{"cells":[{"metadata":{},"cell_type":"markdown","source":"# MNIST"},{"metadata":{"trusted":true,"_kg_hide-input":false},"cell_type":"code","source":"import cv2\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils.np_utils import to_categorical\nfrom keras import layers, models, optimizers\nfrom keras.preprocessing.image import ImageDataGenerator, img_to_array\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.models import Sequential\n\n\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\n\nimport os \nimport random \nimport gc","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data"},{"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')\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['label']\nx = train.drop(['label'], axis=1, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\ntrain.shape, test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(20,10))\ncolumns=5\nfor i in range(columns):\n    plt.subplot(5/columns + 1, columns, i+1)\n    plt.imshow(train[i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = np.array(train)\ny = np.array(y)\ny = to_categorical(y,num_classes=10)\n\ntest = np.array(test)\ntrain.shape\n\nX_train, X_val, Y_train, Y_val = train_test_split(train, y, test_size=0.1, random_state=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(y)\nplt.title('Lable for digits')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del train\ndel y\n\nn_train = len(X_train)\nn_val = len(X_val)\n\nbatch_size = 256","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same', activation='relu', input_shape=(28, 28, 1)))\nmodel.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\n\n#model.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))\n\n#model.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation=\"relu\"))\n\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(10, activation=\"softmax\"))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_gen = ImageDataGenerator(rescale=1./255)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator = data_gen.flow(X_train, Y_train, batch_size=batch_size)\nval_generator = data_gen.flow(X_val, Y_val, batch_size=batch_size)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training"},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(train_generator, \n                             steps_per_epoch = n_train//batch_size,\n                             epochs=50,\n                             validation_data = val_generator,\n                             validation_steps = n_val//batch_size)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Results"},{"metadata":{"trusted":true},"cell_type":"code","source":"acc = history.history['accuracy']\nval_acc = history.history['val_accuracy']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nep = range(1,len(acc) + 1)\n\nplt.plot(ep, acc, 'b', label='Training Accuracy')\nplt.plot(ep, val_acc, 'r', label='Validation Accuracy')\nplt.title('Training and Validation Accuracy')\nplt.legend()\n\nplt.figure()\n\nplt.plot(ep, loss, 'b', label='Training Loss')\nplt.plot(ep, val_loss, 'r', label='Validation Loss')\nplt.title('Training and Validation Loss')\nplt.legend()\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_result = model.predict(test)\nprint('Prediction Shape is {}'.format(y_result.shape))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = np.argmax(y_result, 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\nsubmission.to_csv(\"submission.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}