{"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 5GB 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":"train = pd.read_csv(\"/kaggle/input/facebook-recruiting-iv-human-or-bot/train.csv.zip\")\ntest = pd.read_csv(\"/kaggle/input/facebook-recruiting-iv-human-or-bot/test.csv.zip\")\nbids = pd.read_csv(\"/kaggle/input/facebook-recruiting-iv-human-or-bot/bids.csv.zip\")","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# pd.options.display.max_columns = 999\ntrain.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bids.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#train2 = pd.merge(train, bids, on='bidder_id', how='left')\n\n#test2 = pd.merge(test, bids, on='bidder_id', how='left')\n\nalldata = pd.concat([train,test])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"alldata2=alldata.drop([\"outcome\",\"bidder_id\",\"payment_account\",\"address\"],1)\nalldata2.dtypes","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"alldata2","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# print(len(alldata))\n# print(len(alldata[\"bidder_id\"].unique()))\n# print(len(alldata[\"payment_account\"].unique()))\n# print(len(alldata[\"address\"].unique()))\n# print(len(alldata[\"bid_id\"].unique()))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\n#alldata2 = alldata.drop([\"bidder_id\",\"payment_account\",\"address\"],1)\nobj_col = alldata2.columns[alldata2.dtypes == object]\n#obj_col\n#obj_col2 = ['auction', 'merchandise','device', 'country', 'ip', 'url']\nfor i in obj_col:\n    alldata2[i] = le.fit_transform(list(alldata2[i]))\nalldata2","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"alldata2.isna().any()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"alldata2 = alldata2.fillna(-1)\n\nalldata2.isna().any()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train3 = alldata2[:len(train2)]\ntest3 = alldata2[len(train2):]\ntrain3","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test3","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\nrf = RandomForestClassifier(n_jobs = -1)\nrf.fit(train3,train2[\"outcome\"])\nresult = rf.predict_proba(test3)[:,1]\nresult","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test3","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test4 = test3\ntest4[\"result\"]=result","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test4","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = test4[[\"bid_id\",\"result\"]]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test2","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"final = pd.merge(test2,df, on='bid_id', how='left')\nfinal2 = final[[\"bidder_id\",\"result\"]]\nfinal2","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"grouped = final2.groupby(['bidder_id'])\nsubmit = grouped.mean()\nsubmit.loc[:, 'result']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/facebook-recruiting-iv-human-or-bot/sampleSubmission.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submit.columns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub[\"prediction\"]=submit['result']\nsub\n# sub.to_csv(\"0918_fb_sub.csv\",index=0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}