def csvfile_to_dataframe(input_file, date_format='%Y%j'):
""" Return sorted filenames of images from input text file
Args:
input_file (str): text file of dates and files
date_format (str): format of dates in file
Returns:
pd.DataFrame: pd.DataFrame of dates, sensor IDs, and filenames
"""
df = pd.read_csv(input_file)
# Guess and convert date field
date_col = [i for i, n in enumerate(df.columns) if 'date' in n.lower()]
if not date_col:
raise KeyError('Could not find date column in input file')
if len(date_col) > 1:
logger.warning('Multiple date columns found in input CSV file. '
'Using %s' % df.columns[date_col[0]])
date_col = df.columns[date_col[0]]
df[date_col] = pd.to_datetime(
df[date_col], format=date_format).map(lambda x: dt.toordinal(x))
return df
def csvfile_to_dataframe(input_file, date_format='%Y%j'):
""" Return sorted filenames of images from input text file
Args:
input_file (str): text file of dates and files
date_format (str): format of dates in file
Returns:
pd.DataFrame: pd.DataFrame of dates, sensor IDs, and filenames
"""
df = pd.read_csv(input_file)
# Guess and convert date field
date_col = [i for i, n in enumerate(df.columns) if 'date' in n.lower()]
if not date_col:
raise KeyError('Could not find date column in input file')
if len(date_col) > 1:
logger.warning('Multiple date columns found in input CSV file. '
'Using %s' % df.columns[date_col[0]])
date_col = df.columns[date_col[0]]
df[date_col] = pd.to_datetime(
df[date_col], format=date_format).map(lambda x: dt.toordinal(x))
return df
def read_cache_file(cache_filename, image_IDs=None):
""" Returns image data from a cache file
If `image_IDs` is not None this function will try to ensure data from cache
file come from the list of image IDs provided. If cache file does not
contain a list of image IDs, it will skip the check and return cache data.
Args:
cache_filename (str): cache filename
image_IDs (iterable, optional): list of image IDs corresponding to data
in cache file. If not specified, function will not check for
correspondence (default: None)
Returns:
np.ndarray, or None: Return Y as np.ndarray if possible and if the
cache file passes the consistency check specified by `image_IDs`; else
None
"""
try:
cache = np.load(cache_filename)
except IOError:
return None
if _image_ID_str in cache.files and image_IDs is not None:
if not np.array_equal(image_IDs, cache[_image_ID_str]):
logger.warning('Cache file data in {f} do not match images '
'specified'.format(f=cache_filename))
return None
return cache['Y']
def read_cache_file(cache_filename, image_IDs=None):
""" Returns image data from a cache file
If ``image_IDs`` is not None this function will try to ensure data from
cache file come from the list of image IDs provided. If cache file does not
contain a list of image IDs, it will skip the check and return cache data.
Args:
cache_filename (str): cache filename
image_IDs (iterable, optional): list of image IDs corresponding to data
in cache file. If not specified, function will not check for
correspondence (default: None)
Returns:
np.ndarray, or None: Return Y as np.ndarray if possible and if the
cache file passes the consistency check specified by ``image_IDs``,
else None
"""
try:
cache = np.load(cache_filename)
except IOError:
return None
if _image_ID_str in cache.files and image_IDs is not None:
if not np.array_equal(image_IDs, cache[_image_ID_str]):
logger.warning('Cache file data in {f} do not match images '
'specified'.format(f=cache_filename))
return None
return cache['Y']
def test_cache(dataset_config):
""" Test cache directory for ability to read from or write to
Args:
dataset_config (dict): dictionary of dataset configuration options
Returns:
(read_cache, write_cache): tuple of bools describing ability to read from
and write to cache directory
"""
# Try to find / use cache
read_cache = False
write_cache = False
cache_dir = dataset_config.get('cache_line_dir')
if cache_dir:
# Test existence
if os.path.isdir(cache_dir):
if os.access(cache_dir, os.R_OK):
read_cache = True
if os.access(cache_dir, os.W_OK):
write_cache = True
if read_cache and not write_cache:
logger.warning('Cache directory exists but is not writable')
else:
