{"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)\nfrom sklearn.model_selection import train_test_split\nimport tensorflow.compat.v1 as tf\ntf.disable_v2_behavior()\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 20GB 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":"train=pd.read_csv('../input/digit-recognizer/train.csv')\ntest=pd.read_csv('../input/digit-recognizer/test.csv')\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Making training set\ny_train=train['label']\nx_train=train.drop(['label'],axis=1)\nx_train,x_dev,y_train,y_dev=train_test_split(x_train,y_train)\ny_train=np.array(y_train)\ny_train=y_train.reshape((y_train.shape[0],1))\n\ny_dev=np.array(y_dev)\ny_dev=y_dev.reshape((y_dev.shape[0],1))\n\n# Making test set\nx_test=test\n\nprint(x_train.shape)\nprint(y_train.shape)\nprint(x_dev.shape)\nprint(y_dev.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def change_y(Y):\n    y=np.zeros((Y.shape[0],10))\n    for i in range(y.shape[0]):\n        y[i][Y[i]]=1\n    return y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train=change_y(y_train)\ny_dev=change_y(y_dev)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Making tensorflow variables\nX=tf.placeholder(tf.float32,[None,x_train.shape[1]])\nW=tf.Variable(tf.zeros([784,10]))\nb=tf.Variable(tf.zeros([10]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Making model\n# y=wx+b\n# a=softmax(y)\n# softmax is the activation function here\nY=tf.nn.softmax(tf.matmul(X,W)+b)\nY_=tf.placeholder(tf.float32,[None,1])\n# Loss function\ncross_entropy=-tf.reduce_sum(Y_*tf.log(Y))\nis_correct=tf.equal(tf.argmax(Y,1),tf.argmax(Y_,1))\naccuracy=tf.reduce_mean(tf.cast(is_correct,tf.float32))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimisor=tf.train.GradientDescentOptimizer(0.003)\ntrain_step=optimisor.minimize(cross_entropy)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# making session\nsess=tf.Session()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# use sess.run to run the equations\ninit=tf.initialize_all_variables()\nsess.run(init)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# for i in range(10000):\ntrain_data={X:x_train,Y_:y_train.reshape(y_train.shape[0],1)}\ndev_data={X:x_dev,Y_:y_dev}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sess.run(train_step,feed_dict=train_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"a,c=sess.run([accuracy,is_correct],feed_dict=train_data)\na","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"a,c=sess.run([accuracy,is_correct],feed_dict=dev_data)\na","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.datasets import mnist\ntr,tt=mnist.load_data()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# a[0]\na,c=sess.run([accuracy,is_correct],feed_dict={X:tr[0].reshape(tr[0].shape[0],-1),Y_:tr[1].reshape(tr[1].shape[0],1)})\na","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"a,c=sess.run([accuracy,is_correct],feed_dict={X:tt[0].reshape(tt[0].shape[0],-1),Y_:tt[1].reshape(tt[1].shape[0],1)})\na","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}