{"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":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')  \ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\nX_train = (train.iloc[:,1:].values).astype('float32') # all pixel values\nY_train = train.iloc[:,0].values.astype('int32') # only labels i.e targets digits\nx_test = test.values.astype('float32')\n\n# Dividing in training and dev set\nx_train = X_train[0:38000]\ny_train = Y_train[0:38000]\nx_dev = X_train[38000:42000]\ny_dev = Y_train[38000:42000]\n\n# Reshape image in 3 dimensions (height = 28px, width = 28px , canal = 1)\nx_train = x_train.reshape(-1,28,28,1)\nx_dev = x_dev.reshape(-1,28,28,1)\nx_test = x_test.reshape(-1,28,28,1)\n\n# tocategorical\nfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding\ny_train = to_categorical(y_train, num_classes = 10)\ny_dev = to_categorical(y_dev, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import layers\nfrom keras import models\n\nmodel = models.Sequential()\n\nmodel.add(layers.Conv2D(filters=16, kernel_size=(5, 5), activation='relu', input_shape=(28,28,1)))\nmodel.add(layers.Conv2D(filters=32, kernel_size=(3, 3), padding='same', activation='relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Conv2D(filters=64, kernel_size=(3, 3), padding='same', activation='relu'))\nmodel.add(layers.Conv2D(filters=64, kernel_size=(3, 3), padding='same', activation='relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Conv2D(filters=128, kernel_size=(3, 3), padding='same', activation='relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Flatten())\n\nmodel.add(layers.Dense(units=512, activation='relu'))\nmodel.add(layers.Dense(units=128, activation='relu'))\nmodel.add(layers.Dense(units=10, activation = 'softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import time\nmodel.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])\n\n# Training\ntic = time.time()\nmodel.fit(x_train, y_train, epochs=10, batch_size=64)\ntoc = time.time()\nprint(\"The total training time is\", toc-tic, \"seconds\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dev_loss, dev_acc = model.evaluate(x_dev, y_dev)\ndev_acc","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# predict results\nresults = model.predict(x_test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\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)","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}