Last active
March 17, 2016 11:20
-
-
Save phonism/d550d059eb9270a026ff to your computer and use it in GitHub Desktop.
test.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import pandas as pd\n", | |
"import numpy as np\n", | |
"import xgboost as xgb\n", | |
"from sklearn import preprocessing, linear_model\n", | |
"import math" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"train = pd.read_csv('../data/train/PPD_Training_Master_GBK_3_1_Training_Set.csv')\n", | |
"test = pd.read_csv('../data/test/PPD_Master_GBK_2_Test_Set.csv')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"all_data = train.append(test)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"cat_cols = [\"UserInfo_2\", \"UserInfo_4\", \"UserInfo_7\", \"UserInfo_8\", \"UserInfo_19\", \"UserInfo_20\", \"UserInfo_1\", \\\n", | |
" \"UserInfo_3\", \"UserInfo_5\", \"UserInfo_6\", \"UserInfo_9\", \"UserInfo_2\", \"UserInfo_4\", \\\n", | |
" \"UserInfo_7\", \"UserInfo_8\", \"UserInfo_19\", \"UserInfo_20\", \"UserInfo_11\", \"UserInfo_12\", \"UserInfo_13\", \\\n", | |
" \"UserInfo_14\", \"UserInfo_15\", \"UserInfo_16\", \"UserInfo_18\", \"UserInfo_21\", \"UserInfo_22\", \"UserInfo_23\", \\\n", | |
" \"UserInfo_24\", \"Education_Info1\", \"Education_Info2\", \"Education_Info3\", \"Education_Info4\", \\\n", | |
" \"Education_Info5\", \"Education_Info6\", \"Education_Info7\", \"Education_Info8\", \"WeblogInfo_19\", \\\n", | |
" \"WeblogInfo_20\", \"WeblogInfo_21\", \"SocialNetwork_1\", \"SocialNetwork_2\", \"SocialNetwork_7\", \\\n", | |
" \"ListingInfo\", \"SocialNetwork_12\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"for col in cat_cols:\n", | |
" if col in all_data.columns.values:\n", | |
" all_data[col] = pd.factorize(all_data[col])[0]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"all_data.fillna(-1, inplace=True)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"train = all_data[all_data['target'] > -1].copy()\n", | |
"test = all_data[all_data['target'] == -1].copy()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"dtrain = xgb.DMatrix(train.drop([\"Idx\", \"target\"], axis=1), train[\"target\"].values)\n", | |
"dtest = xgb.DMatrix(test.drop([\"Idx\", \"target\"], axis=1), label=test[\"target\"].values)\n", | |
"\n", | |
"params = {}\n", | |
"params['objective'] = 'binary:logistic'\n", | |
"params['eta'] = 0.02\n", | |
"params['min_child_weight'] = 1\n", | |
"params['subsample'] = 0.8\n", | |
"params['colsample_bytree'] = 0.8\n", | |
"params['max_depth'] = 8\n", | |
"params['eval_metric'] = 'auc'\n", | |
"params['nthread'] = 3\n", | |
"params['silent'] = 1\n", | |
"num_rounds = 120" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"model = xgb.train(params, dtrain, num_rounds)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"y_pred = model.predict(dtest, ntree_limit=model.best_iteration)\n", | |
"pd.DataFrame({'Idx': test['Idx'].values, 'score': y_pred}).to_csv('submit.csv', index=False)" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.10" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment