alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-11-10 06:54:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

analysis.py - v 1.0.6.000

Browse Source 
changelog:
    - added calc_overfit, which calculates two measures of overfit, error and performance
    - added calculating overfit to optimize_regression
This commit is contained in:
ltcptgeneral 2018-11-27 22:45:28 -06:00
parent 367b2fe60d
commit 7c3cc13014
2 changed files with 68 additions and 11 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.

79
data analysis/analysis.py
View File

@ -8,9 +8,12 @@
#setup:
__version__ = "1.0.5.000"
__version__ = "1.0.6.000"
__changelog__ = """changelog:
1.0.6.000:
- added calc_overfit, which calculates two measures of overfit, error and performance
- added calculating overfit to optimize_regression
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)
@ -667,6 +670,24 @@ def rms(predictions, targets): # assumes equal size inputs
return float(out)
def calc_overfit(equation, rms_train, r2_train, x_test, y_test):
#overfit = performance(train) - performance(test) where performance is r^2
#overfir = error(train) - error(test) where error is rms
vals = []
for i in range(0, len(x_test), 1):
z = x_test[i]
exec("vals.append(" + equation + ")")
r2_test = r_squared(vals, y_test)
rms_test = rms(vals, y_test)
return rms_train - rms_test, r2_train - r2_test
def strip_data(data, mode):
if mode == "adam": #x is the row number, y are the data
@ -686,6 +707,30 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
if type(resolution) != int:
raise error("resolution must be int")
x = x
y = y
x_train = []
y_train = []
x_test = []
y_test = []
for i in range (0, math.floor(len(x) * 0.4), 1):
index = random.randint(0, len(x) - 1)
x_test.append(x[index])
y_test.append(y[index])
x.pop(index)
y.pop(index)
x_train = x
y_train = y
#print(x_train, x_test)
#print(y_train, y_test)
eqs = []
@ -695,17 +740,17 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
for i in range (0, _range + 1, 1):
eqs.append(poly_regression(x, y, i)[0])
rmss.append(poly_regression(x, y, i)[1])
r2s.append(poly_regression(x, y, i)[2])
eqs.append(poly_regression(x_train, y_train, i)[0])
rmss.append(poly_regression(x_train, y_train, i)[1])
r2s.append(poly_regression(x_train, y_train, i)[2])
for i in range (1, 100 * resolution + 1):
try:
eqs.append(exp_regression(x, y, float(i / resolution))[0])
rmss.append(exp_regression(x, y, float(i / resolution))[1])
r2s.append(exp_regression(x, y, float(i / resolution))[2])
eqs.append(exp_regression(x_train, y_train, float(i / resolution))[0])
rmss.append(exp_regression(x_train, y_train, float(i / resolution))[1])
r2s.append(exp_regression(x_train, y_train, float(i / resolution))[2])
except:
@ -715,9 +760,9 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
try:
eqs.append(log_regression(x, y, float(i / resolution))[0])
rmss.append(log_regression(x, y, float(i / resolution))[1])
r2s.append(log_regression(x, y, float(i / resolution))[2])
eqs.append(log_regression(x_train, y_train, float(i / resolution))[0])
rmss.append(log_regression(x_train, y_train, float(i / resolution))[1])
r2s.append(log_regression(x_train, y_train, float(i / resolution))[2])
except:
@ -743,7 +788,13 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
break
return eqs, rmss, r2s
overfit = []
for i in range (0, len(eqs), 1):
overfit.append(calc_overfit(eqs[i], rmss[i], r2s[i], x_test, y_test))
return eqs, rmss, r2s, overfit
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.
@ -855,6 +906,12 @@ def debug():
print(exp_regression([1, 2, 3, 4], [2, 4, 8, 16], 2.717))
x, y, z = optimize_regression([0, 1, 2, 3, 4], [1, 2, 4, 7, 19], 10, 100)
for i in range(0, len(x), 1):
print(str(x[i]) + " | " + str(y[i]) + " | " + str(z[i]))
#statistics def below------------------------------------------------------------------------------------------------------------------------------------------------------
class StatisticsError(ValueError):