dataset = np.load(inputfile)
print("dataset..", dataset.shape)
dataset = dataset[:54663, 1, :] ##700 pressure
print("700 pressure dataset..", dataset.shape)
sys.path.insert(1, '../final_eval/')
os.chdir("../final_eval")
from Dataset_transformations import Dataset_transformations
from Clustering import Clustering
from netcdf_subset import netCDF_subset
import dataset_utils as utils
print(os.getcwd())
sys.path.insert(1, '../wrfhy/wrfvol/')
os.chdir("../wrfhy/wrfvol/")
export_template = netCDF_subset('40years.nc', [700], ['GHT'],
lvlname='num_metgrid_levels',
timename='Times')
sys.path.insert(1, '../../final_eval/')
os.chdir("../../final_eval/")
ds = Dataset_transformations(dataset, 1000, dataset.shape)
print ds._items.shape
# times = export_template.get_times()
# nvarin = []
# for var in export_template.get_times():
# if var[0] != 'masked':
# str=''
# for v in var:
# str += v
# # print(str)
ds = Dataset_transformations(data.T, 1000, data.shape)
if os.path.exists(PREFIX+CONFIG_NAME+'.zip'):
clust_obj = dataset_utils.load_single(PREFIX+CONFIG_NAME+'.zip')
else:
print 'Doing kmeans.....'
clust_obj = Clustering(ds,n_clusters=15,n_init=100,features_first=False)
clust_obj.batch_kmeans(10)
print 'Saving .....'
clust_obj.save(PREFIX+CONFIG_NAME+'.zip')
# Descriptor num_min: 1
num_min = 1
times_pos = closest(clust_obj._link, ds._items, num_min, win=4, t=8, save=False)
np.save(PREFIX+'time_pos_desc'+str(num_min)+'.npy', times_pos)
ns = netCDF_subset(NC_PATH, [500, 700, 900], ['GHT'], timename='Times')
desc_date(clust_obj, ns, times_pos)
clust_obj.save(PREFIX+CONFIG_NAME+'_'+str(num_min)+'.zip')
for c, i in enumerate(times_pos):
if not os.path.exists(PREFIX+'descriptors1/'):
os.mkdir(PREFIX+'descriptors1/')
name = PREFIX+'descriptors1/desc_'+str(c)+'.nc'
ns.exact_copy_file(name, i[0])
# Descriptor num_min: 10
num_min = 10
times_pos = closest(clust_obj._link, ds._items, num_min, win=4, t=8, save=False)
np.save(PREFIX+'time_pos_desc'+str(num_min)+'.npy', times_pos)
ns = netCDF_subset(NC_PATH, [500, 700, 900], ['GHT'], timename='Times')
PREFIX = "PCA_INV_SEED_16"
NC_PATH = '/mnt/disk1/thanasis/data/11_train.nc'
if __name__ == '__main__':
parser = ArgumentParser(description='Extract variables from netcdf file')
parser.add_argument('-i',
'--input',
required=True,
type=str,
help='input file')
parser.add_argument('-o', '--output', type=str, help='output file')
opts = parser.parse_args()
getter = attrgetter('input', 'output')
inp, outp = getter(opts)
export_template = netCDF_subset(NC_PATH, [700], ['GHT'],
lvlname='num_metgrid_levels',
timename='Times')
pca = PCA(n_components=16)
items = np.load(inp)
X = pca.fit_transform(items.T).T
print 'hello'
print X.shape
pcared = PCA(n_components=16)
seed = pcared.fit_transform(X)
print seed.shape
pcared2 = PCA(n_components=16)
items = pcared2.fit_transform(items)
print items.shape
ds = Dataset_transformations(items, 1000)
print ds._items.shape
times = export_template.get_times()