# 12 - amount of listening music
# 13 - playing instrument or singing
# 17\18 - mood in VA
# 19\20 - mood color
# 21:40 - preception of 10 labels
# 41:57 - presence of mood
# 58:77 - color perception for 10 lables
# 81 - song id
# 82:101 - induced labels positions
# 102:129 - perceived labels positions
# 130/131 - color for song
# ni 134:136 - HSV for song
# calculate fetures for song in train set
#ids, feat = calc_mfcc_features_dict('audio/full')
feat = read_feature_from_json('features/mfcc_our_dataset_20.json')
X = feature_matrix_by_id(all_ids, feat)
Yv = all_val
Ya = all_aro
# add data to X
#hsv = np.array(read_csv_col('csv/survery2dataMin1.csv', 134, 136))
color = np.array(read_csv_col('csv/survery2dataMin1.csv', 130, 131))
vamood = np.array(read_csv_col('csv/survery2dataMin1.csv', 17, 18))
musicschool = np.array(read_csv_col('csv/survery2dataMin1.csv', 6, 6))
sex = np.array(read_csv_col('csv/survery2dataMin1.csv', 4, 4))
listening = np.array(read_csv_col('csv/survery2dataMin1.csv', 12, 12))
moodcolor = np.array(read_csv_col('csv/survery2dataMin1.csv', 19, 20))
moodperception = np.array(read_csv_col('csv/survery2dataMin1.csv', 21, 40))
presencemood = np.array(read_csv_col('csv/survery2dataMin1.csv', 41, 57))
# 12 - amount of listening music
# 13 - playing instrument or singing
# 17\18 - mood in VA
# 19\20 - mood color
# 21:40 - preception of 10 labels
# 41:57 - presence of mood
# 58:77 - color perception for 10 lables
# 81 - song id
# 82:101 - induced labels positions
# 102:129 - perceived labels positions
# 130/131 - color for song
# ni 134:136 - HSV for song
# calculate fetures for song in train set
#ids, feat = calc_mfcc_features_dict('audio/full')
feat = read_feature_from_json('features/mfcc_our_dataset_20.json')
X = feature_matrix_by_id(all_ids, feat)
Yv = all_val
Ya = all_aro
# add data to X
#hsv = np.array(read_csv_col('csv/survery2dataMin1.csv', 134, 136))
color = np.array(read_csv_col('csv/survery2dataMin1.csv', 130, 131))
vamood = np.array(read_csv_col('csv/survery2dataMin1.csv', 17, 18))
musicschool = np.array(read_csv_col('csv/survery2dataMin1.csv', 6, 6))
sex = np.array(read_csv_col('csv/survery2dataMin1.csv', 4, 4))
listening = np.array(read_csv_col('csv/survery2dataMin1.csv', 12, 12))
moodcolor = np.array(read_csv_col('csv/survery2dataMin1.csv', 19, 20))
moodperception = np.array(read_csv_col('csv/survery2dataMin1.csv', 21, 40))
presencemood = np.array(read_csv_col('csv/survery2dataMin1.csv', 41, 57))
import random
import sys
import numpy as np
from sklearn.tree import DecisionTreeRegressor
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')
va_dict, aro_dict = csv_2_dict_va('csv/survery2dataMin1.csv')
# calculate fetures for song in train set
feat = read_feature_from_json('features/chroma.json')
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))