{"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","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"code","source":"\nimport csv\nimport numpy as np\nimport keras\nimport tensorflow as tf\nfrom keras.models import Sequential\nfrom keras.layers import Dense,Dropout,Activation,BatchNormalization\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping\nfrom keras import layers,regularizers\nimport pandas as pd\nfrom keras.optimizers import Adam,RMSprop\ndecay=1e-4\nxtrain = []\nytrain = []\nxtest  = []\n#rough  = []\nxval   = []\nyval   = []\n\n# XTRAIN.   YTRAIN    XVAL    YVAL    XTEST.            DATA Extraction\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n        \ntrain =pd.read_csv(os.path.join(dirname,'train.csv'))\n# print(\"train\",np.shape(train))\ntest =pd.read_csv(os.path.join(dirname,'test.csv'))\n# print(\"test\",np.shape(test))\nsample_submission =pd.read_csv(os.path.join(dirname,'sample_submission.csv')) \nDig_MNIST=pd.read_csv(os.path.join(dirname,'Dig-MNIST.csv'))\n\nxtrain=train.drop('label',axis=1)\nytrain=train.label\nxtest = test.drop('id', axis = 1)\nxval=Dig_MNIST.drop('label',axis=1)\nyval=Dig_MNIST.label\n\n\nxtrain=xtrain.values\nxtest=xtest.values\nxval=xval.values\nytrain=ytrain.values\nyval=yval.values\n# print(np.shape(xval))\n# print(np.shape(xtrain))\n# xtrain=np.append(xtrain,xval,axis=0) # error yahan hai\n# ytrain=np.append(ytrain,yval,axis=0)\n# print(np.shape(xtrain))\n\n# xval=xval[7000:,:]\n# yval=yval[7000:,:]\n\n\nxtrain=xtrain.reshape(-1,28,28,1).astype('float32')\nxtest=xtest.reshape(-1,28,28,1).astype('float32')\nxval=xval.reshape(-1,28,28,1).astype('float32')\n# print(np.shape(xtest))\n\nxtrain=(xtrain-np.mean(xtrain))/255\nxtest=(xtest-np.mean(xtest))/255\nxval=(xval-np.mean(xval))/255\n       \nmodel=Sequential()\n# model.add(layers.Conv2D(filters=32,kernel_size=(3, 3), activation='relu', input_shape=(28,28,1)))\n# model.add(layers.BatchNormalization())\n# model.add(layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu'))\n# model.add(layers.BatchNormalization())\n# model.add(layers.Conv2D(filters=32, kernel_size=(5, 5), activation='relu'))\n# model.add(layers.BatchNormalization())\n# model.add(layers.Dropout(0.4))\n# # model.add(layers.MaxPooling2D(pool_size=[2,2], strides=2))\n# model.add(layers.Conv2D(filters=64, kernel_size=(5, 5), activation='relu'))\n# model.add(layers.BatchNormalization())\n# # model.add(layers.Dropout(0.1))\n# model.add(layers.Conv2D(filters=64,  kernel_size=(7, 7),kernel_regularizer=regularizers.l2(decay), activation='relu'))\n# model.add(layers.BatchNormalization())\n# model.add(layers.Conv2D(filters=64, kernel_size=(7, 7),kernel_regularizer=regularizers.l2(decay), activation='relu'))\n# model.add(layers.BatchNormalization())\n# model.add(layers.Dropout(0.4))\n# model.add(layers.Conv2D(filters=128, kernel_size=(4, 4),kernel_regularizer=regularizers.l2(decay), activation='relu'))\n# # model.add(keras.layers.AveragePooling2D(pool_size=[2,2], strides=2))\n# model.add(layers.BatchNormalization())\n# model.add(keras.layers.Flatten())\n# model.add(keras.layers.Dropout(0.4))\n# # model.add(Dense(300,activation='relu'))\n# # model.add(Dense(64,activation='relu'))\n# model.add(Dense(10,activation='softmax'))\n########################################################################################################\nmodel.add(layers.Conv2D(64, (3,3), padding='same', input_shape=(28, 28, 1)))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\nmodel.add(layers.Conv2D(64,  (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\nmodel.add(layers.Conv2D(64,  (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\n\nmodel.add(layers.MaxPooling2D(2, 