropout(0.2))\n\n# model.add(Conv2D(128,(3,3), activation='relu', padding='same'))\n# # model.add(Conv2D(128,(3,3), activation='relu'))\n# model.add(MaxPooling2D((2,2)))\n# model.add(Dropout(0.2))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.4))\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(train_arr, labels, validation_data=(valid_arrx,valid_arry), epochs=15, batch_size=128)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = test.values\ntest_arr = test[0:,1:]\nid_samples = test[0:,0]\ntest_arr = test_arr / 255.0\ntest_arr = test_arr.reshape((test_arr.shape[0],28,28,1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = model.predict_classes(test_arr)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.DataFrame()\nsub['id'] = list(id_samples)\nsub['label'] = y_pred\nsub.head()\nsub.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}