{"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"test = pd.read_csv('../input/digit-recognizer/test.csv')\ntrain = pd.read_csv('../input/digit-recognizer/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().values.any()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().values.any()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(12,6))\nax = sns.countplot(train[\"label\"])","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(train.iloc[i,1:].to_numpy().reshape((28,28)), cmap=plt.cm.binary)\n    plt.xlabel([train.iloc[i,0]])\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras\nfrom sklearn.model_selection import train_test_split\nfrom keras.models import Sequential\nfrom keras.layers.core import Dense, Activation, Dropout, Flatten\nfrom keras.layers.convolutional import Conv2D, MaxPooling2D\nfrom sklearn.metrics import classification_report\nfrom keras.optimizers import SGD\n\n\nnp.random.seed(42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.drop(\"label\",axis=1).values.astype(\"float32\")\ny = train[\"label\"].values.astype(\"int32\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_cnn = train.drop(\"label\",axis=1).values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(train_cnn, y, test_size=0.2, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train / 255.0\nX_test = X_test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = keras.utils.to_categorical(y_train, 10)\ny_test = keras.utils.to_categorical(y_test, 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', input_shape=(28, 28, 1)))\nmodel.add(MaxPooling2D((2, 2)))\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform'))\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform'))\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Conv2D(100, (3, 3), activation='relu', kernel_initializer='he_uniform'))\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(100, activation='relu', kernel_initializer='he_uniform'))\nmodel.add(Dense(10, activation='softmax'))\n# compile model\nopt = SGD(lr=0.01, momentum=0.9)\nmodel.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(X_train, y_train, epochs=20, batch_size =64, validation_data=(X_test,y_test));","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = model.predict(X_test)\ny_pred = np.argmax(y_pred, axis = 1)\ny_test = np.argmax(y_test, axis = 1)\nprint(classification_report(y_test, y_pred))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_loss(history):\n  plt.plot(history.history['loss'], label='loss')\n  plt.plot(history.history['val_loss'], label='val_loss')\n  plt.xlabel('Epoch')\n  plt.ylabel('Error')\n  plt.legend()\n  plt.grid(True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_loss(history)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_cnn = test.values.reshape(-1,28,28,1).astype(\"float32\")\ntest_cnn = test_cnn / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_cnn.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(test_cnn)\nsubmissions = pd.DataFrame({\"ImageId\": list(range(1,len(results)+1)),\n                         \"Label\": np.argmax(results, axis = 1)})\n\nsubmissions.to_csv(\"Digit_Recognizer.csv\", index=False, header=True)","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}