#2011 #0.1 percent sample data #train train11 = functions.read_class( tabular_data=file_train11_dbf, gt_array_file='/Volumes/ga87rif/Study Project/Samples/A_train11.npy') #test test11 = functions.read_class( tabular_data=file_test11_dbf, gt_array_file='/Volumes/ga87rif/Study Project/Samples/A_test11.npy') #----------------------------------------------------------------------------------------------- #read raster values and combine them into train_array #2009 b1_09_ar = functions.extract_values(shp=file_train09_shp, raster=b1_09) b2_09_ar = functions.extract_values(shp=file_train09_shp, raster=b2_09) b3_09_ar = functions.extract_values(shp=file_train09_shp, raster=b3_09) b4_09_ar = functions.extract_values(shp=file_train09_shp, raster=b4_09) b5_09_ar = functions.extract_values(shp=file_train09_shp, raster=b5_09) b7_09_ar = functions.extract_values(shp=file_train09_shp, raster=b7_09) ndvi_09_ar = functions.extract_values(shp=file_train09_shp, raster=ndvi_09) train_array_09 = functions.combine_bands( b1=b1_09_ar, b2=b2_09_ar, b3=b3_09_ar, b4=b4_09_ar, b5=b5_09_ar, b7=b7_09_ar, ndvi=ndvi_09_ar,
ndbi_11 = 'L2 imagery/2011/ndbi.tif' mndbi_11 = 'L2 imagery/2011/mndbi.tif' """ locate the test shapefiles """ file_train09_shp = 'Samples/SLC off/2percent/s09train.shp' file_train11_shp = 'Samples/SLC off/2percent/s11train.shp' file_test09_shp = 'Samples/SLC off/2percent/s09test.shp' file_test11_shp = 'Samples/SLC off/2percent/s11test.shp' #----------------------------------------------------------------------------------------------- #read raster values and combine them into train_array (test datasets) #2009 b1_09_t = functions.extract_values(shp = file_test09_shp, raster = b1_09) b2_09_t = functions.extract_values(shp = file_test09_shp, raster = b2_09) b3_09_t = functions.extract_values(shp = file_test09_shp, raster = b3_09) b4_09_t = functions.extract_values(shp = file_test09_shp, raster = b4_09) b5_09_t = functions.extract_values(shp = file_test09_shp, raster = b5_09) b7_09_t = functions.extract_values(shp = file_test09_shp, raster = b7_09) ndvi_09_t = functions.extract_values(shp = file_test09_shp, raster = ndvi_09) ndwi_09_t = functions.extract_values(shp = file_test09_shp, raster = ndwi_09) mndwi1_09_t = functions.extract_values(shp = file_test09_shp, raster = mndwi1_09) mndwi2_09_t = functions.extract_values(shp = file_test09_shp, raster = mndwi2_09) ndbi_09_t = functions.extract_values(shp = file_test09_shp, raster = ndbi_09) mndbi_09_t = functions.extract_values(shp = file_test09_shp, raster = mndbi_09) test_09 = functions.combine_bands_sf(b1 = b1_09_t, b2 = b2_09_t, b3 = b3_09_t, b4 = b4_09_t, b5 = b5_09_t, b7 = b7_09_t, ndvi = ndvi_09_t, ndwi = ndwi_09_t, mndwi1 = mndwi1_09_t, mndwi2 = mndwi2_09_t, ndbi = ndbi_09_t, mndbi = mndbi_09_t,
#!/usr/bin/python # # hack@uchicago Introduction to Python Workshop # Borja Sotomayor, 2013-2014 """ Prints out the ten most-frequent values for the "favorite_count" and "retweet_count" fields in a tweet dataset """ import workshop import operator import sys # For this script to run, you need to implement the extract_values # and compute_frequencies values in exercise_functions.py from functions import extract_values, compute_frequencies tfile = sys.argv[1] n = int(sys.argv[2]) for field in ["favorite_count", "retweet_count"]: print "Top 10 frequencies of %s" % field l = extract_values(tfile, n, field) freqs = compute_frequencies(l) freqs = freqs.items() freqs.sort(key=operator.itemgetter(1), reverse=True) for value, count in freqs[:10]: print value, count print
gt_array_file='Samples/SLC off/B_test09.npy') #2011 #0.1 percent sample data #train train11 = functions.read_class(tabular_data=file_train11_dbf, gt_array_file='Samples/SLC off/B_train11.npy') #test test11 = functions.read_class(tabular_data=file_test11_dbf, gt_array_file='Samples/SLC off/B_test11.npy') #----------------------------------------------------------------------------------------------- #read raster values and combine them into train_array (training datasets) #2009 b1_09_ar = functions.extract_values(shp=file_train09_shp, raster=b1_09) b2_09_ar = functions.extract_values(shp=file_train09_shp, raster=b2_09) b3_09_ar = functions.extract_values(shp=file_train09_shp, raster=b3_09) b4_09_ar = functions.extract_values(shp=file_train09_shp, raster=b4_09) b5_09_ar = functions.extract_values(shp=file_train09_shp, raster=b5_09) b7_09_ar = functions.extract_values(shp=file_train09_shp, raster=b7_09) ndvi_09_ar = functions.extract_values(shp=file_train09_shp, raster=ndvi_09) train_array_09 = functions.combine_bands( b1=b1_09_ar, b2=b2_09_ar, b3=b3_09_ar, b4=b4_09_ar, b5=b5_09_ar, b7=b7_09_ar, ndvi=ndvi_09_ar,
# hack@uchicago Introduction to Python Workshop # Borja Sotomayor, 2013-2014 """ Prints out the ten most-frequent values for the "favorite_count" and "retweet_count" fields in a tweet dataset """ import workshop import operator import sys # For this script to run, you need to implement the extract_values # and compute_frequencies values in exercise_functions.py from functions import extract_values, compute_frequencies tfile = sys.argv[1] n = int(sys.argv[2]) for field in ["favorite_count", "retweet_count"]: print "Top 10 frequencies of %s" % field l = extract_values(tfile, n, field) freqs = compute_frequencies(l) freqs = freqs.items() freqs.sort(key = operator.itemgetter(1), reverse = True) for value, count in freqs[:10]: print value, count print