{"cells":[{"metadata":{"_execution_state":"idle","_uuid":"72334cb006d02a4bcfc2a2fe622524eba824c6f8","_cell_guid":"f67b9393-8ea1-4e23-b856-2ce149cfe421","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\n%matplotlib inline\n\nnp.random.seed(2)\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n\nfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\n\nsns.set(style='white', context='notebook', palette='deep')","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"84bbd5ab8d7895bd430d5ecfe2f7ddf77baa7b74","_cell_guid":"5e51d00e-62fd-4141-bf73-50ac4f2da7d0","trusted":true},"cell_type":"code","source":"# Load the data\ntrain = pd.read_csv(\"../input/train.csv\")\ntest = pd.read_csv(\"../input/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"1213b979d5ed3e0d13824d17d694c79d2ece92fa","_cell_guid":"86570a36-5c20-460a-9dfd-2070548532a7","trusted":true},"cell_type":"code","source":"Y_train = train[\"label\"]\n\n# Drop 'label' column\nX_train = train.drop(labels = [\"label\"],axis = 1) \n\ng = sns.countplot(Y_train)\n\nY_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"cdf27c27e2a5b15e6d7bfc70de7a18c08f3feb7a","_cell_guid":"ececaa00-2ae3-4d13-b631-438df085b030","trusted":true},"cell_type":"code","source":"# Check the data\nX_train.isnull().any()","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"a0089bb7ec9aec76373db475399aea24699ae989","_cell_guid":"92572e80-8543-4e72-8767-5c9be8381b04","trusted":true},"cell_type":"code","source":"test.isnull().any()","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"b5d4f8fcf2a967e2c7d57daedf95aa8c5ab7f8cb","_cell_guid":"cdc4340b-6e24-4e12-be99-ac806098ff17","trusted":true},"cell_type":"code","source":"# Normalize the data\nX_train = X_train / 255.0\ntest = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"f0a6ad80dab8e0f2c2e46165ccd9cd82dd162bc3","_cell_guid":"34b6a5f7-8fd2-4387-8ef4-c9dc19584fed","trusted":true},"cell_type":"code","source":"# Reshape image in 3 dimensions (height = 28px, width = 28px , canal = 1)\nX_train = X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\nY_train = to_categorical(Y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"6e51c925c6e0f1b936679c9649fef345c853555f","_cell_guid":"3a698301-9759-4279-ae48-fd980f89ea53","trusted":true},"cell_type":"code","source":"# Set the random seed\nrandom_seed = 2","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"b779ac76d8317647db92d5a88b4098d212d72884","_cell_guid":"dcd25ebb-d845-4d32-9867-082e352b1396","trusted":true},"cell_type":"code","source":"# Split the train and the validation set for the fitting\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=random_seed)","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"e0dae8943d3d35f075dba3d7ba31bde1d4bf2ff4","_cell_guid":"5f76131b-4ba0-45f1-a98c-bd4e7d561793","trusted":true},"cell_type":"code","source":"# Some examples\ng = plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"f7991ef6871a26f9fa57acdcd460a69bab53e804","_cell_guid":"1e0f3f88-2ad7-459e-8e02-aecc5f3511ae","trusted":true},"cell_type":"code","source":"# Set the CNN model \n# my CNN architechture is In -> [[Conv2D->relu]*2 -> MaxPool2D -> Dropout]*2 -> Flatten -> Dense -> Dropout -> Out\n\nmodel = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\n\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"420c704367b397b8255fefe9d882b35ac8929b95","_cell_guid":"a4c55409-6a65-400a-b5e8-a1dc535429c0","trusted":true},"cell_type":"code","source":"# Define the optimizer\noptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"b4c0288622227a3cd05479aa765e324dbb852f34","_cell_guid":"0bd89b79-1a74-40da-af9a-7a76a8b96ff2","trusted":true},"cell_type":"code","source":"# Compile the model\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"c4a5b4e462ec5362c47eef4fcc7956fd4e203307","_cell_guid":"b5987a18-6bbe-42a2-9d31-333ebc4f7af1","trusted":true},"cell_type":"code","source":"# Set a learning rate annealer\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"26b0647c46efdb6b1096cf7335a7bf2a3417543a","_cell_guid":"970db455-b393-4b25-806d-92c6766c12c0","trusted":true},"cell_type":"code","source":"epochs = 10 # Turn epochs to 30 to get 0.9967 accuracy\nbatch_size = 86","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"d4e9e1ade3c04f9ca4d8cd44e799f9e09524d5a1","_cell_guid":"ade93d2d-90c6-4401-af95-f7d65f8c0a20","trusted":true},"cell_type":"code","source":"# Without data augmentation i obtained an accuracy of 0.98114\nhistory = model.fit(X_train, Y_train, batch_size = batch_size, epochs = epochs, \n          validation_data = (X_val, Y_val), verbose = 1)","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"21d6192c87d92d497c797656474bccd9cefc5647","_cell_guid":"b342befe-1a6f-44bf-8dab-28033a729122","trusted":true},"cell_type":"code","source":"\ndatagen = ImageDataGenerator(\n        rotation_range=10,  \n        zoom_range = 0.1, \n        width_shift_range=0.1,  \n        height_shift_range=0.1,  \n        horizontal_flip=False,  \n        vertical_flip=False)  \n\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"cf36b3d029f95b553be02d612e097a9769ee8252","_cell_guid":"b453af8d-9736-43e3-b486-7a1cd7dd8909","trusted":true},"cell_type":"code","source":"# Fit the model\nhistory = model.fit_generator(datagen.flow(X_train,Y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (X_val,Y_val),\n                              verbose = 1, steps_per_epoch=X_train.shape[0] // batch_size\n                              , callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#  \"Accuracy\"\nplt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'validation'], loc='upper left')\nplt.show()\n# \"Loss\"\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'validation'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"7f17e7bf0a54a01a52fef2d554780f6bc6580dc6","_cell_guid":"05ff3b9f-c3bb-4cec-a8c2-2c128e8f15b3","trusted":true},"cell_type":"code","source":"# predict results\nresults = model.predict(test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"_execution_state":"idle","_uuid":"369dfaab09240f3f12bcff91953ffd315ab84985","_cell_guid":"b5f1f39f-13b8-439a-8913-0f120e3d47a9","trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"sub.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":4}