{"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_minor":4,"nbformat":4,"cells":[{"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 20GB 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"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 import Sequential\nfrom keras import layers\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')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n ","metadata":{}},{"cell_type":"markdown","source":"

Load Data

","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv('../input/digit-recognizer/train.csv')\ntest = pd.read_csv('../input/digit-recognizer/test.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Y_train = train['label']\nX_train = train.drop(['label'], axis = 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"g =sns.countplot(x= Y_train)\nY_train.value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

check for null values

","metadata":{}},{"cell_type":"code","source":"X_train.isnull().any().describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ntest.isnull().any().describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Normalization

","metadata":{}},{"cell_type":"code","source":"X_train = X_train/255.0\ntest = test/255.0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Reshape","metadata":{}},{"cell_type":"code","source":"X_train.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train = X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Label Encoding","metadata":{}},{"cell_type":"code","source":"Y_train = to_categorical(Y_train, num_classes=10)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size=0.2, random_state=42)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.imshow(X_train[0,:])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\nmodel.add(layers.Conv2D(filters = 32, kernel_size=(5,5), activation='relu', padding='same', input_shape=(28,28,1)))\nmodel.add(layers.Conv2D(filters = 32, kernel_size=(5,5), activation='relu', padding='same'))\nmodel.add(layers.MaxPool2D(pool_size = (2,2)))\nmodel.add(layers.Dropout(0.25))\n\nmodel.add(layers.Conv2D(filters = 64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel.add(layers.Conv2D(filters = 64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel.add(layers.MaxPool2D(pool_size = (2,2), strides = (2,2)))\nmodel.add(layers.Dropout(0.25))\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(256 ,activation='relu'))\nmodel.add(layers.Dropout(0.5))\n\nmodel.add(layers.Dense(10, activation='softmax'))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"optimizer = RMSprop(learning_rate = 0.01 , rho = 0.9 , epsilon=1e-08, decay = 0.0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer = optimizer, loss = 'categorical_crossentropy', metrics = ['accuracy'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"reduce_learning_rate = ReduceLROnPlateau(\n mointer = 'val_acc',\n verbose = 1,\n patience = 3,\n factor = 0.5,\n min_lr= 0.00001,\n )","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"epochs = 30\nbatch_size = 86","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Data augmentation

","metadata":{}},{"cell_type":"code","source":"datagen = ImageDataGenerator(\n \n featurewise_center = False,\n samplewise_center = False,\n featurewise_std_normalization = False,\n samplewise_std_normalization = False,\n \n zca_whitening = False,\n rotation_range = 10,\n width_shift_range =0.1,\n height_shift_range = 0.1,\n zoom_range =0.1,\n horizontal_flip = False,\n vertical_flip = False, \n)\ndatagen.fit(X_train)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(datagen.flow(X_train, Y_train, batch_size=batch_size), epochs = epochs, validation_data = (X_val,Y_val),\n verbose = 2, steps_per_epoch=X_train.shape[0]//batch_size, callbacks=[reduce_learning_rate])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.history","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history.history.keys()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef 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\n# Predict the values from the validation dataset\nY_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))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}