def get_zone_inds(ar_size, zone_size, tx, feat):
'''
Return the array offset indices for pixels overlapping a feature from a
vector dataset. Array indices are returned as (upper_row, lower_row, left_col,_right col)
to be used to index an array as [upper_row : lower_row, left_col : right_col]
'''
geom = feat.GetGeometryRef()
x1, x2, y1, y2 = geom.GetEnvelope()
# Get the feature ul x and y, and calculate the pixel offset
ar_ulx, x_res, x_rot, ar_uly, y_rot, y_res = tx
x_sign = x_res/abs(x_res)
y_sign = y_res/abs(y_res)
f_ulx = min([x0/x_sign for x0 in [x1, x2]])/x_sign
f_uly = min([y0/y_sign for y0 in [y1, y2]])/y_sign
offset = stem.calc_offset((ar_ulx, ar_uly), (f_ulx, f_uly), tx)
# Get the inds for the overlapping portions of each array
a_inds, m_inds = mosaic.get_offset_array_indices(ar_size, zone_size, offset)
return a_inds, m_inds
def main(params, inventory_txt=None, constant_vars=None):
inputs, df_var = stem.read_params(params)
for i in inputs:
exec ("{0} = str({1})").format(i, inputs[i])
df_var.data_band = [int(b) for b in df_var.data_band]#sometimes read as float
try:
n_tiles = [int(i) for i in n_tiles.split(',')]
support_size = [int(i) for i in support_size.split(',')]
nodata = int(nodata)
str_check = model_dir, mosaic_path, out_dir, train_params
except NameError as e:
missing_var = str(e).split("'")[1]
msg = "Variable '%s' not specified in param file:\n%s" % (missing_var, params)
raise NameError(msg)
# Check that all the variables given were used in training and vice versa
try:
train_inputs, train_vars = stem.read_params(train_params)
except:
raise NameError('train_params not specified or does not exist')
train_vars = sorted(train_vars.index)
pred_vars = sorted(df_var.index)
# Make sure vars are sorted alphabetically since they were for training
df_var = df_var.reindex(pred_vars)
# If constants were given, make a dict and make sure they match the training
# constants
if 'constant_vars' in inputs:
constant_vars = parse_constant_vars(constant_vars)
pred_constants = sorted(constant_vars.keys())
train_constants = [i.replace(' ', '') for i in train_inputs['constant_vars'].strip('"').split(',')]
train_constants = sorted(train_constants)
unmatched_vars = [v for v in pred_vars if v not in train_vars]
if 'constant_vars' in inputs:
unmatched_vars += [v for v in pred_constants if v not in train_constants]
if len(unmatched_vars) != 0:
unmatched_str = '\n'.join(unmatched_vars)
msg = 'Columns not in train params but specified in predict params:\n' + unmatched_str
raise NameError(msg)
unmatched_vars = [v for v in train_vars if v not in pred_vars]
if 'constant_vars' in inputs:
unmatched_vars += [v for v in train_constants if v not in pred_constants]
pred_vars += pred_constants # Add here because it would screw with stuff upstream
if len(unmatched_vars) != 0:
unmatched_str = '\n'.join(unmatched_vars)
msg = 'Columns not in predict params but specified in train params:\n' + unmatched_str
raise NameError(msg)
if not os.path.exists(out_dir): os.mkdir(out_dir)
else: print ('WARNING: out_dir already exists:\n%s\nAny existing files ' + \
'will be overwritten...\n') % out_dir
if not os.path.exists(os.path.join(out_dir, os.path.basename(params))):
shutil.copy2(params, out_dir) #Copy the params for reference
if 'confusion_params' in inputs:
conf_bn = os.path.basename(confusion_params)
new_conf_path = os.path.join(out_dir, conf_bn)
if not os.path.exists(new_conf_path):
shutil.copy2(confusion_params, out_dir)
confusion_params = new_conf_path
if not os.path.exists(model_dir):
sys.exit('model_dir does not exist:\n%s' % model_dir)
if not os.path.exists(mosaic_path):
sys.exit('mosaic_path does not exist:\n%s' % mosaic_path)
mosaic_ds = gdal.Open(mosaic_path)
mosaic_tx = mosaic_ds.GetGeoTransform()
xsize = mosaic_ds.RasterXSize
ysize = mosaic_ds.RasterYSize
prj = mosaic_ds.GetProjection()
driver = mosaic_ds.GetDriver()
m_ulx, x_res, x_rot, m_uly, y_rot, y_res = mosaic_tx
predict_dir = os.path.join(out_dir, 'decisiontree_predictions')
if not os.path.exists(predict_dir):
os.mkdir(predict_dir)
set_txt = glob.glob(os.path.join(model_dir, 'decisiontree_models/*support_sets.txt'))[0]
df_sets = pd.read_csv(set_txt, sep='\t', index_col='set_id')
total_sets = len(df_sets)
t0 = time.time()
if 'n_jobs' in inputs:
# Predict in parallel
n_jobs = int(n_jobs)
args = []
t1 = time.time()
print 'Predicting in parallel with %s jobs...' % n_jobs
print 'Building args and making rasters of TSA arrays...'
for c, (set_id, row) in enumerate(df_sets.iterrows()):
# Save rasters of tsa arrays ahead of time to avoid needing to pickle or fork mosaic_ds
coords = row[['ul_x', 'ul_y', 'lr_x', 'lr_y']]
tsa_ar, tsa_off = mosaic.extract_kernel(mosaic_ds, 1, coords, mosaic_tx,
xsize, ysize, nodata=nodata)
tsa_raster = os.path.join(predict_dir, 'tsa_%s.bsq' % set_id)
tx_out = row.ul_x, mosaic_tx[1], mosaic_tx[2], row.ul_y, mosaic_tx[4], mosaic_tx[5]
dtype_code = mosaic_ds.GetRasterBand(1).DataType
mosaic.array_to_raster(tsa_ar, tx_out, prj, driver, tsa_raster, stem.get_gdal_dtype(dtype_code), silent=True)
# Build list of args to pass to the Pool
tsa_raster = os.path.join(predict_dir, 'tsa_%s.bsq' % set_id)
ds = gdal.Open(tsa_raster)
tsa_tx = ds.GetGeoTransform()
ds = None
tsa_off = stem.calc_offset((mosaic_tx[0], mosaic_tx[3]), (tsa_tx[0], tsa_tx[3]), tsa_tx)
args.append([c, total_sets, set_id, df_var, tsa_raster, tsa_off, coords,
mosaic_tx, xsize, ysize, row.dt_file, nodata, np.uint8,
constant_vars, predict_dir])
print '%.1f minutes\n' % ((time.time() - t1)/60)
p = Pool(n_jobs)
p.map(stem.par_predict, args, 1)
else:
# Loop through each set and generate predictions
for c, (set_id, row) in enumerate(df_sets.ix[1043:].iterrows()):
t1 = time.time()
with open(row.dt_file, 'rb') as f:
dt_model = pickle.load(f)
print '\nPredicting for set %s of %s' % (c + 1, total_sets)
coords = row[['ul_x', 'ul_y', 'lr_x', 'lr_y']]
ar_predict = stem.predict_set(set_id, df_var, mosaic_ds, coords,
mosaic_tx, xsize, ysize, dt_model, nodata,
np.int16, constant_vars)
tx = coords.ul_x, x_res, x_rot, coords.ul_y, y_rot, y_res
out_path = os.path.join(predict_dir, 'prediction_%s.bsq' % set_id)
mosaic.array_to_raster(ar_predict, tx, prj, driver, out_path, gdal.GDT_Byte, nodata=nodata)
print 'Total time for this set: %.1f minutes' % ((time.time() - t1)/60)
#mosaic_ds = None
print '\nTotal time for predicting: %.1f hours\n' % ((time.time() - t0)/3600)#'''
#Aggregate predictions by tile and stitch them back together
if not 'file_stamp' in inputs: file_stamp = os.path.basename(model_dir)
ar_vote, pct_importance, df_sets = stem.aggregate_predictions(ysize, xsize, nodata, n_tiles, mosaic_ds, support_size, predict_dir, df_sets, out_dir, file_stamp, prj, driver, 0)
#df_sets.to_csv(set_txt, sep='\t')'''
mosaic_ds = None
# Save the importance values
importance = pd.DataFrame({'variable': pred_vars,
'pct_importance': pct_importance,
'index': range(len(pred_vars))
})
importance.set_index('index', inplace=True)
importance['rank'] = [int(r) for r in importance.pct_importance.rank(method='first', ascending=False)]
out_txt = os.path.join(out_dir, '%s_importance.txt' % file_stamp)
importance.to_csv(out_txt, sep='\t')#'''
'''ds = gdal.Open(os.path.join(model_dir, '%s_vote.bsq' % file_stamp))
ar_vote = ds.ReadAsArray()
ds = None
ds = gdal.Open(os.path.join(model_dir, '%s_mean.bsq' % file_stamp))
ar_mean = ds.ReadAsArray()
ds = None#'''
if 'confusion_params' in locals():
import confusion_matrix as confusion
vote_dir = os.path.join(model_dir, 'evaluation_vote')
mean_dir = os.path.join(model_dir, 'evaluation_mean')
print '\nComputing confusion matrix for vote...'
