From 1e0a20eb54e43ca9a88e23319e3586bd16553ff2 Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Wed, 19 Oct 2022 14:00:57 +0400
Subject: [PATCH 01/12] start example

---
 .../sample_data/notes.txt                     |  2 +
 .../medical_text_understanding/scispacy.py    | 91 +++++++++++++++++++
 fortex/health/processors/test.py              | 18 ++++
 3 files changed, 111 insertions(+)
 create mode 100644 examples/medical_text_understanding/sample_data/notes.txt
 create mode 100644 examples/medical_text_understanding/scispacy.py
 create mode 100644 fortex/health/processors/test.py

diff --git a/examples/medical_text_understanding/sample_data/notes.txt b/examples/medical_text_understanding/sample_data/notes.txt
new file mode 100644
index 00000000..96ff5feb
--- /dev/null
+++ b/examples/medical_text_understanding/sample_data/notes.txt
@@ -0,0 +1,2 @@
+Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
+Keystone plant species such as fig trees are good for the soil.
\ No newline at end of file
diff --git a/examples/medical_text_understanding/scispacy.py b/examples/medical_text_understanding/scispacy.py
new file mode 100644
index 00000000..f503b60e
--- /dev/null
+++ b/examples/medical_text_understanding/scispacy.py
@@ -0,0 +1,91 @@
+import sys
+from termcolor import colored
+
+from forte.data.data_pack import DataPack
+from forte.data.readers import PlainTextReader
+from forte.pipeline import Pipeline
+from forte.processors.writers import PackIdJsonPackWriter
+
+from ft.onto.base_ontology import (
+    Token,
+)
+from fortex.spacy import SpacyProcessor
+
+from ftx.medical.clinical_ontology import Hyponym, Abbreviation, Phrase
+from fortex.health.processors.scispacy_processor import (
+    ScispaCyProcessor,
+)
+
+
+def main(
+    input_path: str,  # Path to mimic3 data if use_mimic3_reader=True else path to notes directory
+    output_path: str,  # Path to output directory
+    max_packs: int = -1,  # Max number of notes to read from mimic3 dataset. Set to -1 to read all.
+    use_mimic3_reader: bool = True,  # Read from mimic3 dataset or plain text
+):
+    pl = Pipeline[DataPack]()
+
+    if use_mimic3_reader is False:
+        pl.set_reader(PlainTextReader())
+    else:
+        pl.set_reader(Mimic3DischargeNoteReader(), config={"max_num_notes": max_packs})
+
+    pl.add(
+        SpacyProcessor(),
+        {"processors": ["sentence"], "lang": "en_ner_bionlp13cg_md"},
+    )
+    pl.add(
+        ICDCodingProcessor(),
+        {
+            "entry_type": "ft.onto.base_ontology.Document",
+            "attribute_name": "classification",
+            "multi_class": True,
+            "model_name": "AkshatSurolia/ICD-10-Code-Prediction",  # You can use other ICD predictors here.
+            "cuda_devices": -1,
+        },
+    )
+    pl.add(
+        PackIdJsonPackWriter(),
+        {
+            "output_dir": output_path,
+            "indent": 2,
+            "overwrite": True,
+            "drop_record": True,
+            "zip_pack": True,
+        },
+    )
+
+    pl.initialize()
+
+    packs = pl.process_dataset(input_path)
+    for pack in packs:
+        show_data(pack)
+
+
+def show_data(pack: DataPack):
+    # The ICD processor predicts ICD code for each article.
+    # The result is stored as article.icd_code.
+    # The articles are packed into DataPack.
+    # Therefore, we first extract articles from DataPack and then get their ICD codes.
+
+    for article in pack.get(MedicalArticle):
+        article_text = article.text
+
+        # get the ICD code and its coding version
+        icd_code = article.icd_code
+        icd_version = article.icd_version
+
+        print(colored("Article:", "red"), article_text, "\n")
+        print(colored(f"ICD-{icd_version} Code:", "cyan"), icd_code, "\n")
+
+        input(colored("Press ENTER to continue...\n", "green"))
+
+
+# Examples:
+#
+# Read from MIMIC3:
+# python icd_coding.py /path/to/mimiciii/1.4/NOTEEVENTS.csv.gz /path_to_sample_output 1000 True
+#
+# Read from sample_data:
+# python icd_coding.py sample_data/ /path_to_sample_output 1000 False
+main(sys.argv[1], sys.argv[2], int(sys.argv[3]), sys.argv[4].lower() == "true")
diff --git a/fortex/health/processors/test.py b/fortex/health/processors/test.py
new file mode 100644
index 00000000..d9fd9f86
--- /dev/null
+++ b/fortex/health/processors/test.py
@@ -0,0 +1,18 @@
+import spacy
+from timexy import Timexy
+
+nlp = spacy.load("en_core_web_sm")
+
+# Optionally add config if varying from default values
+config = {
+    "kb_id_type": "timex3",  # possible values: 'timex3'(default), 'timestamp'
+    "label": "timexy",  # default: 'timexy'
+    "overwrite": False,  # default: False
+}
+nlp.add_pipe("timexy", config=config, before="ner")
+
+doc = nlp(
+    "Today is the 10.10.2010. I was in Paris for six years. 2 pm 3 days ago"
+)
+for e in doc.ents:
+    print(f"{e.text}\t{e.label_}\t{e.kb_id_}")

