{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"sourceType":"competition"}],"dockerImageVersionId":8561,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# Loading packages\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\n%matplotlib inline\n\nnp.random.seed(2)\n\n# Loading Keras packages\nimport itertools\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","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.status.busy":"2024-04-30T00:08:38.443563Z","iopub.execute_input":"2024-04-30T00:08:38.444141Z","iopub.status.idle":"2024-04-30T00:08:39.702674Z","shell.execute_reply.started":"2024-04-30T00:08:38.444057Z","shell.execute_reply":"2024-04-30T00:08:39.701780Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load Train and Test Datasets\ntrain = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')","metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.status.busy":"2024-04-30T00:08:39.703965Z","iopub.execute_input":"2024-04-30T00:08:39.704223Z","iopub.status.idle":"2024-04-30T00:08:48.169891Z","shell.execute_reply.started":"2024-04-30T00:08:39.704172Z","shell.execute_reply":"2024-04-30T00:08:48.168999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-30T00:08:48.174039Z","iopub.execute_input":"2024-04-30T00:08:48.174343Z","iopub.status.idle":"2024-04-30T00:08:48.327605Z","shell.execute_reply.started":"2024-04-30T00:08:48.174280Z","shell.execute_reply":"2024-04-30T00:08:48.326499Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train = train['label']\ny_train = train.drop(['label'],axis = 1)","metadata":{"execution":{"iopub.status.busy":"2024-04-30T00:10:43.964413Z","iopub.execute_input":"2024-04-30T00:10:43.964776Z","iopub.status.idle":"2024-04-30T00:10:44.255567Z","shell.execute_reply.started":"2024-04-30T00:10:43.964709Z","shell.execute_reply":"2024-04-30T00:10:44.254462Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train.values[0]","metadata":{"execution":{"iopub.status.busy":"2024-04-30T00:12:40.311927Z","iopub.execute_input":"2024-04-30T00:12:40.312535Z","iopub.status.idle":"2024-04-30T00:12:40.322301Z","shell.execute_reply.started":"2024-04-30T00:12:40.312481Z","shell.execute_reply":"2024-04-30T00:12:40.321572Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_image = y_train.values[0]\nplt.imshow(sample_image.reshape(28,28), cmap='gray', interpolation='none')\n","metadata":{"execution":{"iopub.status.busy":"2024-04-30T00:24:31.810718Z","iopub.execute_input":"2024-04-30T00:24:31.811357Z","iopub.status.idle":"2024-04-30T00:24:32.079785Z","shell.execute_reply.started":"2024-04-30T00:24:31.811060Z","shell.execute_reply":"2024-04-30T00:24:32.078461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Regularization of values\ny_train = y_train/255.0\ntest = test/255.0\n\n# Reshaping for an Image rather than line data.\ny_train = y_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\n\nX_train = to_categorical(X_train, num_classes = 10)\n\nX_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2)","metadata":{"_cell_guid":"260e5aaa-ab2f-4f4b-b4e9-752e869708bd","_uuid":"09889782668a25157262bdb90c1a38ba449c409e","collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Setting the CNN Model\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)))\nmodel.add(Dropout(0.25))\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(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))","metadata":{"_cell_guid":"ba509db7-0565-4c4c-8dd4-28bc0bf8b1d5","_uuid":"92be729d3fdcc8f8a44756c631066cbc375fe3c8","collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])\n\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)\nepochs = 30\nbatch_size = 86","metadata":{"_cell_guid":"31094ac2-f6db-4dc9-b156-6c3aef6a9bc7","_uuid":"55c0f42e8040ea22dac0b8c17d384c626085a561","collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"datagen = ImageDataGenerator(\n        featurewise_center=False,  # set input mean to 0 over the dataset\n        samplewise_center=False,  # set each sample mean to 0\n        featurewise_std_normalization=False,  # divide inputs by std of the dataset\n        samplewise_std_normalization=False,  # divide each input by its std\n        zca_whitening=False,  # apply ZCA whitening\n        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.1, # Randomly zoom image \n        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=False,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\n\n\ndatagen.fit(y_train)","metadata":{"_cell_guid":"49c9a765-af77-4bba-b94d-3f082c4b4d05","_uuid":"b234eabc2a91e967eef08752b67a28434196ba69","collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit_generator(datagen.flow(y_train,X_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (y_test,X_test),\n                              verbose = 2, steps_per_epoch=y_train.shape[0] // batch_size\n                              , callbacks=[learning_rate_reduction])","metadata":{"_cell_guid":"253f3444-e3c4-4435-8aa4-7beb7dd8f78f","_uuid":"04dddc39d1db642ff4e093c7f5b8d7f7be070ceb","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"results = model.predict(test)\nresults = np.argmax(results,axis = 1)\nresults = pd.Series(results,name=\"Label\")\n\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)","metadata":{"_cell_guid":"edc8e5da-503a-48ed-bda0-ecad8e102795","_uuid":"cfd75764166e6d93f5f6ebc7b972fcfdbc553303","collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]}]}