''' prints out the names of raster files inside the directory ''' from tsraster.prep import image_to_series #file directory path = "../docs/img/temperature/" data = image_to_series(path) print(data.shape)
def calculateFeatures(path,
parameters,
reset_df,
raster_mask=None,
tiff_output=True,
workers=None):
'''
Calculates features or the statistical characteristics of time-series raster data.
It can also save features as a csv file (dataframe) and/or tiff file.
:param path: directory path to the raster files
:param parameters: a dictionary of features to be extracted
:param reset_df: boolean option for existing raster inputs as dataframe
:param raster_mask: path to binary raster mask
:param tiff_output: boolean option for exporting tiff file
:return: extracted features as a dataframe and tiff file
'''
if reset_df == False:
#if reset_df =F read in csv file holding saved version of my_df
my_df = tr.read_my_df(path)
else:
#if reset_df =T calculate ts_series and save csv
my_df = image_to_series(path)
print('df: ' + os.path.join(path, 'my_df.csv'))
my_df.to_csv(os.path.join(path, 'my_df.csv'),
chunksize=10000,
index=False)
# mask
if raster_mask is not None:
my_df = tr.mask_df(raster_mask=raster_mask, original_df=my_df)
if workers is not None:
Distributor = MultiprocessingDistributor(
n_workers=workers,
disable_progressbar=False,
progressbar_title="Feature Extraction")
#Distributor = LocalDaskDistributor(n_workers=workers)
else:
Distributor = None
extracted_features = extract_features(
my_df,
default_fc_parameters=parameters,
column_sort="time",
column_value="value",
column_id="pixel_id",
column_kind="kind",
#chunksize = 1000,
distributor=Distributor)
# change index name to match pixel and time period
extracted_features.index.rename('pixel_id', inplace=True)
extracted_features.reset_index(inplace=True, level=['pixel_id'])
extracted_features['time'] = str(my_df.time.min()) + "_" + str(
my_df.time.max())
extracted_features.set_index(['pixel_id', 'time'], inplace=True)
# unmask extracted features
extracted_features = tr.unmask_from_mask(mask_df_output=extracted_features,
missing_value=-9999,
raster_mask=raster_mask)
# deal with output location
out_path = Path(path).parent.joinpath(Path(path).stem + "_features")
out_path.mkdir(parents=True, exist_ok=True)
# write out features to csv file
print("features:" + os.path.join(out_path, 'extracted_features.csv'))
extracted_features.to_csv(os.path.join(out_path, 'extracted_features.csv'),
chunksize=10000)
# write out feature names
kr = pd.DataFrame(list(extracted_features.columns))
kr.index += 1
kr.index.names = ['band']
kr.columns = ['feature_name']
kr.to_csv(os.path.join(out_path, "features_names.csv"))
# write out features to tiff file
if tiff_output == False:
return extracted_features
else:
# get image dimension from raw data
rows, cols, num = image_to_array(path).shape
# get the total number of features extracted
matrix_features = extracted_features.values
num_of_layers = matrix_features.shape[1]
#reshape the dimension of features extracted
f2Array = matrix_features.reshape(rows, cols, num_of_layers)
output_file = 'extracted_features.tiff'
#Get Meta Data from raw data
raw_data = read_images(path)
GeoTransform = raw_data[0].GetGeoTransform()
driver = gdal.GetDriverByName('GTiff')
noData = -9999
Projection = raw_data[0].GetProjectionRef()
DataType = gdal.GDT_Float32
#export tiff
CreateTiff(output_file,
f2Array,
driver,
noData,
GeoTransform,
Projection,
DataType,
path=out_path)
return extracted_features
#extracted_features.head() #%%Mask a dataframe raster_mask = u"F:/Boundary/StatePoly_buf.tif" original_df = r"F:\3month_features\extracted_features.csv" df_mask = tr.mask_df(raster_mask, original_df) #%% Mask a series raster_mask = u"F:/Boundary/StatePoly_buf.tif" original_series = tr.image_to_series_simple(raster_mask) series_mask = tr.mask_df(raster_mask, original_series) #%% mask a long format dataframe path = r"F://3month/" my_df = tr.image_to_series(path) raster_mask = r"F:/Boundary/StatePoly_buf.tif" long_mask = tr.mask_df(raster_mask, my_df) #%% Test unmask for series # Update the values in the masked dataset to something else, here 10 series_mask.iloc[:] = 10 # unmask and update values of original df print(original_series.iloc[:].value_counts().head(4)) updated_s = tr.unmask_df(original_series, series_mask) print(updated_s.iloc[:, 0].value_counts().head(4)) print(original_series.shape) print(series_mask.shape) print(updated_s.shape) updated_s.head()
''' prints out the names of raster files inside the directory ''' from tsraster.prep import image_to_series #file directory path = "../docs/img/temperature/" series_df = image_to_series(path) print(series_df)
#%% read_images PASS print(tr.read_images(ex_crs)) print(tr.read_images(ex_ts)) tr.read_images(ex_single) #%% image_to_array PASS print(tr.image_to_array(ex_crs).shape) print(tr.image_to_array(ex_ts).shape) print(tr.image_to_array(ex_single).shape) #%% image_to_series PASS print(tr.image_to_series(ex_crs).head()) print( tr.image_to_series(ex_ts).head()) print( tr.image_to_series(ex_single).head()) #%% image_to_series for target data (PASS) print(tr.image_to_series(tg_crs).head()) print( tr.image_to_series(tg_ts).head()) print( tr.image_to_series(tg_single).head()) #%% mask unmask PASS I think mk_ex_crs might have too many observations, but can't figure out how df_ex_crs = tr.image_to_series(ex_crs) df_ex_ts = tr.image_to_series(ex_ts)