From ff8f48ba2c750e4169eec68bec9d4773aebca56a Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Mon, 7 Nov 2022 16:13:42 +0400
Subject: [PATCH 02/12] Add scispacy processor to example

---
 ...spacy.py => medical_text_understanding.py} | 66 ++++++++++---------
 .../sample_data/notes.txt                     |  2 +-
 2 files changed, 35 insertions(+), 33 deletions(-)
 rename examples/medical_text_understanding/{scispacy.py => medical_text_understanding.py} (56%)

diff --git a/examples/medical_text_understanding/scispacy.py b/examples/medical_text_understanding/medical_text_understanding.py
similarity index 56%
rename from examples/medical_text_understanding/scispacy.py
rename to examples/medical_text_understanding/medical_text_understanding.py
index f503b60e..4e6a817e 100644
--- a/examples/medical_text_understanding/scispacy.py
+++ b/examples/medical_text_understanding/medical_text_understanding.py
@@ -9,57 +9,58 @@
 from ft.onto.base_ontology import (
     Token,
 )
-from fortex.spacy import SpacyProcessor
 
 from ftx.medical.clinical_ontology import Hyponym, Abbreviation, Phrase
-from fortex.health.processors.scispacy_processor import (
+# from fortex.health.processors.scispacy_processor import (
+#     ScispaCyProcessor,
+# )
+
+import sys
+sys.path.append("/Users/nikhil.ranjan/Desktop/ForteHealth/fortex/health/processors")
+from scispacy_processor import (
     ScispaCyProcessor,
 )
 
-
 def main(
     input_path: str,  # Path to mimic3 data if use_mimic3_reader=True else path to notes directory
     output_path: str,  # Path to output directory
-    max_packs: int = -1,  # Max number of notes to read from mimic3 dataset. Set to -1 to read all.
-    use_mimic3_reader: bool = True,  # Read from mimic3 dataset or plain text
 ):
     pl = Pipeline[DataPack]()
+    pl.set_reader(PlainTextReader())
 
-    if use_mimic3_reader is False:
-        pl.set_reader(PlainTextReader())
-    else:
-        pl.set_reader(Mimic3DischargeNoteReader(), config={"max_num_notes": max_packs})
-
-    pl.add(
-        SpacyProcessor(),
-        {"processors": ["sentence"], "lang": "en_ner_bionlp13cg_md"},
-    )
+    # pl.add(
+    #     SpacyProcessor(),
+    #     {"processors": ["sentence"], "lang": "en_core_sci_sm"},
+    # )
     pl.add(
-        ICDCodingProcessor(),
+        ScispaCyProcessor(),
         {
             "entry_type": "ft.onto.base_ontology.Document",
-            "attribute_name": "classification",
-            "multi_class": True,
-            "model_name": "AkshatSurolia/ICD-10-Code-Prediction",  # You can use other ICD predictors here.
-            "cuda_devices": -1,
-        },
-    )
-    pl.add(
-        PackIdJsonPackWriter(),
-        {
-            "output_dir": output_path,
-            "indent": 2,
-            "overwrite": True,
-            "drop_record": True,
-            "zip_pack": True,
+            "model_name": "en_core_sci_sm",
+            "pipe_name": "abbreviation_detector",
+            "prefer_gpu": True,
+            "require_gpu": False,
+            "gpu_id": 0,
         },
     )
+    # pl.add(
+    #     PackIdJsonPackWriter(),
+    #     {
+    #         "output_dir": output_path,
+    #         "indent": 2,
+    #         "overwrite": True,
+    #         "drop_record": True,
+    #         "zip_pack": True,
+    #     },
+    # )
 
