{"cells":[{"metadata":{"_uuid":"ab88a873-1019-4b40-980a-6aa091e3cefe","_cell_guid":"5648bddb-ed32-418d-b141-ee82a9d8c731","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')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\np = tf.config.experimental.list_physical_devices('GPU')\ntf.config.experimental.set_visible_devices(p[0], 'GPU')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"877b304b-fa7a-4646-90f4-3ef8ebac448b","_cell_guid":"724817e5-8e8c-4ea4-bf67-a9eab907f12d","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = train[\"label\"]\n\n# Drop 'label' column\nX_train = train.drop(labels = [\"label\"],axis = 1) \n\n# free some space\ndel train \n\ng = sns.countplot(Y_train)\n\nY_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"5c73a7d2-70df-4f07-ba0e-343ef2a9e612","_cell_guid":"cfb2d0b4-c385-44a7-a6e1-a76d12706a34","trusted":true},"cell_type":"code","source":"X_train.isnull().any().describe()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().any().describe()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train / 255.0\ntest = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = to_categorical(Y_train, num_classes = 10)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=2)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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(X_train)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"fca82f1c-41d3-41ed-87b3-acd5a7a050bd","_cell_guid":"cdb755e2-ffcb-4835-92cd-8c0589db27fe","trusted":true},"cell_type":"code","source":"import tensorflow.keras.backend as K\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.models import Sequential, load_model\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D \nfrom tensorflow.keras.layers import MaxPool2D, BatchNormalization\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import LearningRateScheduler, ModelCheckpoint\n\n\nmodel = Sequential()\nmodel.add(Conv2D(32, kernel_size = 3, activation='relu', \n                     input_shape = (28, 28, 1)))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32, kernel_size = 3, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32, kernel_size = 5, strides=2, padding='same', \n                     activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\nmodel.add(Conv2D(64, kernel_size = 3, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64, kernel_size = 3, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64, kernel_size = 5, strides=2, padding='same', \n                     activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\nmodel.add(Conv2D(128, kernel_size = 4, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Flatten())\nmodel.add(Dropout(0.4))\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\", \n                  metrics=[\"accuracy\"])\n    \nmodel.summary()    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import RMSprop\n\noptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_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":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 30\nbatch_size = 86\n\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 = 2, steps_per_epoch=X_train.shape[0] // batch_size)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"901ccb3a-ecba-4406-8d27-9cf59a22806f","_cell_guid":"dac34211-2774-4a8c-908a-02ff49018e69","trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(2,1)\nax[0].plot(history.history['loss'], color='b', label=\"Training loss\")\nax[0].plot(history.history['val_loss'], color='r', label=\"validation loss\",axes =ax[0])\nlegend = ax[0].legend(loc='best', shadow=True)\n\nax[1].plot(history.history['accuracy'], color='b', label=\"Training accuracy\")\nax[1].plot(history.history['val_accuracy'], color='r',label=\"Validation accuracy\")\nlegend = ax[1].legend(loc='best', shadow=True)\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b1a88d27-e01d-4fcc-b3f0-e945f02130a4","_cell_guid":"1606f10c-0ed4-4b8e-8ed4-420a5038841e","trusted":true},"cell_type":"code","source":"def plot_confusion_matrix(cm, classes,\n                          normalize=False,\n                          title='Confusion matrix',\n                          cmap=plt.cm.Blues):\n    \"\"\"\n    This function prints and plots the confusion matrix.\n    Normalization can be applied by setting `normalize=True`.\n    \"\"\"\n    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n    plt.title(title)\n    plt.colorbar()\n    tick_marks = np.arange(len(classes))\n    plt.xticks(tick_marks, classes, rotation=45)\n    plt.yticks(tick_marks, classes)\n\n    if normalize:\n        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n\n    thresh = cm.max() / 2.\n    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n        plt.text(j, i, cm[i, j],\n                 horizontalalignment=\"center\",\n                 color=\"white\" if cm[i, j] > thresh else \"black\")\n\n    plt.tight_layout()\n    plt.ylabel('True label')\n    plt.xlabel('Predicted label')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_pred = model.predict(X_val)\n# Convert predictions classes to one hot vectors \nY_pred_classes = np.argmax(Y_pred,axis = 1) \n# Convert validation observations to one hot vectors\nY_true = np.argmax(Y_val,axis = 1) \n# compute the confusion matrix\nconfusion_mtx = confusion_matrix(Y_true, Y_pred_classes) \n# plot the confusion matrix\nplot_confusion_matrix(confusion_mtx, classes = range(10)) ","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"89b5d197-7f63-4dd1-98af-b095d4c00ed2","_cell_guid":"050ea3d8-5bbf-4de3-862a-3a609f74644a","trusted":true},"cell_type":"code","source":"errors = (Y_pred_classes - Y_true != 0)\n\nY_pred_classes_errors = Y_pred_classes[errors]\nY_pred_errors = Y_pred[errors]\nY_true_errors = Y_true[errors]\nX_val_errors = X_val[errors]\n\ndef display_errors(errors_index,img_errors,pred_errors, obs_errors):\n    \"\"\" This function shows 6 images with their predicted and real labels\"\"\"\n    n = 0\n    nrows = 2\n    ncols = 3\n    fig, ax = plt.subplots(nrows,ncols,sharex=True,sharey=True)\n    for row in range(nrows):\n        for col in range(ncols):\n            error = errors_index[n]\n            ax[row,col].imshow((img_errors[error]).reshape((28,28)))\n            ax[row,col].set_title(\"Predicted label :{}\\nTrue label :{}\".format(pred_errors[error],obs_errors[error]))\n            n += 1\n\n# Probabilities of the wrong predicted numbers\nY_pred_errors_prob = np.max(Y_pred_errors,axis = 1)\n\n# Predicted probabilities of the true values in the error set\ntrue_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1))\n\n# Difference between the probability of the predicted label and the true label\ndelta_pred_true_errors = Y_pred_errors_prob - true_prob_errors\n\n# Sorted list of the delta prob errors\nsorted_dela_errors = np.argsort(delta_pred_true_errors)\n\n# Top 6 errors \nmost_important_errors = sorted_dela_errors[-6:]\n\n# Show the top 6 errors\ndisplay_errors(most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"a02f230e-9cc8-4d0c-b849-a7a514af6f0f","_cell_guid":"f45cac42-682f-45fe-892f-02e7e1799c8e","trusted":true},"cell_type":"code","source":"results = 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":{"_uuid":"6f629fcf-636a-4052-8ab1-52413e9845bd","_cell_guid":"5719fa6c-95cb-4701-bbd5-20f30f32772d","trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)\nsubmission","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":4}