{"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":"## Summary\nIn this kernel, we present a simple logistic regression model for \"GCT APAC D&A Race\" competition.","metadata":{}},{"cell_type":"markdown","source":"## Load Data","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)\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":"from sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.model_selection import cross_val_score\nimport matplotlib.pyplot as plt\nimport seaborn as sns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('../input/gct-apac-d-and-a-race/train.csv')\ntest = pd.read_csv('../input/gct-apac-d-and-a-race/test.csv')\nprint(\"{} observations and {} features in train set.\".format(train.shape[0],train.shape[1]))\nprint(\"{} observations and {} features in test set.\".format(test.shape[0],test.shape[1]))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Exploratory data analysis","metadata":{}},{"cell_type":"markdown","source":"The features are looking like perfectly normal distribution!","metadata":{}},{"cell_type":"code","source":"train.target.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(12, 5))\nplt.hist(train.target.values, bins=200)\nplt.title('Histogram target counts')\nplt.xlabel('Count')\nplt.ylabel('Target')\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(12, 5))\nplt.hist(train['ramscoop-ventrodorsal-regendering-Kandinsky'].values, bins=200)\nplt.title('Histogram ramscoop-ventrodorsal-regendering-Kandinsky counts')\nplt.xlabel('Value')\nplt.ylabel('Count')\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(12, 5))\nplt.hist(train['piecener-brannigan-shole-oppositionists'].values, bins=200)\nplt.title('Histogram piecener-brannigan-shole-oppositionists counts')\nplt.xlabel('Value')\nplt.ylabel('Count')\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Things to notice:\n\nMost features appear to be numerical\n\nMost features seem perfectly normally distributed\n\nMost features seem to be normalized and centered to approximately same values (with some sligth differences)\n\nThe target is almost perfectly balanced between positive and negative classes","metadata":{}},{"cell_type":"markdown","source":"## Training","metadata":{}},{"cell_type":"code","source":"%%time\nfeatues_to_use = [c for c in train.columns if c not in ['id', 'target']]\ntarget = train['target']\ntrain = train[featues_to_use]\ntest = test[featues_to_use]\nclassifier = LogisticRegression(C=1, solver='sag')\ncv_score = np.mean(cross_val_score(classifier, train, target, cv=3, scoring='roc_auc'))\nprint(cv_score) \n\nclassifier.fit(train,target)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prediction","metadata":{}},{"cell_type":"code","source":"%%time\nsubmission = pd.read_csv('../input/gct-apac-d-and-a-race/sample_submission.csv')\npred_lr = classifier.predict_proba(test)[:, 1]\nsubmission['target'] = pred_lr\nsubmission.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}