     pl.initialize()
 
     packs = pl.process_dataset(input_path)
+
     for pack in packs:
-        show_data(pack)
+        for idx, abv_item in enumerate(pack.get(Abbreviation)):
+            print(abv_item.long_form.text)
 
 
 def show_data(pack: DataPack):
@@ -87,5 +88,6 @@ def show_data(pack: DataPack):
 # python icd_coding.py /path/to/mimiciii/1.4/NOTEEVENTS.csv.gz /path_to_sample_output 1000 True
 #
 # Read from sample_data:
-# python icd_coding.py sample_data/ /path_to_sample_output 1000 False
-main(sys.argv[1], sys.argv[2], int(sys.argv[3]), sys.argv[4].lower() == "true")
+# python medical_text_understanding.py sample_data/ /path_to_sample_output 1000 False
+# python medical_text_understanding.py sample_data/ .
+main(sys.argv[1], sys.argv[2])
diff --git a/examples/medical_text_understanding/sample_data/notes.txt b/examples/medical_text_understanding/sample_data/notes.txt
index 96ff5feb..6c7cd6df 100644
--- a/examples/medical_text_understanding/sample_data/notes.txt
+++ b/examples/medical_text_understanding/sample_data/notes.txt
@@ -1,2 +1,2 @@
 Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
-Keystone plant species such as fig trees are good for the soil.
\ No newline at end of file
+Keystone Alpha Deca Docile (ADD) plant species such as fig trees are good for the soil. MOM.
\ No newline at end of file

From a3f951d689daf1f77b06f76e64516a0972c24d5e Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Tue, 8 Nov 2022 12:21:25 +0400
Subject: [PATCH 03/12] add abbreviation detection

---
 .../medical_text_understanding.py             | 49 ++-----------------
 .../sample_data/notes.txt                     |  3 +-
 2 files changed, 5 insertions(+), 47 deletions(-)

diff --git a/examples/medical_text_understanding/medical_text_understanding.py b/examples/medical_text_understanding/medical_text_understanding.py
index 4e6a817e..36876f1e 100644
--- a/examples/medical_text_understanding/medical_text_understanding.py
+++ b/examples/medical_text_understanding/medical_text_understanding.py
@@ -22,16 +22,10 @@
 )
 
 def main(
-    input_path: str,  # Path to mimic3 data if use_mimic3_reader=True else path to notes directory
-    output_path: str,  # Path to output directory
+    input_path: str,
 ):
     pl = Pipeline[DataPack]()
     pl.set_reader(PlainTextReader())
-
-    # pl.add(
-    #     SpacyProcessor(),
-    #     {"processors": ["sentence"], "lang": "en_core_sci_sm"},
-    # )
     pl.add(
         ScispaCyProcessor(),
         {
@@ -43,16 +37,6 @@ def main(
             "gpu_id": 0,
         },
     )
-    # pl.add(
-    #     PackIdJsonPackWriter(),
-    #     {
-    #         "output_dir": output_path,
-    #         "indent": 2,
-    #         "overwrite": True,
-    #         "drop_record": True,
-    #         "zip_pack": True,
-    #     },
-    # )
 
     pl.initialize()
 
@@ -60,34 +44,9 @@ def main(
 
     for pack in packs:
         for idx, abv_item in enumerate(pack.get(Abbreviation)):
-            print(abv_item.long_form.text)
-
-
-def show_data(pack: DataPack):
-    # The ICD processor predicts ICD code for each article.
-    # The result is stored as article.icd_code.
-    # The articles are packed into DataPack.
-    # Therefore, we first extract articles from DataPack and then get their ICD codes.
-
-    for article in pack.get(MedicalArticle):
-        article_text = article.text
-
-        # get the ICD code and its coding version
-        icd_code = article.icd_code
-        icd_version = article.icd_version
-
-        print(colored("Article:", "red"), article_text, "\n")
-        print(colored(f"ICD-{icd_version} Code:", "cyan"), icd_code, "\n")
-
-        input(colored("Press ENTER to continue...\n", "green"))
-
+            print(colored("Long form text:", "red"), colored( abv_item.long_form.text, "blue"), "\n")
 
