def ga2m(self):
# Explore the Data
marginal = Marginal().explain_data(self.x, self.y, name="Raw Data")
# Train the Explainable Boosting Machine(EBM)
lr = LinearRegression()
lr.fit(self.x, self.y)
rt = RegressionTree()
rt.fit(self.x, self.y)
ebm = ExplainableBoostingRegressor(
) # For Classifier, use ebm = ExplainableBoostingClassifier()
ebm.fit(self.x, self.y)
# How Does the EBM Model Perform?
ebm_perf = RegressionPerf(ebm.predict).explain_perf(self.x,
self.y,
name="EBM")
lr_perf = RegressionPerf(lr.predict).explain_perf(
self.x, self.y, name="Linear Regression")
rt_perf = RegressionPerf(rt.predict).explain_perf(
self.x, self.y, name="Regression Tree")
# Global Interpretability - What the Model says for All Data
ebm_global = ebm.explain_global(name="EBM")
lr_global = lr.explain_global(name="LinearRegression")
rt_global = rt.explain_global(name="Regression Tree")
# Put All in a Dashboard - This is the best
show([
marginal, lr_global, lr_perf, rt_global, rt_perf, ebm_perf,
ebm_global
])
def train_titanic_regression(interactions):
df = pd.read_csv(os.path.join('examples', 'titanic_train.csv'))
df = df.dropna()
feature_columns = ['SibSp', 'Fare', 'Pclass']
label_column = "Age"
y = df[[label_column]]
le = LabelEncoder()
y_enc = le.fit_transform(y)
x = df[feature_columns]
x_train, x_test, y_train, y_test = train_test_split(x, y_enc)
model = ExplainableBoostingRegressor(interactions=interactions)
model.fit(x_train, y_train)
return model, x_test, y_test
def fit(self,
X,
y,
sample_weight=None,
eval_set=None,
sample_weight_eval_set=None,
**kwargs):
from interpret.glassbox import (
ExplainableBoostingClassifier,
ExplainableBoostingRegressor,
)
logging.root.level = (
10
) # HACK - EBM can't handle our custom logger with unknown level 9 (DATA)
orig_cols = list(X.names)
if self.num_classes >= 2:
lb = LabelEncoder()
lb.fit(self.labels)
y = lb.transform(y)
model = ExplainableBoostingClassifier(**self.params)
else:
model = ExplainableBoostingRegressor(**self.params)
# Replace missing values with a value smaller than all observed values
self.min = dict()
for col in X.names:
XX = X[:, col]
self.min[col] = XX.min1()
if self.min[col] is None or np.isnan(self.min[col]):
self.min[col] = -1e10
else:
self.min[col] -= 1
XX.replace(None, self.min[col])
X[:, col] = XX
assert X[dt.isna(dt.f[col]), col].nrows == 0
X = X.to_numpy()
model.fit(X, y)
importances = self.get_importances(model, X.shape[1])
self.set_model_properties(
model=model,
features=orig_cols,
importances=importances,
iterations=self.params["n_estimators"],
)
def fit(self,
X,
y,
sample_weight=None,
eval_set=None,
sample_weight_eval_set=None,
**kwargs):
from interpret.glassbox import (
ExplainableBoostingClassifier,
ExplainableBoostingRegressor,
)
logging.root.level = (
10
) # HACK - EBM can't handle our custom logger with unknown level 9 (DATA)
orig_cols = list(X.names)
if self.num_classes >= 2:
lb = LabelEncoder()
lb.fit(self.labels)
y = lb.transform(y)
model = ExplainableBoostingClassifier(**self.params)
else:
model = ExplainableBoostingRegressor(**self.params)
X = self.basic_impute(X)
X = X.to_numpy()
model.fit(X, y)
importances = self.get_importances(model, X.shape[1])
self.set_model_properties(
model=model,
features=orig_cols,
importances=importances,
iterations=self.params["n_estimators"],
)
y = df[label]
#X,y = datasets.load_boston(return_X_y=True)
seed = 1
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.20,
random_state=seed)
from interpret import show
from interpret.data import ClassHistogram
hist = ClassHistogram().explain_data(X_train, y_train, name='Train Data')
show(hist)
print(type(hist))
from interpret.glassbox import ExplainableBoostingRegressor, LogisticRegression, ClassificationTree, DecisionListClassifier
ebm = ExplainableBoostingRegressor(random_state=seed)
ebm.fit(X_train, y_train) #Works on dataframes and numpy arrays
ebm_global = ebm.explain_global(name='EBM')
for i in range(7):
ebm_global.visualize(i).write_html('Concrete_Strength/CS_' +
df.columns[i] + '.html')
preds = ebm.predict(X_test)
#for i in range(len(preds)):
#print(preds[i],y_test[i])
print(preds)
print(y_test)
#ebm_global.visualize(0).write_html('zero.html')
#ebm_local = ebm.explain_local(X_test, y_test)
#ebm_local.visualize(0).write_html("local_zero.html")
ax.set_ylabel('Cumulative Area Prediction')
ax.set_title("Cumulative Gains Chart")
ax = liftChart(pred_v, ax=axes[1], labelBars=False)
ax.set_ylabel("Lift")
plt.tight_layout()
plt.show()
# ### Explainable Boosting Machine Regression
# In[22]:
from interpret.glassbox import ExplainableBoostingRegressor
ebm = ExplainableBoostingRegressor()
ebm.fit(train_X, train_y)
# In[23]:
# Display the error performance measures
regressionSummary(train_y, ebm.predict(train_X))
print()
regressionSummary(test_y, ebm.predict(test_X))
# In[19]:
from interpret import show
ebm_global = ebm.explain_global()
def build_estimator(args, train_data=None):
feature_names = [f"featur_{i}" for i in range(train_data[0].shape[1])]
return ExplainableBoostingRegressor(random_state=RANDOM_STATE,
feature_names=feature_names,
**args)