out_txt = os.path.join(vote_dir, 'confusion.txt')
print confusion_params
df_v = confusion.main(confusion_params, ar_vote, out_txt, match=True)
try:
out_txt = os.path.join(vote_dir, 'confusion_avg_kernel.txt')
df_v_off = confusion.main(confusion_params, ar_vote, out_txt)
except Exception as e:
print e
'''print '\nGetting confusion matrix for mean...'
out_txt = os.path.join(mean_dir, 'confusion.txt')
df_m = confusion.main(confusion_params, ar_mean, out_txt, match=True)
try:
out_txt = os.path.join(mean_dir, 'confusion_avg_kernel.txt')
df_m_off = confusion.main(confusion_params, ar_mean, out_txt)
except Exception as e:
print e#'''
vote_acc = df_v.ix['producer', 'user']
vote_kap = df_v.ix['producer', 'kappa']
#mean_acc = df_m.ix['user','producer']
#mean_kap = df_m.ix['user', 'kappa']
if 'inventory_txt' in inputs:
df_inv = pd.read_csv(inventory_txt, sep='\t', index_col='stamp')
cols = ['vote_accuracy', 'vote_kappa']#, 'vote_mask', 'mean_accuracy', 'mean_kappa', 'vote_mask']
df_inv.ix[file_stamp, cols] = vote_acc, vote_kap#, False, mean_acc, mean_kap, False
df_inv.to_csv(inventory_txt, sep='\t')
else:
print '\n"inventory_txt" was not specified.' +\
' Model evaluation scores will not be recorded...'
print ''
print 'Vote accuracy .............. ', vote_acc
print 'Vote kappa ................. ', vote_kap
#print 'Mean accuracy .............. ', mean_acc
#print 'Mean kappa ................. ', mean_kap
else:
print '\n"confusion_params" was not specified.' +\
' This model will not be evaluated...' #'''
print '\nTotal prediction runtime: %.1f\n' % ((time.time() - t0)/60)
def main(params,
inventory_txt=None,
constant_vars=None,
mosaic_shp=None,
resolution=30,
n_jobs=0,
n_jobs_agg=0,
mosaic_nodata=0,
snap_coord=None,
overwrite_tiles=False,
tile_id_field='name'):
inputs = stem.read_params(params)
for i in inputs:
exec("{0} = str({1})").format(i, inputs[i])
df_var = pd.read_csv(var_info, sep='\t', index_col='var_name')
df_var.data_band = [int(b)
for b in df_var.data_band] #sometimes read as float
try:
support_size = [int(i) for i in support_size.split(',')]
nodata = int(nodata)
str_check = model_dir, mosaic_path, out_dir, train_params
except NameError as e:
missing_var = str(e).split("'")[1]
msg = "Variable '%s' not specified in param file:\n%s" % (missing_var,
params)
raise NameError(msg)
# Check that all the variables given were used in training and vice versa
try:
train_inputs = stem.read_params(train_params)
except:
raise NameError('train_params not specified or does not exist')
train_vars = pd.read_csv(train_inputs['var_info'].replace('"', ''),
sep='\t',
index_col='var_name')
train_vars = sorted(train_vars.index)
pred_vars = sorted(df_var.index)
# Make sure vars are sorted alphabetically since they were for training
df_var = df_var.reindex(pred_vars)
unmatched_vars = [v for v in pred_vars if v not in train_vars]
if len(unmatched_vars) != 0:
unmatched_str = '\n'.join(unmatched_vars)
msg = 'Columns not in predict params but specified in train params:\n' + unmatched_str
raise NameError(msg)
if not os.path.exists(out_dir): os.mkdir(out_dir)
else: print ('WARNING: out_dir already exists:\n%s\nAny existing files ' + \
'will be overwritten...\n') % out_dir
if not os.path.exists(os.path.join(out_dir, os.path.basename(params))):
shutil.copy2(params, out_dir) #Copy the params for reference
if 'confusion_params' in inputs:
conf_bn = os.path.basename(confusion_params)
new_conf_path = os.path.join(out_dir, conf_bn)
if not os.path.exists(new_conf_path):
shutil.copy2(confusion_params, out_dir)
confusion_params = new_conf_path
if overwrite_tiles.lower() == 'false':
overwrite_tiles = False
if not os.path.exists(model_dir):
sys.exit('model_dir does not exist:\n%s' % model_dir)
if not os.path.exists(mosaic_path):
sys.exit('mosaic_path does not exist:\n%s' % mosaic_path)
if not 'file_stamp' in inputs: file_stamp = os.path.basename(model_dir)
db_path = os.path.join(model_dir, os.path.basename(model_dir) + '.db')
if os.path.exists(db_path):
engine = sqlalchemy.create_engine('sqlite:///%s' % db_path)
with engine.connect() as con, con.begin():
df_sets = pd.read_sql_table('support_sets',
con,
index_col='set_id') #'''
else:
set_txt = stem.find_file(model_dir, '*support_sets.txt')
if not os.path.isfile(set_txt):
raise IOError('No database or support set txt file found')
df_sets = pd.read_csv(set_txt, sep='\t', index_col='set_id')
if mosaic_path.endswith('.shp'):
mosaic_type = 'vector'
# if subset specified, clip the mosaic and set mosaic path to clipped shp
if 'subset_shp' in inputs:
out_shp_bn = os.path.basename(mosaic_path).replace(
'.shp', '_clipped.shp')
out_shp = os.path.join(out_dir, out_shp_bn)
cmd = 'ogr2ogr -clipsrc {clip_shp} {out_shp} {in_shp}'.format(
clip_shp=subset_shp, out_shp=out_shp, in_shp=mosaic_path)
subprocess.call(cmd, shell=True) #'''
mosaic_path = out_shp
mosaic_dataset = ogr.Open(mosaic_path, 1)
mosaic_ds = mosaic_dataset.GetLayer()
min_x, max_x, min_y, max_y = mosaic_ds.GetExtent()
if 'resolution' not in inputs:
warnings.warn('Resolution not specified. Using default of 30...\n')
# If subset specified, just get sets that overlap the subset
if 'subset_shp' in inputs:
mosaic_geom = ogr.Geometry(ogr.wkbMultiPolygon)
i = 0
for feature in mosaic_ds:
g = feature.GetGeometryRef()
# Check that the feature is valid. Clipping can produce a feautre
# w/ an area of 0
if g.GetArea() > 1:
mosaic_geom.AddGeometry(g)
else:
fid = feature.GetFID()
feature.Destroy()
mosaic_ds.DeleteFeature(fid)
#import pdb; pdb.set_trace()
df_sets = stem.get_overlapping_sets(df_sets,
mosaic_geom.UnionCascaded())
xsize = int((max_x - min_x) / resolution)
ysize = int((max_y - min_y) / resolution)
prj = mosaic_ds.GetSpatialRef().ExportToWkt()