 # Examples:
-#
-# Read from MIMIC3:
-# python icd_coding.py /path/to/mimiciii/1.4/NOTEEVENTS.csv.gz /path_to_sample_output 1000 True
-#
 # Read from sample_data:
-# python medical_text_understanding.py sample_data/ /path_to_sample_output 1000 False
-# python medical_text_understanding.py sample_data/ .
-main(sys.argv[1], sys.argv[2])
+# python medical_text_understanding.py sample_data/
+main(sys.argv[1])
diff --git a/examples/medical_text_understanding/sample_data/notes.txt b/examples/medical_text_understanding/sample_data/notes.txt
index 6c7cd6df..abef4a83 100644
--- a/examples/medical_text_understanding/sample_data/notes.txt
+++ b/examples/medical_text_understanding/sample_data/notes.txt
@@ -1,2 +1 @@
-Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
-Keystone Alpha Deca Docile (ADD) plant species such as fig trees are good for the soil. MOM.
\ No newline at end of file
+Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
\ No newline at end of file

From cf02ab5009b1ab8142f2b9295b4fc915f8fbf1eb Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Tue, 8 Nov 2022 16:22:41 +0400
Subject: [PATCH 04/12] Add hyponym example code

---
 .../medical_text_understanding.py             | 61 +++++++++++++------
 .../sample_data/notes.txt                     |  3 +-
 .../health/processors/scispacy_processor.py   |  3 +
 3 files changed, 49 insertions(+), 18 deletions(-)

diff --git a/examples/medical_text_understanding/medical_text_understanding.py b/examples/medical_text_understanding/medical_text_understanding.py
index 36876f1e..8abc9f2d 100644
--- a/examples/medical_text_understanding/medical_text_understanding.py
+++ b/examples/medical_text_understanding/medical_text_understanding.py
@@ -10,7 +10,8 @@
     Token,
 )
 
-from ftx.medical.clinical_ontology import Hyponym, Abbreviation, Phrase
+from ftx.medical.clinical_ontology import Hyponym, Abbreviation
+
 # from fortex.health.processors.scispacy_processor import (
 #     ScispaCyProcessor,
 # )
@@ -23,30 +24,56 @@
 
 def main(
     input_path: str,
+    process: str,
 ):
     pl = Pipeline[DataPack]()
     pl.set_reader(PlainTextReader())
-    pl.add(
-        ScispaCyProcessor(),
-        {
-            "entry_type": "ft.onto.base_ontology.Document",
-            "model_name": "en_core_sci_sm",
-            "pipe_name": "abbreviation_detector",
-            "prefer_gpu": True,
-            "require_gpu": False,
-            "gpu_id": 0,
-        },
-    )
+    if process == "abb":
+        pl.add(
+            ScispaCyProcessor(),
+            {
+                "entry_type": "ft.onto.base_ontology.Document",
+                "model_name": "en_core_sci_sm",
+                "pipe_name": "abbreviation_detector",
+                "prefer_gpu": True,
+                "require_gpu": False,
+                "gpu_id": 0,
+            },
+        )
+    elif process == "hyp":
+        pl.add(
+            ScispaCyProcessor(),
+            {
+                "entry_type": "ft.onto.base_ontology.Document",
+                "model_name": "en_core_sci_sm",
+                "pipe_name": "hyponym_detector",
+                "prefer_gpu": True,
+                "require_gpu": False,
+                "gpu_id": 0,
+            },
+        )
 
     pl.initialize()
 
     packs = pl.process_dataset(input_path)
 
     for pack in packs:
-        for idx, abv_item in enumerate(pack.get(Abbreviation)):
-            print(colored("Long form text:", "red"), colored( abv_item.long_form.text, "blue"), "\n")
+        if process == "abb":
+            for idx, abv_item in enumerate(pack.get(Abbreviation)):
+                print(colored("Long form text:", "red"), colored( abv_item.long_form.text, "blue"), "\n")
 
