Causal ML包详解：使用Python进行uplift建模和因果推断

$ git clone https://github.com/uber/causalml.git
$ cd causalml/envs/
$ conda env create -f environment-py38.yml	# for the virtual environment with Python 3.8 and CausalML
$ conda activate causalml-py38
(causalml-py38)

$ cd causalml/envs/
$ conda env create -f environment-tf-py38.yml	# for the virtual environment with Python 3.8 and CausalML
$ conda activate causalml-tf-py38
(causalml-tf-py38) pip install -U numpy			# this step is necessary to fix [#338](https://github.com/uber/causalml/issues/338)
In

$ git clone https://github.com/uber/causalml.git
$ cd causalml
$ pip install -r requirements.txt
$ pip install causalml

$ git clone https://github.com/uber/causalml.git
$ cd causalml
$ pip install -r requirements-tf.txt
$ pip install causalml[tf]
$ pip install -U numpy							# this step is necessary to fix [#338](https://github.com/uber/causalml/issues/338)

$ git clone https://github.com/uber/causalml.git
$ cd causalml
$ pip install -r requirements.txt
$ python setup.py build_ext --inplace
$ python setup.py install

from causalml.inference.meta import LRSRegressor
from causalml.inference.meta import XGBTRegressor, MLPTRegressor
from causalml.inference.meta import BaseXRegressor
from causalml.inference.meta import BaseRRegressor
from xgboost import XGBRegressor
from causalml.dataset import synthetic_data

y, X, treatment, _, _, e = synthetic_data(mode=1, n=1000, p=5, sigma=1.0)

lr = LRSRegressor()
te, lb, ub = lr.estimate_ate(X, treatment, y)
print('Average Treatment Effect (Linear Regression): {:.2f} ({:.2f}, {:.2f})'.format(te[0], lb[0], ub[0]))

xg = XGBTRegressor(random_state=42)
te, lb, ub = xg.estimate_ate(X, treatment, y)
print('Average Treatment Effect (XGBoost): {:.2f} ({:.2f}, {:.2f})'.format(te[0], lb[0], ub[0]))

nn = MLPTRegressor(hidden_layer_sizes=(10, 10),
                 learning_rate_init=.1,
                 early_stopping=True,
                 random_state=42)
te, lb, ub = nn.estimate_ate(X, treatment, y)
print('Average Treatment Effect (Neural Network (MLP)): {:.2f} ({:.2f}, {:.2f})'.format(te[0], lb[0], ub[0]))

xl = BaseXRegressor(learner=XGBRegressor(random_state=42))
te, lb, ub = xl.estimate_ate(X, treatment, y, e)
print('Average Treatment Effect (BaseXRegressor using XGBoost): {:.2f} ({:.2f}, {:.2f})'.format(te[0], lb[0], ub[0]))

rl = BaseRRegressor(learner=XGBRegressor(random_state=42))
te, lb, ub =  rl.estimate_ate(X=X, p=e, treatment=treatment, y=y)
print('Average Treatment Effect (BaseRRegressor using XGBoost): {:.2f} ({:.2f}, {:.2f})'.format(te[0], lb[0], ub[0]))

from causalml.inference.meta import BaseSRegressor, BaseTRegressor, BaseXRegressor, BaseRRegressor
from causalml.dataset.regression import synthetic_data

# Load synthetic data
y, X, treatment, tau, b, e = synthetic_data(mode=1, n=10000, p=25, sigma=0.5)
w_multi = np.array(['treatment_A' if x==1 else 'control' for x in treatment]) # customize treatment/control names

slearner = BaseSRegressor(LGBMRegressor(), control_name='control')
slearner.estimate_ate(X, w_multi, y)
slearner_tau = slearner.fit_predict(X, w_multi, y)

model_tau_feature = RandomForestRegressor()  # specify model for model_tau_feature

slearner.get_importance(X=X, tau=slearner_tau, model_tau_feature=model_tau_feature,
                        normalize=True, method='auto', features=feature_names)

# Using the feature_importances_ method in the base learner (LGBMRegressor() in this example)
slearner.plot_importance(X=X, tau=slearner_tau, normalize=True, method='auto')

# Using eli5's PermutationImportance
slearner.plot_importance(X=X, tau=slearner_tau, normalize=True, method='permutation')

# Using SHAP
shap_slearner = slearner.get_shap_values(X=X, tau=slearner_tau)

# Plot shap values without specifying shap_dict
slearner.plot_shap_values(X=X, tau=slearner_tau)

# Plot shap values WITH specifying shap_dict
slearner.plot_shap_values(X=X, shap_dict=shap_slearner)

# interaction_idx set to 'auto' (searches for feature with greatest approximate interaction)
slearner.plot_shap_dependence(treatment_group='treatment_A',
                              feature_idx=1,
                              X=X,
                              tau=slearner_tau,
                              interaction_idx='auto')

from IPython.display import Image
from causalml.inference.tree import UpliftTreeClassifier, UpliftRandomForestClassifier
from causalml.inference.tree import uplift_tree_string, uplift_tree_plot

uplift_model = UpliftTreeClassifier(max_depth=5, min_samples_leaf=200, min_samples_treatment=50,
                                    n_reg=100, evaluationFunction='KL', control_name='control')

uplift_model.fit(df[features].values,
                 treatment=df['treatment_group_key'].values,
                 y=df['conversion'].values)

graph = uplift_tree_plot(uplift_model.fitted_uplift_tree, features)
Image(graph.create_png())