def process_data(info, features=['r', 'g', 'b', 'h', 's', 'v', 'fft_std', 'fft_max']):
'''
processes images listed in a given info object into usable data
Args:
info (DataFrame):
info object containing 'source', 'label' and 'params' columns
features opt(list):
list of features to include in the ouput data
default: ['r', 'g', 'b', 'h', 's', 'v', 'fft_std', 'fft_max']
Returns:
DataFrame: processed image data
'''
# create data from info
data = info.copy()
data.reset_index(drop=True, inplace=True)
data = data[['source', 'label', 'params']]
err = data.source.tolist()
data.source = data.source.apply(lambda x: PIL.Image.open(x))
data = data.apply(lambda x:
generate_samples(x['source'], x['label'], x['params']),
axis=1
)
# create new expanded dataframe
data = list(chain(*data.tolist()))
data = DataFrame(data, columns=['x', 'y', 'params'])
data['bgr'] = data.x.apply(pil_to_opencv)
del data['x']
# create feature lists
rgb = filter(lambda x: x in list('rgb'), features)
hsv = filter(lambda x: x in list('hsv'), features)
fft = filter(lambda x: x in ['fft_std', 'fft_max'], features)
# rgb distributions
if rgb:
temp = data[['bgr', 'params']].apply(lambda x: (x['bgr'], x['params']), axis=1)
for chan in rgb:
chan_data = temp.apply(lambda x: get_channel_histogram(x[0], chan, **x[1]))
# data[chan] = chan_data.apply(lambda x: x.tolist())
create_histogram_stats(data, chan_data, chan)
# hsv distributions
if hsv:
try:
data['hsv'] = data.bgr.apply(lambda x: cv2.cvtColor(x, cv2.COLOR_BGR2HSV))
except:
print(err)
raise SyntaxError
temp = data[['hsv', 'params']].apply(lambda x: (x['hsv'], x['params']), axis=1)
for chan in hsv:
chan_data = temp.apply(lambda x: get_channel_histogram(x[0], chan, **x[1]))
# data[chan] = chan_data.apply(lambda x: x.tolist())
create_histogram_stats(data, chan_data, chan)
del data['hsv']
# grain frequency
if fft:
data['gray'] = data.bgr.apply(lambda x: cv2.cvtColor(x, cv2.COLOR_BGR2GRAY))
data.gray = data.gray.apply(lambda x: np.fft.hfft(x).astype(float))
data.gray = data.gray.apply(lambda x: np.histogram(x.ravel(), bins=256)[0])
if 'fft_std' in fft:
data['fft_std'] = data.gray.apply(lambda x: x.std())
if 'fft_max' in fft:
data['fft_max'] = data.gray.apply(lambda x: x.max())
del data['gray']
del data['bgr']
del data['params']
# shuffle data to destroy serial correlations
index = data.index.tolist()
np.random.shuffle(index)
data = data.ix[index]
data.reset_index(drop=True, inplace=True)
# Normalize features
cols = data.drop('y', axis=1).columns.tolist()
ss = StandardScaler()
data[cols] = ss.fit_transform(data[cols])
return data
