{"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# 加载数据\ntrain = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv',delimiter=',')\nprint(train.head())\nprint(train.columns)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 数据分布研究\nprint(train.describe())\nprint((train.shape[0] - train.count())/(train.shape[0]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 将df数据转化为tensor_slices\n# def df_to_dataset(df):\n#     df = df.copy()\n#     labels = df.pop('label')\n#     ds = tf.data.Dataset.from_tensor_slices((dict(df),labels))\n#     return ds\n\n# train_ds = df_to_dataset(train)\n# print(train_ds.take(1))\ndata = train.copy()\ntrain_y = data['label'].values\ndata.pop('label')\ntrain_x = data.values\n\n# 数据归一化\ntrain_x = train_x / 255\nprint(train_x.shape, ' ', train_y.shape)\nprint(train_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 构建模型\nimport tensorflow as tf\nfrom tensorflow.keras import layers\nimport matplotlib.pyplot as plt\n\nmodel = tf.keras.Sequential(\n    [\n        \n        layers.Dense(64,activation='relu',kernel_initializer='he_normal', input_shape=(784,)),\n        layers.Dense(64,activation='relu',kernel_initializer='he_normal'),\n        layers.Dense(64,activation='relu',kernel_initializer='he_normal'),\n        layers.Dense(64,activation='relu',kernel_initializer='he_normal'),\n        layers.Dense(10,activation='softmax')\n    ]\n)\n\nmodel.compile(optimizer=tf.keras.optimizers.Adam(),loss=tf.keras.losses.SparseCategoricalCrossentropy(),metrics=['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 模型训练\nhistory = model.fit(train_x, train_y, batch_size=256, epochs=100, validation_split=0.3, verbose=1)\nprint(history.history['accuracy'],history.history['val_accuracy'])\n\nplt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.legend(['training', 'validation'], loc='upper left')\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 模型评估\nresult = model.evaluate(train_x,train_y)\nprint(result)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 预测数据\ntest = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\ntest_id = test.id\n\ntest = test.drop('id',axis=1)\ntest = test/255\n\ny_pre = model.predict(test)\nprint(y_pre)\ny_pre = np.argmax(y_pre,axis=1)\nprint(y_pre)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 保存数据\nsample_sub = pd.read_csv('/kaggle/input/Kannada-MNIST/sample_submission.csv')\nprint(sample_sub)\n\nsample_sub['id'] = test_id\nsample_sub['label'] = y_pre\nsample_sub.to_csv('/kaggle/working/submission.csv',index=False)\n\nprint(sample_sub.head())","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":1}