# If it doesn't already exist, can we create it?
try:
os.makedirs(cache_dir)
except:
logger.warning('Could not create cache directory')
else:
read_cache = True
write_cache = True
logger.debug(
'Attempt reading in from cache directory?: {b}'.format(b=read_cache))
logger.debug(
'Attempt writing to cache directory?: {b}'.format(b=write_cache))
return read_cache, write_cache
def test_cache(dataset_config):
""" Test cache directory for ability to read from or write to
Args:
dataset_config (dict): dictionary of dataset configuration options
Returns:
tuple: tuple of bools describing ability to read from and write to
cache directory
"""
# Try to find / use cache
read_cache = False
write_cache = False
cache_dir = dataset_config.get('cache_line_dir')
if cache_dir:
# Test existence
if os.path.isdir(cache_dir):
if os.access(cache_dir, os.R_OK):
read_cache = True
if os.access(cache_dir, os.W_OK):
write_cache = True
if read_cache and not write_cache:
logger.warning('Cache directory exists but is not writable')
else:
# If it doesn't already exist, can we create it?
try:
os.makedirs(cache_dir)
except:
logger.warning('Could not create cache directory')
else:
read_cache = True
write_cache = True
logger.debug('Attempt reading in from cache directory?: {b}'.format(
b=read_cache))
logger.debug('Attempt writing to cache directory?: {b}'.format(
b=write_cache))
return read_cache, write_cache
def parse_config_file(config_file):
""" Parses config file into dictionary of attributes """
config = configparser.ConfigParser(allow_no_value=True)
config.readfp(StringIO.StringIO(defaults))
config.read(config_file)
version = config.get('metadata', 'version')
# Warn on difference in minor or major version
mm_config_version = version.split('.')[0:2]
mm_yatsm_version = __version__.split('.')[0:2]
if mm_config_version[0] != mm_yatsm_version[0] or \
mm_config_version[1] != mm_yatsm_version[1]:
logger.warning('Config file version does not match YATSM version')
logger.warning(' config file: v{v}'.format(v=version))
logger.warning(' YATSM: v{v}'.format(v=__version__))
dataset_config = {}
yatsm_config = {}
dataset_config.update(parse_dataset_config(config))
yatsm_config.update(parse_algorithm_config(config))
yatsm_config.update(parse_phenology_config(config))
dataset_config.update(parse_classification_config(config))
return (dataset_config, yatsm_config)
def parse_config_file(config_file):
""" Parses config file into dictionary of attributes """
config = configparser.ConfigParser(allow_no_value=True)
config.readfp(StringIO.StringIO(defaults))
config.read(config_file)
version = config.get('metadata', 'version')
# Warn on difference in minor or major version
mm_config_version = version.split('.')[0:2]
mm_yatsm_version = __version__.split('.')[0:2]
if mm_config_version[0] != mm_yatsm_version[0] or \
mm_config_version[1] != mm_yatsm_version[1]:
logger.warning('Config file version does not match YATSM version')
logger.warning(' config file: v{v}'.format(v=version))
logger.warning(' YATSM: v{v}'.format(v=__version__))
dataset_config = {}
yatsm_config = {}
dataset_config.update(parse_dataset_config(config))
yatsm_config.update(parse_algorithm_config(config))
yatsm_config.update(parse_phenology_config(config))
dataset_config.update(parse_classification_config(config))
return (dataset_config, yatsm_config)
def iter_records(records, warn_on_empty=False, yield_filename=False):
""" Iterates over records, returning result NumPy array
Args:
records (list): List containing filenames of results
warn_on_empty (bool, optional): Log warning if result contained no
result records (default: False)
