Fix lots of ruff linter warnings

aimodel/src/lib/ai/RainfallWaterContraster.py

@@ -6,8 +6,8 @@ import tensorflow as tf
 
 from ..dataset.batched_iterator import batched_iterator
 
-from ..io.find_paramsjson import find_paramsjson
-from ..io.readfile import readfile
+# from ..io.find_paramsjson import find_paramsjson
+# from ..io.readfile import readfile
 from ..io.writefile import writefile
 
 from .model_rainfallwater_contrastive import model_rainfallwater_contrastive
@@ -16,7 +16,7 @@ from .helpers import summarywriter
 from .components.LayerContrastiveEncoder import LayerContrastiveEncoder
 from .components.LayerConvNeXtGamma import LayerConvNeXtGamma
 from .components.LayerCheeseMultipleOut import LayerCheeseMultipleOut
-from .helpers.summarywriter import summarywriter
+
 
 class RainfallWaterContraster(object):
 	def __init__(self, dir_output=None, filepath_checkpoint=None, epochs=50, batch_size=64, **kwargs):
@@ -28,8 +28,8 @@ class RainfallWaterContraster(object):
 		self.batch_size = batch_size
 		
 		
-		if filepath_checkpoint == None:
-			if self.dir_output == None:
+		if filepath_checkpoint is None:
+			if self.dir_output is None:
 				raise Exception("Error: dir_output was not specified, and since no checkpoint was loaded training mode is activated.")
 			if not os.path.exists(self.dir_output):
 				os.mkdir(self.dir_output)

aimodel/src/lib/ai/RainfallWaterMono.py

@@ -4,10 +4,10 @@ import json
 from loguru import logger
 import tensorflow as tf
 
-from ..dataset.batched_iterator import batched_iterator
+# from ..dataset.batched_iterator import batched_iterator
 
-from ..io.find_paramsjson import find_paramsjson
-from ..io.readfile import readfile
+# from ..io.find_paramsjson import find_paramsjson
+# from ..io.readfile import readfile
 from ..io.writefile import writefile
 
 from .model_rainfallwater_mono import model_rainfallwater_mono
@@ -16,7 +16,6 @@ from .helpers import summarywriter
 from .components.LayerConvNeXtGamma import LayerConvNeXtGamma
 from .components.LayerStack2Image import LayerStack2Image
 from .components.LossCrossentropy import LossCrossentropy
-from .helpers.summarywriter import summarywriter
 
 class RainfallWaterMono(object):
 	def __init__(self, dir_output=None, filepath_checkpoint=None, epochs=50, batch_size=64, **kwargs):
@@ -28,8 +27,8 @@ class RainfallWaterMono(object):
 		self.batch_size = batch_size
 		
 		
-		if filepath_checkpoint == None:
-			if self.dir_output == None:
+		if filepath_checkpoint is None:
+			if self.dir_output is None:
 				raise Exception("Error: dir_output was not specified, and since no checkpoint was loaded training mode is activated.")
 			if not os.path.exists(self.dir_output):
 				os.mkdir(self.dir_output)

aimodel/src/lib/ai/RainfallWaterSegmenter.py

@@ -4,10 +4,10 @@ import json
 from loguru import logger
 import tensorflow as tf
 
-from ..dataset.batched_iterator import batched_iterator
+# from ..dataset.batched_iterator import batched_iterator
 
-from ..io.find_paramsjson import find_paramsjson
-from ..io.readfile import readfile
+# from ..io.find_paramsjson import find_paramsjson
+# from ..io.readfile import readfile
 from ..io.writefile import writefile
 
 from .model_rainfallwater_segmentation import model_rainfallwater_segmentation
@@ -15,7 +15,6 @@ from .helpers import make_callbacks
 from .helpers import summarywriter
 from .components.LayerConvNeXtGamma import LayerConvNeXtGamma
 from .components.LayerStack2Image import LayerStack2Image
-from .helpers.summarywriter import summarywriter
 
 class RainfallWaterSegmenter(object):
 	def __init__(self, dir_output=None, filepath_checkpoint=None, epochs=50, batch_size=64, **kwargs):
@@ -27,8 +26,8 @@ class RainfallWaterSegmenter(object):
 		self.batch_size = batch_size
 		