x_res = resolution
y_res = -resolution
x_rot = 0
y_rot = 0
if 'snap_coord' in train_inputs:
snap_coord = train_inputs['snap_coord'].replace('"', '')
snap_coord = [float(c) for c in snap_coord.split(',')] #'''
mosaic_tx, extent = stem.tx_from_shp(mosaic_path,
x_res,
y_res,
snap_coord=snap_coord)
tiles = stem.attributes_to_df(
mosaic_path) # Change to accept arbittary geometry
else:
mosaic_type = 'raster'
mosaic_ds = gdal.Open(mosaic_path)
mosaic_tx = mosaic_ds.GetGeoTransform()
xsize = mosaic_ds.RasterXSize
ysize = mosaic_ds.RasterYSize
prj = mosaic_ds.GetProjection()
driver = mosaic_ds.GetDriver()
m_ulx, x_res, x_rot, m_uly, y_rot, y_res = mosaic_tx
#driver = gdal.GetDriverByName('gtiff')
# If number of tiles not given, need to set it
if 'n_tiles' not in inputs:
print 'n_tiles not specified. Using default: 90 x 40 ...\n'
n_tiles = 90, 40
else:
n_tiles = [int(i) for i in n_tiles.split(',')]
#df_tiles, df_tiles_rc, tile_size = stem.get_tiles(n_tiles, xsize, ysize, mosaic_tx)
total_sets = len(df_sets)
t0 = time.time()
last_dts = pd.Series()
agg_stats = [s.strip().lower() for s in agg_stats.split(',')]
n_jobs = int(n_jobs)
tile_dir = os.path.join(out_dir, '_temp_tiles')
#tile_dir = '/home/server/pi/homes/shooper/delete_test'
if not os.path.isdir(tile_dir):
os.mkdir(tile_dir)
tile_path_template = os.path.join(tile_dir, 'tile_{tile_id}_%(stat)s.tif')
n_tiles = len(tiles)
if not overwrite_tiles:
files = os.listdir(tile_dir)
tile_files = pd.DataFrame(columns=agg_stats,
index=tiles[tile_id_field])
for stat in agg_stats:
pattern = re.compile('tile_\d+_%s.tif' % stat)
stat_match = [f.split('_')[1] for f in files if pattern.match(f)]
try:
tile_files[stat] = pd.Series(np.ones(len(stat_match)),
index=stat_match)
except:
pass #import pdb; pdb.set_trace()
index_field = tiles.index.name
tiles[index_field] = tiles.index
tiles = tiles.set_index(tile_id_field, drop=False)
tiles.set_index(index_field, inplace=True) #'''
tiles['ul_x'] = [
stem.get_ul_coord(xmin, xmax, x_res)
for i, (xmin, xmax) in tiles[['xmin', 'xmax']].iterrows()
]
tiles['ul_y'] = [
stem.get_ul_coord(ymin, ymax, y_res)
for i, (ymin, ymax) in tiles[['ymin', 'ymax']].iterrows()
]
tiles['lr_x'] = [
xmax if ulx == xmin else xmin
for i, (ulx, xmin, xmax) in tiles[['ul_x', 'xmin', 'xmin']].iterrows()
]
tiles['lr_y'] = [
ymax if uly == ymin else ymin
for i, (uly, ymin, ymax) in tiles[['ul_y', 'ymin', 'ymin']].iterrows()
]
support_nrows = int(support_size[0] / abs(y_res))
support_ncols = int(support_size[1] / abs(x_res))
t1 = time.time()
# Patch for unknown Landcover screwup
args = [(i + 1, n_tiles, t1, tile_info, mosaic_path, mosaic_tx, df_sets,
df_var, (support_nrows, support_ncols), agg_stats,
tile_path_template, prj, nodata, snap_coord)
for i, (t_ind,
tile_info) in enumerate(tiles.loc[tiles['name'].isin([
'1931', '2810', '0705', '0954', '2814', '1986', '2552',
'2019', '2355', '3354', '2278', '2559'
])].iterrows())]
args = [(i + 1, n_tiles, t1, tile_info, mosaic_path, mosaic_tx, df_sets,
df_var, (support_nrows, support_ncols), agg_stats,
tile_path_template, prj, nodata, snap_coord)
for i, (t_ind, tile_info) in enumerate(tiles.loc[
tiles['name'].isin(['0705'])].iterrows())]
# Patch for the GEE subset 2 outside-of-buffer 'slice'
#args = [(i + 1, n_tiles, t1, tile_info, mosaic_path, mosaic_tx, df_sets, df_var, (support_nrows, support_ncols), agg_stats, tile_path_template, prj, nodata, snap_coord) for i, (t_ind, tile_info) in enumerate(tiles.loc[tiles['name'].isin(['0639','0718','0797','0876','0955','1034'])].iterrows())]
# Original line
#args = [(i + 1, n_tiles, t1, tile_info, mosaic_path, mosaic_tx, df_sets, df_var, (support_nrows, support_ncols), agg_stats, tile_path_template, prj, nodata, snap_coord) for i, (t_ind, tile_info) in enumerate(tiles.loc[tile_files.isnull().any(axis=1).values].iterrows())]
limits = []
for arg in args:
print tile_info[tile_id_field]
limits.append(stem.par_predict_tile(arg)) #'''
###
return
print '\n\nFinished predicting in %.1f hours. \n\nStitching tiles...' % (
(time.time() - t1) / 3600)
try:
limits = pd.concat(limits)
except:
# They're all None
pass
t1 = time.time()
mosaic_ul = mosaic_tx[0], mosaic_tx[3]
driver = gdal.GetDriverByName('gtiff')
for stat in agg_stats:
#dtype = mosaic.get_min_numpy_dtype(limits[stat])
dtype = np.int16
if stat == 'stdv':
this_nodata = -9999
ar = np.full((ysize, xsize), this_nodata, dtype=np.int16) #dtype)
else:
this_nodata = nodata
ar = np.full((ysize, xsize), this_nodata, dtype=dtype)
for tile_id, tile_coords in tiles.iterrows():
tile_file = os.path.join(
tile_dir,
'tile_%s_%s.tif' % (tile_coords[tile_id_field], stat))
try:
ds = gdal.Open(tile_file)
except:
print 'Tile not found'
continue
tile_tx = ds.GetGeoTransform()
tile_ul = tile_tx[0], tile_tx[3]
row_off, col_off = stem.calc_offset(mosaic_ul, tile_ul, mosaic_tx)
# Make sure the tile doesn't exceed the size of ar
tile_rows = min(ds.RasterYSize + row_off, ysize) - row_off
tile_cols = min(ds.RasterXSize + col_off, xsize) - col_off
ar_tile = ds.ReadAsArray(0, 0, tile_cols, tile_rows)
try:
ar[row_off:row_off + tile_rows,
col_off:col_off + tile_cols] = ar_tile
except Exception as e:
pass #import pdb; pdb.set_trace()
out_path = os.path.join(out_dir, '%s_%s.tif' % (file_stamp, stat))
#out_path = os.path.join('/home/server/pi/homes/shooper/delete_test', '%s_%s.tif' % (file_stamp, stat))
gdal_dtype = gdal_array.NumericTypeCodeToGDALTypeCode(ar.dtype)
mosaic.array_to_raster(ar,
mosaic_tx,
prj,
driver,
out_path,
gdal_dtype,
nodata=this_nodata)
# Clean up the tiles
#shutil.rmtree(tile_dir)
print 'Time for stitching: %.1f minutes\n' % ((time.time() - t1) / 60)
# Get feature importances and max importance per set
t1 = time.time()
print 'Getting importance values...'