+        elif process == "hyp":
+            for idx, detected in enumerate(pack.get(Hyponym)):
+                print("hyponym_link:", detected.hyponym_link)
+                print("hyponym_parent:", detected.parent)
+                print("hyponym_child:", detected.child)
+             
 # Examples:
-# Read from sample_data:
-# python medical_text_understanding.py sample_data/
-main(sys.argv[1])
+'''
+Read from sample_data:
+Abbreviation:
+    python medical_text_understanding.py sample_data/ abb
+Hyponym detection:
+    python medical_text_understanding.py sample_data/ hyp
+'''
+main(sys.argv[1], sys.argv[2])
diff --git a/examples/medical_text_understanding/sample_data/notes.txt b/examples/medical_text_understanding/sample_data/notes.txt
index abef4a83..96ff5feb 100644
--- a/examples/medical_text_understanding/sample_data/notes.txt
+++ b/examples/medical_text_understanding/sample_data/notes.txt
@@ -1 +1,2 @@
-Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
\ No newline at end of file
+Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
+Keystone plant species such as fig trees are good for the soil.
\ No newline at end of file
diff --git a/fortex/health/processors/scispacy_processor.py b/fortex/health/processors/scispacy_processor.py
index daa37073..34e6aa0b 100644
--- a/fortex/health/processors/scispacy_processor.py
+++ b/fortex/health/processors/scispacy_processor.py
@@ -110,11 +110,14 @@ def _process(self, input_pack: DataPack):
                     ) = self.find_index(
                         input_pack.text, item[2].start, item[2].end
                     )
+                    print(general_concept.text)
+                    print(item[2])
                     specific_concept = Phrase(
                         pack=input_pack,
                         begin=specific_concept_start,
                         end=specific_concept_end,
                     )
+                    #print(specific_concept.text)
                     hlink = Hyponym(
                         pack=input_pack,
                         parent=general_concept,

From ec04e1b3ee6a52eff0fe07b27b75ba878afc6590 Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Thu, 8 Dec 2022 15:41:41 +0400
Subject: [PATCH 05/12] Add abbreviation

---
 .../medical_text_understanding/medical_text_understanding.py   | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/examples/medical_text_understanding/medical_text_understanding.py b/examples/medical_text_understanding/medical_text_understanding.py
index 8abc9f2d..594c834c 100644
--- a/examples/medical_text_understanding/medical_text_understanding.py
+++ b/examples/medical_text_understanding/medical_text_understanding.py
@@ -60,7 +60,8 @@ def main(
     for pack in packs:
         if process == "abb":
             for idx, abv_item in enumerate(pack.get(Abbreviation)):
-                print(colored("Long form text:", "red"), colored( abv_item.long_form.text, "blue"), "\n")
+                print(colored("Abbreviation:", "blue"), colored( abv_item.text, "green"), "\n")
+                print(colored("Long form text:", "blue"), colored( abv_item.long_form.text, "green"), "\n")
 
         elif process == "hyp":
             for idx, detected in enumerate(pack.get(Hyponym)):

From c1577c7d413bb2a72f4b7f12d6567ebf2af741f1 Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Thu, 8 Dec 2022 15:46:43 +0400
Subject: [PATCH 06/12] fix old commits

---
 fortex/health/processors/scispacy_processor.py |  3 ---
 fortex/health/processors/test.py               | 18 ------------------
 2 files changed, 21 deletions(-)
 delete mode 100644 fortex/health/processors/test.py

diff --git a/fortex/health/processors/scispacy_processor.py b/fortex/health/processors/scispacy_processor.py
index 34e6aa0b..daa37073 100644
--- a/fortex/health/processors/scispacy_processor.py
+++ b/fortex/health/processors/scispacy_processor.py
@@ -110,14 +110,11 @@ def _process(self, input_pack: DataPack):
                     ) = self.find_index(
                         input_pack.text, item[2].start, item[2].end
                     )
-                    print(general_concept.text)
-                    print(item[2])
                     specific_concept = Phrase(
                         pack=input_pack,
                         begin=specific_concept_start,
                         end=specific_concept_end,
                     )
-                    #print(specific_concept.text)
                     hlink = Hyponym(
                         pack=input_pack,
                         parent=general_concept,
diff --git a/fortex/health/processors/test.py b/fortex/health/processors/test.py
deleted file mode 100644
index d9fd9f86..00000000
--- a/fortex/health/processors/test.py
+++ /dev/null
@@ -1,18 +0,0 @@
-import spacy
-from timexy import Timexy
-
-nlp = spacy.load("en_core_web_sm")
-
-# Optionally add config if varying from default values
-config = {
-    "kb_id_type": "timex3",  # possible values: 'timex3'(default), 'timestamp'
-    "label": "timexy",  # default: 'timexy'
-    "overwrite": False,  # default: False
-}
-nlp.add_pipe("timexy", config=config, before="ner")
-
-doc = nlp(
-    "Today is the 10.10.2010. I was in Paris for six years. 2 pm 3 days ago"
-)
-for e in doc.ents:
-    print(f"{e.text}\t{e.label_}\t{e.kb_id_}")

