{"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_minor":4,"nbformat":4,"cells":[{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.linear_model import LogisticRegression\ndata=pd.read_csv(r'D:\\SMPB Project\\BA\\train_data.csv')\nimport seaborn as sns\n\ndata=data.dropna()\n\ntarget=data.TARGET\ndata=data.drop('TARGET',axis=1)\n\ndata=data.drop('SK_ID_CURR',axis=1)\n\ndummies=pd.get_dummies(data.NAME_CONTRACT_TYPE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('NAME_CONTRACT_TYPE',axis=1)\n\ndummies=pd.get_dummies(data.CODE_GENDER)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('CODE_GENDER',axis=1)\n\ndummies=pd.get_dummies(data.FLAG_OWN_CAR)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('FLAG_OWN_CAR',axis=1)\n\ndummies=pd.get_dummies(data.FLAG_OWN_REALTY)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('FLAG_OWN_REALTY',axis=1)\n\ndummies=pd.get_dummies(data.NAME_TYPE_SUITE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('NAME_TYPE_SUITE',axis=1)\n\ndummies=pd.get_dummies(data.NAME_INCOME_TYPE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('NAME_INCOME_TYPE',axis=1)\n\ndummies=pd.get_dummies(data.NAME_EDUCATION_TYPE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('NAME_EDUCATION_TYPE',axis=1)\n\ndummies=pd.get_dummies(data.NAME_FAMILY_STATUS)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('NAME_FAMILY_STATUS',axis=1)\n\ndummies=pd.get_dummies(data.NAME_HOUSING_TYPE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('NAME_HOUSING_TYPE',axis=1)\n\ndummies=pd.get_dummies(data.OCCUPATION_TYPE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('OCCUPATION_TYPE',axis=1)\n\ndummies=pd.get_dummies(data.WEEKDAY_APPR_PROCESS_START)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('WEEKDAY_APPR_PROCESS_START',axis=1)\n\ndummies=pd.get_dummies(data.ORGANIZATION_TYPE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('ORGANIZATION_TYPE',axis=1)\n\ndummies=pd.get_dummies(data.HOUSETYPE_MODE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('HOUSETYPE_MODE',axis=1)\n\ndummies=pd.get_dummies(data.WALLSMATERIAL_MODE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('WALLSMATERIAL_MODE',axis=1)\n\ndummies=pd.get_dummies(data.EMERGENCYSTATE_MODE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('EMERGENCYSTATE_MODE',axis=1)\n\ndummies=pd.get_dummies(data.FONDKAPREMONT_MODE)\nmerged=pd.concat([data,dummies], axis='columns')\ndata=merged.drop('FONDKAPREMONT_MODE',axis=1)\n\ndata=data.drop('Academic degree',axis=1)\n\nbata=pd.read_csv(r'D:\\SMPB Project\\BA\\test_data.csv')\nbata=bata.drop('SK_ID_CURR',axis=1)\nbata=bata.dropna()\n\ndummies=pd.get_dummies(bata.NAME_CONTRACT_TYPE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('NAME_CONTRACT_TYPE',axis=1)\n\ndummies=pd.get_dummies(bata.CODE_GENDER)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('CODE_GENDER',axis=1)\n\ndummies=pd.get_dummies(bata.FLAG_OWN_CAR)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('FLAG_OWN_CAR',axis=1)\n\ndummies=pd.get_dummies(bata.FLAG_OWN_REALTY)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('FLAG_OWN_REALTY',axis=1)\n\ndummies=pd.get_dummies(bata.NAME_TYPE_SUITE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('NAME_TYPE_SUITE',axis=1)\n\ndummies=pd.get_dummies(bata.NAME_INCOME_TYPE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('NAME_INCOME_TYPE',axis=1)\n\ndummies=pd.get_dummies(bata.NAME_EDUCATION_TYPE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('NAME_EDUCATION_TYPE',axis=1)\n\ndummies=pd.get_dummies(bata.NAME_FAMILY_STATUS)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('NAME_FAMILY_STATUS',axis=1)\n\ndummies=pd.get_dummies(bata.NAME_HOUSING_TYPE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('NAME_HOUSING_TYPE',axis=1)\n\ndummies=pd.get_dummies(bata.OCCUPATION_TYPE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('OCCUPATION_TYPE',axis=1)\n\ndummies=pd.get_dummies(bata.WEEKDAY_APPR_PROCESS_START)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('WEEKDAY_APPR_PROCESS_START',axis=1)\n\ndummies=pd.get_dummies(bata.ORGANIZATION_TYPE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('ORGANIZATION_TYPE',axis=1)\n\ndummies=pd.get_dummies(bata.HOUSETYPE_MODE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('HOUSETYPE_MODE',axis=1)\n\ndummies=pd.get_dummies(bata.WALLSMATERIAL_MODE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('WALLSMATERIAL_MODE',axis=1)\n\ndummies=pd.get_dummies(bata.EMERGENCYSTATE_MODE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('EMERGENCYSTATE_MODE',axis=1)\n\ndummies=pd.get_dummies(bata.FONDKAPREMONT_MODE)\nmerged=pd.concat([bata,dummies], axis='columns')\nbata=merged.drop('FONDKAPREMONT_MODE',axis=1)\n\nfrom sklearn.linear_model import LogisticRegression\nlog = LogisticRegression(penalty='l1', solver='liblinear')\nlog.fit(data, target)\n\na=log.predict(bata)\n\na\n\nnp.unique(a)\n\n","metadata":{},"execution_count":null,"outputs":[]}]}