importance_cols = sorted([c for c in df_sets.columns if 'importance' in c])
df_sets['max_importance'] = nodata
if len(importance_cols) == 0:
# Loop through and get importance
importance_per_var = []
for s, row in df_sets.iterrows():
with open(row.dt_file, 'rb') as f:
dt_model = pickle.load(f)
max_importance, this_importance = stem.get_max_importance(dt_model)
df_sets.ix[s, 'max_importance'] = max_importance
importance_per_var.append(this_importance)
importance = np.array(importance_per_var).mean(axis=0)
else:
df_sets['max_importance'] = np.argmax(df_sets[importance_cols].values,
axis=1)
importance = df_sets[importance_cols].mean(axis=0).values
pct_importance = importance / importance.sum()
print '%.1f minutes\n' % ((time.time() - t1) / 60)
# Save the importance values
importance = pd.DataFrame({
'variable': pred_vars,
'pct_importance': pct_importance,
'index': range(len(pred_vars))
})
importance.set_index('index', inplace=True)
importance['rank'] = [
int(r) for r in importance.pct_importance.rank(method='first',
ascending=False)
]
out_txt = os.path.join(out_dir, '%s_importance.txt' % file_stamp)
importance.to_csv(out_txt, sep='\t') #'''
print '\nTotal prediction runtime: %.1f hours\n' % (
(time.time() - t0) / 3600)
def main(txt, n_sample, out_txt, bins, train_params, by_psu=True, extract_predictors=True):
n_sample = int(n_sample)
bins = parse_bins(bins)
df = pd.read_csv(txt, sep='\t', dtype={'tile_id': object})
sample = pd.DataFrame(columns=df.columns)
n_bins = len(bins)
psu_ids = df.tile_id.unique()
train_params = stem.read_params(train_params)
for var in train_params:
exec ("{0} = str({1})").format(var, train_params[var])
tiles = attributes_to_df(MOSAIC_SHP)
if extract_predictors:
var_info = pd.read_csv(var_info, sep='\t', index_col='var_name')
for i, tile in enumerate(psu_ids):
print("extracting %s of %s" % (i, len(psu_ids)))
sample_mask = df.tile_id == tile
this_sample = df.loc[sample_mask]
tile_ul = tiles.loc[tiles['name'] == tile, ['xmin', 'ymax']].values[0]
#point_dict = get_point_dict(df, psu_ids)
mosaic_tx, extent = stem.tx_from_shp(MOSAIC_SHP, 30, -30)
row_off, col_off = stem.calc_offset([mosaic_tx[0], mosaic_tx[3]], tile_ul, mosaic_tx)
this_sample['local_row'] = this_sample.row - row_off
this_sample['local_col'] = this_sample.col - col_off
for var_name, var_row in var_info.iterrows():
#tiles = pd.DataFrame({'tile_id': psu_ids, 'tile_str': psu_ids})
file_path = stem.find_file(var_row.basepath, var_row.search_str, tile)
ds = gdal.Open(file_path)
ar = ds.GetRasterBand(var_row.data_band).ReadAsArray()
try:
if len(this_sample) == ar.size:
df.loc[sample_mask, var_name] = ar.ravel()
else:
df.loc[sample_mask, var_name] = ar[this_sample.local_row, this_sample.local_col]
except Exception as e:
print(e)
import pdb; pdb.set_trace()
ds = None
df.to_csv(txt.replace('.txt', '_predictors.txt'))
#df[var_name], _ = extract.extract_var('', var_name, var_row.by_tile, var_row.data_band, var_row.data_type, tiles, df, point_dict, var_row.basepath, var_row.search_str, var_row.path_filter, mosaic_tx, 0, 0, silent=True)
if by_psu:
n_per_psu = n_sample/len(psu_ids)
n_per_bin = n_per_psu/n_bins
for i, pid in enumerate(psu_ids):
psu_pixels = df.loc[df.tile_id == pid]
print("Sampling for %s of %s PSUs" % (i + 1, len(psu_ids)))
for l, u in bins:
this_bin = psu_pixels.loc[(l < psu_pixels.value) & (psu_pixels.value <= u)]
if len(this_bin) > 0:
bin_sample_size = min(n_per_bin, len(this_bin))
sample = pd.concat([sample, this_bin.sample(bin_sample_size)])
print("Sampled %s for bin %s-%s" % (n_per_bin, l, u))
else:
print("No pixels between %s and %s found" % (l, u))
print("")
else:
n_per_bin = n_sample/n_bins
for l, u in bins:
sample = pd.concat([sample, df.sample(n_per_bin)])
sample.to_csv(out_txt, index=False)
print 'Sample written to ', out_txt
def main(raster, nodata, psu_shp, out_dir):
nodata = int(nodata)
psus = attributes_to_df(psu_shp)
ds = gdal.Open(raster)
ar = ds.GetVirtualMemArray() #ReadAsArray()
tx = ds.GetGeoTransform()
prj = ds.GetProjection()
driver = gdal.GetDriverByName('gtiff')
# Just extract the test sample first
test_sample_dfs = []
print '\nGetting test samples for PSUs...'