From 39edf56fb76996f99e58559d84b766eea787ff1e Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Thu, 8 Dec 2022 16:00:32 +0400
Subject: [PATCH 07/12] Add medical text understanding example

---
 .../medical_text_understanding.py             | 24 +++++++------------
 .../sample_data/notes.txt                     |  2 --
 .../sample_data_abb/abb.txt                   |  2 ++
 .../sample_data_hyp/hyp.txt                   |  1 +
 4 files changed, 12 insertions(+), 17 deletions(-)
 delete mode 100644 examples/medical_text_understanding/sample_data/notes.txt
 create mode 100644 examples/medical_text_understanding/sample_data_abb/abb.txt
 create mode 100644 examples/medical_text_understanding/sample_data_hyp/hyp.txt

diff --git a/examples/medical_text_understanding/medical_text_understanding.py b/examples/medical_text_understanding/medical_text_understanding.py
index 594c834c..52ce2731 100644
--- a/examples/medical_text_understanding/medical_text_understanding.py
+++ b/examples/medical_text_understanding/medical_text_understanding.py
@@ -11,14 +11,7 @@
 )
 
 from ftx.medical.clinical_ontology import Hyponym, Abbreviation
-
-# from fortex.health.processors.scispacy_processor import (
-#     ScispaCyProcessor,
-# )
-
-import sys
-sys.path.append("/Users/nikhil.ranjan/Desktop/ForteHealth/fortex/health/processors")
-from scispacy_processor import (
+from fortex.health.processors.scispacy_processor import (
     ScispaCyProcessor,
 )
 
@@ -59,22 +52,23 @@ def main(
 
     for pack in packs:
         if process == "abb":
+            print(colored("Input Sentence:", "blue"), colored( pack.text, "red"))
             for idx, abv_item in enumerate(pack.get(Abbreviation)):
-                print(colored("Abbreviation:", "blue"), colored( abv_item.text, "green"), "\n")
+                print(colored("Abbreviation:", "blue"), colored( abv_item.text, "green"))
                 print(colored("Long form text:", "blue"), colored( abv_item.long_form.text, "green"), "\n")
 
         elif process == "hyp":
+            print(colored("Input Sentence:", "blue"), colored( pack.text, "red"))
             for idx, detected in enumerate(pack.get(Hyponym)):
-                print("hyponym_link:", detected.hyponym_link)
-                print("hyponym_parent:", detected.parent)
-                print("hyponym_child:", detected.child)
-             
+                print(colored("hyponym_link:", "blue"), colored(detected.hyponym_link, "green"))
+                print(colored("hypernym:", "blue"), colored(detected.general, "green"))
+                print(colored("hyponym:", "blue"), colored(detected.specific, "green"))
 # Examples:
 '''
 Read from sample_data:
 Abbreviation:
-    python medical_text_understanding.py sample_data/ abb
+    python medical_text_understanding.py sample_data_abb/ abb
 Hyponym detection:
-    python medical_text_understanding.py sample_data/ hyp
+    python medical_text_understanding.py sample_data_hyp/ hyp
 '''
 main(sys.argv[1], sys.argv[2])
diff --git a/examples/medical_text_understanding/sample_data/notes.txt b/examples/medical_text_understanding/sample_data/notes.txt
deleted file mode 100644
index 96ff5feb..00000000
--- a/examples/medical_text_understanding/sample_data/notes.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen receptor (AR). SBMA can be caused by this easily.
-Keystone plant species such as fig trees are good for the soil.
\ No newline at end of file
diff --git a/examples/medical_text_understanding/sample_data_abb/abb.txt b/examples/medical_text_understanding/sample_data_abb/abb.txt
new file mode 100644
index 00000000..0f8600f5
--- /dev/null
+++ b/examples/medical_text_understanding/sample_data_abb/abb.txt
@@ -0,0 +1,2 @@
+Spinal and bulbar muscular atrophy (SBMA) is an inherited motor neuron disease caused by the expansion of a polyglutamine tract within the androgen 
+receptor (AR). SBMA can be caused by this easily.
diff --git a/examples/medical_text_understanding/sample_data_hyp/hyp.txt b/examples/medical_text_understanding/sample_data_hyp/hyp.txt
new file mode 100644
index 00000000..b707de89
--- /dev/null
+++ b/examples/medical_text_understanding/sample_data_hyp/hyp.txt
@@ -0,0 +1 @@
+Keystone plant species such as fig trees are good for the soil.

