baselines code updated

baselines/impweight.py

@@ -4,6 +4,20 @@ from sklearn.linear_model import LogisticRegression
 from sklearn.model_selection import GridSearchCV
 from sklearn.neighbors import KernelDensity
 
+from baselines import densratio
+from baselines.pykliep import DensityRatioEstimator
+
+
+def kliep(Xtr, ytr, Xte):
+    kliep = DensityRatioEstimator()
+    kliep.fit(Xtr, Xte)
+    return kliep.predict(Xtr)
+
+
+def usilf(Xtr, ytr, Xte, alpha=0.0):
+    dense_ratio_obj = densratio(Xtr, Xte, alpha=alpha, verbose=False)
+    return dense_ratio_obj.compute_density_ratio(Xtr)
+
 
 def logreg(Xtr, ytr, Xte):
     # check "Direct Density Ratio Estimation for

baselines/models.py

@@ -123,7 +123,7 @@ if __name__ == "__main__":
 
     results = []
     for sample in protocol():
-        wx = iw.logreg(d.validation.X, d.validation.y, sample.X)
+        wx = iw.kliep(d.validation.X, d.validation.y, sample.X)
         test_preds = lr.predict(sample.X)
         estim_acc = np.sum((1.0 * (val_preds == d.validation.y)) * wx) / np.sum(wx)
         true_acc = metrics.accuracy_score(sample.y, test_preds)

baselines/pykliep.py

@@ -74,7 +74,9 @@ class DensityRatioEstimator:
         #     X_test_shuffled = X_test.copy()
         X_test_shuffled = X_test.copy()
 
-        np.random.shuffle(X_test_shuffled)
+        X_test_index = np.arange(X_test_shuffled.shape[0])
+        np.random.shuffle(X_test_index)
+        X_test_shuffled = X_test_shuffled[X_test_index, :]
 
         j_scores = {}