for i, psu in psus.iterrows():
# Calc offsets
row_off, col_off = calc_offset((tx[0], tx[3]), psu[['ul_x', 'ul_y']],
tx)
n_rows = abs(int((psu.ymax - psu.ymin) / tx[5]))
n_cols = abs(int((psu.xmax - psu.xmin) / tx[1]))
# Get values
test_data = ar[row_off:row_off + n_rows,
col_off:col_off + n_cols].ravel()
mask = test_data != nodata
# Get row/col and x/y vals
test_data = test_data[mask]
row_inds, col_inds = np.indices((n_rows, n_cols), dtype=np.uint32)
row_inds = row_inds.ravel()[mask]
col_inds = col_inds.ravel()[mask]
these_row_inds = row_inds + row_off
these_col_inds = col_inds + col_off
y_coords = row_inds * tx[5] + psu.ul_y
x_coords = col_inds * tx[1] + psu.ul_x
df = pd.DataFrame({
'row': these_row_inds,
'col': these_col_inds,
'y': y_coords,
'x': x_coords,
'value': test_data,
'tile_id': psu['name']
})
#import pdb; pdb.set_trace()
test_sample_dfs.append(df)
test_sample = pd.concat(test_sample_dfs, ignore_index=True)
basename = os.path.basename(raster)
out_txt = os.path.join(out_dir, basename.replace(basename[-4:],
'_test.txt'))
test_sample.to_csv(out_txt, sep='\t', index=False)
# Read the raster as a write-able array and set all test samples to nodata
print '\nAssigning nodata val to PSUs in training raster...\n'
ar = ds.ReadAsArray()
ar[test_sample.row, test_sample.col] = nodata
out_raster = out_txt.replace('_test.txt', '_train.tif')
array_to_raster(ar, tx, prj, driver, out_raster, nodata=nodata)
desc = 'Training raster and test sample (text file with the same name but "_test" at the end) for making and evaluating STEM CONUS maps. Primary sampling units (PSUs) reserved for testing are assigned nodata.'
desc += '\n\tInput raster: %s' % os.path.abspath(raster)
desc += '\n\tNodata value: %s' % nodata
desc += '\n\tPSU shapefile: %s' % os.path.abspath(psu_shp)
desc += '\n\tOutput directory: %s\n' % os.path.abspath(out_dir)
createMetadata(sys.argv, out_raster, description=desc) #'''
ds = None
def main(model_dir, n_tiles, **kwargs):
t0 = time.time()
n_tiles = [int(n) for n in n_tiles.split(',')]
if not os.path.isdir(model_dir):
message = 'model directory given does not exist or is not a directory: ', model_dir
raise IOError(message)
model = os.path.basename(model_dir)
dt_dir = os.path.join(model_dir, 'decisiontree_models')
set_txt = os.path.join(dt_dir, '%s_support_sets.txt' % model)
df_sets = pd.read_csv(set_txt, sep='\t', index_col='set_id')
pred_param_path = glob(os.path.join(model_dir,
'predict_stem_*params.txt'))[0]
predict_params, df_var = stem.read_params(pred_param_path)
train_param_path = glob(os.path.join(model_dir,
'train_stem_*params.txt'))[0]
train_params, _ = stem.read_params(train_param_path)
df_var.sort_index(inplace=True)
nodata = int(predict_params['nodata'].replace('"', ''))
if len(kwargs) == 0:
var_ids = df_sets.max_importance.unique()
var_names = df_var.ix[var_ids].index
variables = zip(var_ids, var_names)
else:
variables = [(variable_id, variable_name)
for variable_name, variable_id in kwargs]
mask_path = os.path.join(model_dir, '%s_vote.bsq' % model)
if not os.path.exists(mask_path):
mask_path = mask_path.replace('.bsq', '.tif')
mask_ds = gdal.Open(mask_path)
mask_tx = mask_ds.GetGeoTransform()
xsize = mask_ds.RasterXSize
ysize = mask_ds.RasterYSize
prj = mask_ds.GetProjection()
df_tiles, df_tiles_rc, tile_size = stem.get_tiles(n_tiles, xsize, ysize,
mask_tx)
total_tiles = len(df_tiles)
df_tiles['tile'] = df_tiles.index
# Find the tiles that have only nodata values
t1 = time.time()
print '\nFinding empty tiles...'
mask = mask_ds.ReadAsArray() == nodata
empty_tiles = stem.find_empty_tiles(df_tiles, ~mask, mask_tx)
mask_ds = None
print '%s empty tiles found of %s total tiles\n%.1f minutes\n' %\
(len(empty_tiles), total_tiles, (time.time() - t1)/60)
# Select only tiles that are not empty
df_tiles = df_tiles.select(lambda x: x not in empty_tiles)
total_tiles = len(df_tiles)
#some_set = df_sets.iloc[0]
support_size = [
int(s)
for s in train_params['support_size'].replace('"', '').split(',')
]
set_size = [int(abs(s / mask_tx[1])) for s in support_size]
out_dir = os.path.join(model_dir, 'importance_maps')
if not os.path.exists(out_dir):
os.mkdir(out_dir)
print variables
for vi, (v_id, v_name) in enumerate(variables):
t1 = time.time()
print 'Making map for %s: %s of %s variables\n' % (v_name, vi + 1,
len(variables))
ar = np.full((ysize, xsize), nodata, dtype=np.uint8)
for i, (t_ind, t_row) in enumerate(df_tiles.iterrows()):
t2 = time.time()
print 'Aggregating for %s of %s tiles' % (i + 1, total_tiles)
# Calculate the size of this tile in case it's at the edge where the
# tile size will be slightly different
this_size = abs(t_row.lr_y - t_row.ul_y), abs(t_row.lr_x -
t_row.ul_x)
df_these_sets = stem.get_overlapping_sets(df_sets, t_row,
this_size, support_size)
rc = df_tiles_rc.ix[t_ind]
this_size = rc.lr_r - rc.ul_r, rc.lr_c - rc.ul_c
n_sets = len(df_these_sets)
# Load overlapping predictions from disk and read them as arrays
tile_ul = t_row[['ul_x', 'ul_y']]
print n_sets, ' Overlapping sets'
importance_bands = []
importance_values = []
for s_ind, s_row in df_these_sets.iterrows():
# Calculate offset and array/tile indices
offset = stem.calc_offset(tile_ul, (s_row.ul_x, s_row.ul_y),
mask_tx)
#if abs(offset[0]) > this_size[0] or abs(offset[1] > this_size[1]):
tile_inds, a_inds = mosaic.get_offset_array_indices(
tile_size, set_size, offset)
# Get feature with maximum importance and fill tile with that val
try:
with open(s_row.dt_file, 'rb') as f:
dt_model = pickle.load(f)
importance_value = int(
dt_model.feature_importances_[v_id] * 100)
importance_values.append(importance_value)
#filled = np.full((nrows, ncols), importance_value, dtype=np.uint8)
#import_band = stem.fill_tile_band(this_size, filled, tile_inds, nodata)
import_band = np.full(this_size, np.nan, dtype=np.float16)
