{"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport matplotlib as mpl\n\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":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\nprint(train.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\nprint(test.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train = train[\"label\"]\nX_train = train.drop(labels=[\"label\"],axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(15,7))\ng = sns.countplot(y_train, palette=\"icefire\")\nplt.title(\"Number of digit classes\")\nprint(\" \\t # y_train value counts # \\n\",y_train.value_counts())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train = X_train / 255.0\nX_test = test / 255.0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = X_test.values.reshape(-1,28,28,1)\nX_train = X_train.values.reshape(-1,28,28,1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nY_train = to_categorical(y_train, num_classes = 10)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=2)\nprint(\"x_train shape\",X_train.shape)\nprint(\"x_val shape\",X_val.shape)\nprint(\"y_train shape\",Y_train.shape)\nprint(\"y_val shape\",Y_val.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\nimport itertools\n\nfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop,Adam\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\nmodel = Sequential()\n\nmodel.add(Conv2D(filters = 8, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 16, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\n# fully connected\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"optimizer = Adam(lr=0.001, beta_1=0.9, beta_2=0.999)","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":"epochs = 100  \nbatch_size = 250","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"datagen = ImageDataGenerator(\n        featurewise_center=False,  \n        samplewise_center=False, \n        featurewise_std_normalization=False,  \n        samplewise_std_normalization=False,  \n        zca_whitening=False, \n        rotation_range=5,  \n        zoom_range = 0.1, \n        width_shift_range=0.1,  \n        height_shift_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":"from tensorflow.keras.callbacks import EarlyStopping\nearly_stopping = EarlyStopping(monitor='val_loss', mode='min', verbose=1,patience=6)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit_generator(datagen.flow(X_train,Y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (X_val,Y_val), steps_per_epoch=X_train.shape[0] // batch_size,\n                              callbacks=[early_stopping])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Accuracy of the model is --> \" , model.evaluate(X_val, Y_val, batch_size=batch_size)[1]*100 , \"%\")\nprint(\"Loss of the model is --> \" , model.evaluate(X_val, Y_val, batch_size=batch_size)[0])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = model.predict(X_test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = np.argmax(labels, axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission = pd.read_csv(\"../input/digit-recognizer/sample_submission.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"index = test.index.values + 1\ndata = {'ImageId' : index, \"Label\" : labels}\ndf = pd.DataFrame(data=data)\ndf.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submit = pd.DataFrame({'ImageId' : index, \"Label\" : labels.astype(int).ravel()})\nsubmit.to_csv(\"submission.csv\",index = False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submit","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}