{"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 matplotlib import pyplot as plt\nimport seaborn as sns\nfrom sklearn.preprocessing import StandardScaler, MinMaxScaler\nfrom sklearn.metrics import confusion_matrix, classification_report\nfrom sklearn.feature_selection import VarianceThreshold\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom keras import Sequential\nfrom keras.layers import Conv2D, MaxPool2D, Dropout, Flatten, Dense\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 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":{},"cell_type":"markdown","source":"Lets read the available data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\nx_test = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\ny_test = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape, x_test.shape, y_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"(42000)/(42000+28000)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"60% of data is for training and remaining for testing purpose."},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Here label denotes the output"},{"metadata":{},"cell_type":"markdown","source":"let seprate the input and output data so that we can build and train our model"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = train.drop('label', axis = 1)\ny_train = train['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.head(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test.head(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test.head(3)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Lets check distribution of data"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"every output label contains nearly equal numubers no. of data points to make predictions. It means data is equally distributed"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.loc[1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.loc[1].max()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"we will have to perform feature scalling because deep neural networks works well on s"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train/255\nx_test = x_test/255","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"two fit the data in CNN we have to change it in 3D"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = np.array(x_train).reshape(np.array(x_train).shape[0],28,28,1)\nx_test = np.array(x_test).reshape(np.array(x_test).shape[0], 28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test = y_test\ny_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(filters = 32, kernel_size=(3,3), activation='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(64, (3,3), activation='relu'))\nmodel.add(MaxPool2D(2,2))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(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":"model.compile(loss = 'sparse_categorical_crossentropy', optimizer= 'adam', metrics = ['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(x_train, y_train, batch_size=120, epochs=10, verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred_train = model.predict_classes(x_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"classification_report(y_train, y_pred_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cm = confusion_matrix(y_train, y_pred_train)\nplt.figure(figsize=(10,8))\nsns.heatmap(cm, annot=True)\nplt.xlabel('predicted')\nplt.ylabel('true')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = model.predict_classes(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test['Label'] = y_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}