{"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":"# 加载相关数据文件\ntrain = pd.read_csv('../input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('../input/Kannada-MNIST/test.csv')\nsubmission = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nval= pd.read_csv('../input/Kannada-MNIST/Dig-MNIST.csv')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 显示训练数据集文件的头几条\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 显示测试集文件的头几条\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 对训练数据集进行数据，标签分离\nX_train = train.drop('label', axis=1)\nY_train = train['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 将训练数据集划分为训练集和验证集\nfrom sklearn.model_selection import train_test_split\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size=0.15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 调用XGBoost分类器并在训练集上拟合模型\nfrom xgboost import XGBClassifier\nmodel = XGBClassifier()\neval_set = [(X_val,Y_val)]\nmodel.fit(X_train, Y_train, early_stopping_rounds=5, eval_set=eval_set, verbose=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 将训练过的模型应用在验证集上，得到预测值\nY_pred = model.predict(X_val)\npredictions = [round(value) for value in Y_pred] ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 通过对比预测值和真实值，得到在验证集上的预测准确率\nfrom sklearn.metrics import accuracy_score\n# evaluate predictions\naccuracy = accuracy_score(Y_val, predictions)\nprint(\"Accuracy XGBOOST: %.2f%%\" % (accuracy * 100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = test.drop('id', axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 将模型应用在测试集上\ntest_pred = model.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 获得提交文件\nsubmission = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nsubmission['label'] = test_pred\nsubmission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head(5)","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":1}