If you like this kernel then please consider giving an upvote !
","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Importing necessary libraries !","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\n\nfrom keras.utils.np_utils import to_categorical\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization\nfrom keras.optimizers import RMSprop,Adam\nfrom keras.callbacks import ReduceLROnPlateau","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Loading the data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train=pd.read_csv('../input/Kannada-MNIST/train.csv')\ntest=pd.read_csv('../input/Kannada-MNIST/test.csv')\nsample_sub=pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Understanding the data ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print('The Train dataset has {} rows and {} columns'.format(train.shape[0],train.shape[1]))\nprint('The Test dataset has {} rows and {} columns'.format(test.shape[0],test.shape[1]))\n","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":"test.head(3)\ntest=test.drop('id',axis=1)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Checking wether target column is balanced or not\n* Target variable **label** is balanced","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set_style('whitegrid')\nsns.countplot(x='label',data=train,palette='RdBu_r')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data preparation ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=train.drop('label',axis=1)\nY_train=train.label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train/255\ntest=test/255","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Reshape","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train.values.reshape(-1,28,28,1)\ntest=test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('The shape of train set now is',X_train.shape)\nprint('The shape of test set now is',test.shape)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Encoding Target Values","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"Now we will encode our target value.Keras inbuild library to_categorical() is used to do the on-hot encoding.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train=to_categorical(Y_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Splitting train and test","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train,X_test,y_train,y_test=train_test_split(X_train,Y_train,random_state=42,test_size=0.15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"It's Nine in Kannada\n","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### Data Augmentation!","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# CREATE MORE IMAGES VIA DATA AUGMENTATION\ndatagen = ImageDataGenerator(\n rotation_range=10, \n zoom_range = 0.10, \n width_shift_range=0.1, \n height_shift_range=0.1)\n\n\ndatagen.fit(X_train)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Modelling ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"\nmodel = Sequential()\n\nmodel.add(Conv2D(32,kernel_size=3,activation='relu',input_shape=(28,28,1)))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32,kernel_size=3,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32,kernel_size=5,strides=2,padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\nmodel.add(Conv2D(64,kernel_size=3,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,kernel_size=3,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,kernel_size=5,strides=2,padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\nmodel.add(Dense(10, activation='softmax'))","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":"# Set a learning rate annealer\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n patience=3, \n verbose=1, \n factor=0.5, \n min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs=5 #change this to 30 if you need to get better score\nbatch_size=64","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Fit the model\nhistory = model.fit_generator(datagen.flow(X_train,y_train, batch_size=batch_size),\n epochs = epochs, validation_data = (X_test,y_test),\n verbose = 2, steps_per_epoch=X_train.shape[0] // batch_size\n , callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submission \n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"test=pd.read_csv('../input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_id=test.id\n\ntest=test.drop('id',axis=1)\ntest=test/255\ntest=test.values.reshape(-1,28,28,1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We will make our prediction using our CNN model.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pre=model.predict(test) ##making prediction\ny_pre=np.argmax(y_pre,axis=1) ##changing the prediction intro labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub['label']=y_pre\nsample_sub.to_csv('submission.csv',index=False)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub.head()","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}