{"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)\nimport tensorflow as tf\nimport matplotlib.pyplot as plt\nfrom matplotlib.pyplot import imshow\nimport seaborn as sns\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.optimizers import RMSprop\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":"df_train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ndf_test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\ndf_subm = pd.read_csv(\"/kaggle/input/digit-recognizer/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df_train.shape)\nprint(df_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_labels = df_train[\"label\"] \ndf_train.drop([\"label\"], axis = 1, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = df_train.values.reshape(-1,28,28,1)\ndf_test = df_test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df_train.shape)\nprint(df_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Change the value of i to check different labels\ni = 1001\nprint(\"Image label is: \", train_labels[i])\nplt.imshow(df_train[i][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Normalizing Pixels\ndf_train = df_train/255.0\ndf_train = df_train/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Check distribution of differnet labels across Training Data\nsns.countplot(train_labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(df_train, train_labels, test_size = 0.05, random_state = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# model = tf.keras.Sequential([tf.keras.layers.Conv2D(32, (3,3), activation = \"relu\", input_shape = (28,28,1))\n#                             ,tf.keras.layers.MaxPooling2D(2,2)\n#                             ,tf.keras.layers.Conv2D(64, (3,3), activation = \"relu\")\n#                             ,tf.keras.layers.MaxPooling2D(2,2)\n#                             ,tf.keras.layers.Conv2D(64,(3,3), activation = \"relu\")\n#                             ,tf.keras.layers.MaxPooling2D(2,2)\n#                             ,tf.keras.layers.Flatten()\n#                             ,tf.keras.layers.Dense(150 , activation = \"relu\")\n#                             ,tf.keras.layers.Dense(10, activation = \"softmax\")])\n# model.compile(optimizer = RMSprop(lr = 0.001), loss = \"sparse_categorical_crossentropy\", metrics = [\"accuracy\"])\n\nmodel = tf.keras.Sequential([tf.keras.layers.Conv2D(32, (3,3), activation = \"relu\", input_shape = (28,28,1))\n                            ,tf.keras.layers.MaxPooling2D(2,2)\n                            ,tf.keras.layers.Conv2D(64, (3,3), activation = \"relu\")\n                            ,tf.keras.layers.MaxPooling2D(2,2)\n                            ,tf.keras.layers.Conv2D(64, (3,3), activation = \"relu\")\n                            ,tf.keras.layers.MaxPooling2D(2,2)\n                            ,tf.keras.layers.Flatten()\n                            ,tf.keras.layers.Dense(150, activation = \"relu\")\n                            ,tf.keras.layers.Dense(10, activation = \"softmax\")])\nmodel.compile(optimizer = RMSprop(lr = 0.001), loss = \"sparse_categorical_crossentropy\",  metrics = [\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(X_train, y_train, validation_data = (X_test, y_test), epochs = 20)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history[\"val_accuracy\"], label = \"Validation Accuracy\")\nplt.plot(history.history[\"accuracy\"], label = \"Training Accuracy\")\nplt.legend()\nplt.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history[\"val_loss\"], label = \"Validation Loss\")\nplt.plot(history.history[\"loss\"], label = \"Training loss\")\nplt.legend()\nplt.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_preds = np.argmax(model.predict(df_test), axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Checking the predictions on Test Data, Change the value of i to see different predictions  \ni = 100\nprint(\"Image label is: \", y_preds[i])\nplt.imshow(df_test[i][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_subm.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({\"ImageId\" : range(1, 28001), \"Label\" : y_preds})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv(\"submission.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}