2))\nmodel.add(layers.Dropout(0.2))\n\nmodel.add(layers.Conv2D(128, (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\nmodel.add(layers.Conv2D(128, (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\nmodel.add(layers.Conv2D(128, (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\n\nmodel.add(layers.MaxPooling2D(2,2))\nmodel.add(layers.Dropout(0.2)) \n\nmodel.add(layers.Conv2D(256, (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\nmodel.add(layers.Conv2D(256, (3,3), padding='same'))\nmodel.add(layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(layers.LeakyReLU(alpha=0.1))\n\nmodel.add(layers.MaxPooling2D(2,2))\nmodel.add(layers.Dropout(0.2))\n\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(256))\nmodel.add(layers.LeakyReLU(alpha=0.1))\n\nmodel.add(layers.BatchNormalization())\nmodel.add(layers.Dense(256))\nmodel.add(layers.LeakyReLU(alpha=0.1))\n\nmodel.add(layers.BatchNormalization())\nmodel.add(layers.Dense(10, activation='softmax'))\n\n\n\n\n\nadam_opt = Adam(lr=0.0002, beta_1=0.9, beta_2=0.999,  decay=0.0, amsgrad=False)\noptimizer = RMSprop(learning_rate=0.002,rho=0.9)#,momentum=0.1,epsilon=1e-07,centered=True,name='RMSprop')\nmodel.compile(optimizer=optimizer,loss='sparse_categorical_crossentropy',metrics=['accuracy'])\ndatagen = ImageDataGenerator(\n    rotation_range=12, \n    zoom_range=0.35, \n    width_shift_range=0.3, \n    height_shift_range=0.3,\n#     rescale=1./255\n)\ndatagen.fit(xtrain)\nlearning_rate_reduction = tf.keras.callbacks.ReduceLROnPlateau( \n    monitor='loss',    # Quantity to be monitored.\n    factor=0.2,       # Factor by which the learning rate will be reduced. new_lr = lr * factor\n    patience=2,        # The number of epochs with no improvement after which learning rate will be reduced.\n    verbose=1,         # 0: quiet - 1: update messages.\n    mode=\"min\",       # {auto, min, max}. In min mode, lr will be reduced when the quantity monitored has stopped decreasing; \n                       # in the max mode it will be reduced when the quantity monitored has stopped increasing; \n                       # in auto mode, the direction is automatically inferred from the name of the monitored quantity.\n    min_delta=0.0001,  # threshold for measuring the new optimum, to only focus on significant changes.\n    cooldown=0,        # number of epochs to wait before resuming normal operation after learning rate (lr) has been reduced.\n    min_lr=0.00001     # lower bound on the learning rate.\n    )\n\nes = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=300, restore_best_weights=True)\nmodel.fit_generator(datagen.flow(xtrain, ytrain, batch_size=512),\n                              steps_per_epoch=len(xtrain)//512,\n                              epochs=42,\n                              validation_data=(np.array(xval),np.array(yval)),\n                              validation_steps=50,\n                              callbacks=[learning_rate_reduction, es])\n\n\n\nmodel.summary()\n# model.fit(np.array(xtrain),np.array(ytrain),epochs=20,batch_size=16,validation_data = (np.array(xval),np.array(yval)), verbose = 2)\nscore=model.evaluate(np.array(xval),np.array(yval),batch_size=512)\n\n# ytest=model.predict(xtest)\n# ytest=np.argmax(ytest,axis=1)\n# id_col=np.arange(ytest.shape[0])\n# # print(id_col)\n\n# sample=pd.read_csv(os.path.join(dirname,'sample_submission.csv'))\n# sample['label']=ytest\n# sample.to_csv('submission.csv',index=False)\n\n\n#################\n# USE IT TODAY\n\nytest = model.predict_classes(xtest)\nid_col = np.arange(ytest.shape[0])\nsubmission = pd.DataFrame({'id': id_col, 'label': ytest})\nsubmission.to_csv('submission.csv', index = False)\n\n##################\n\n\n\n# sub_preds = model.predict_classes(test_df)\n# id_col = np.arange(sub_preds.shape[0])\n# submission = pd.DataFrame({'id': id_col, 'label': ytest})\n# submission.to_csv('submission.csv', index = False)\n\nprint(\"accuracy\",score[1])","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}