{"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\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 csv\nimport numpy as np\nimport tensorflow as tf\nfrom tensorflow.keras import Model\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom os import getcwd\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv (\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv (\"/kaggle/input/digit-recognizer/test.csv\")\ntrain.shape, test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train=train['label']\nX_train=train.drop(['label'],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train/255.0\ntest=test/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape,test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train.values.reshape(-1,28,28,1)\ntest=test.values.reshape(-1,28,28,1)\nX_train.shape,test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\nY_train = to_categorical(Y_train, num_classes = 10)\nY_train = Y_train.astype(\"int8\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_val, y_train, y_val = train_test_split(X_train, Y_train, test_size=0.22, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nmodel = tf.keras.models.Sequential([\n\n    tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(28,28,1)),\n    tf.keras.layers.MaxPooling2D(2, 2),\n    # The second convolution\n    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),\n    tf.keras.layers.MaxPooling2D(2,2),\n    \n    \n    tf.keras.layers.Dropout(0.2),\n    tf.keras.layers.Flatten(),\n    tf.keras.layers.Dense(512, activation='relu'),\n    tf.keras.layers.Dense(10, activation='softmax')\n    ])\n\n# Compile Model. \nmodel.compile(loss = 'categorical_crossentropy',\n              optimizer='rmsprop', metrics=['acc'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    rescale=1/255,\n    zoom_range=0.2,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    shear_range=0.2,\n    rotation_range=40,\n    horizontal_flip=True,\n    fill_mode='nearest'\n    )\n\nvalidation_datagen=ImageDataGenerator(rescale=1/255)\n\ntrain_datagen.fit(x_train)\nvalidation_datagen.fit(x_val)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x_train, y_train,batch_size=50, epochs=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_predictions = model.predict(test)\n\n\nresults = np.argmax(test_predictions,axis = 1) \n\nresults = pd.Series(results,name=\"Label\")\n\n\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"digit_recognition.csv\",index=False)","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}