{"cells":[{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1 align='center'><b>\n    <img src='https://media3.giphy.com/media/KAq5w47R9rmTuvWOWa/giphy.gif' width=100 height=100>\n    <font color='sky blue' face='lucida handwriting'size=300>Py</font><font color='yellow' face='lucida handwriting' size=300>Tech</font></b></h1>\n   \n</html>","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1><i><font face='Courier' size = 10>Importing Libraries</font></i></h1>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport os\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow import keras\nfrom sklearn.metrics import classification_report\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1><i><font face='Courier' size = 10>Data Prepration</font></i></h1>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/digit-recognizer/train.csv')\n\ntest = pd.read_csv('../input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train.drop(['label'],axis =1)\n\ntrain = train/255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train.values.reshape(-1, 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.01, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1><i><font face='Courier' size = 10>Model</font></i></h1>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"m = keras.Sequential()\nm.add(keras.layers.Conv2D(32, (3, 3), activation=\"relu\", kernel_initializer='he_uniform', input_shape=(28, 28, 1)))\nm.add(keras.layers.BatchNormalization())\n\nm.add(keras.layers.Conv2D(32, (3, 3), activation=\"relu\", padding='same', kernel_initializer='he_uniform'))\nm.add(keras.layers.BatchNormalization())\nm.add(keras.layers.MaxPool2D(2, 2))\nm.add(keras.layers.Dropout(0.20))\n\nm.add(keras.layers.Conv2D(64, (3, 3), activation=\"relu\", padding='same', kernel_initializer='he_uniform'))\nm.add(keras.layers.BatchNormalization())\n\nm.add(keras.layers.Conv2D(64, (3, 3), activation=\"relu\", padding='same', kernel_initializer='he_uniform'))\nm.add(keras.layers.BatchNormalization())\nm.add(keras.layers.MaxPool2D(2, 2))\nm.add(keras.layers.Dropout(0.2))\n\nm.add(keras.layers.Conv2D(128, (3, 3), activation=\"relu\", padding='same', kernel_initializer='he_uniform'))\nm.add(keras.layers.BatchNormalization())\n\nm.add(keras.layers.Conv2D(128, (3, 3), activation=\"relu\", padding='same', kernel_initializer='he_uniform'))\nm.add(keras.layers.BatchNormalization())\nm.add(keras.layers.MaxPool2D(2, 2))\nm.add(keras.layers.Dropout(0.2))\n\nm.add(keras.layers.Flatten())\nm.add(keras.layers.Dropout(0.2))\nm.add(keras.layers.Dense(128, activation=\"relu\"))\nm.add(keras.layers.Dense(10, activation=\"softmax\"))\n\nm.compile(optimizer=keras.optimizers.RMSprop(), loss=\"sparse_categorical_crossentropy\", metrics=[\"acc\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"m.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=50000,batch_size=20, validation_batch_size=20)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1><i><font face='Courier' size = 10>Prediction</font></i></h1>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntest = test.values.reshape(-1,28,28,1)\ntest = test/255.0\npred = np.argmax(m.predict(test), axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Submission = pd.DataFrame({\"ImageId\" : range(1, 28001), \"Label\":pred})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Submission.to_csv('Submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1><i><font face='Courier' size = 10>Testing</font></i></h1>","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"<html>\n    <h1><i><font face='Courier' size = 3>Enter any Number from 0 to 27999, in the num spot below and it will show you the image at that spot and its prediction (not 100% Correct)</font></i></h1>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"\nfrom matplotlib import pyplot as plt\n\n\nnum = 3\nprint(\"Image label is:| \", pred[num])\nplt.imshow(test[num][:,:,0])","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}