y_test = np.zeros((X_test.shape[0],1))
y_train = np.zeros((X_train.shape[0],1))
y_train[range(X_train_pos.shape[0])]=1
y_test[range(X_test_pos.shape[0])]=1
print("X size: ",X_train.shape[0],'x',X_train.shape[1])
print("y size: ",y_train.shape[0],'x',y_train.shape[1])
print("X-test size: ",X_test.shape[0],'x',X_test.shape[1])
print("y-test size: ",y_test.shape[0],'x',y_test.shape[1])
# train and test, performance output
#clf = tune_ebm(X_train, y_train)
clf = ExplainableBoostingClassifier(random_state=seed, interactions=100)
clf.fit(X_train, y_train)
print("Finished training ...")
curr_perf = []
y_pred = clf.predict(X_test)
curr_perf += [metrics.accuracy_score(y_test, y_pred)]
print(metrics.confusion_matrix(y_test, y_pred))
y_pred = clf.predict_proba(X_test)
curr_perf += [get_aucpr(y_test, y_pred[:,1])]
curr_perf += [get_auc(y_test, y_pred[:,1])]
print("Performance: ",curr_perf)
# predict on larger set, output predictions
print("Predicting on all test pairs now... ")
scores = (clf.predict_proba(X_neg_all))[:,1]
neg_pps['score'] = scores
neg_pps.to_csv(outfile)
# save model
#save_model(clf,format("models/ebm_covonly_split%d_1to1_int.pkl" % split))
iX_train, iX_test, y_train, y_test = \
train_test_split(iX, y, test_size=0.25, stratify=y, random_state=0)
X_train, X_test = X[iX_train], X[iX_test]
X_test_out = data_test_out
y_test_out = labels_test_out
#%%
from interpret.glassbox import ExplainableBoostingClassifier
ebm = ExplainableBoostingClassifier()
ebm.fit(data_pts_1, labels_pts_1)
labels_pt_2_pred = ebm.predict(data_pts_2)
#%%
# Try isolation forest for outlier detection
X = data_pts_1
from sklearn.ensemble import IsolationForest
clf = IsolationForest(random_state=0, n_jobs=-1, contamination=0.25).fit(X)
A = clf.predict(X)
print((A == -1).mean(), (labels != 0).mean(),
((A == -1) == (labels != 0)).mean())
#%%
show(lr_global)
# %% Fit decision tree model
tree = ClassificationTree()
tree.fit(X_train, y_train)
print("Training finished.")
y_pred = tree.predict(X_test)
print(f"F1 Score {f1_score(y_test, y_pred, average='macro')}")
print(f"Accuracy {accuracy_score(y_test, y_pred)}")
# %% Explain local prediction
tree_local = tree.explain_local(X_test[:100], y_test[:100], name='Tree')
show(tree_local)
# %% Fit Explainable Boosting Machine
ebm = ExplainableBoostingClassifier(random_state=2021)
ebm.fit(X_train, y_train)
print("Training finished.")
y_pred = ebm.predict(X_test)
print(f"F1 Score {f1_score(y_test, y_pred, average='macro')}")
print(f"Accuracy {accuracy_score(y_test, y_pred)}")
# %% Explain locally
ebm_local = ebm.explain_local(X_test[:100], y_test[:100], name='EBM')
show(ebm_local)
# %% Explain globally
ebm_global = ebm.explain_global(name='EBM')
show(ebm_global)
# %%
plt.show() # ### Explainable Boosting Machine # In[9]: from interpret.glassbox import ExplainableBoostingClassifier ebm = ExplainableBoostingClassifier() ebm.fit(train_X, train_y) # In[12]: # display confusion matrices for train and test data classificationSummary(train_y, ebm.predict(train_X)) classificationSummary(test_y, ebm.predict(test_X)) # In[10]: from interpret import show ebm_global = ebm.explain_global() show(ebm_global) # In[ ]: ebm_local = ebm.explain_local(test_X, test_y) show(ebm_local) # ### RandomForest Regression Model
test_idxes = []
for train_index, test_index in kf.split(X, y):
train_idxes.append(train_index)
test_idxes.append(test_index)
splitwise_perf = []
for split in range(0, 5):
X_train, X_test = X.iloc[train_idxes[split], :], X.iloc[
test_idxes[split], :]
y_train, y_test = y[train_idxes[split]], y[test_idxes[split]]
#X_train, X_test, X_cov = normalize_train_test_cov(X_train, X_test, X_cov)
y_train = y_train.ravel()
clf = ExplainableBoostingClassifier(
random_state=seed) #, interactions=100)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(metrics.confusion_matrix(y_test, y_pred))
curr_perf = []
curr_perf += [metrics.accuracy_score(y_test, y_pred)]
y_pred = clf.predict_proba(X_test)
curr_perf += [get_aucpr(y_test, y_pred[:, 1])]
curr_perf += [get_auc(y_test, y_pred[:, 1])]
y_pred_cov = clf.predict(X_cov)
print(metrics.confusion_matrix(y_cov, y_pred_cov))
y_pred_cov = clf.predict_proba(X_cov)
curr_perf += [get_aucpr(y_cov, y_pred_cov[:, 1])]
curr_perf += [get_auc(y_cov, y_pred_cov[:, 1])]
print(curr_perf)
splitwise_perf.append(curr_perf)
# save model
#save_model(clf,format("models/ebm_humanpartners_1to1_no3mer_nonorm_split%d.pkl" % split))
y_train_cov, y_test_cov = y_cov[train_idxes_cov[split]], y_cov[
test_idxes_cov[split]]
#X_train_cov, y_train_cov = undersample_negatives(X_train_cov, y_train_cov, 50)
y_train_cov = y_train_cov.ravel()
#clf = tune_ebm(X_train_cov, y_train_cov)
if interac == 0:
clf = ExplainableBoostingClassifier()
else:
clf = ExplainableBoostingClassifier(interactions=interac)
clf.fit(X_train_cov, y_train_cov)
curr_perf = []
y_pred_cov = clf.predict(X_test_cov)
#curr_perf += [metrics.accuracy_score(y_test_cov, y_pred_cov)]
print(metrics.confusion_matrix(y_test_cov, y_pred_cov))
y_pred_cov = clf.predict_proba(X_test_cov)
curr_perf += [get_aucpr_R(y_test_cov, y_pred_cov[:, 1])]
curr_perf += [get_auc_R(y_test_cov, y_pred_cov[:, 1])]
curr_perf += [get_fmax(y_test_cov, y_pred_cov[:, 1])]
curr_perf += get_early_prec(y_test_cov, y_pred_cov[:, 1])
print(curr_perf)
splitwise_perf.append(curr_perf)
# save model
#save_model(clf,format("models//ebm_covonly_split%d_1to10_int%d.pkl" % (split, interac)))
save_model(
clf,
format("%s/split%d_1to%d_int%d_trial%d.pkl" %
(out_dir, split, int(negfrac), interac, trial)))