r_dict, g_dict, b_dict = csv_2_dict_rgb('csv/surveydatahsv.csv') # calculate fetures for song in train set X = np.column_stack((va, aro)) Yr = r Yg = g Yb = b best_avg = sys.maxint best_r = sys.maxint best_g = sys.maxint best_b = sys.maxint for i in range(100): X, Yr, Yg, Yb, ids = shufle_same(X, Yr, Yg, Yb, ids) trainlen = int(len(Yr) * 0.7) Xtrain = X[1:trainlen] Yrtrain = Yr[1:trainlen] Ygtrain = Yg[1:trainlen] Ybtrain = Yb[1:trainlen] Xtest = X[trainlen + 1:] Yrtest = Yr[trainlen + 1:] Ygtest = Yg[trainlen + 1:] Ybtest = Yb[trainlen + 1:] idstest = ids[trainlen + 1:] rr = regression_one(Xtrain, Yrtrain)
# print X best_avg = sys.maxint best_near = sys.maxint best_std = sys.maxint best_val = sys.maxint best_aro = sys.maxint print "check 3" print X.shape print len(Yv) print len(Ya) for i in range(50): X, Yv, Ya, all_ids = shufle_same(X, Yv, Ya, all_ids) print "check 4" print X.shape print len(Yv) print len(Ya) trainlen = int(len(Yv) * 0.7) Xtrain = X[1:trainlen] Yvtrain = Yv[1:trainlen] Yatrain = Ya[1:trainlen] Xtest = X[trainlen + 1:] Yvtest = Yv[trainlen + 1:] Yatest = Ya[trainlen + 1:]
print "check 3" print X.shape print len(Yv) print len(Ya) best_avg = sys.maxint best_near = sys.maxint best_std = sys.maxint best_val = sys.maxint best_aro = sys.maxint for j in range(1, 2): for i in range(200): X, Yv, Ya, all_ids = shufle_same(X, Yv, Ya, all_ids) # print "check 4" # print X.shape # print len(Yv) # print len(Ya) trainlen = int(len(Yv) * 0.7) Xtrain = X[1:trainlen] Yvtrain = Yv[1:trainlen] Yatrain = Ya[1:trainlen] Xtest = X[trainlen+1:] Yvtest = Yv[trainlen+1:] Yatest = Ya[trainlen+1:]
h_dict, s_dict, v_dict = csv_2_dict_hsv('csv/surveydatahsv.csv') # calculate fetures for song in train set X = np.column_stack((va,aro)) Yh = h Ys = s Yv = v best_avg = sys.maxint best_h = sys.maxint best_s = sys.maxint best_v = sys.maxint for i in range(100): X, Yh, Ys, Yv, ids = shufle_same(X, Yh, Ys, Yv, ids) trainlen = int(len(Yh) * 0.7) Xtrain = X[1:trainlen] Yhtrain = Yh[1:trainlen] Ystrain = Ys[1:trainlen] Yvtrain = Yv[1:trainlen] Xtest = X[trainlen+1:] Yhtest = Yh[trainlen+1:] Ystest = Ys[trainlen+1:] Yvtest = Yv[trainlen+1:] idstest = ids[trainlen+1:]
from utils.cross_validation import cross_valid ''' regression tree for each response ''' # get exsisting valence and arousal data ids, va, aro, rows = seperate_va('csv/survery2dataMin1.csv') while 101 in ids: id101 = ids.index(101) ids[id101:(id101+1)] = [] va[id101:(id101+1)] = [] aro[id101:(id101+1)] = [] va_dict, aro_dict = csv_2_dict_va('csv/survery2dataMin1.csv') # calculate fetures for song in train set no, feat = read_fake_chroma('features/fakechroma') X = feature_matrix_by_id(ids, feat) Yva = va Yaro = aro #for i in range(100): X, Yva, Yaro, ids = shufle_same(X, Yva, Yaro, ids) print 'v: ' + str(cross_valid(10, X, Yva, ids, va_dict)) print 'A: ' + str(cross_valid(10, X, Yaro, ids, aro_dict))
h_dict, s_dict, v_dict = csv_2_dict_hsv('csv/surveydatahsv.csv') # calculate fetures for song in train set X = np.column_stack((va, aro)) Yh = h Ys = s Yv = v best_avg = sys.maxint best_h = sys.maxint best_s = sys.maxint best_v = sys.maxint for i in range(100): X, Yh, Ys, Yv, ids = shufle_same(X, Yh, Ys, Yv, ids) trainlen = int(len(Yh) * 0.7) Xtrain = X[1:trainlen] Yhtrain = Yh[1:trainlen] Ystrain = Ys[1:trainlen] Yvtrain = Yv[1:trainlen] Xtest = X[trainlen + 1:] Yhtest = Yh[trainlen + 1:] Ystest = Ys[trainlen + 1:] Yvtest = Yv[trainlen + 1:] idstest = ids[trainlen + 1:] rh = regression_one(Xtrain, Yhtrain)
ids, va, aro, h, s, v= uniform_va_hsv('csv/surveydatahsv.csv') va_dict, aro_dict = csv_2_dict_va('csv/survery2dataMin1.csv') # calculate fetures for song in train set X = np.column_stack((h,s,v)) Yva = va Yaro = aro best_avg = sys.maxint best_aro = sys.maxint best_va = sys.maxint for i in range(100): X, Yva, Yaro, ids = shufle_same(X, Yva, Yaro, ids) trainlen = int(len(Yaro) * 0.7) Xtrain = X[1:trainlen] Yvatrain = Yva[1:trainlen] Yarotrain = Yaro[1:trainlen] Xtest = X[trainlen+1:] Yvatest = Yva[trainlen+1:] Yarotest = Yaro[trainlen+1:] idstest = ids[trainlen+1:] rva = regression_one(Xtrain, Yvatrain) raro = regression_one(Xtrain, Yarotrain)
r_dict, g_dict, b_dict = csv_2_dict_rgb('csv/surveydatahsv.csv') # calculate fetures for song in train set X = np.column_stack((va,aro)) Yr = r Yg = g Yb = b best_avg = sys.maxint best_r = sys.maxint best_g = sys.maxint best_b = sys.maxint for i in range(100): X, Yr, Yg, Yb, ids = shufle_same(X, Yr, Yg, Yb, ids) trainlen = int(len(Yr) * 0.7) Xtrain = X[1:trainlen] Yrtrain = Yr[1:trainlen] Ygtrain = Yg[1:trainlen] Ybtrain = Yb[1:trainlen] Xtest = X[trainlen+1:] Yrtest = Yr[trainlen+1:] Ygtest = Yg[trainlen+1:] Ybtest = Yb[trainlen+1:] idstest = ids[trainlen+1:] rr = regression_one(Xtrain, Yrtrain)