Fix printed score; demonstrate best() function

README.md

@@ -65,7 +65,7 @@ pip install pysr
 
 ```python
 import numpy as np
-from pysr import pysr
+from pysr import pysr, best, get_hof
 
 # Dataset
 X = 2*np.random.randn(100, 5)
@@ -73,25 +73,30 @@ y = 2*np.cos(X[:, 3]) + X[:, 0]**2 - 2
 
 # Learn equations
 equations = pysr(X, y, niterations=5,
-            binary_operators=["plus", "mult"],
-            unary_operators=["cos", "exp", "sin"])
+        binary_operators=["plus", "mult"],
+        unary_operators=["cos", "exp", "sin"])
 
-...
+...# (you can use ctl-c to exit early)
 
-print(equations)
+print(best())
 ```
 
 which gives:
 
-```
-   Complexity       MSE                                                Equation
-0           5  1.947431                          plus(-1.7420927, mult(x0, x0))
-1           8  0.486858           plus(-1.8710494, plus(cos(x3), mult(x0, x0)))
-2          11  0.000000  plus(plus(mult(x0, x0), cos(x3)), plus(-2.0, cos(x3)))
+```python
+x0**2 + 2.000016*cos(x3) - 1.9999845
 ```
 
-The newest version of PySR also returns three additional columns:
+One can also use `best_tex` to get the LaTeX form,
+or `best_callable` to get a function you can call.
+This uses a score which balances complexity and error;
+however, one can see the full list of equations with:
+```python
+print(get_hof())
+```
+This is a pandas table, with additional columns:
 
+- `MSE` - the mean square error of the formula
 - `score` - a metric akin to Occam's razor; you should use this to help select the "true" equation.
 - `sympy_format` - sympy equation.
 - `lambda_format` - a lambda function for that equation, that you can pass values through.

TODO.md

@@ -58,6 +58,7 @@
 ## Feature ideas
 
 - [ ] Create backup csv file so always something to copy from for `PySR`. Also use random hall of fame file by default. Call function to read from csv after running, so dont need to run again. Dump scores alongside MSE to .csv (and return with Pandas).
+- [ ] Do printing from Python side. Then we can do simplification and pretty-printing.
 - [ ] Cross-validation
 - [ ] Sympy printing
 - [ ] Better cleanup of zombie processes after <ctl-c>

docs/start.md

@@ -26,7 +26,7 @@ pip install pysr
 
 ```python
 import numpy as np
-from pysr import pysr
+from pysr import pysr, best, get_hof
 
 # Dataset
 X = 2*np.random.randn(100, 5)
@@ -34,25 +34,30 @@ y = 2*np.cos(X[:, 3]) + X[:, 0]**2 - 2
 
 # Learn equations
 equations = pysr(X, y, niterations=5,
-            binary_operators=["plus", "mult"],
-            unary_operators=["cos", "exp", "sin"])
+        binary_operators=["plus", "mult"],
+        unary_operators=["cos", "exp", "sin"])
 
-...
+...# (you can use ctl-c to exit early)
 
-print(equations)
+print(best())
 ```
 
 which gives:
 
-```
-   Complexity       MSE                                                Equation
-0           5  1.947431                          plus(-1.7420927, mult(x0, x0))
-1           8  0.486858           plus(-1.8710494, plus(cos(x3), mult(x0, x0)))
-2          11  0.000000  plus(plus(mult(x0, x0), cos(x3)), plus(-2.0, cos(x3)))
+```python
+x0**2 + 2.000016*cos(x3) - 1.9999845
 ```
 
-The newest version of PySR also returns three additional columns:
+One can also use `best_tex` to get the LaTeX form,
+or `best_callable` to get a function you can call.
+This uses a score which balances complexity and error;
+however, one can see the full list of equations with:
+```python
+print(get_hof())
+```
+This is a pandas table, with additional columns:
 
+- `MSE` - the mean square error of the formula
 - `score` - a metric akin to Occam's razor; you should use this to help select the "true" equation.
 - `sympy_format` - sympy equation.
 - `lambda_format` - a lambda function for that equation, that you can pass values through.

pysr/__init__.py

@@ -1 +1 @@
-from .sr import pysr, get_hof, best, best_tex, best_function
+from .sr import pysr, get_hof, best, best_tex, best_callable, best_row

pysr/sr.py

@@ -391,7 +391,7 @@ def get_hof(equation_file=None, n_features=None, variable_names=None, extra_symp
         if lastMSE is None:
             cur_score = 0.0
         else:
-            cur_score = np.log(curMSE/lastMSE)/(curComplexity - lastComplexity)
+            cur_score = - np.log(curMSE/lastMSE)/(curComplexity - lastComplexity)
 
         scores.append(cur_score)
         lastMSE = curMSE
@@ -427,7 +427,7 @@ def best_tex(equations=None):
     best_sympy = best_row(equations)['sympy_format']
     return sympy.latex(best_sympy.simplify())
 
-def best_function(equations=None):
+def best_callable(equations=None):
     """Return the equation with the best score, in callable format"""
     if equations is None: equations = get_hof()
     return best_row(equations)['lambda_format']