{"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":{},"cell_type":"markdown","source":"> Importing the necessary libraries"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow.keras as keras\nimport matplotlib.pyplot as plt\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D,BatchNormalization\nfrom keras.models import Sequential\nfrom keras.utils import to_categorical\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')","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.head()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"- Splitting the labels"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_1 = train.iloc[:,1:785]\ntrain_1.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_y = train[\"label\"]\ntrain_y.head()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"- Convert it into numpy arrays from pandas dataframe for normalization"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_n =train_1.to_numpy()\n\ntrain_yn = train_y.to_numpy()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"raw","source":"Normalise the data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_n = train_n/255\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntrain_n = train_n.reshape((train_n.shape[0],28,28,1))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"CNN Model"},{"metadata":{},"cell_type":"markdown","source":"# Define the model and Compile it\n- `Adam as optimizer` \n- `categorical crossentropy` as loss function"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.add(Conv2D(64,(3,3),activation = 'relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,(3,3),activation = 'relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,(5,5),activation = 'relu',strides=True,padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\n\nmodel.add(Conv2D(128,(3,3),activation = 'relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128,(3,3),activation = 'relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128,(5,5),activation = 'relu',strides=True,padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n          \nmodel.add(Conv2D(256,(4,4),activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Flatten())\nmodel.add(Dropout(0.4))\n\nmodel.add(Dense(10,activation = 'softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.compile(optimizer = 'adam',loss = 'sparse_categorical_crossentropy',metrics = ['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history =  model.fit(train_n,train_yn,epochs=40,batch_size =32,verbose=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Visualisation"},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=[8,6])\nplt.plot(history.history['accuracy'],'b')\nplt.legend(['Training Accuracy','Validation Accuracy'])\nplt.xlabel('Epochs')\nplt.ylabel('Accuracy')\nplt.title('learning curves')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"- Loading the test data\n- Data Preprocessing of the same"},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\ntest.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_n = test.to_numpy()\ntest_n = test_n / 255\ntest_n = test_n.reshape((test_n.shape[0],28,28,1))\ntest_n.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"- Predictions"},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = model.predict(test_n)\npreds = np.asarray([np.argmax(pred) for pred in preds])\npreds.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Saving the predictions as a Data Frame**"},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = pd.DataFrame(preds).rename(columns={0:\"Label\"})\npredictions.index.names = [\"ImageID\"]\npredictions.index +=1\npredictions.head(25)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions.shape\npredictions.to_csv(\"Y_Predictions1.csv\")","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}