{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np;\nimport pandas as pd;\nimport seaborn as sns;\nimport os;\nimport matplotlib.pyplot as plt;\nimport matplotlib.image as mpimg;\n#%matplotlib inline\n\nfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\nfrom sklearn.metrics import confusion_matrix;\nimport itertools;\nfrom sklearn.model_selection import train_test_split;\n\ndf_train= pd.read_csv(\"../input/digit-recognizer/train.csv\");\n\ndf_test= pd.read_csv(\"../input/digit-recognizer/test.csv\");\n\n\n\n\nY_train=df_train[\"label\"];\nX_train=df_train.drop(labels=[\"label\"],axis=1);\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test=df_test/255.0;\nX_train=X_train/255.0;\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test=df_test.values.reshape(-1,28,28,1);\nX_train=X_train.values.reshape(-1,28,28,1);\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train=to_categorical(Y_train,num_classes=10);\n#X_norm_onehot=to_categorical(X_train,num_classes=41999);\n\n\nprint(Y_train);\n\n\nnp.random.seed(2);\nX_train,X_val,Y_train,Y_val= train_test_split(X_train,Y_train,test_size=0.2,random_state=2);\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model=Sequential();\n\n\nmodel.add(Conv2D(filters=32,kernel_size=(5,5),padding='Same',activation='relu',input_shape=(28,28,1)));\nmodel.add(Conv2D(filters=32,kernel_size=(5,5),padding='Same',activation='relu'));\nmodel.add(MaxPool2D(pool_size=(2,2)));\nmodel.add(Dropout(0.25));\n\nmodel.add(Conv2D(filters=64,kernel_size=(3,3),padding='Same',activation='relu'));\nmodel.add(Conv2D(filters=64,kernel_size=(3,3),padding='Same',activation='relu'));\nmodel.add(MaxPool2D(pool_size=(2,2),strides=(2,2)));\nmodel.add(Dropout(0.25));\nmodel.add(Flatten());\nmodel.add(Dense(256,activation='relu'));\nmodel.add(Dropout(0.5));\nmodel.add(Dense(10,activation='softmax'));\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_val,Y_val);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer=RMSprop(lr=0.001,rho=0.9,epsilon=1e-08,decay=0.0);\nmodel.compile(optimizer=optimizer,loss='categorical_crossentropy',metrics=[\"accuracy\"]);\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_reduction=ReduceLROnPlateau(monitor='val_acc',patience=3,verbose=1,factor=0.5,min_lr=0.00001);\nepochs=50;\nbatch_size=86;\n\nhistory = model.fit(X_train, Y_train, batch_size = batch_size, epochs = epochs,validation_data = (X_val, Y_val), verbose = 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(df_test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")\nprint(results)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission=pd.concat([pd.Series(range(1,28001),name=\"ImageId\"),results],axis=1)\nsubmission.to_csv(\"cnn_dataset_mnist\",index=False);","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}