Merge pull request #260 from cytomining/partition_profiling

Partition column in the metadata during profiling

deepprofiler/__main__.py

@@ -146,7 +146,7 @@ def prepare(context):
 def sample_sc(context):
     if context.parent.obj["config"]["prepare"]["compression"]["implement"]:
         context.parent.obj["config"]["paths"]["images"] = context.obj["config"]["paths"]["compressed_images"]
-    dset = deepprofiler.dataset.image_dataset.read_dataset(context.obj["config"])
+    dset = deepprofiler.dataset.image_dataset.read_dataset(context.obj["config"], mode='train')
     deepprofiler.dataset.sampling.sample_dataset(context.obj["config"], dset)
     print("Single-cell sampling complete.")
 
@@ -159,7 +159,7 @@ def sample_sc(context):
 def train(context, epoch, seed):
     if context.parent.obj["config"]["prepare"]["compression"]["implement"]:
         context.parent.obj["config"]["paths"]["images"] = context.obj["config"]["paths"]["compressed_images"]
-    dset = deepprofiler.dataset.image_dataset.read_dataset(context.obj["config"])
+    dset = deepprofiler.dataset.image_dataset.read_dataset(context.obj["config"], mode='train')
     deepprofiler.learning.training.learn_model(context.obj["config"], dset, epoch, seed)
 
 
@@ -177,8 +177,8 @@ def profile(context, part):
     if part >= 0:
         partfile = "index-{0:03d}.csv".format(part)
         config["paths"]["index"] = context.obj["config"]["paths"]["index"].replace("index.csv", partfile)
-    metadata = deepprofiler.dataset.image_dataset.read_dataset(context.obj["config"])
-    deepprofiler.learning.profiling.profile(context.obj["config"], metadata)
+    dset = deepprofiler.dataset.image_dataset.read_dataset(context.obj["config"], mode='profile')
+    deepprofiler.learning.profiling.profile(context.obj["config"], dset)
 
 
 # Auxiliary tool: Split index in multiple parts

deepprofiler/dataset/image_dataset.py

@@ -195,7 +195,7 @@ def number_of_records(self, dataset):
     def add_target(self, new_target):
         self.targets.append(new_target)
 
-def read_dataset(config):
+def read_dataset(config, mode = 'train'):
     # Read metadata and split dataset in training and validation
     metadata = deepprofiler.dataset.metadata.Metadata(config["paths"]["index"], dtype=None)
     if config["prepare"]["compression"]["implement"]:
@@ -211,10 +211,12 @@ def read_dataset(config):
     print(metadata.data.info())
 
     # Split training data
-    split_field = config["train"]["partition"]["split_field"]
-    trainingFilter = lambda df: df[split_field].isin(config["train"]["partition"]["training_values"])
-    validationFilter = lambda df: df[split_field].isin(config["train"]["partition"]["validation_values"])
-    metadata.splitMetadata(trainingFilter, validationFilter)
+    if mode == 'train':
+        split_field = config["train"]["partition"]["split_field"]
+        trainingFilter = lambda df: df[split_field].isin(config["train"]["partition"]["training_values"])
+        validationFilter = lambda df: df[split_field].isin(config["train"]["partition"]["validation_values"])
+        metadata.splitMetadata(trainingFilter, validationFilter)
+
 
     # Create a dataset
     keyGen = lambda r: "{}/{}-{}".format(r["Metadata_Plate"], r["Metadata_Well"], r["Metadata_Site"])
@@ -228,9 +230,10 @@ def read_dataset(config):
     )
 
     # Add training targets
-    for t in config["train"]["partition"]["targets"]:
-        new_target = deepprofiler.dataset.target.MetadataColumnTarget(t, metadata.data[t].unique())
-        dset.add_target(new_target)
+    if mode == 'train':
+        for t in config["train"]["partition"]["targets"]:
+            new_target = deepprofiler.dataset.target.MetadataColumnTarget(t, metadata.data[t].unique())
+            dset.add_target(new_target)
 
     # Activate outlines for masking if needed
     if config["dataset"]["locations"]["mask_objects"]: