{"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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":105,"outputs":[{"output_type":"stream","text":"['train.csv', 'sample_submission.csv', 'test.csv']\n","name":"stdout"}]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train=pd.read_csv('../input/train.csv')\ntest=pd.read_csv('../input/test.csv')\nprint(train.info())\nprint(train.head())","execution_count":106,"outputs":[{"output_type":"stream","text":"\nRangeIndex: 42000 entries, 0 to 41999\nColumns: 785 entries, label to pixel783\ndtypes: int64(785)\nmemory usage: 251.5 MB\nNone\n label pixel0 pixel1 ... pixel781 pixel782 pixel783\n0 1 0 0 ... 0 0 0\n1 0 0 0 ... 0 0 0\n2 1 0 0 ... 0 0 0\n3 4 0 0 ... 0 0 0\n4 0 0 0 ... 0 0 0\n\n[5 rows x 785 columns]\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train.isnull().any().describe())\nprint(train.shape)","execution_count":107,"outputs":[{"output_type":"stream","text":"count 785\nunique 1\ntop False\nfreq 785\ndtype: object\n(42000, 785)\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"d=pd.get_dummies(train['label'])\nnames=['0','1','2','3','4','5','6','7','8','9']\nc=0\nfor col in names:\n train[col]=d[c]\n c+=1\ntrain.drop('label',axis=1,inplace=True)\nprint(train.info())","execution_count":108,"outputs":[{"output_type":"stream","text":"\nRangeIndex: 42000 entries, 0 to 41999\nColumns: 794 entries, pixel0 to 9\ndtypes: int64(784), uint8(10)\nmemory usage: 251.6 MB\nNone\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=train.drop(names,axis=1)\nY=train[names]","execution_count":109,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train,x_test,y_train,y_test=train_test_split(X,Y,test_size=0.1)\nprint(x_train.shape,y_train.shape,x_test.shape,y_test.shape)","execution_count":110,"outputs":[{"output_type":"stream","text":"(37800, 784) (37800, 10) (4200, 784) (4200, 10)\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense,Dropout,Conv2D,MaxPooling2D,Flatten,GlobalAveragePooling2D\nfrom keras.optimizers import SGD\nmodel=Sequential()\nmodel.add(Dense(64, activation='relu',input_shape=(784,)))\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dense(50, activation='relu'))\nmodel.add(Dense(50, activation='relu'))\nmodel.add(Dense(50, activation='relu'))\nmodel.add(Dense(10,activation='softmax'))\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","execution_count":111,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hist=model.fit(x_train,y_train,epochs=10,batch_size=32)","execution_count":112,"outputs":[{"output_type":"stream","text":"Epoch 1/10\n37800/37800 [==============================] - 9s 236us/step - loss: 1.0135 - acc: 0.8206\nEpoch 2/10\n37800/37800 [==============================] - 8s 202us/step - loss: 0.2450 - acc: 0.9294\nEpoch 3/10\n37800/37800 [==============================] - 8s 201us/step - loss: 0.1922 - acc: 0.9451\nEpoch 4/10\n37800/37800 [==============================] - 8s 203us/step - loss: 0.1640 - acc: 0.9524\nEpoch 5/10\n37800/37800 [==============================] - 8s 201us/step - loss: 0.1383 - acc: 0.9597\nEpoch 6/10\n37800/37800 [==============================] - 7s 197us/step - loss: 0.1221 - acc: 0.9644\nEpoch 7/10\n37800/37800 [==============================] - 7s 196us/step - loss: 0.1084 - acc: 0.9692\nEpoch 8/10\n37800/37800 [==============================] - 8s 210us/step - loss: 0.1008 - acc: 0.9713\nEpoch 9/10\n37800/37800 [==============================] - 7s 193us/step - loss: 0.0891 - acc: 0.9737\nEpoch 10/10\n37800/37800 [==============================] - 7s 194us/step - loss: 0.0817 - acc: 0.9764\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(x_test,y_test)","execution_count":113,"outputs":[{"output_type":"stream","text":"4200/4200 [==============================] - 1s 170us/step\n","name":"stdout"},{"output_type":"execute_result","execution_count":113,"data":{"text/plain":"[0.1350477811863779, 0.9654761904761905]"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":114,"outputs":[{"output_type":"execute_result","execution_count":114,"data":{"text/plain":" pixel0 pixel1 pixel2 ... pixel781 pixel782 pixel783\n0 0 0 0 ... 0 0 0\n1 0 0 0 ... 0 0 0\n2 0 0 0 ... 0 0 0\n3 0 0 0 ... 0 0 0\n4 0 0 0 ... 0 0 0\n\n[5 rows x 784 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
pixel0pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8pixel9pixel10pixel11pixel12pixel13pixel14pixel15pixel16pixel17pixel18pixel19pixel20pixel21pixel22pixel23pixel24pixel25pixel26pixel27pixel28pixel29pixel30pixel31pixel32pixel33pixel34pixel35pixel36pixel37pixel38pixel39...pixel744pixel745pixel746pixel747pixel748pixel749pixel750pixel751pixel752pixel753pixel754pixel755pixel756pixel757pixel758pixel759pixel760pixel761pixel762pixel763pixel764pixel765pixel766pixel767pixel768pixel769pixel770pixel771pixel772pixel773pixel774pixel775pixel776pixel777pixel778pixel779pixel780pixel781pixel782pixel783
00000000000000000000000000000000000000000...0000000000000000000000000000000000000000
10000000000000000000000000000000000000000...0000000000000000000000000000000000000000
20000000000000000000000000000000000000000...0000000000000000000000000000000000000000
30000000000000000000000000000000000000000...0000000000000000000000000000000000000000
40000000000000000000000000000000000000000...0000000000000000000000000000000000000000
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"ans=model.predict(test)\nans=pd.DataFrame(ans)\nans=ans.idxmax(axis=1)\na=[]\nid=[]\nfor i in range(0,28000):\n a.append(ans[:][i])\n id.append(i+1)","execution_count":115,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub=pd.DataFrame({'ImageId':id,'Label':a})\nsub.to_csv('output.csv',index=False)","execution_count":116,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}