{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Uplift Tree Visualization"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Introduction\n",
"This example notebooks illustrates how to visualize uplift trees for interpretation and diagnosis. \n",
"\n",
"#### Supported Models\n",
"These visualization functions work only for tree-based algorithms:\n",
"\n",
"- Uplift tree/random forests on KL divergence, Euclidean Distance, and Chi-Square\n",
"- Uplift tree/random forests on Contextual Treatment Selection\n",
"\n",
"Currently, they are NOT supporting Meta-learner algorithms\n",
"\n",
"- S-learner\n",
"- T-learner\n",
"- X-learner\n",
"- R-learner\n",
"\n",
"#### Supported Usage\n",
"This notebook will show how to use visualization for:\n",
"\n",
"- Uplift Tree and Uplift Random Forest\n",
" - Visualize a trained uplift classification tree model\n",
" - Visualize an uplift tree in a trained uplift random forests\n",
"\n",
"- Training and Validation Data\n",
" - Visualize the validation tree: fill the trained uplift classification tree with validation (or testing) data, and show the statistics for both training data and validation data\n",
" \n",
"- One Treatment Group and Multiple Treatment Groups\n",
" - Visualize the case where there are one control group and one treatment group\n",
" - Visualize the case where there are one control group and multiple treatment groups\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 1 Load Modules"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load CausalML modules"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2019-12-20T17:23:34.805462Z",
"start_time": "2019-12-20T17:23:31.732721Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/jeong/.conda/envs/py36/lib/python3.6/site-packages/lightgbm/__init__.py:48: UserWarning: Starting from version 2.2.1, the library file in distribution wheels for macOS is built by the Apple Clang (Xcode_8.3.3) compiler.\n",
"This means that in case of installing LightGBM from PyPI via the ``pip install lightgbm`` command, you don't need to install the gcc compiler anymore.\n",
"Instead of that, you need to install the OpenMP library, which is required for running LightGBM on the system with the Apple Clang compiler.\n",
"You can install the OpenMP library by the following command: ``brew install libomp``.\n",
" \"You can install the OpenMP library by the following command: ``brew install libomp``.\", UserWarning)\n",
"Using TensorFlow backend.\n"
]
}
],
"source": [
"from causalml.dataset import make_uplift_classification\n",
"from causalml.inference.tree import UpliftTreeClassifier, UpliftRandomForestClassifier\n",
"from causalml.inference.tree import uplift_tree_string, uplift_tree_plot"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load standard modules"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2019-12-20T17:23:34.809659Z",
"start_time": "2019-12-20T17:23:34.807258Z"
}
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from IPython.display import Image\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## One Control + One Treatment for Uplift Classification Tree "
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2019-12-20T17:23:34.901230Z",
"start_time": "2019-12-20T17:23:34.811586Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" mean | \n",
" size | \n",
"
\n",
" \n",
" | \n",
" conversion | \n",
" conversion | \n",
"
\n",
" \n",
" | treatment_group_key | \n",
" | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | control | \n",
" 0.5110 | \n",
" 1000 | \n",
"
\n",
" \n",
" | treatment1 | \n",
" 0.5140 | \n",
" 1000 | \n",
"
\n",
" \n",
" | All | \n",
" 0.5125 | \n",
" 2000 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" mean | \n",
" size | \n",
"
\n",
" \n",
" | \n",
" conversion | \n",
" conversion | \n",
"
\n",
" \n",
" | treatment_group_key | \n",
" | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | control | \n",
" 0.511 | \n",
" 1000 | \n",
"
\n",
" \n",
" | treatment1 | \n",
" 0.514 | \n",
" 1000 | \n",
"
\n",
" \n",
" | treatment2 | \n",
" 0.559 | \n",
" 1000 | \n",
"
\n",
" \n",
" | treatment3 | \n",
" 0.600 | \n",
" 1000 | \n",
"
\n",
" \n",
" | All | \n",
" 0.546 | \n",
" 4000 | \n",
"
\n",
" \n",
"
\n",
"