def f(mi, s, md, r, c):
clf = BoostedTreesClassifier(max_iterations = mi,
step_size = s,
max_depth = md,
row_subsample = r,
column_subsample = c,
verbose = 0)
clf.fit(X[valid_idx], y[valid_idx])
#yhat = clf.predict_proba(X[train_idx])
#return -log_loss(y[train_idx], yhat)
return clf.score(X[train_idx], y[train_idx])
def f(params):
mi = params['mi']
md = params['md']
s = params['s']
r = params['r']
c = params['c']
mi = int(mi)
md = int(md)
clf = BoostedTreesClassifier(max_iterations = mi,
step_size = s,
max_depth = md,
row_subsample = r,
column_subsample = c,
verbose = 0)
clf.fit(X[valid_idx], y[valid_idx])
yhat = clf.predict_proba(X[train_idx])
return log_loss(y[train_idx], yhat)
import numpy as np
import itertools
from scipy.stats import uniform
from scipy.stats import randint
import logging
from ml import *
X, _ = GetDataset('original')
_, y, _ = LoadData()
from gl import BoostedTreesClassifier
clf = BoostedTreesClassifier(verbose = 0)
clf.fit(X[:10], y[:10])
np.random.seed(1)
if False:
Cs = [.001, .01, .1, 1., 10.]
gammas = [.001, .01, .1, 1., 10.]
res = []; i = 0
for (C, gamma) in itertools.product(Cs, gammas):
print i, C, gamma; i += 1
clf = SVC(C = C, gamma = gamma)
clf.fit(X[train], y[train])
res.append(clf.score(X[valid], y[valid]))
res2 = []
for i in xrange(len(res)*100):
C = 10**uniform(-3.5,5).rvs()
gamma = 10**uniform(-3.5,5).rvs()
print i, C, gamma