{"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_minor":4,"nbformat":4,"cells":[{"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\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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Importing important libraries\n\nimport pandas as pd             #library for tabular data\nimport numpy as np              #library for manupulating array\nimport matplotlib.pyplot as plt #library for visualization\nimport matplotlib.image as mpimg\nfrom sklearn.model_selection import train_test_split  #for dividing data into train and validation\n%matplotlib inline\nfrom keras.callbacks import ReduceLROnPlateau,EarlyStopping\n\n#Importing important library for CNN model\nimport keras \nfrom keras.utils.np_utils import to_categorical \nfrom keras.optimizers import RMSprop          # module for optimizers \nfrom keras.preprocessing.image import ImageDataGenerator      # module for image augmentation","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" **Loading of dataset into train and test folder with help of pandas library**","metadata":{}},{"cell_type":"code","source":"train=pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest=pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\ntrain.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x=train.iloc[:,1:].values.astype('float32') #values changes it into array \ny=train['label'] \nx.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"learning_rate=ReduceLROnPlateau(monitor='val_loss',patience=3,verbose=1,factor=0.5,min_lr=0.0001)\nearlystop=EarlyStopping(monitor='val_loss',patience=87,verbose=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x=x.reshape(42000,28,28,1) # (28*28*1=784)  #cnn model take array in form of size with color channel  for gray-(150,150,1)& for color (150,150,3)\ntest=test.values.reshape(len(test),28,28,1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.shape\nx=x/255.0\ntest=test/255.0 #scaling value between 0-1\ny=to_categorical(y,num_classes=10)\nxtrain,xvalid,ytrain,yvalid=train_test_split(x,y,test_size=0.1,random_state=49)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**CNN model for trainig model**","metadata":{}},{"cell_type":"code","source":"model=keras.models.Sequential([\n    keras.layers.Conv2D(16,(3,3),activation='relu',padding='same',input_shape=(28,28,1)),\n    keras.layers.Conv2D(16,(3,3),activation='relu',padding='same',input_shape=(28,28,1)),\n                              keras.layers.BatchNormalization(axis=1),\n                              keras.layers.Conv2D(64,(3,3),activation='relu',padding='same'),\n    keras.layers.Conv2D(64,(3,3),activation='relu',padding='same'),\n                              keras.layers.MaxPooling2D(2,2),\n    keras.layers.Dropout(0.3),\n    keras.layers.Conv2D(128,(3,3),activation='relu',padding='same'),\n                              keras.layers.MaxPooling2D(2,2),\n                            \n                            \n                        keras.layers.Conv2D(128,(3,3),activation='relu',padding='same'),\n                              keras.layers.MaxPooling2D(2,2),\n                              keras.layers.Dropout(0.4),\n                              keras.layers.Flatten(),\n                              keras.layers.Dense(1286,activation='relu'),\n                              keras.layers.Dropout(0.1),\n                              keras.layers.Dense(10,activation='softmax')])\nmodel.compile(optimizer=RMSprop(lr=0.001),loss='categorical_crossentropy',metrics=['accuracy'])\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_augment=ImageDataGenerator(rescale=1.0/255.0,width_shift_range=0.3,height_shift_range=0.3,rotation_range=35)\nbatch_train=data_augment.flow((xtrain,ytrain),batch_size=90)\nbatch_valid=data_augment.flow((xvalid,yvalid),batch_size=20)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history=model.fit(xtrain,ytrain,epochs=100,steps_per_epoch=420,validation_data=(xvalid,yvalid),verbose=1,validation_steps=41,callbacks=[learning_rate,earlystop])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.evaluate(test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = model.predict_classes(test, verbose=0)\n\nsubmissions=pd.DataFrame({\"ImageId\": list(range(1,len(predictions)+1)),\n                         \"Label\": predictions})\nsubmissions.to_csv(\"DR.csv\", index=False, header=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submissions","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}