{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as  np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\n\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, Nadam\nfrom keras.callbacks import ReduceLROnPlateau, EarlyStopping, ModelCheckpoint, Callback","execution_count":null,"outputs":[]},{"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\")","execution_count":null,"outputs":[]},{"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]))","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)","execution_count":null,"outputs":[]},{"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":{"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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train=to_categorical(Y_train)","execution_count":null,"outputs":[]},{"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=0.20,stratify=Y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n        featurewise_center=False,  # set input mean to 0 over the dataset\n        samplewise_center=False,  # set each sample mean to 0\n        featurewise_std_normalization=False,  # divide inputs by std of the dataset\n        samplewise_std_normalization=False,  # divide each input by its std\n        zca_whitening=False,  # apply ZCA whitening\n        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.35, # Randomly zoom image \n        width_shift_range=0.35,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.25,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=True,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\n\n\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import initializers\ninitializers.get('glorot_uniform')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import regularizers","execution_count":null,"outputs":[]},{"metadata":{"jupyter":{"outputs_hidden":true},"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 128, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization(momentum=.15))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 128, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 32, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization(momentum=0.15))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 32, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 128, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization(momentum=0.15))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 128, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization(momentum=.15))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation = \"relu\"))\nmodel.add(Dropout(0.3))\nmodel.add(Dense(512, activation = \"relu\"))\nmodel.add(Dropout(0.3))\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.3))\n\nmodel.add(Dense(256, activation = \"relu\",\n                kernel_regularizer=regularizers.l1(0.001)\n                #activity_regularizer=regularizers.l1(0.001)\n               ))\n\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#optimizer=Nadam(lr=0.01,beta_1=0.9,beta_2=0.999)\n#optimizer=Nadam(lr=0.01,beta_1=0.9,beta_2=0.999)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='nadam',loss=['binary_crossentropy'],metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_loss', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.3, \n                                            #min_lr=0.00001\n                                            mode     = 'auto',\n                                            #epsilon  = 0.0001,\n                                            cooldown = 0,\n                                            min_lr   = 0\n                                           )\n\ncheckpoint = ModelCheckpoint(\"model.h5\", monitor='val_loss', verbose=1, save_best_only=True, mode='min')\n\nearly = EarlyStopping(monitor=\"val_loss\", mode=\"min\", patience=5)\n\ncallbacks_list = [checkpoint, learning_rate_reduction, early]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs=50\nbatch_size=512","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, \n                              validation_data = (X_test,y_test),\n                              verbose = 1, \n                              steps_per_epoch=X_train.shape[0] // batch_size, \n                              callbacks=callbacks_list)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('Model loss')\nplt.ylabel('Loss')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Val'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('Model accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Val'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pre_test=model.predict(X_test)\ny_pre_test=np.argmax(y_pre_test,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test=np.argmax(y_test,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"conf=confusion_matrix(y_test,y_pre_test)\nconf=pd.DataFrame(conf,index=range(0,10),columns=range(0,10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"conf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x=(y_pre_test-y_test!=0).tolist()\nx=[i for i,l in enumerate(x) if l!=False]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax=plt.subplots(1,4,sharey=False,figsize=(15,15))\n\nfor i in range(4):\n    ax[i].imshow(X_test[x[i]][:,:,0])\n    ax[i].set_xlabel('Real {}, Predicted {}'.format(y_test[x[i]],y_pre_test[x[i]]))","execution_count":null,"outputs":[]},{"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 = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\nsample_sub['label']=y_pre\nsample_sub.to_csv('submission_v1.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.load_weights('model.h5')\ny_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 = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\nsample_sub['label']=y_pre\nsample_sub.to_csv('submission.csv',index=False)\nsample_sub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.7.3"}},"nbformat":4,"nbformat_minor":1}