Upload 4 files

README.txt

@@ -0,0 +1,13 @@
+---
+title: ⚕️MedNER - Biomed Entity Recognizer
+emoji: 👩‍⚕️🩺⚕️🙋
+colorFrom: purple
+colorTo: red
+sdk: gradio
+sdk_version: 3.8
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+import pandas as pd
+import json
+from collections import defaultdict
+
+# Create tokenizer for biomed model
+from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
+tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
+model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")
+pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
+
+# Matplotlib for entity graph
+import matplotlib.pyplot as plt
+plt.switch_backend("Agg")
+
+# Load examples from JSON
+EXAMPLES = {}
+with open("examples.json", "r") as f:
+    example_json = json.load(f)
+    EXAMPLES = {x["text"]: x["label"] for x in example_json}
+
+def group_by_entity(raw):
+    out = defaultdict(int)
+    for ent in raw:
+        out[ent["entity_group"]] += 1
+    # out["total"] = sum(out.values())
+    return out
+
+
+def plot_to_figure(grouped):
+    fig = plt.figure()
+    plt.bar(x=list(grouped.keys()), height=list(grouped.values()))
+    plt.margins(0.2)
+    plt.subplots_adjust(bottom=0.4)
+    plt.xticks(rotation=90)
+    return fig
+
+
+def ner(text):
+    raw = pipe(text)
+    ner_content = {
+        "text": text,
+        "entities": [
+            {
+                "entity": x["entity_group"],
+                "word": x["word"],
+                "score": x["score"],
+                "start": x["start"],
+                "end": x["end"],
+            }
+            for x in raw
+        ],
+    }
+    
+    grouped = group_by_entity(raw)
+    figure = plot_to_figure(grouped)
+    label = EXAMPLES.get(text, "Unknown")
+
+    meta = {
+        "entity_counts": grouped,
+        "entities": len(set(grouped.keys())),
+        "counts": sum(grouped.values()),
+    }
+
+    return (ner_content, meta, label, figure)
+
+
+interface = gr.Interface(
+    ner,
+    inputs=gr.Textbox(label="Note text", value=""),
+    outputs=[
+        gr.HighlightedText(label="NER", combine_adjacent=True),
+        gr.JSON(label="Entity Counts"),
+        gr.Label(label="Rating"),
+        gr.Plot(label="Bar"),
+    ],
+    examples=list(EXAMPLES.keys()),
+    allow_flagging="never",
+)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,71 @@
+aiohttp==3.8.3
+aiosignal==1.2.0
+anyio==3.6.1
+async-timeout==4.0.2
+attrs==22.1.0
+bcrypt==4.0.1
+black==22.10.0
+certifi==2022.9.24
+cffi==1.15.1
+charset-normalizer==2.1.1
+click==8.1.3
+contourpy==1.0.5
+cryptography==38.0.1
+cycler==0.11.0
+fastapi==0.85.0
+ffmpy==0.3.0
+filelock==3.8.0
+fonttools==4.37.4
+frozenlist==1.3.1
+fsspec==2022.8.2
+gradio==3.4.1
+h11==0.12.0
+httpcore==0.15.0
+httpx==0.23.0
+huggingface-hub==0.10.0
+idna==3.4
+Jinja2==3.1.2
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
+MarkupSafe==2.1.1
+matplotlib==3.6.1
+mdit-py-plugins==0.3.1
+mdurl==0.1.2
+multidict==6.0.2
+mypy-extensions==0.4.3
+numpy==1.23.3
+orjson==3.8.0
+packaging==21.3
+pandas==1.5.0
+paramiko==2.11.0
+pathspec==0.10.1
+Pillow==9.2.0
+platformdirs==2.5.2
+pycparser==2.21
+pycryptodome==3.15.0
+pydantic==1.10.2
+pydub==0.25.1
+PyNaCl==1.5.0
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2022.4
+PyYAML==6.0
+regex==2022.9.13
+requests==2.28.1
+rfc3986==1.5.0
+six==1.16.0
+sniffio==1.3.0
+starlette==0.20.4
+tokenizers==0.12.1
+tomli==2.0.1
+torch==1.12.1
+tqdm==4.64.1
+transformers==4.22.2
+typing_extensions==4.4.0
+uc-micro-py==1.0.1
+urllib3==1.26.12
+uvicorn==0.18.3
+websockets==10.3
+yarl==1.8.1

test.json

@@ -0,0 +1,12 @@
+{
+  "type": "service_account",
+  "project_id": "clinical-nlp-b9117",
+  "private_key_id": "6972d02311e8ee0c5b582551fbcf9c99b9169b58",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nh8qPMwuMcQ/vKGhl3xLYo9M=\n-----END PRIVATE KEY-----\n",
+  "client_email": "firebase-adminsdk-qaxaj@clinical-nlp-b9117.iam.gserviceaccount.com",
+  "client_id": "117623958723912081118",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/firebase-adminsdk-qaxaj%40clinical-nlp-b9117.iam.gserviceaccount.com"
+}