Updated README and reorganized folders.

README.md

@@ -3,8 +3,29 @@
 
 This library is a collection of statistical methods to simulate and estimate non-deterministic differential equations. Inference of SDEs is a topic I personally find very interesting but while the tools for their deterministic counterparts are well-developed (and especially well-implemented), stochastic differential equations lack a common tool set in Python.
 
-
 ![Alt text](misc/cirpaths.png?raw=true)
 
+In current focus are one-dimensional Itô - diffusions and the focus will lie on such until the framework for the one-dimensional case is stable enough. The multidimensional case is in scope and the code is developed with the later extension to that case in mind.
+
+## Usage
+
+All numerical schemes and estimation algorithms rely on a stochastic differential equation, given by
+```Python
+SDE(drift, diffusion, timerange=[0,2])
+```
+
+with generic drift and diffusion functions. These can be specified in any way - it is useful though to ensure that the theoretical boundaries for existence of weak or strong solutions are set.
+
+Schemes are implemented as iterators. To import the Euler-Mayurama scheme, use
+```Python
+from simulation.strong.taylor import Order_05 as Euler
+
+[...]
+
+
+for path_value in Euler(SDE, parameter, steps=50):
+    do_stuff_with_it(path_value)
+```
+which gives you maximal flexibility, speed and effective memory management.
 
-Currently implemented are strong schemes with different properties and besides the Euler scheme they all have first-order convergence.
+A short introduction on estimation methods will later be included.

examples/convergence order_cir.py

@@ -1,9 +1,9 @@
 import numpy as np
 
-from src.sde import SDE
-from src.simulation.strong.explicit import Order_10 as Platen
-from src.simulation.strong.taylor import Order_05 as Euler
-from src.simulation.strong.taylor import Order_10 as Milstein
+from sde import SDE
+from simulation.strong.explicit import Order_10 as Platen
+from simulation.strong.taylor import Order_05 as Euler
+from simulation.strong.taylor import Order_10 as Milstein
 
 """
 We compare the order of convergence between two strong Taylor schemes and one derivative-free strong

examples/simulate_cir.py

@@ -3,9 +3,9 @@
 
 import numpy as np
 
-from src.sde import SDE
-from src.simulation.strong.explicit import Order_10 as Platen
-from src.simulation.strong.taylor import Order_05 as Euler
+from sde import SDE
+from simulation.strong.explicit import Order_10 as Platen
+from simulation.strong.taylor import Order_05 as Euler
 
 """
 We begin with the definition of both drift and diffusion functions and define the CIR process.
@@ -29,7 +29,7 @@ def cir_diffusion(c, x):
 
 euler_path = np.zeros([100, 2001])
 platen_path = np.zeros([100, 2001])
-print("Run time estimation between Euler and Platen discretization of an CIR process.")
+print("Run time estimation for Euler and Platen discretization of an CIR process.")
 
 """
 A dictionary for all parameters is given to the iterators representing the schemes.

src/simulation/strong/explicit.py → simulation/strong/explicit.py

@@ -1,7 +1,7 @@
 
 import numpy as np
 
-from src.simulation.scheme import Scheme
+from simulation.scheme import Scheme
 
 
 class Order_10(Scheme):

src/simulation/strong/implicit.py → simulation/strong/implicit.py

@@ -1,7 +1,7 @@
 
 from scipy.optimize import newton
 
-from src.simulation.scheme import Scheme
+from simulation.scheme import Scheme
 
 
 class Order_10(Scheme):

src/simulation/strong/predictorcorrector.py → simulation/strong/predictorcorrector.py

@@ -1,7 +1,7 @@
 
 import numpy as np
 
-from src.simulation.scheme import Scheme
+from simulation.scheme import Scheme
 
 
 class Order_10(Scheme):

src/simulation/strong/taylor.py → simulation/strong/taylor.py

@@ -1,5 +1,4 @@
-
-from src.simulation.scheme import Scheme
+from simulation.scheme import Scheme
 
 
 class Order_05(Scheme):