alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-26 17:49:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

analysis.py - v 1.0.5.000

Browse Source 
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:
ltcptgeneral 2018-11-27 19:56:16 -06:00
parent 07a381b01b
commit 367b2fe60d
2 changed files with 27 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
data analysis/__pycache__/analysis.cpython-37.pyc
View File

Binary file not shown.

30
data analysis/analysis.py
View File

@ -8,9 +8,13 @@
#setup:
__version__ = "1.0.4.001"
__version__ = "1.0.5.000"
__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:
- added __changelog__
- updated debug function with log and exponential regressions
@ -678,7 +682,7 @@ def strip_data(data, mode):
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
#usage not: for demonstration purpose only, performance is shit
if type(resolution) != int:
raise error("resolution must be int")
@ -719,7 +723,27 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
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.