Skip to content

Instantly share code, notes, and snippets.

@jfpuget

jfpuget/xgb_check.ipynb

Created November 26, 2017 11:46
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save jfpuget/caf314ea06471835e61617bb05865e51 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save jfpuget/caf314ea06471835e61617bb05865e51 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
xgb_check.ipynb
{
"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"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>X10</th>\n",
" <th>X100</th>\n",
" <th>X101</th>\n",
" <th>X102</th>\n",
" <th>X103</th>\n",
" <th>X104</th>\n",
" <th>X105</th>\n",
" <th>X106</th>\n",
" <th>X108</th>\n",
" <th>X109</th>\n",
" <th>...</th>\n",
" <th>X89</th>\n",
" <th>X90</th>\n",
" <th>X91</th>\n",
" <th>X92</th>\n",
" <th>X94</th>\n",
" <th>X95</th>\n",
" <th>X96</th>\n",
" <th>X97</th>\n",
" <th>X98</th>\n",
" <th>X99</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 322 columns</p>\n",
"</div>"
],
"text/plain": [
" X10 X100 X101 X102 X103 X104 X105 X106 X108 X109 ... X89 X90 \\\n",
"0 0 0 0 0 0 0 0 0 0 0 ... 0 0 \n",
"1 0 1 1 0 0 0 0 0 0 0 ... 0 0 \n",
"2 0 0 1 0 0 0 0 0 0 0 ... 0 0 \n",
"3 0 0 1 0 0 0 0 0 1 0 ... 0 0 \n",
"4 0 0 1 0 0 0 0 0 1 0 ... 0 0 \n",
"\n",
" X91 X92 X94 X95 X96 X97 X98 X99 \n",
"0 0 0 0 0 0 0 0 0 \n",
"1 0 0 0 0 1 0 1 0 \n",
"2 0 0 0 0 1 0 1 0 \n",
"3 0 0 0 0 1 0 1 0 \n",
"4 0 0 0 0 1 0 1 0 \n",
"\n",
"[5 rows x 322 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train = pd.read_csv('Mercedes-Benz/data/train_notype.csv')\n",
"y_train = pd.read_csv('Mercedes-Benz/input/train.csv.zip', usecols=['y'])\n",
"train.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"x_train = xgb.DMatrix(train, label=y_train)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"params = {\n",
" 'eta': 0.0045,\n",
" 'max_depth': 4,\n",
" 'subsample': 0.93,\n",
" 'objective': 'reg:linear',\n",
" 'eval_metric': 'rmse',\n",
" 'nthread':6,\n",
" 'silent': 0\n",
"}\n",
"\n",
"bst = xgb.train(params, x_train, num_boost_round=500)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<xgboost.core.Booster at 0x107a81470>"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bst"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 89.09706116, 84.26348877, 69.81824493, ..., 100.67781067,\n",
" 84.15869141, 84.2922821 ], dtype=float32)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bst.predict(x_train)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pickle as pkl"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"with open('test.plk', 'wb') as file:\n",
" pkl.dump(bst, file)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"with open('test.plk', 'rb') as file:\n",
" bst1 = pkl.load(file)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 89.09706879, 84.2634964 , 69.8182373 , ..., 100.67781067,\n",
" 84.15869904, 84.29228973], dtype=float32)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bst1.predict(x_train)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "feature_names must be unique",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-11-9e304fedfca2>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mtrain1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrename\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'X100'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m'X101'\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mx_train1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mxgb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDMatrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mbst1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx_train1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/Users/JFPuget/anaconda/lib/python3.5/site-packages/xgboost-0.6-py3.5.egg/xgboost/core.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, data, label, missing, weight, silent, feature_names, feature_types)\u001b[0m\n\u001b[1;32m 278\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_weight\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mweight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 279\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 280\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfeature_names\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfeature_names\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 281\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfeature_types\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfeature_types\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 282\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/Users/JFPuget/anaconda/lib/python3.5/site-packages/xgboost-0.6-py3.5.egg/xgboost/core.py\u001b[0m in \u001b[0;36mfeature_names\u001b[0;34m(self, feature_names)\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[0mfeature_names\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeature_names\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 583\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeature_names\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeature_names\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 584\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'feature_names must be unique'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 585\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeature_names\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_col\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 586\u001b[0m \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'feature_names must have the same length as data'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: feature_names must be unique"
]
}
],
"source": [
"train1 = train.rename(columns={'X100':'X101'})\n",
"x_train1 = xgb.DMatrix(train1, label=y_train)\n",
"bst1.predict(x_train1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"anaconda-cloud": {},
"kernelspec": {
"display_name": "Python [default]",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 1
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment