mirror of
https://github.com/titanscouting/tra-analysis.git
synced 2024-12-27 01:59:08 +00:00
analysis.py - v 1.0.5.000
changelog: - added optimize_regression function, which is a sample function to find the optimal regressions - optimize_regression function filters out some overfit funtions (functions with r^2 = 1) - planned addition: overfit detection in the optimize_regression function
This commit is contained in:
parent
07a381b01b
commit
367b2fe60d
Binary file not shown.
@ -8,9 +8,13 @@
|
|||||||
|
|
||||||
#setup:
|
#setup:
|
||||||
|
|
||||||
__version__ = "1.0.4.001"
|
__version__ = "1.0.5.000"
|
||||||
|
|
||||||
__changelog__ = """changelog:
|
__changelog__ = """changelog:
|
||||||
|
1.0.5.000:
|
||||||
|
- added optimize_regression function, which is a sample function to find the optimal regressions
|
||||||
|
- optimize_regression function filters out some overfit funtions (functions with r^2 = 1)
|
||||||
|
- planned addition: overfit detection in the optimize_regression function
|
||||||
1.0.4.002:
|
1.0.4.002:
|
||||||
- added __changelog__
|
- added __changelog__
|
||||||
- updated debug function with log and exponential regressions
|
- updated debug function with log and exponential regressions
|
||||||
@ -678,7 +682,7 @@ def strip_data(data, mode):
|
|||||||
raise error("mode error")
|
raise error("mode error")
|
||||||
|
|
||||||
def optimize_regression(x, y, _range, resolution):#_range in poly regression is the range of powers tried, and in log/exp it is the inverse of the stepsize taken from -1000 to 1000
|
def optimize_regression(x, y, _range, resolution):#_range in poly regression is the range of powers tried, and in log/exp it is the inverse of the stepsize taken from -1000 to 1000
|
||||||
|
#usage not: for demonstration purpose only, performance is shit
|
||||||
if type(resolution) != int:
|
if type(resolution) != int:
|
||||||
|
|
||||||
raise error("resolution must be int")
|
raise error("resolution must be int")
|
||||||
@ -719,7 +723,27 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
|
|||||||
|
|
||||||
pass
|
pass
|
||||||
|
|
||||||
return [eqs, rmss, r2s]
|
for i in range (0, len(eqs), 1): #marks all equations where r2 = 1 as they 95% of the time overfit the data
|
||||||
|
|
||||||
|
if r2s[i] == 1:
|
||||||
|
|
||||||
|
eqs[i] = ""
|
||||||
|
rmss[i] = ""
|
||||||
|
r2s[i] = ""
|
||||||
|
|
||||||
|
while True: #removes all equations marked for removal
|
||||||
|
|
||||||
|
try:
|
||||||
|
|
||||||
|
eqs.remove('')
|
||||||
|
rmss.remove('')
|
||||||
|
r2s.remove('')
|
||||||
|
|
||||||
|
except:
|
||||||
|
|
||||||
|
break
|
||||||
|
|
||||||
|
return eqs, rmss, r2s
|
||||||
|
|
||||||
def basic_analysis(filepath): #assumes that rows are the independent variable and columns are the dependant. also assumes that time flows from lowest column to highest column.
|
def basic_analysis(filepath): #assumes that rows are the independent variable and columns are the dependant. also assumes that time flows from lowest column to highest column.
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user