 		
-		if filepath_checkpoint == None:
-			if self.dir_output == None:
+		if filepath_checkpoint is None:
+			if self.dir_output is None:
 				raise Exception("Error: dir_output was not specified, and since no checkpoint was loaded training mode is activated.")
 			if not os.path.exists(self.dir_output):
 				os.mkdir(self.dir_output)

aimodel/src/lib/ai/components/CallbackExtraValidation.py

@@ -27,7 +27,7 @@ class CallbackExtraValidation(tf.keras.callbacks.Callback):
 		self.verbose = verbose
 
 	def on_epoch_end(self, epoch, logs=None):
-		if logs == None:
+		if logs is None:
 			logger.warning(
 				"[CallbackExtraValidation] logs is None! Can't do anything here.")
 			return False

aimodel/src/lib/ai/components/LossCrossEntropyDice.py

@@ -1,4 +1,3 @@
-import math
 
 import tensorflow as tf
 

aimodel/src/lib/ai/components/LossDice.py

@@ -1,5 +1,3 @@
-import math
-
 import tensorflow as tf
 
 def dice_coef(y_true, y_pred, smooth=100):        
@@ -27,7 +25,7 @@ def dice_coef_loss(y_true, y_pred, **kwargs):
 		y_true (Tensor): The ground truth
 		y_pred (Tensor): The predicted output.
 	Returns:
-		Tensor: The Dice coefficient, but as a loss value that decreases instead fo increases as the model learns.
+		Tensor: The Dice coefficient, but as a loss value that decreases instead of increases as the model learns.
 	"""
 	return 1 - dice_coef(y_true, y_pred, **kwargs)
 

aimodel/src/lib/ai/components/MetricDice.py

@@ -1,5 +1,3 @@
-import math
-
 import tensorflow as tf
 
 

aimodel/src/lib/ai/components/MetricMeanIoU.py

@@ -1,5 +1,3 @@
-import math
-
 import tensorflow as tf
 
 

aimodel/src/lib/ai/components/MetricSensitivity.py

@@ -1,5 +1,3 @@
-import math
-
 import tensorflow as tf
 
 

aimodel/src/lib/ai/components/MetricSpecificity.py

@@ -1,5 +1,3 @@
-import math
-
 import tensorflow as tf
 
 

aimodel/src/lib/ai/model_rainfallwater_contrastive.py

@@ -1,6 +1,3 @@
-import math
-
-from curses import meta
 from loguru import logger
 import tensorflow as tf
 

aimodel/src/lib/ai/model_rainfallwater_mono.py

@@ -1,5 +1,3 @@
-import math
-
 from loguru import logger
 import tensorflow as tf
 

aimodel/src/lib/ai/model_rainfallwater_segmentation.py

@@ -1,5 +1,3 @@
-import math
-
 from loguru import logger
 import tensorflow as tf
 

aimodel/src/lib/dataset/dataset.py

@@ -1,6 +1,5 @@
 import os
 import math
-import json
 
 from loguru import logger
 
@@ -8,7 +7,6 @@ import tensorflow as tf
 
 from lib.dataset.read_metadata import read_metadata
 
-from ..io.readfile import readfile
 from .primitives.shuffle import shuffle
 
 
@@ -63,7 +61,7 @@ def make_dataset(filepaths, metadata, shape_water_desired=[100,100], compression
 		dataset = dataset.shuffle(shuffle_buffer_size)
 	dataset = dataset.map(parse_item(metadata, shape_water_desired=shape_water_desired, dummy_label=dummy_label), num_parallel_calls=tf.data.AUTOTUNE)
 		
-	if batch_size != None:
+	if batch_size is not None:
 		dataset = dataset.batch(batch_size, drop_remainder=True)
 	if prefetch:
 		dataset = dataset.prefetch(0 if "NO_PREFETCH" in os.environ else tf.data.AUTOTUNE)

aimodel/src/lib/dataset/dataset_encoderonly.py

@@ -1,6 +1,5 @@
 import os
 import math
-import json
 
 from loguru import logger
 
@@ -8,9 +7,9 @@ import tensorflow as tf
 
 from lib.dataset.read_metadata import read_metadata
 
-from ..io.readfile import readfile
 from .primitives.shuffle import shuffle
 from .parse_heightmap import parse_heightmap
+from .dataset_mono import dataset_mono
 
 
 
@@ -125,7 +124,7 @@ def make_dataset(filepaths, compression_type="GZIP", parallel_reads_multiplier=3
 		# defaults = (33*33 + 1) * 2**16 * 8 = about 2.219GiB
 		dataset = dataset.shuffle(shuffle_buffer_size)
 	
