diff --git a/example.py b/examples/example.py
similarity index 95%
rename from example.py
rename to examples/example.py
index e8a794b157206b9c3703370129fc48a02520fa44..42062e526c9ee3f26ff8f965426f5423122b776e 100644
--- a/example.py
+++ b/examples/example.py
@@ -6,8 +6,8 @@
 import numpy as np
 from matplotlib import pyplot as plt
 
-from kernels_PDE import Gaussian_laplace
-from vkoga_PDE import VKOGA_PDE
+from vkoga_pde.kernels_PDE import Gaussian_laplace
+from vkoga_pde.vkoga_PDE import VKOGA_PDE
 
 np.random.seed(1)
 
diff --git a/kernels_PDE.py b/vkoga_pde/kernels_PDE.py
similarity index 100%
rename from kernels_PDE.py
rename to vkoga_pde/kernels_PDE.py
diff --git a/vkoga_PDE.py b/vkoga_pde/vkoga_PDE.py
similarity index 99%
rename from vkoga_PDE.py
rename to vkoga_pde/vkoga_PDE.py
index 7763c89830afec6d1e0d946ac164903b9ba9ccaa..534434682dacf791e1e9af8ef5611810d242dac8 100644
--- a/vkoga_PDE.py
+++ b/vkoga_pde/vkoga_PDE.py
@@ -1,7 +1,7 @@
 # First approach to develope code for greedy PDE.
 # ToDo: Not sure whether vector valued output makes sense, but let's try to implement it ..
 
-from kernels_PDE import wendland32_laplace
+from vkoga_pde.kernels_PDE import wendland32_laplace
 import numpy as np
 from sklearn.base import BaseEstimator
 from sklearn.utils.validation import check_X_y, check_array