{"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)\nimport matplotlib.pyplot as plt\nfrom keras.models import Sequential, Model\nfrom keras.layers import Dense, Dropout,Activation,Conv2D,Flatten,MaxPool2D, GlobalAveragePooling2D\nfrom keras.utils import np_utils\nfrom sklearn.metrics import confusion_matrix\nfrom keras.datasets import mnist\nfrom keras.wrappers.scikit_learn import KerasClassifier\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import cross_val_score, StratifiedKFold\nfrom keras.applications.resnet50 import ResNet50\n\n\n\n        \ndata_train = pd.read_csv('../input/digit-recognizer/train.csv')\ndata_test = pd.read_csv('../input/digit-recognizer/test.csv')\n\ndata_train_w = data_train.drop(['label'],axis = 1)\ndata = data_train_w.append(data_test,ignore_index = True)\n\n\n\ny_train = data_train.iloc[:,0]\nprint(y_train.shape)\nX_train = (data_train.iloc[:,1:].values).astype('float32')\nprint(X_train.shape)\n\n\n\nX_test = (data_test.iloc[:,0:].values).astype('float32')\n\n\n\n\n# pre-processing: divide by max and substract mean\nscale = np.max(X_train)\nscale\nX_train /= scale\nX_test /= scale\n\nmean = np.std(X_train)\nX_train -= mean\nX_test -= mean\n\ny_train = np_utils.to_categorical(y_train,10)\n\n\n\ny_train =(np.array(y_train))\n\n\n\nX_train2,X_test2,y_train2,y_test2 = train_test_split(X_train,y_train)\n\n\nval = round((784+10) / 2)\n\nX_train2 = X_train2.reshape(-1,28,28,1)\n\n\n\nmodelo = Sequential()\n\nmodelo.add(Conv2D(32,(3,3),input_shape = (28,28,1)))\nmodelo.add(Activation('relu'))\nmodelo.add(MaxPool2D(pool_size =(2,2)))\nmodelo.add(Conv2D(32,(3,3),input_shape = (28,28,1)))\nmodelo.add(Activation('relu'))\nmodelo.add(MaxPool2D(pool_size =(2,2)))\n\nmodelo.add(Conv2D(32,(3,3),input_shape = (28,28,1)))\nmodelo.add(Activation('relu'))\nmodelo.add(MaxPool2D(pool_size =(2,2)))\n\nmodelo.add(Flatten())\nmodelo.add(Dense(10))\nmodelo.add(Activation('softmax'))\n\n\nmodelo.summary()\n\nmodelo.compile(optimizer = 'rmsprop', loss = 'categorical_crossentropy',metrics=['accuracy'])\n\n#neural_network = KerasClassifier(build_fn = modelo, epochs = 20, batch_size = 100, verbose = 0)\n#scores = cross_val_score(modelo,data,y,cv= 5,scoring = 'accuracy')\n\nmodelo.fit(X_train2, y_train2, epochs=20, batch_size=16, validation_split=0.1, verbose=2)\n\n\npreds = modelo.predict_classes(X_test.reshape(-1,28,28,1), verbose=0)\n\ndef write_preds(preds, fname):\n    pd.DataFrame({\"ImageId\": list(range(1,len(preds)+1)), \"Label\": preds}).to_csv(fname, index=False, header=True)\n\nwrite_preds(preds, \"keras-mlp.csv\")\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"","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":1}