import_band[tile_inds[0]:tile_inds[1],
tile_inds[2]:tile_inds[3]] = importance_value
importance_bands.append(import_band)
except Exception as e:
print e
continue #'''
print 'Average importance for this tile: %.1f' % np.mean(
importance_values)
#Aggregate
importance_stack = np.dstack(importance_bands)
importance_tile = np.nanmean(importance_stack, axis=2)
tile_mask = mask[rc.ul_r:rc.lr_r,
rc.ul_c:rc.lr_c] | np.isnan(importance_tile)
importance_tile[tile_mask] = nodata
ar[rc.ul_r:rc.lr_r,
rc.ul_c:rc.lr_c] = np.round(importance_tile).astype(np.uint8)
print 'Aggregation time for this tile: %.1f minutes\n' % (
(time.time() - t2) / 60)
'''temp_dir = os.path.join(out_dir, 'delete')
if not os.path.isdir(temp_dir):
os.mkdir(temp_dir)
t_tx = tile_ul[0], 30, 0, tile_ul[1], 0, -30
array_to_raster(np.round(importance_tile).astype(np.uint8), t_tx, prj, gdal.GetDriverByName('gtiff'), os.path.join(temp_dir, 'delete_%s.tif' % t_ind), gdal.GDT_Byte, 255, True)'''
out_path = os.path.join(out_dir,
'%s_importance_%s.tif' % (model, v_name))
try:
array_to_raster(ar, mask_tx, prj, gdal.GetDriverByName('gtiff'),
out_path, gdal.GDT_Byte, nodata)
except Exception as e:
print e
import pdb
pdb.set_trace()
print 'Time for this variable: %.1f minutes\n' % (
(time.time() - t1) / 60)
print '\nTotal time for %s variables: %.1f hours\n' % (len(variables), (
(time.time() - t0) / 3600))
def main(params, pct_train=None, aggregate_presence=False):
t0 = time.time()
# Read params. Make variables from each line of the 1-line variables
inputs, df_vars = stem.read_params(params)
for var in inputs:
exec("{0} = str({1})").format(var, inputs[var])
try:
if 'years' in inputs:
years = np.array([int(yr) for yr in years.split(',')])
else:
year_start = int(year_start)
year_end = int(year_end)
years = np.arange(year_start, year_end + 1)
'''tsa_mosaic = inputs['tsa_mosaic']
search_dir = inputs['search_dir']
search_str = inputs['search_str']
obs_txt = inputs['obs_txt']
index_col = inputs['index_col']
year_col = inputs['year_col']
target_col = inputs['target_col']
out_txt = inputs['out_txt']'''
add_file_tag = int(add_file_tag)
#count_type = inputs['count_type']
except KeyError as e:
missing_var = str(e).split("'")[1]
if missing_var in ['year_start', 'year_end', 'years']:
msg = ('No list of years or year_start/year_end specified in' +\
' param file:\n%s\n. Re-run script with either of these' +\
' parameters given.') % params
msg = "Variable '%s' not specified in param file:\n%s" % (missing_var,
params)
raise NameError(msg)
out_dir, original_bn = os.path.split(out_txt)
# Add informative tags to output dir and basename
if add_file_tag:
res = years[1] - years[0]
#out_dir = os.path.basename(out_dir)
now = datetime.datetime.now()
date_str = str(now.date()).replace('-', '')
time_str = str(now.time()).replace(':', '')[:4]
out_dirname = '{0}_res{1}yr_{2}_{3}'.format(target_col, res, date_str,
time_str)
out_dir = os.path.join(out_dir, out_dirname)
if not os.path.exists(out_dir):
os.mkdir(out_dir)
out_bn = '{0}_{1}'.format(
os.path.basename(obs_txt).replace('.txt', ''), original_bn)
out_txt = os.path.join(out_dir, out_bn)
if params != os.path.exists(os.path.join(out_dir,
os.path.basename(params))):
print 'Copying params to output dir: %s\n' % out_dir
shutil.copy2(params, out_dir)
print 'Getting predictors... '
t1 = time.time()
df_obs = pd.read_csv(obs_txt, sep='\t', index_col=index_col)
original_columns = df_obs.columns
df = get_predictors(years, search_dir, search_str, df_obs, index_col,
year_col, df_vars)
print '%.1f seconds\n' % (time.time() - t1)
# Select count type and date range
if 'count_type' in inputs:
count_type = [t.strip() for t in count_type.split(',')]
df = df[df.COUNT_TYPE.isin(count_type)]
#df.drop(['COUNT_TYPE'], axis=1, inplace=True)
if 'P21' in count_type:
df = df[df.EFFORT_DISTANCE_KM < .1]
if 'day_minmax' in inputs:
day_min, day_max = [int(d) for d in day_minmax.split(',')]
df = df[(df.DAY >= day_min) & (df.DAY <= day_max)]
if 'time_minmax' in inputs:
time_min, time_max = [int(t) for t in time_minmax.split(',')]
df = df[(df.TIME >= time_min) & (df.TIME <= time_max)]
if 'max_effort_time' in inputs:
max_effort_time = int(max_effort_time)
df = df[df.EFFORT_HRS < max_effort_time]
if 'max_effort_dist' in inputs:
max_effort_dist = int(max_effort_dist)
df = df[df.EFFORT_DISTANCE_KM < max_effort_time]
#df = df[(df.YEAR >= min(years)) & (df.YEAR <= max(years))]
#df[target_col] *= 100 # To be able to keep stuff as 8 bit ints
# Calc row and col from x, y
ds = gdal.Open(tsa_mosaic)
tx = ds.GetGeoTransform()
ds = None
ul_xy = tx[0], tx[3]
df['row'], df['col'] = zip(*[
stem.calc_offset(ul_xy, xy, tx) for i, xy in df[['x', 'y']].iterrows()
])
if 'kernel_dist' in inputs:
t1 = time.time()
print 'Calculating kernel density...'
kernel_dist = int(kernel_dist)
for yr in df.YEAR.unique():
yr_mask = df.YEAR == yr
df_w = gaussain_weights(df[yr_mask], target_col, kernel_dist)
df.ix[yr_mask, target_col] = df_w.weighted
'''
df_w = gaussain_weights(df, target_col, kernel_dist)
df[target_col] = df_w.weighted
#df = df.drop_duplicates(subset=[target_col, 'row', 'col'])'''
print '%.1f seconds\n' % (time.time() - t1) #"""
if aggregate_presence:
t1 = time.time()
print 'Aggregating presence records...'
df.ix[df[target_col] > 0, target_col] = 1
for yr in df.YEAR.unique():
yr_mask = df.YEAR == yr
df_yr = df[yr_mask]
# Get unique locations for this year
unique = df_yr[['row', 'col']].drop_duplicates().values
for row, col in unique:
this_loc = df_yr[(df_yr.row == row) & (df_yr.col == col)]
#If there are ones and 0s, drop the 0s
if this_loc[target_col].min(
) == 0 and this_loc[target_col].max() == 1:
df.drop(this_loc[this_loc[target_col] == 0].index,
inplace=True)
print '%.1f seconds\n' % (time.time() - t1)
if pct_train:
print 'Splitting training and test sets...'
