{"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 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":"import tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_path = '/kaggle/input/digit-recognizer/train.csv'\ntest_path = '/kaggle/input/digit-recognizer/test.csv'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(train_path)\ntest_df = pd.read_csv(test_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"split = 0.8\ntrain_count = int(train_df.shape[0]*split)\ntrain_data, val_data = train_df.iloc[:train_count, :], train_df.iloc[train_count:, :]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_data.shape, val_data.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, y_train_labels = train_data.iloc[:, 1:], train_data.iloc[:, 0]\nX_train = X_train/255.\nprint(X_train.shape, y_train_labels.shape)\nX_val, y_val_labels = val_data.iloc[:, 1:], val_data.iloc[:, 0]\nX_val = X_val/255.\nprint(X_val.shape, y_val_labels.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = np.zeros((y_train_labels.shape[0], 10))\ny_val = np.zeros((y_val_labels.shape[0], 10))\n\nfor i, tr_lbl in enumerate(y_train_labels):\n    y_train[i, tr_lbl] = 1\n\nfor j, val_lbl in enumerate(y_val_labels):\n    y_val[j, val_lbl] = 1\n\nprint(y_train.shape, y_train[0])\nprint(y_val.shape, y_val[0])\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.Sequential([\n    tf.keras.Input([X_train.shape[1]]),\n    tf.keras.layers.Dense(1500, activation='relu'),\n    tf.keras.layers.Dense(3000, activation='relu'),\n    tf.keras.layers.Dense(10, activation='softmax')\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(\n    loss = 'mean_squared_error',\n    optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n    metrics='accuracy'\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(\n    x=X_train,\n    y=y_train,\n    validation_data=(X_val, y_val),\n    batch_size=512,\n    shuffle=True,\n    epochs=100\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history_df = pd.DataFrame(history.history)\nprint(history_df.loc[:, 'val_accuracy'].max(), history_df.loc[99, 'val_accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history_df.loc[50:, ['accuracy', 'val_accuracy']].plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = test_df.to_numpy()\nX_test = X_test/255.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions_np = model.predict(x=X_test, batch_size=256)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(np.argmax(predictions_np[0]), predictions_np.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = {\n    'ImageId': np.arange(1, predictions_np.shape[0]+1),\n    'Label': np.argmax(predictions_np, axis=1)\n       }\npredictions = pd.DataFrame(data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions.to_csv('my_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}