def n_deriv(vals):
evals = extend_vals(vals)
if type(vals) != type(coeffs) or len(evals) != len(coeffs):
print("Error in list sizes. Vals {} // Coeffs {}".format(evals, coeffs))
raise IndexError
prod = dot(evals, coeffs)
deriv = -logistic_func(vals)**2 * (-evals[n] * math.exp(-prod))
return deriv
stdpts = stdpts_with_stats["points"]
stats = stdpts_with_stats["stats"]
print("Standardized points: {} // stats {}".format(stdpts, stats))
params = (0.1, 0.1, 0.1, 0.1)
log_func = logistic_function(params)
print("Cost 1: {}".format(non_regularized_cost(log_func, stdpts)))
final_func = regularized_logistic_regression_bounded(log_func, 0.1, 0.000001,
10, stdpts, 0.01)
print(list(final_func["params"]))
print("Output values: {}".format([((x, y), final_func["func"](x))
for x, y in stdpts]))
print("Vals {} // Coeffs{} // Dot: {}".format(
extend_vals(pts[0][0]), final_func["params"],
dot(extend_vals(pts[0][0]), final_func["params"])))
final_func = logistic_regression_bounded(log_func, 0.1, 0.000001, 10, stdpts)
print(list(final_func["params"]))
print("Output values: {}".format([((x, y), final_func["func"](x))
for x, y in stdpts]))
print("Vals {} // Coeffs{} // Dot: {}".format(
extend_vals(pts[0][0]), final_func["params"],
dot(extend_vals(pts[0][0]), final_func["params"])))
def n_deriv(vals):
return extend_vals(vals)[n]
def generated(vals):
vals = extend_vals(vals)
if len(vals) != len(coeffs):
raise IndexError
return sum(c*v for (c, v) in zip(coeffs, vals))
def generated(vals):
vals = extend_vals(vals)
if len(vals) != len(coeffs):
raise IndexError
prod = dot(vals, coeffs)
return 1/(1 + math.exp(-prod))