{"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.\nimport warnings\nwarnings.filterwarnings('ignore')\n\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.metrics import confusion_matrix\n\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop\nfrom keras.utils.np_utils import to_categorical\n\nfrom keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(\n  rotation_range=10,\n  zoom_range=0.1,\n  width_shift_range=0.1,\n  height_shift_range=0.1\n)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")\nssub = pd.read_csv(\"../input/digit-recognizer/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ssub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train.label\nX = train.drop('label', axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X/255.0\ntest = test/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X.to_numpy().reshape(-1, 28,28,1)\ntest = test.to_numpy().reshape(-1, 28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X[0][:,:,0], cmap='gray');","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"kfold = StratifiedKFold(n_splits=4, shuffle=True, random_state=2)\ni = 1\nfor sub_train, sub_test in kfold.split(X, y):\n    yy = to_categorical(y.copy(), num_classes = 10)\n    model = Sequential()\n    model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu', input_shape=X.shape[1:]))\n    model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu'))\n    model.add(MaxPool2D(pool_size=(2, 2)))\n    model.add(Dropout(rate=0.25))\n    model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))\n    model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))\n    model.add(MaxPool2D(pool_size=(2, 2)))\n    model.add(Dropout(rate=0.25))\n    model.add(Flatten())\n    model.add(Dense(256, activation='relu'))\n    model.add(Dropout(rate=0.5))\n    model.add(Dense(10, activation='softmax'))\n    \n    model.compile(\n        loss='categorical_crossentropy', \n        optimizer='adam', \n        metrics=['accuracy']\n    )\n    \n    model.fit_generator(datagen.flow(X[sub_train], yy[sub_train], batch_size=50), epochs=1, verbose=1)\n    \n    y_pred = model.predict(X[sub_test])\n    \n    Y_pred_classes = np.argmax(y_pred,axis = 1) \n    # Convert validation observations to one hot vectors\n    Y_true = np.argmax(yy[sub_test],axis = 1) \n    # compute the confusion matrix\n    confusion_mtx = confusion_matrix(Y_true, Y_pred_classes)\n#     cm = confusion_matrix(yy[test], y_pred)\n\n    print(i,'*'*10)\n    print(confusion_mtx)\n    plt.imshow(confusion_mtx, interpolation='nearest')\n    i += 1\n    \n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"4-fold accuracy: \nEpoch 1/1\n630/630 [==============================] - 11s 17ms/step - loss: 0.5285 - accuracy: 0.8277\n1 **********\nEpoch 1/1\n630/630 [==============================] - 11s 17ms/step - loss: 0.5680 - accuracy: 0.8135\n2 **********\nEpoch 1/1\n630/630 [==============================] - 11s 17ms/step - loss: 0.5427 - accuracy: 0.8235\n3 **********\nEpoch 1/1\n631/631 [==============================] - 11s 17ms/step - loss: 0.5442 - accuracy: 0.8218\n4 **********"},{"metadata":{"trusted":true},"cell_type":"code","source":"yy = to_categorical(y.copy(), num_classes = 10)\nmodel = Sequential()\nmodel.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu', input_shape=X.shape[1:]))\nmodel.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Dropout(rate=0.25))\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Dropout(rate=0.25))\nmodel.add(Flatten())\nmodel.add(Dense(256, activation='relu'))\nmodel.add(Dropout(rate=0.5))\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.compile(\n    loss='categorical_crossentropy', \n    optimizer='adam', \n    metrics=['accuracy']\n)\n\nmodel.fit_generator(datagen.flow(X, yy, batch_size=100), epochs=5, verbose=1)\n\ny_pred = model.predict(test)\n\ny_submission = np.argmax(y_pred,axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({'ImageId': range(1,28001), 'Label':y_submission})\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv('cnn_submission_01.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}