From 4c0c4bd077b51260851082d4d2c901b4979b0b0a Mon Sep 17 00:00:00 2001
From: bhaskar-IITB <bhaskar2443053@gmail.com>
Date: Mon, 19 Dec 2022 12:11:56 +0400
Subject: [PATCH 08/12] Update xray_image_reader.py

---
 fortex/health/readers/xray_image_reader.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fortex/health/readers/xray_image_reader.py b/fortex/health/readers/xray_image_reader.py
index 39934197..a3bf8796 100644
--- a/fortex/health/readers/xray_image_reader.py
+++ b/fortex/health/readers/xray_image_reader.py
@@ -64,7 +64,7 @@ def default_configs(cls):
 
         Here:
 
-          - file_ext (str): The file extension to find the target audio files
+          - file_ext (str): The file extension to find the target files
              under a specific directory path. Default value is ".jpeg".
 
           - read_kwargs (dict): A dictionary containing all the keyword

From a35b58b77b0c8341f710cab2ab7f1caf1650df2f Mon Sep 17 00:00:00 2001
From: bhaskar-IITB <bhaskar2443053@gmail.com>
Date: Mon, 19 Dec 2022 12:12:27 +0400
Subject: [PATCH 09/12] Update xray_image_reader.py

---
 fortex/health/readers/xray_image_reader.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fortex/health/readers/xray_image_reader.py b/fortex/health/readers/xray_image_reader.py
index a3bf8796..819150bd 100644
--- a/fortex/health/readers/xray_image_reader.py
+++ b/fortex/health/readers/xray_image_reader.py
@@ -26,7 +26,7 @@
 
 
 class XrayImageReader(PackReader):
-    r""":class:`ImageReader` is designed to read image files from a given folder."""
+    r""":class:`XrayImageReader` is designed to read image files from a given folder."""
 
     def __init__(self):
         super().__init__()

From c936d59121801da43a2cb3f6f2f48f4a03f1f828 Mon Sep 17 00:00:00 2001
From: bhaskar-IITB <bhaskar2443053@gmail.com>
Date: Wed, 21 Dec 2022 14:51:19 +0400
Subject: [PATCH 10/12] Update main.yml

remove python 3.6
downgrade numpy version
add deps for x-ray processor in work flow
---
 .github/workflows/main.yml | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 20909fed..23d79079 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [ 3.6, 3.7, 3.8, 3.9 ]
+        python-version: [ 3.7, 3.8, 3.9 ]
         torch-version: [ 1.5.0, 1.6.0, 1.7.1, 1.8.1 ]
         tensorflow-version: [ 1.15.0, 2.2.0, 2.5.0 ]
         test-details:
@@ -21,8 +21,8 @@ jobs:
           - { dep: forte-wrapper, testfile: tests/fortex/health/processors/negation_context_analysis_test.py }
           - { dep: scispacy, testfile: tests/fortex/health/processors/scispacy_processor_test.py }
           - { testfile: tests/fortex/health/readers/mimic3_note_reader_test.py }
-          - { testfile: tests/fortex/health/readers/xray_image_reader_test.py }
-          - { testfile: tests/fortex/health/processors/xray_processor_test.py }
+          - { dep: xray_image_processor,testfile: tests/fortex/health/readers/xray_image_reader_test.py }
+          - { dep: xray_image_processor,testfile: tests/fortex/health/processors/xray_processor_test.py }
         exclude:
           - python-version: 3.6
             torch-version: 1.7.1
@@ -72,7 +72,6 @@ jobs:
         restore-keys: |
           ${{ runner.os }}-pip-
           ${{ runner.os }}-
-
     - name: Install dependencies
       run: |
         sudo apt-get install -y libsndfile1-dev
@@ -81,35 +80,28 @@ jobs:
         pip install --progress-bar off pylint==2.10.2 importlib-metadata==4.8.0 flake8==3.9.2 mypy==0.931 pytest==5.1.3 black==20.8b1 click==8.0.1
         pip install --progress-bar off types-PyYAML==5.4.8 types-typed-ast==1.4.4 types-requests==2.25.6 types-dataclasses==0.1.7
         pip install --progress-bar off coverage codecov
-
     - name: Install deep learning frameworks
       run: |
         pip install --progress-bar off torch==${{ matrix.torch-version }}
         pip install --progress-bar off tensorflow==${{ matrix.tensorflow-version }}
-
     - name: Format check with Black
       run: |
         black --line-length 80 --check fortex/ tests/
-
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names
         flake8 fortex/ examples/ tests/ ftx/ --count --select=E9,F63,F7,F82 --show-source --statistics
         # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
         flake8 fortex/ examples/ ftx/ tests/ --ignore E203,W503 --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-
     - name: Lint with pylint
       run: |
         pylint fortex/ tests/
-
     - name: Lint main code with mypy when torch version is not 1.5.0 and python is 3.9
       run: |
         if [[ ${{ matrix.torch-version }} != "1.5.0" && ${{ matrix.python-version }} == "3.9" ]]; then mypy fortex/ tests/ ; fi
-
     - name: Install requirements for tests
       run: |
         pip install --progress-bar off .[test]
-
     - name: Install Forte-wrappers-spacy
       if: ${{ matrix.test-details.dep == 'forte-wrapper' ||
               contains(matrix.test-details.dep, 'forte-wrapper') }}
@@ -117,13 +109,18 @@ jobs:
         git clone https://github.com/asyml/forte-wrappers.git
         cd forte-wrappers
         pip install src/spacy
-
     - name: Install scispacy
       if: ${{ matrix.test-details.dep == 'scispacy' ||
               contains(matrix.test-details.dep, 'scispacy') }}
       run: |        
         pip install --progress-bar off .[scispacy_processor]
-
+        
+    - name: Install xray_image_processor
+      if: ${{ matrix.test-details.dep == 'xray_image_processor' ||
+              contains(matrix.test-details.dep, 'xray_image_processor') }}
+      run: |        
+        pip install --progress-bar off .[xray_image_processor]
+    
     - name: Test with pytest and run coverage
       run: |
         coverage run -m pytest ${{ matrix.test-details.testfile}}
@@ -152,7 +149,6 @@ jobs:
           restore-keys: |
             ${{ runner.os }}-pip-
             ${{ runner.os }}-
-
       - name: Install dependencies
         run: |
           python -m pip install --progress-bar off --upgrade pip
@@ -160,7 +156,6 @@ jobs:
           pip install --progress-bar off -r requirements.txt
           pip install --progress-bar off -r docs/requirements.txt
           pip install --progress-bar off .
-
       - name: Build Docs
         run: |
           cd docs

