{"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":"test = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\ntrain = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train.iloc[:,1:]\nY_train = train.iloc[:,0]\nX_train /= 255\ntest /= 255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\n\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\nfrom sklearn.model_selection import train_test_split\n\nimport matplotlib.pyplot as plt\n\nplt.figure(figsize=(10,10))\nfor i in range(25):\n    plt.subplot(5,5,i+1)\n    plt.xticks([])\n    plt.yticks([])\n    plt.grid(False)\n    plt.imshow(X_train.iloc[i,:].to_numpy().reshape((28,28)), cmap=plt.cm.binary)\n    plt.xlabel(Y_train[i])\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(28, (3, 3), activation='relu', input_shape=(28, 28, 1)))\nmodel.add(MaxPooling2D((2, 2)))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2, 2)))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\n\nmodel.add(Flatten())\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dense(10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam',\n              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n              metrics=['accuracy']\n             )\n\nX_train = X_train.to_numpy().reshape((-1, 28, 28, 1))\nY_train = Y_train.to_numpy().reshape((-1, 1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 10","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(X_train,Y_train,\n                    epochs = epochs,\n                    validation_data = (X_val,Y_val),\n                    steps_per_epoch=X_train.shape[0]\n                   )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['accuracy'], label='accuracy')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy')\nplt.ylim([0.5, 1])\nplt.legend(loc='lower right')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = test.to_numpy().reshape((len(test), 28, 28, 1))\n\noutput = model.predict(test_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output_labels = np.argmax(output, axis =1).reshape((len(test), 1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,10))\nfor i in range(25):\n    plt.subplot(5,5,i+1)\n    plt.xticks([])\n    plt.yticks([])\n    plt.grid(False)\n    plt.imshow(test_data[i].reshape(28,28), cmap=plt.cm.binary)\n    plt.xlabel(output_labels[i])\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.DataFrame(output_labels)\nsubmission = pd.DataFrame({'ImageId': df.index+1, 'Label': df[0]})\nsubmission.to_csv('my_submission.csv', index=False)\nprint(\"Your submission was successfully saved!\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Credits\n\nAdapted from [TensorFlow: Convolutional Neural Network (CNN)](https://www.tensorflow.org/tutorials/images/cnn)","execution_count":null}],"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}