{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.19.1\n",
"0.20.3\n"
]
}
],
"source": [
"import pandas as pd\n",
"import os\n",
"import sklearn\n",
"import warnings\n",
"warnings.filterwarnings('ignore')\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from xgboost import XGBClassifier\n",
"from mlxtend.classifier import StackingClassifier\n",
"from sklearn.cross_validation import train_test_split\n",
"\n",
"print sklearn.__version__\n",
"print pd.__version__"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ID</th>\n",
" <th>JobFamily</th>\n",
" <th>JobFamilyDescription</th>\n",
" <th>JobClass</th>\n",
" <th>JobClassDescription</th>\n",
" <th>PayGrade</th>\n",
" <th>EducationLevel</th>\n",
" <th>Experience</th>\n",
" <th>OrgImpact</th>\n",
" <th>ProblemSolving</th>\n",
" <th>Supervision</th>\n",
" <th>ContactLevel</th>\n",
" <th>FinancialBudget</th>\n",
" <th>PG</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Accounting And Finance</td>\n",
" <td>1</td>\n",
" <td>Accountant I</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" <td>PG05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>Accounting And Finance</td>\n",
" <td>2</td>\n",
" <td>Accountant II</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>PG06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>Accounting And Finance</td>\n",
" <td>3</td>\n",
" <td>Accountant III</td>\n",
" <td>8</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>PG08</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>Accounting And Finance</td>\n",
" <td>4</td>\n",
" <td>Accountant IV</td>\n",
" <td>10</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>8</td>\n",
" <td>11</td>\n",
" <td>PG10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>Administrative Support</td>\n",
" <td>5</td>\n",
" <td>Admin Support I</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>PG01</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ID JobFamily JobFamilyDescription JobClass JobClassDescription \\\n",
"0 1 1 Accounting And Finance 1 Accountant I \n",
"1 2 1 Accounting And Finance 2 Accountant II \n",
"2 3 1 Accounting And Finance 3 Accountant III \n",
"3 4 1 Accounting And Finance 4 Accountant IV \n",
"4 5 2 Administrative Support 5 Admin Support I \n",
"\n",
" PayGrade EducationLevel Experience OrgImpact ProblemSolving \\\n",
"0 5 3 1 3 3 \n",
"1 6 4 1 5 4 \n",
"2 8 4 2 6 5 \n",
"3 10 5 5 6 6 \n",
"4 1 1 0 1 1 \n",
"\n",
" Supervision ContactLevel FinancialBudget PG \n",
"0 4 3 5 PG05 \n",
"1 5 7 7 PG06 \n",
"2 6 7 10 PG08 \n",
"3 7 8 11 PG10 \n",
"4 1 1 1 PG01 "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# reading data to df\n",
"DATA_DIR = '../data'\n",
"\n",
"df = pd.read_csv(os.path.abspath(os.path.join(DATA_DIR, 'day15/jobclass.csv')))\n",
"df.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"# target is to predict the column PG using rest (all to one)\n",
"target = df['PG']\n",
"\n",
"# dropping unnecessary columns and keeping just the concerned features\n",
"df.drop(['ID', 'JobFamilyDescription', 'JobClassDescription', 'PG'], axis=1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>JobFamily</th>\n",
" <th>JobClass</th>\n",
" <th>PayGrade</th>\n",
" <th>EducationLevel</th>\n",
" <th>Experience</th>\n",
" <th>OrgImpact</th>\n",
" <th>ProblemSolving</th>\n",
" <th>Supervision</th>\n",
" <th>ContactLevel</th>\n",
" <th>FinancialBudget</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" JobFamily JobClass PayGrade EducationLevel Experience OrgImpact \\\n",
"0 1 1 5 3 1 3 \n",
"1 1 2 6 4 1 5 \n",
"\n",
" ProblemSolving Supervision ContactLevel FinancialBudget \n",
"0 3 4 3 5 \n",
"1 4 5 7 7 "
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(2)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"JobFamily 0\n",
"JobClass 0\n",
"PayGrade 0\n",
"EducationLevel 0\n",
"Experience 0\n",
"OrgImpact 0\n",
"ProblemSolving 0\n",
"Supervision 0\n",
"ContactLevel 0\n",
"FinancialBudget 0\n",
"dtype: int64"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check for NaN (Missing values)\n",
"df.isnull().sum()\n",
"\n",
"# Luckily not a single missing values"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"X = df[:].values\n",
"Y = target.values"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"# ideal practice is to use test as 20% - 30% of training data\n",
"# defined by test_size in train_test_split()\n",
"# random_state is required to avoid sequential biasness in the data distribution\n",
"def data_split(X, Y):\n",
" X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size=0.2, random_state = 10)\n",
" return X_train, X_test, Y_train, Y_test\n",
"\n",
"X_train, X_test, Y_train, Y_test = data_split(X, Y)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Model - 1 [Random Forest]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"clf1 = RandomForestClassifier(random_state=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Model - 2 [XGBoost]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"clf2 = XGBClassifier()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Meta Model [Logit]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"lr = LogisticRegression()\n",
"sclf = StackingClassifier(\n",
" classifiers = [clf1, clf2], \n",
" meta_classifier=lr,\n",
" use_probas=True,\n",
" average_probas=False,\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5-fold cross validation:\n",
"\n",
"Accuracy: 0.70 (+/- 0.10) [Random Forest]\n",
"Accuracy: 0.92 (+/- 0.09) [XGBoost]\n",
"Accuracy: 0.86 (+/- 0.14) [StackingClassifier]\n"
]
}
],
"source": [
"print('5-fold cross validation:\\n')\n",
"\n",
"for clf, label in zip([clf1, clf2, sclf], \n",
" ['Random Forest', \n",
" 'XGBoost',\n",
" 'StackingClassifier']):\n",
"\n",
" scores = sklearn.model_selection.cross_val_score(clf, X_train, Y_train, \n",
" cv=5, scoring='accuracy')\n",
" print(\"Accuracy: %0.2f (+/- %0.2f) [%s]\" \n",
" % (scores.mean(), scores.std(), label))"
]
}
],
"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": "2.7.12"
}
},
"nbformat": 4,
"nbformat_minor": 1
}