From 7dc5af2ee680b2cb943756c5b387cef67d10c1f9 Mon Sep 17 00:00:00 2001
From: bhaskar-IITB <bhaskar2443053@gmail.com>
Date: Wed, 21 Dec 2022 15:30:37 +0400
Subject: [PATCH 11/12] Update setup.py

add xray processor deps and change numpy version
---
 setup.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/setup.py b/setup.py
index 515d989b..b4e55063 100644
--- a/setup.py
+++ b/setup.py
@@ -28,15 +28,19 @@
         "test": [
             "ddt",
             "testfixtures",
-            "transformers==4.18.0",
+            "transformers==4.2.2",
             "protobuf==3.19.4",
-            "Pillow==8.4.0",
+            "numpy==1.21.6",
             'forte @ git+https://github.com/asyml/forte',
         ],
         "scispacy_processor": [
             "scispacy==0.5.0",
             "en-core-sci-sm @ https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.0/en_core_sci_sm-0.5.0.tar.gz"
         ],
+        "xray_image_processor": [
+            "Pillow==8.4.0",
+            "transformers==4.18.0",
+        ],
     },
     include_package_data=True,
     python_requires='>=3.6',

From 1ddd3c2204a8561e94f2f624bb2a8b9c6027fb6d Mon Sep 17 00:00:00 2001
From: nikhilranjan7 <nikhilranjan7@gmail.com>
Date: Tue, 27 Dec 2022 12:47:39 +0400
Subject: [PATCH 12/12] remove python 3.6 from exclude

---
 .github/workflows/main.yml | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 23d79079..53433f7c 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -24,14 +24,6 @@ jobs:
           - { dep: xray_image_processor,testfile: tests/fortex/health/readers/xray_image_reader_test.py }
           - { dep: xray_image_processor,testfile: tests/fortex/health/processors/xray_processor_test.py }
         exclude:
-          - python-version: 3.6
-            torch-version: 1.7.1
-          - python-version: 3.6
-            torch-version: 1.8.1
-          - python-version: 3.6
-            tensorflow-version: 2.2.0
-          - python-version: 3.6
-            tensorflow-version: 2.5.0
           - python-version: 3.7
             torch-version: 1.7.1
           - python-version: 3.7