{"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":"import pandas as pd\nimport tensorflow as tf\nfrom keras.utils.np_utils import to_categorical\ntrain = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntrain.head()\n\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\ntest.head()\n\ny=train['label'].values\nx=train.drop('label',axis=1).values\nprint(x.shape)\nprint(y.shape)\n\nimport matplotlib.pyplot as plt\nx=x.reshape(x.shape[0],28,28)\nfig=plt.figure()\nfor i in range(9):\n    plt.subplot(3,3,i+1)\n    plt.imshow(x[i],cmap='gray')\n\nx = x.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\n\nx.shape\n\nx = x/255\ntest = test/255\ny = to_categorical(y)\n\nfrom sklearn.model_selection import train_test_split\n\ntrain_x,valid_x,train_y,valid_y = train_test_split(x,y,random_state=1,test_size=0.2)\n\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Conv2D,Dropout,GlobalAveragePooling2D,MaxPool2D,Flatten\n\nmodel = Sequential()\nmodel.add(Conv2D(64,kernel_size=(3,3,),padding='same',strides=(2,2),activation=tf.nn.relu6,input_shape=(28,28,1)))\nmodel.add(tf.keras.layers.BatchNormalization(axis=-1))\nmodel.add(MaxPool2D(strides=(2,2),padding='same'))\nmodel.add(Conv2D(128,kernel_size=(3,3),strides=(2,2),padding='same',activation=tf.nn.relu6))\nmodel.add(MaxPool2D())\nmodel.add(Dropout(0.2))\n\nmodel.add(GlobalAveragePooling2D())\nmodel.add(tf.keras.layers.Dense(256,activation=tf.nn.relu6))\nmodel.add(tf.keras.layers.Dense(10,activation='softmax'))\n\nmodel.compile(loss='categorical_crossentropy',optimizer=tf.keras.optimizers.Adam(learning_rate=10e-4),metrics = ['accuracy'])\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\ntrain_datagen=ImageDataGenerator(\n    rescale=1/.255,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    zoom_range=0.2,\n    fill_mode='nearest'\n)\ntrain_generator=train_datagen.flow(\n    train_x,train_y,\n    batch_size=128\n    )\n\nvalid_datagen=ImageDataGenerator(\n    rescale=1/.255)\nvalid_generator=valid_datagen.flow(\n    valid_x,valid_y,\n    batch_size=128)\n\nimport tensorflow as tf\ncallback=tf.keras.callbacks.EarlyStopping(monitor='accuracy',min_delta=0,patience=5,verbose=2,mode='auto',restore_best_weights=True)\nhistory=model.fit(train_generator,\n                  epochs=100,\n                  steps_per_epoch=train_x.shape[0]//128,\n                  verbose=2,\n                  validation_data=valid_generator,\n                  validation_steps=valid_x.shape[0]//128,\n                  callbacks=[callback])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\ndef plot_model(history):\n    fig,(ax1,ax2)=plt.subplots(1,2,figsize=(12,4))\n    fig.suptitle('Model Accuracy and Loss')\n\n    ax1.plot(history.history['accuracy'])\n    ax1.plot(history.history['val_accuracy'])\n    ax1.title.set_text('Accuracy')\n    ax1.set_ylabel('Accuracy')\n    ax1.set_xlabel('Epoch')\n    ax1.legend(['Train','Valid'],loc=4)\n\n    ax2.plot(history.history['loss'])\n    ax2.plot(history.history['val_loss'])\n    ax2.title.set_text('Loss')\n    ax2.set_ylabel('Loss')\n    ax2.set_xlabel('Epoch')\n    ax2.legend(['Train','Valid'],loc=1)\n\n    fig.show()\n\nplot_model(history)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction=model.predict(test)\nprediction=np.argmax(prediction,axis = 1)\nprediction=pd.Series(prediction,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"zz","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}