{"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom tensorflow import keras","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train=pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest=pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","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.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#checks for null values\ntrain.isnull().any().describe()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=(train.iloc[:,1:].values.astype('float32'))\ny_train=(train.iloc[:,0].values.astype('float32'))\nX_test=test.values   #.astype('float32')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","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":"#normalize the data\nX_train=X_train/255.0\ntest=test/255.0","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# visualization ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"#Convert train datset to (num_images, img_rows, img_cols) format \nX_train = X_train.reshape(X_train.shape[0], 28, 28)\n\nfor i in range(6, 9):\n    plt.subplot(330 + (i+1))\n    plt.imshow(X_train[i], cmap=plt.get_cmap('gray'))\n    plt.title(y_train[i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train.reshape(X_train.shape[0],28,28,1)\nX_test=X_test.reshape(X_test.shape[0],28,28,1)\nX_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(y_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# conver data to categorical ****","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\ny_train= to_categorical(y_train)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# split the data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train,X_val,y_train,y_val=train_test_split(X_train ,y_train ,test_size=.2 , random_state=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[1][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"onv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))","execution_count":null},{"metadata":{"trusted":true},"cell_type":"markdown","source":"model = keras.Sequential([keras.layers.Conv2D (filters=32,kernel_size=(5,5), activation=\"relu\", input_shape=(28,28,1)),\n    keras.layers.Flatten(),\n    keras.layers.Dense(128, activation=\"relu\"),\n    keras.layers.Dense(10, activation=\"softmax\")\n])","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import layers\nfrom keras import models\nmodel = models.Sequential()\nmodel.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(64, activation='relu'))\nmodel.add(layers.Dense(10, activation='softmax'))\n\n\nmodel.compile(optimizer='rmsprop',loss='categorical_crossentropy',metrics=['accuracy'])\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing import image\ngen = image.ImageDataGenerator()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batches = gen.flow(X_train, y_train, batch_size=64)\nval_batches=gen.flow(X_val, y_val, batch_size=64)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history=model.fit_generator(generator=batches, steps_per_epoch=batches.n, epochs=1, \n                    validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_loss, test_acc = model.evaluate(X_val, y_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_loss","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_acc","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test=model.predict(X_test)\n#\ny_pred = np.argmax(y_test,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = pd.Series(y_pred,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"Sub.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# output","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"submission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\"Sub.csv\"","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":1}