pct_train = float(pct_train)
#n_test = int(len(df) * (1 - pct_train))
unique = df[['row', 'col']].drop_duplicates().values
n_test = int(len(unique) * (1 - pct_train))
random_idx = random.sample(xrange(len(unique)), n_test)
random_row, random_col = zip(*unique[random_idx])
df_test = df[df.row.isin(random_row) & df.col.isin(random_col)]
test_idx = df_test.index
test_txt = out_txt.replace('.txt', '_test.txt')
df = df[~df.index.isin(test_idx)]
df_test.to_csv(test_txt, sep='\t')
df.to_csv(out_txt, sep='\t')
obs_out_txt = out_txt.replace('_' + original_bn[:-4], '')
df[original_columns].to_csv(obs_out_txt, sep='\t')
print '\nLength of output df:', len(df)
print 'Text file written to: ', out_txt
print '\nTotal time: %.1f minutes' % ((time.time() - t0) / 60)
def main(params, inventory_txt=None, constant_vars=None, mosaic_shp=None, resolution=30, n_jobs=0, n_jobs_agg=0, mosaic_nodata=0, snap_coord=None, overwrite_tiles=False, tile_id_field='name'):
inputs, df_var = stem.read_params(params)
for i in inputs:
exec ("{0} = str({1})").format(i, inputs[i])
df_var.data_band = [int(b) for b in df_var.data_band]#sometimes read as float
try:
support_size = [int(i) for i in support_size.split(',')]
nodata = int(nodata)
str_check = model_dir, mosaic_path, out_dir, train_params
except NameError as e:
missing_var = str(e).split("'")[1]
msg = "Variable '%s' not specified in param file:\n%s" % (missing_var, params)
raise NameError(msg)
# Check that all the variables given were used in training and vice versa
try:
train_inputs, train_vars = stem.read_params(train_params)
except:
raise NameError('train_params not specified or does not exist')
train_vars = sorted(train_vars.index)
pred_vars = sorted(df_var.index)
# Make sure vars are sorted alphabetically since they were for training
df_var = df_var.reindex(pred_vars)
unmatched_vars = [v for v in pred_vars if v not in train_vars]
if len(unmatched_vars) != 0:
unmatched_str = '\n'.join(unmatched_vars)
msg = 'Columns not in predict params but specified in train params:\n' + unmatched_str
raise NameError(msg)
if not os.path.exists(out_dir): os.mkdir(out_dir)
else: print ('WARNING: out_dir already exists:\n%s\nAny existing files ' + \
'will be overwritten...\n') % out_dir
if not os.path.exists(os.path.join(out_dir, os.path.basename(params))):
shutil.copy2(params, out_dir) #Copy the params for reference
if 'confusion_params' in inputs:
conf_bn = os.path.basename(confusion_params)
new_conf_path = os.path.join(out_dir, conf_bn)
if not os.path.exists(new_conf_path):
shutil.copy2(confusion_params, out_dir)
confusion_params = new_conf_path
if not os.path.exists(model_dir):
sys.exit('model_dir does not exist:\n%s' % model_dir)
if not os.path.exists(mosaic_path):
sys.exit('mosaic_path does not exist:\n%s' % mosaic_path)
predict_dir = os.path.join(out_dir, 'decisiontree_predictions')
if not os.path.exists(predict_dir):
os.mkdir(predict_dir)
if not 'file_stamp' in inputs: file_stamp = os.path.basename(model_dir)
db_path = os.path.join(model_dir, file_stamp + '.db')
try:
engine = sqlalchemy.create_engine('sqlite:///%s' % db_path)
with engine.connect() as con, con.begin():
df_sets = pd.read_sql_table('support_sets', con, index_col='set_id')#'''
except:
set_txt = glob.glob(os.path.join(model_dir, 'decisiontree_models/*support_sets.txt'))[0]
if not os.path.isfile(set_txt):
raise IOError('No database or support set txt file found')
df_sets = pd.read_csv(set_txt, sep='\t', index_col='set_id')
if mosaic_path.endswith('.shp'):
mosaic_type = 'vector'
# if subset specified, clip the mosaic and set mosaic path to clipped shp
if 'subset_shp' in inputs:
out_shp_bn = os.path.basename(mosaic_path).replace('.shp', '_clipped.shp')
out_shp = os.path.join(out_dir, out_shp_bn)
cmd = 'ogr2ogr -clipsrc {clip_shp} {out_shp} {in_shp}'.format(clip_shp=subset_shp, out_shp=out_shp, in_shp=mosaic_path)
subprocess.call(cmd, shell=True)#'''
mosaic_path = out_shp
mosaic_dataset = ogr.Open(mosaic_path)
mosaic_ds = mosaic_dataset.GetLayer()
min_x, max_x, min_y, max_y = mosaic_ds.GetExtent()
if 'resolution' not in inputs:
warnings.warn('Resolution not specified. Using default of 30...\n')
# If subset specified, just get sets that overlap the subset
if 'subset_shp' in inputs:
mosaic_geom = ogr.Geometry(ogr.wkbMultiPolygon)
for feature in mosaic_ds:
mosaic_geom.AddGeometry(feature.GetGeometryRef())
df_sets = stem.get_overlapping_sets(df_sets, mosaic_geom)
xsize = int((max_x - min_x)/resolution)
ysize = int((max_y - min_y)/resolution)
prj = mosaic_ds.GetSpatialRef().ExportToWkt()
x_res = resolution
y_res = -resolution
x_rot = 0
y_rot = 0
if 'snap_coord' in train_inputs:
snap_coord = train_inputs['snap_coord'].replace('"','')
snap_coord = [float(c) for c in snap_coord.split(',')]#'''
mosaic_tx, extent = stem.tx_from_shp(mosaic_path, x_res, y_res, snap_coord=snap_coord)
tiles = stem.attributes_to_df(mosaic_path) # Change to accept arbittary geometry
else:
mosaic_type = 'raster'
mosaic_ds = gdal.Open(mosaic_path)
mosaic_tx = mosaic_ds.GetGeoTransform()
xsize = mosaic_ds.RasterXSize
ysize = mosaic_ds.RasterYSize
prj = mosaic_ds.GetProjection()
driver = mosaic_ds.GetDriver()
m_ulx, x_res, x_rot, m_uly, y_rot, y_res = mosaic_tx
#driver = gdal.GetDriverByName('gtiff')
# If number of tiles not given, need to set it
if 'n_tiles' not in inputs:
print 'n_tiles not specified. Using default: 25 x 15 ...\n'
n_tiles = 90, 40
else:
n_tiles = [int(i) for i in n_tiles.split(',')]
#df_tiles, df_tiles_rc, tile_size = stem.get_tiles(n_tiles, xsize, ysize, mosaic_tx)
total_sets = len(df_sets)
t0 = time.time()
last_dts = pd.Series()
agg_stats = [s.strip().lower() for s in agg_stats.split(',')]
n_jobs = int(n_jobs)
tile_dir = os.path.join(model_dir, 'temp_tiles')
#tile_dir = '/home/server/pi/homes/shooper/delete_test'
if not os.path.isdir(tile_dir):
os.mkdir(tile_dir)
tile_path_template = os.path.join(tile_dir, 'tile_{tile_id}_%(stat)s.tif')
n_tiles = len(tiles)
if not overwrite_tiles:
files = os.listdir(tile_dir)
tile_files = pd.DataFrame(columns=agg_stats, index=tiles[tile_id_field])
for stat in agg_stats:
stat_match = [f.split('_')[1] for f in fnmatch.filter(files, 'tile*%s.tif' % stat)]
tile_files[stat] = pd.Series(np.ones(len(stat_match)), index=stat_match)
index_field = tiles.index.name
tiles[index_field] = tiles.index
