{"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":"markdown","source":"## Installations","metadata":{}},{"cell_type":"code","source":"%%capture\n!pip install pycaret --ignore-installed llvmlite\n!pip install numpy==1.20\n!pip install numba==0.53","metadata":{"execution":{"iopub.status.busy":"2022-07-30T17:07:31.611199Z","iopub.execute_input":"2022-07-30T17:07:31.612388Z","iopub.status.idle":"2022-07-30T17:12:26.232323Z","shell.execute_reply.started":"2022-07-30T17:07:31.612330Z","shell.execute_reply":"2022-07-30T17:12:26.229972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Imports","metadata":{}},{"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)\ntry:\n    from pycaret.classification import * # doing some magic\nexcept:\n    from pycaret.classification import * # doing some magic\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","execution":{"iopub.status.busy":"2022-07-30T17:12:41.659289Z","iopub.execute_input":"2022-07-30T17:12:41.660138Z","iopub.status.idle":"2022-07-30T17:12:44.534995Z","shell.execute_reply.started":"2022-07-30T17:12:41.660095Z","shell.execute_reply":"2022-07-30T17:12:44.533667Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Loading Data","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv('../input/predict-potential-spammers-on-fiverr/train.csv')\ntest = pd.read_csv('../input/predict-potential-spammers-on-fiverr/test.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = train.drop(columns=['user_id'])\ntest = test.drop(columns=['user_id'])\n\nfeature_cols = [col for col in train if col.startswith('X')]\n\nno_variation_cols = list()\nfor col in feature_cols:\n    if train[col].nunique() == 1:\n        no_variation_cols.append(col)\n        \ntrain.drop(columns = no_variation_cols, inplace = True)\ntest.drop(columns = no_variation_cols, inplace = True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## PyCaret Magic Starts Here","metadata":{}},{"cell_type":"code","source":"s = setup(train, target = 'label', silent=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"best_model = compare_models(fold=3)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tuned = tune_model(best_model)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predict_model(tuned)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"final_model = finalize_model(tuned)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = predict_model(final_model, data=test)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions['Label'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission File","metadata":{}},{"cell_type":"code","source":"submission = pd.read_csv('../input/predict-potential-spammers-on-fiverr/sample_submission.csv')\nsubmission.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.label = predictions['Label']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.columns = ['user_id','prediction']","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}