yield_filename (bool, optional): Yield the filename and the record
Yields:
np.ndarray or tuple: Result saved in record and the filename, if desired
"""
n_records = len(records)
for _i, r in enumerate(records):
# Verbose progress
if np.mod(_i, 100) == 0:
logger.debug('{0:.1f}%'.format(_i / n_records * 100))
# Open output
try:
rec = np.load(r)['record']
except (ValueError, AssertionError, IOError) as e:
logger.warning('Error reading a result file (may be corrupted) '
'({}): {}'.format(r, str(e)))
continue
if rec.shape[0] == 0:
# No values in this file
if warn_on_empty:
logger.warning('Could not find results in {f}'.format(f=r))
continue
if yield_filename:
yield rec, r
else:
yield rec
def iter_records(records, warn_on_empty=False, yield_filename=False):
""" Iterates over records, returning result NumPy array
Args:
records (list): List containing filenames of results
warn_on_empty (bool, optional): Log warning if result contained no
result records (default: False)
yield_filename (bool, optional): Yield the filename and the record
Yields:
np.ndarray or tuple: Result saved in record and the filename, if desired
"""
n_records = len(records)
for _i, r in enumerate(records):
# Verbose progress
if np.mod(_i, 100) == 0:
logger.debug('{0:.1f}%'.format(_i / n_records * 100))
# Open output
try:
rec = np.load(r)['record']
except (ValueError, AssertionError, IOError) as e:
logger.warning('Error reading a result file (may be corrupted) '
'({}): {}'.format(r, str(e)))
continue
if rec.shape[0] == 0:
# No values in this file
if warn_on_empty:
logger.warning('Could not find results in {f}'.format(f=r))
continue
if yield_filename:
yield rec, r
else:
yield rec
def update_cache_file(images,
image_IDs,
old_cache_filename,
new_cache_filename,
line,
reader,
reader_kwargs={}):
""" Modify an existing cache file to contain data within `images`
This should be useful for updating a set of cache files to reflect
modifications to the timeseries dataset without completely reading the
data into another cache file.
For example, the cache file could be updated to reflect the deletion of
a misregistered or cloudy image. Another common example would be for
updating cache files to include newly acquired observations.
Note that this updater will not handle updating cache files to include
new bands.
Args:
images (iterable): list of new image filenames
image_IDs (iterable): list of new image identifying strings
old_cache_filename (str): filename of cache file to update
new_cache_filename (str): filename of new cache file which includes
modified data
line (int): the line of data to be updated
reader (callable): GDAL or BIP image reader function from `yatsm.readers`
reader_kwargs (dict): additional keyword arguments for `reader` other
than the filenames to read and the line to read
Raises:
ValueError: Raise error if old cache file does not record `image_IDs`
"""
images = np.asarray(images)
image_IDs = np.asarray(image_IDs)
# Cannot proceed if old cache file doesn't store filenames
old_cache = np.load(old_cache_filename)
if _image_ID_str not in old_cache.files:
raise ValueError('Cannot update cache.'
'Old cache file does not store image IDs.')
old_IDs = old_cache[_image_ID_str]
old_Y = old_cache['Y']
nband, _, ncol = old_Y.shape
# Create new Y and add in values retained from old cache
new_Y = np.zeros((nband, image_IDs.size, ncol), dtype=old_Y.dtype.type)
new_IDs = np.zeros(image_IDs.size, dtype=image_IDs.dtype)
# Check deletions -- find which indices to retain in new cache
retain_old = np.where(np.in1d(old_IDs, image_IDs))[0]
if retain_old.size == 0:
logger.warning('No image IDs in common in old cache file.')