tiles = tiles.set_index(tile_id_field, drop=False)[tile_files.isnull().any(axis=1)]
tiles.set_index(index_field, inplace=True)
tiles['ul_x'] = [stem.get_ul_coord(xmin, xmax, x_res)
for i, (xmin, xmax) in tiles[['xmin','xmax']].iterrows()]
tiles['ul_y'] = [stem.get_ul_coord(ymin, ymax, y_res)
for i, (ymin, ymax) in tiles[['ymin','ymax']].iterrows()]
tiles['lr_x'] = [xmax if ulx == xmin else xmin for i, (ulx, xmin, xmax)
in tiles[['ul_x', 'xmin','xmin']].iterrows()]
tiles['lr_y'] = [ymax if uly == ymin else ymin for i, (uly, ymin, ymax)
in tiles[['ul_y', 'ymin','ymin']].iterrows()]
support_nrows = int(support_size[0]/abs(y_res))
support_ncols = int(support_size[1]/abs(x_res))
t1 = time.time()
args = [(tile_info, mosaic_path, mosaic_tx, df_sets, df_var, (support_nrows, support_ncols), agg_stats, tile_path_template, prj, nodata, snap_coord) for i, (t_ind, tile_info) in enumerate(tiles[tiles['name'].isin(['1771', '3224', '0333', '0558'])].iterrows())]
#args = [(i + 1, n_tiles, t1, tile_info, mosaic_path, mosaic_tx, df_sets, df_var, (support_nrows, support_ncols), agg_stats, tile_path_template, prj, nodata, snap_coord) for i, (t_ind, tile_info) in enumerate(tiles.iterrows())]
if n_jobs > 1:
print 'Predicting with %s jobs...\n' % n_jobs
pool = Pool(n_jobs)
pool.map(stem.predict_tile, args, 1)
pool.close()
pool.join()
else:
for arg in args:
print 'Predicting with 1 job ...\n'
stem.predict_tile(*arg)#'''
print '\n\nFinished predicting in %.1f hours. \n\nStitching tiles...' % ((time.time() - t1)/3600)
t1 = time.time()
mosaic_ul = mosaic_tx[0], mosaic_tx[3]
driver = gdal.GetDriverByName('gtiff')
for stat in agg_stats:
if stat == 'stdv':
this_nodata = -9999
ar = np.full((ysize, xsize), this_nodata, dtype=np.int16)
else:
this_nodata = nodata
ar = np.full((ysize, xsize), this_nodata, dtype=np.uint8)
for tile_id, tile_coords in tiles.iterrows():
tile_file = os.path.join(tile_dir, 'tile_%s_%s.tif' % (tile_coords[tile_id_field], stat))
ds = gdal.Open(tile_file)
tile_tx = ds.GetGeoTransform()
tile_ul = tile_tx[0], tile_tx[3]
row_off, col_off = stem.calc_offset(mosaic_ul, tile_ul, mosaic_tx)
# Make sure the tile doesn't exceed the size of ar
tile_rows = min(ds.RasterYSize + row_off, ysize) - row_off
tile_cols = min(ds.RasterXSize + col_off, xsize) - col_off
ar_tile = ds.ReadAsArray(0, 0, tile_cols, tile_rows)
try:
ar[row_off : row_off + tile_rows, col_off : col_off + tile_cols] = ar_tile
except Exception as e:
import pdb; pdb.set_trace()
out_path = os.path.join(model_dir, '%s_%s.tif' % (file_stamp, stat))
#out_path = os.path.join('/home/server/pi/homes/shooper/delete_test', '%s_%s.tif' % (file_stamp, stat))
gdal_dtype = gdal_array.NumericTypeCodeToGDALTypeCode(ar.dtype)
mosaic.array_to_raster(ar, mosaic_tx, prj, driver, out_path, gdal_dtype, nodata=this_nodata)
# Clean up the tiles
shutil.rmtree(tile_dir)
print 'Time for stitching: %.1f minutes\n' % ((time.time() - t1)/60)
# Get feature importances and max importance per set
t1 = time.time()
print 'Getting importance values...'
importance_cols = sorted([c for c in df_sets.columns if 'importance' in c])
df_sets['max_importance'] = nodata
if len(importance_cols) == 0:
# Loop through and get importance
importance_per_var = []
for s, row in df_sets.iterrows():
with open(row.dt_file, 'rb') as f:
dt_model = pickle.load(f)
max_importance, this_importance = stem.get_max_importance(dt_model)
df_sets.ix[s, 'max_importance'] = max_importance
importance_per_var.append(this_importance)
importance = np.array(importance_per_var).mean(axis=0)
else:
df_sets['max_importance'] = np.argmax(df_sets[importance_cols].values, axis=1)
importance = df_sets[importance_cols].mean(axis=0).values
pct_importance = importance / importance.sum()
print '%.1f minutes\n' % ((time.time() - t1)/60)
# Save the importance values
importance = pd.DataFrame({'variable': pred_vars,
'pct_importance': pct_importance,
'index': range(len(pred_vars))
})
importance.set_index('index', inplace=True)
importance['rank'] = [int(r) for r in importance.pct_importance.rank(method='first', ascending=False)]
out_txt = os.path.join(out_dir, '%s_importance.txt' % file_stamp)
importance.to_csv(out_txt, sep='\t')#'''
if 'confusion_params' in locals():
import confusion_matrix as confusion
'''
Read the mean or vote back in '''
if 'vote' in agg_stats:
vote_path = os.path.join(out_dir, '%s_vote.tif' % file_stamp)
ar_vote = gdal.Open(vote_path)
print '\nComputing confusion matrix for vote...'
vote_dir = os.path.join(model_dir, 'evaluation_vote')
out_txt = os.path.join(vote_dir, 'confusion.txt')
df_v = confusion.main(confusion_params, ar_vote, out_txt, match=True)
vote_acc = df_v.ix['producer', 'user']
vote_kap = df_v.ix['producer', 'kappa']
'''try:
out_txt = os.path.join(vote_dir, 'confusion_avg_kernel.txt')
df_v_off = confusion.main(confusion_params, ar_vote, out_txt)
except Exception as e:
print e'''
if 'mean' in agg_stats:
mean_path = os.path.join(out_dir, '%s_mean.tif' % file_stamp)
ar_mean = gdal.Open(mean_path)
print '\nGetting confusion matrix for mean...'
mean_dir = os.path.join(model_dir, 'evaluation_mean')
out_txt = os.path.join(mean_dir, 'confusion.txt')
df_m = confusion.main(confusion_params, ar_mean, out_txt, match=True)
mean_acc = df_m.ix['user','producer']
mean_kap = df_m.ix['user', 'kappa']
'''try:
out_txt = os.path.join(mean_dir, 'confusion_avg_kernel.txt')
df_m_off = confusion.main(confusion_params, ar_mean, out_txt)
except Exception as e:
print e#'''
if 'inventory_txt' in inputs:
df_inv = pd.read_csv(inventory_txt, sep='\t', index_col='stamp')
cols = ['vote_accuracy', 'vote_kappa']#, 'vote_mask', 'mean_accuracy', 'mean_kappa', 'vote_mask']
df_inv.ix[file_stamp, cols] = vote_acc, vote_kap#, False, mean_acc, mean_kap, False
df_inv.to_csv(inventory_txt, sep='\t')
else:
print '\n"inventory_txt" was not specified.' +\
' Model evaluation scores will not be recorded...'
print ''
if 'vote' in agg_stats:
print 'Vote accuracy .............. ', vote_acc
print 'Vote kappa ................. ', vote_kap
if 'mean' in agg_stats:
print 'Mean accuracy .............. ', mean_acc
print 'Mean kappa ................. ', mean_kap
else:
print '\n"confusion_params" was not specified.' +\
' This model will not be evaluated...' #'''
print '\nTotal prediction runtime: %.1f hours\n' % ((time.time() - t0)/3600)
