{"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_url = '/kaggle/input/digit-recognizer/train.csv'\ntest_url = '/kaggle/input/digit-recognizer/test.csv'\ntrain = pd.read_csv(train_url)\ntest = pd.read_csv(test_url)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train.shape,\"\\n\",test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.drop('label', axis=1).astype('float32')\ny = train['label']\nX_sub = test.astype('float32')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nimport tensorflow.keras as keras\nfrom keras import Sequential,layers,callbacks,preprocessing","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X.values.reshape(-1,28,28,1)\nX_sub = X_sub.values.reshape(-1,28,28,1)\ny = keras.utils.to_categorical(y, 10)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=7, shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def spatial_cnn():\n    model = Sequential([\n        layers.experimental.preprocessing.Rescaling(scale=1.0/255.0, input_shape=(28,28,1)),\n        layers.Conv2D(32, (3,3), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Conv2D(32, (3,3), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Conv2D(32, (5,5), (2,2), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Conv2D(64, (3,3), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Conv2D(64, (3,3), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Conv2D(64, (5,5), (2,2), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Conv2D(128, (3,3), activation='relu', padding='same'),\n        layers.BatchNormalization(),\n        layers.SpatialDropout2D(0.25),\n        layers.Flatten(),\n        layers.Dense(300, activation=\"relu\"),\n        layers.BatchNormalization(),\n        layers.Dropout(0.4),\n        layers.Dense(10, activation='softmax')],\n        name='spatial_cnn')\n    \n    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics='accuracy')\n    model.summary()\n    return model\n\nmodel = spatial_cnn()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = preprocessing.image.ImageDataGenerator(rotation_range=10, width_shift_range=0.1,\n                                                       height_shift_range=0.1, shear_range=0.1,\n                                                       zoom_range=0.1)\n\ntrain_datagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 64\nepochs = 45\nsteps = X_train.shape[0]//batch_size\nhistory = dict()\nflow = train_datagen.flow(X_train, y_train, batch_size=batch_size, shuffle=True)\nchanged = False\n\nclass cbs(callbacks.Callback):\n    def on_epoch_end(self, epoch, logs):\n        global changed\n        if logs['val_loss']<=0.0205 and not changed:\n            changed = True\n            print(\"\\nChanging LR\\n\")\n            global reduce_lr\n            reduce_lr = callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.05, patience=2, min_lr=1.0e-10)\n            \nreduce_lr = callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=2, min_lr=1.0e-10)\nearly_stop = callbacks.EarlyStopping(monitor=\"val_loss\", patience=10, mode=\"auto\")\nmodel_hist = model.fit_generator(flow, validation_data=(X_test, y_test), verbose=1, shuffle=True,\n                               steps_per_epoch=steps, epochs=epochs, callbacks=[cbs(), reduce_lr, early_stop])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.figure(figsize=(20,5))\nplt.subplot(1,2,1)\nplt.plot(model_hist.history['loss'],'r*-')\nplt.plot(model_hist.history['val_loss'],'b*-')\nplt.title('Training and Validation Losses')\nplt.legend(labels=['Loss','Validation Loss'])\nplt.subplot(1,2,2)\nplt.plot(model_hist.history['accuracy'],'mo-')\nplt.plot(model_hist.history['val_accuracy'],'co-')\nplt.title('Training and Validation Accuracy')\nplt.legend(labels=['Accuracy','Validation Accuracy'])\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds_sub = pd.DataFrame(data={\"ImageId\":list(range(1,X_sub.shape[0]+1)),\"Label\":(model.predict_classes(X_sub))}).astype(int)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds_sub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds_sub.to_csv(\"DigitRecog.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}