{"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":"import matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import classification_report\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.metrics import confusion_matrix\nimport pylab as pl\n\n# 读取对应数据集\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\n\n# 将train数据集划分为训练集和测试集\nX_train, X_test, y_train, y_test = train_test_split(train.iloc[:, 1:], train.iloc[:, 0], test_size=0.2)\n\n# from sklearn.decomposition import PCA\n# pca = PCA(n_components=0.7)\n# 调用sklearn库中的逻辑回归模型并用训练集进行拟合\nfrom sklearn.linear_model import LogisticRegression\nModelLR = LogisticRegression(solver='newton-cg', multi_class='multinomial')\nModelLR.fit(X_train, y_train)\n\n# 获得在测试集上得到的预测值\ny_predLR = ModelLR.predict(X_test)\n\n# Accuracy score\nprint('accuracy is',accuracy_score(y_predLR,y_test))\n\nscore = accuracy_score(y_predLR,y_test)\n\n# 应用在私有测试集\ntest_x = test.values[:,1:]\n\npreds = ModelLR.predict(test_x)\n\nsubmission['label'] = preds\nsubmission.to_csv('submission.csv',index=False)\n\n","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}