{"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":"# Read Data \ntrain_data = pd.read_csv('../input/digit-recognizer/train.csv')\ntest_data =  pd.read_csv('../input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Function To display Image\nimport matplotlib.pyplot as plt\n%matplotlib inline\ndef show_image(image):\n    plt.imshow(image,cmap = 'gray')\n    plt.show()\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"show_image(train_data.values[0,1:].reshape((28,28)))\nprint('LABEL --> ',train_data['label'][0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Here I'm gonna build a convolution model for classification purpose using Tensorflow.\n# Lets import some packages.\n\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense,Conv2D,MaxPooling2D,Flatten,Dropout\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"total_training_data = len(train_data)\ntotal_testing_data = len(test_data)\nprint('TOTAL TRAINING DATA ---> ',total_training_data)\nprint('TOTAL TESTING DATA --->',total_testing_data)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Total data ---> 42000+28000 = 70000\nTest data percentage ---> 0.4%\nTraining data percentage ---> 0.6%\nLet's divide training data ratio in 0.5 +0.1 (Training + Validation)\nSo, Total validation data ---> 4200 (0.1%42000)\nAnd Training data will 37800.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train_data = train_data.drop(labels = 'label',axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train_data = train_data['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = tf.keras.utils.normalize(X_train_data,axis = 1)\nX_test = tf.keras.utils.normalize(test_data,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape((42000,28,28,1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.unique(Y_train_data)\nY_train = tf.keras.utils.to_categorical(Y_train_data,num_classes=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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 = 1)\nprint('Trainig data: ',x_train.shape,y_train.shape)\nprint('Validation data: ',x_val.shape,y_val.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Lets define the model\nmodel = Sequential()\nmodel.add(Conv2D(input_shape = (28,28,1),filters = 16,kernel_size = (3,3),strides = (2,2),padding = 'same',activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size = (1,1)))\nmodel.add(Conv2D(filters = 32,kernel_size = (3,3),strides = (2,2),padding = 'same',activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size = (1,1)))\nmodel.add(Conv2D(filters = 128,kernel_size = (3,3),strides = (2,2),padding = 'same',activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size =  (1,1)))\nmodel.add(Flatten())\nmodel.add(Dense(10,activation = 'softmax'))\n","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',loss = 'categorical_crossentropy',metrics = ['Accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 64\nEPOCHS = 500","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit?","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hist = model.fit(x = X_train,y = Y_train,batch_size = BATCH_SIZE,validation_data=(x_val,y_val),epochs = EPOCHS,verbose = 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(hist.history['loss'],'red',label = 'Loss')\nplt.plot(hist.history['accuracy'],'blue',label = 'Accuracy')\nplt.plot(hist.history['val_loss'],'green',label = 'val_loss')\nplt.plot(hist.history['val_accuracy'],'pink',label = 'val_accuracy')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = X_test.reshape((-1,28,28,1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_out = []\nfor p in pred:\n    Y_out.append(np.argmax(p))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"show_image(X_test[0].reshape((28,28)))\nY_out[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ImageId = [i for i in range(1,X_test.shape[0]+1)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dict1 =  {'ImageId':ImageId,\n         'Label':Y_out}\ndf = pd.DataFrame(dict1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}