{"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\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 read-only \"../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# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\nimport 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\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, BatchNormalization\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\n# http://seaborn.pydata.org/generated/seaborn.set.html\nsns.set(style='white', context='notebook', palette='deep')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 'label'\nY_train = train[\"label\"]\nprint(Y_train.shape)\n\n\nX_train = train.drop(labels = [\"label\"],axis = 1) \nprint(X_train.shape)\n\n\ndel train\n\n\n# https://seaborn.pydata.org/generated/seaborn.countplot.html?highlight=countplot\ng = sns.countplot(Y_train)\n\n\n# https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.value_counts.html\nY_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().any().describe()","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":"#(height = 28px, width = 28px , canal = 1)\nX_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":"#2 -> [0,0,1,0,0,0,0,0,0,0])\nY_train = to_categorical(Y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"random_seed = 2\n\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":{"trusted":true},"cell_type":"code","source":"g = plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPool2D(pool_size=(2,2)))\n# model.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n# model.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\"))\n\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nmodel.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\", metrics=[\"accuracy\"])\n\n\n# model.compile(optimizer=\"sgd\", loss=\"categorical_crossentropy\", metrics=[\"accuracy\"])\n# optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\n\n# 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":"epochs = 30\n# epochs = 30 \nbatch_size = 86","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n        featurewise_center=False,  \t\t\t\t\n        samplewise_center=False,  \t\t\t\t\n        featurewise_std_normalization=False,\n        samplewise_std_normalization=False,  \t\n        zca_whitening=False,  \t\t\t\t\t\n        rotation_range=10,  \t\t\t\t\t\n        zoom_range = 0.1, \t\t\t\t\t\t\n        width_shift_range=0.1,  \t\t\t\t\n        height_shift_range=0.1,  \t\t\t\t\n        horizontal_flip=False,  \t\t\t\t\n        vertical_flip=False)  \t\t\t\t\n\n\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = 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,\n                              callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{"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)","execution_count":null,"outputs":[]},{"metadata":{"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    \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\n\nY_pred = model.predict(X_val)\n\nY_pred_classes = np.argmax(Y_pred,axis = 1) \n\nY_true = np.argmax(Y_val,axis = 1) \n\nconfusion_mtx = confusion_matrix(Y_true, Y_pred_classes) \n\nplot_confusion_matrix(confusion_mtx, classes = range(10))","execution_count":null,"outputs":[]},{"metadata":{"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    \"\"\"\n    \"\"\"\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\nY_pred_errors_prob = np.max(Y_pred_errors,axis = 1)\n\n\ntrue_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1))\n\n\ndelta_pred_true_errors = Y_pred_errors_prob - true_prob_errors\n\n\nsorted_dela_errors = np.argsort(delta_pred_true_errors)\n\n# Top 6\nmost_important_errors = sorted_dela_errors[-6:]\n\n\ndisplay_errors(most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(test)\n\nresults = np.argmax(results,axis = 1)\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\n\nsubmission.to_csv(\"Abhi_mnist_datagen.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}