else:
logger.debug(' retaining {r} of {n} images'.format(
r=retain_old.size, n=old_IDs.size))
# Find indices of old data to insert into new data
idx_old_IDs = np.argsort(old_IDs)
sorted_old_IDs = old_IDs[idx_old_IDs]
idx_IDs = np.searchsorted(sorted_old_IDs,
image_IDs[np.in1d(image_IDs, old_IDs)])
retain_old = idx_old_IDs[idx_IDs]
# Indices to insert into new data
retain_new = np.where(np.in1d(image_IDs, old_IDs))[0]
new_Y[:, retain_new, :] = old_Y[:, retain_old, :]
new_IDs[retain_new] = old_IDs[retain_old]
# Check additions -- find which indices we need to insert
insert = np.where(np.in1d(image_IDs, old_IDs) == False)[0]
if retain_old.size == 0 and insert.size == 0:
raise ValueError('Cannot update cache file -- '
'no data retained or added')
# Read in the remaining data from disk
if insert.size > 0:
logger.debug(
'Inserting {n} new images into cache'.format(n=insert.size))
insert_Y = reader(images[insert], line, **reader_kwargs)
new_Y[:, insert, :] = insert_Y
new_IDs[insert] = image_IDs[insert]
np.testing.assert_equal(new_IDs, image_IDs)
# Save
write_cache_file(new_cache_filename, new_Y, image_IDs)
def update_cache_file(images, image_IDs,
old_cache_filename, new_cache_filename,
line, reader):
""" Modify an existing cache file to contain data within `images`
This should be useful for updating a set of cache files to reflect
modifications to the timeseries dataset without completely reading the
data into another cache file.
For example, the cache file could be updated to reflect the deletion of
a misregistered or cloudy image. Another common example would be for
updating cache files to include newly acquired observations.
Note that this updater will not handle updating cache files to include
new bands.
Args:
images (iterable): list of new image filenames
image_IDs (iterable): list of new image identifying strings
old_cache_filename (str): filename of cache file to update
new_cache_filename (str): filename of new cache file which includes
modified data
line (int): the line of data to be updated
reader (callable): GDAL or BIP image reader function from
:mod:`yatsm.io.stack_line_readers`
Raises:
ValueError: Raise error if old cache file does not record ``image_IDs``
"""
images = np.asarray(images)
image_IDs = np.asarray(image_IDs)
# Cannot proceed if old cache file doesn't store filenames
old_cache = np.load(old_cache_filename)
if _image_ID_str not in old_cache.files:
raise ValueError('Cannot update cache.'
'Old cache file does not store image IDs.')
old_IDs = old_cache[_image_ID_str]
old_Y = old_cache['Y']
nband, _, ncol = old_Y.shape
# Create new Y and add in values retained from old cache
new_Y = np.zeros((nband, image_IDs.size, ncol),
dtype=old_Y.dtype.type)
new_IDs = np.zeros(image_IDs.size, dtype=image_IDs.dtype)
# Check deletions -- find which indices to retain in new cache
retain_old = np.where(np.in1d(old_IDs, image_IDs))[0]
if retain_old.size == 0:
logger.warning('No image IDs in common in old cache file.')
else:
logger.debug(' retaining {r} of {n} images'.format(
r=retain_old.size, n=old_IDs.size))
# Find indices of old data to insert into new data
idx_old_IDs = np.argsort(old_IDs)
sorted_old_IDs = old_IDs[idx_old_IDs]
idx_IDs = np.searchsorted(sorted_old_IDs,
image_IDs[np.in1d(image_IDs, old_IDs)])
retain_old = idx_old_IDs[idx_IDs]
# Indices to insert into new data
retain_new = np.where(np.in1d(image_IDs, old_IDs))[0]
new_Y[:, retain_new, :] = old_Y[:, retain_old, :]
new_IDs[retain_new] = old_IDs[retain_old]
# Check additions -- find which indices we need to insert
insert = np.where(np.in1d(image_IDs, old_IDs, invert=True))[0]
if retain_old.size == 0 and insert.size == 0:
raise ValueError('Cannot update cache file -- '
'no data retained or added')
# Read in the remaining data from disk
if insert.size > 0:
logger.debug('Inserting {n} new images into cache'.format(
n=insert.size))
insert_Y = reader.read_row(images[insert], line)
new_Y[:, insert, :] = insert_Y
new_IDs[insert] = image_IDs[insert]
np.testing.assert_equal(new_IDs, image_IDs)
# Save
write_cache_file(new_cache_filename, new_Y, image_IDs)
