{"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\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","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = df['label']\ndf.drop(['label'],axis=1,inplace=True)\nnpdf = df.to_numpy()\ns=npdf.shape\nX = npdf.reshape((s[0],28,28))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img = X[3,:,:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#try if we got the image correct by plotting\nplt.imshow(img,cmap=\"gray\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = tf.convert_to_tensor(X)\nX = tf.expand_dims(X,-1)\ny = tf.convert_to_tensor(y,dtype='int32')\ny = tf.keras.utils.to_categorical(y,10)\nprint(X.shape,y.shape)\nXtrain,Xtest,ytrain,ytest = X[:36000,:,:],X[36000:,:,:],y[:36000,:],y[36000:,:]\nprint(Xtrain.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense, Input, Flatten, Softmax","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Flatten())\nmodel.add(Dense(units = 256,activation = 'relu'))\nmodel.add(Dense(units = 128,activation = 'relu'))\nmodel.add(Dense(units = 64,activation = 'relu'))\nmodel.add(Dense(units = 10,activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 128\nepochs = 20","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(Xtest.shape,ytest.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy',optimizer='adam',metrics =['accuracy'])\nmodel.fit(Xtrain,ytrain,batch_size=batch_size,epochs=epochs,validation_data=(Xtest,ytest))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"testdf = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\ntestdf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nptestdf = testdf.to_numpy()\ns=nptestdf.shape\nX_test = nptestdf.reshape((s[0],28,28))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test = model.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test[2]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#try if we got the image correct by plotting\nplt.imshow(X_test[2,:,:],cmap=\"gray\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_label = tf.argmax(y_test,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_label[:10]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fis,axes = plt.subplots(10,1)\nfor i in range(10):\n    axes[i].imshow(X_test[i,:,:],cmap=\"gray\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out_df = pd.DataFrame(y_label)\nout_df['ImageId'] = out_df.index\nout_df['Label'] = out_df[0]\nout_df.drop(columns = [0],inplace = True)\nout_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out_df.to_csv(\"/kaggle/working/out.csv\",index=True)","execution_count":null,"outputs":[]},{"metadata":{"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":4}