-	if batch_size != None:
+	if batch_size is not None:
 		dataset = dataset.batch(batch_size, drop_remainder=True)
 	if prefetch:
 		dataset = dataset.prefetch(0 if "NO_PREFETCH" in os.environ else tf.data.AUTOTUNE)

aimodel/src/lib/dataset/dataset_segmenter.py

@@ -1,12 +1,10 @@
 import os
 import math
-import json
 
 from loguru import logger
 import tensorflow as tf
 
 from lib.dataset.read_metadata import read_metadata
-from ..io.readfile import readfile
 from .primitives.shuffle import shuffle
 
 
@@ -62,7 +60,7 @@ def make_dataset(filepaths, metadata, shape_water_desired=[100,100], water_thres
 		dataset = dataset.shuffle(shuffle_buffer_size)
 	dataset = dataset.map(parse_item(metadata, shape_water_desired=shape_water_desired, water_threshold=water_threshold), num_parallel_calls=tf.data.AUTOTUNE)
 		
-	if batch_size != None:
+	if batch_size is not None:
 		dataset = dataset.batch(batch_size, drop_remainder=True)
 	if prefetch:
 		dataset = dataset.prefetch(0 if "NO_PREFETCH" in os.environ else tf.data.AUTOTUNE)

aimodel/src/lib/primitives/env.py

@@ -51,7 +51,7 @@ def read(name, type_class, default=SYM_RAISE_EXCEPTION):
 	"""
 
 	if name not in os.environ:
-		if type_class == bool and default == SYM_RAISE_EXCEPTION:
+		if type_class is bool and default == SYM_RAISE_EXCEPTION:
 			default = False
 		if default == SYM_RAISE_EXCEPTION:
 			raise Exception(f"Error: Environment variable {name} does not exist")
@@ -59,8 +59,8 @@ def read(name, type_class, default=SYM_RAISE_EXCEPTION):
 		return default
 	
 	result = os.environ[name]
-	if type_class == bool:
-		result = False if default == True else True
+	if type_class is bool:
+		result = False if default is True else True
 	else:
 		result = type_class(result)
 	
@@ -99,7 +99,7 @@ def print_all(table=True):
 		for env in envs_read:
 			key, value, is_default = env
 			prefix = "* " if is_default else ""
-			print(f"> {key.ljust(width_name)} {value}")
+			print(f"> {prefix}{key.ljust(width_name)} {value}")
 		print(f"Total {len(envs_read)} values")
 		print("===================================")
 	

aimodel/src/lib/vis/embeddings.py

@@ -1,8 +1,8 @@
-import os
+# import os
 
 import umap
 import umap.plot
-import numpy as np
+# import numpy as np
 import matplotlib.pylab as plt
 import pandas
 
@@ -24,7 +24,7 @@ def vis_embeddings(filepath_output, features):
 	umap.plot.points(dimreducer,
 		ax=axes["A"]
 	)
-	axes["A"].set_title(f"UMAP Dimensionality Reduction", fontsize=20)
+	axes["A"].set_title("UMAP Dimensionality Reduction", fontsize=20)
 	
 	# 2: Parallel coordinates
 	dataframe = pandas.DataFrame(features)
@@ -39,7 +39,7 @@ def vis_embeddings(filepath_output, features):
 		sort_labels=True
 	)
 	
-	axes["B"].set_title(f"Parallel coordinates plot", fontsize=20)
+	axes["B"].set_title("Parallel coordinates plot", fontsize=20)
 	
 	plt.suptitle(f"RainfallContrastive embeddings | rainfall | E2 ConvNeXt | {len(features)} items", fontsize=28, weight="bold")
 	plt.savefig(filepath_output)

aimodel/src/lib/vis/segmentation_plot.py

@@ -17,11 +17,11 @@ def segmentation_plot(water_actual, water_predict, model_code, filepath_output):
 	figure, axes = plt.subplot_mosaic("AB", figsize=(width*px, height*px))
 	
 	axes["A"].imshow(water_actual)
-	axes["A"].set_title(f"Actual", fontsize=20)
+	axes["A"].set_title("Actual", fontsize=20)
 	
 	
 	axes["B"].imshow(water_predict)
-	axes["B"].set_title(f"Predicted", fontsize=20)
+	axes["B"].set_title("Predicted", fontsize=20)
 	
 	
 	plt.suptitle(f"Rainfall → Water depth prediction | {model_code}", fontsize=28, weight="bold")