Upload folder using huggingface_hub

Pipfile

@@ -0,0 +1,120 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+aiofiles = "==24.1.0"
+annotated-types = "==0.7.0"
+anyio = "==4.10.0"
+audioop-lts = "==0.2.2"
+authlib = "==1.6.1"
+brotli = "==1.1.0"
+certifi = "==2025.8.3"
+cffi = "==1.17.1"
+charset-normalizer = "==3.4.3"
+click = "==8.2.1"
+colorama = "==0.4.6"
+contourpy = "==1.3.3"
+cryptography = "==45.0.6"
+cssselect2 = "==0.8.0"
+cycler = "==0.12.1"
+distro = "==1.9.0"
+dnspython = "==2.7.0"
+dotenv = "==0.9.9"
+faker = "==37.5.3"
+fastapi = "==0.116.1"
+ffmpy = "==0.6.1"
+filelock = "==3.19.1"
+fonttools = "==4.59.1"
+fsspec = "==2025.7.0"
+gradio = "==5.42.0"
+gradio-client = "==1.11.1"
+gradio-modal = "==0.0.4"
+greenlet = "==3.2.4"
+groovy = "==0.1.2"
+h11 = "==0.16.0"
+httpcore = "==1.0.9"
+httpx = "==0.28.1"
+huggingface-hub = "==0.34.4"
+idna = "==3.10"
+itsdangerous = "==2.2.0"
+jinja2 = "==3.1.6"
+jiter = "==0.10.0"
+jsonpatch = "==1.33"
+jsonpointer = "==3.0.0"
+kiwisolver = "==1.4.9"
+langchain = "==0.3.27"
+langchain-core = "==0.3.74"
+langchain-openai = "==0.3.30"
+langchain-text-splitters = "==0.3.9"
+langgraph = "==0.6.5"
+langgraph-checkpoint = "==2.1.1"
+langgraph-prebuilt = "==0.6.4"
+langgraph-sdk = "==0.2.0"
+langsmith = "==0.4.14"
+markdown-it-py = "==4.0.0"
+markdown2 = "==2.5.4"
+markupsafe = "==3.0.2"
+matplotlib = "==3.10.5"
+mdurl = "==0.1.2"
+motor = "==3.7.1"
+narwhals = "==2.1.2"
+numpy = "==2.3.2"
+openai = "==1.99.9"
+orjson = "==3.11.2"
+ormsgpack = "==1.10.0"
+pandas = "==2.3.1"
+pillow = "==11.3.0"
+plotly = "==6.3.0"
+pycparser = "==2.22"
+pydantic = "==2.11.7"
+pydantic-core = "==2.33.2"
+pydub = "==0.25.1"
+pydyf = "==0.11.0"
+pygments = "==2.19.2"
+pymongo = "==4.14.0"
+pyparsing = "==3.2.3"
+pypdf = "==6.0.0"
+pyphen = "==0.17.2"
+python-dateutil = "==2.9.0.post0"
+python-dotenv = "==1.1.1"
+python-multipart = "==0.0.20"
+pytz = "==2025.2"
+pyyaml = "==6.0.2"
+regex = "==2025.7.34"
+reportlab = "==4.4.3"
+requests = "==2.32.4"
+requests-toolbelt = "==1.0.0"
+rich = "==14.1.0"
+ruff = "==0.12.9"
+safehttpx = "==0.1.6"
+semantic-version = "==2.10.0"
+shellingham = "==1.5.4"
+six = "==1.17.0"
+sniffio = "==1.3.1"
+sqlalchemy = "==2.0.43"
+starlette = "==0.47.2"
+tenacity = "==9.1.2"
+tiktoken = "==0.11.0"
+tinycss2 = "==1.4.0"
+tinyhtml5 = "==2.0.0"
+tomlkit = "==0.13.3"
+tqdm = "==4.67.1"
+typer = "==0.16.0"
+typing-extensions = "==4.14.1"
+typing-inspection = "==0.4.1"
+tzdata = "==2025.2"
+urllib3 = "==2.5.0"
+uvicorn = "==0.35.0"
+weasyprint = "==66.0"
+webencodings = "==0.5.1"
+websockets = "==15.0.1"
+xxhash = "==3.5.0"
+zopfli = "==0.2.3.post1"
+zstandard = "==0.23.0"
+
+[dev-packages]
+
+[requires]
+python_version = "3.13"

home.py

@@ -249,8 +249,21 @@ def build_trend_figure(trend_doc: Dict[str, Any]) -> Figure:
             title="No trend data", xaxis_title="Date", yaxis_title="Value"
         )
         return fig
-    dates = [pd.to_datetime(p.get("date"), errors="coerce") for p in points]
-    values = [coerce_to_number(p.get("value")) for p in points]
+
+    # Parse dates and values and pair them
+    date_value_pairs = []
+    for p in points:
+        date = pd.to_datetime(p.get("date"), errors="coerce")
+        value = coerce_to_number(p.get("value"))
+        if pd.notna(date) and value is not None:
+            date_value_pairs.append((date, value))
+
+    # Sort pairs by date
+    date_value_pairs.sort(key=lambda x: x[0])
+
+    # Unpack sorted pairs
+    dates, values = zip(*date_value_pairs) if date_value_pairs else ([], [])
+
     fig = Figure()
     fig.add_trace(
         Scatter(
@@ -268,7 +281,6 @@ def build_trend_figure(trend_doc: Dict[str, Any]) -> Figure:
     )
     return fig
 
-
 # ----- App state + loaders -----
 
 
@@ -513,21 +525,21 @@ def build_home_page():
                     delete_patient_btn = gr.Button(
                         "❌ Delete Patient",
                         size="lg",
-                        scale=1,
+                        scale=0,
                         variant="stop",
                         interactive=False,
                     )
                     edit_patient_btn = gr.Button(
                         "✏️ Edit Patient",
                         size="lg",
-                        scale=1,
+                        scale=0,
                         variant="huggingface",
                         interactive=False,
                     )
                     upload_reports_btn = gr.Button(
                         "📊 Upload Reports",
                         size="lg",
-                        scale=1,
+                        scale=0,
                         variant="huggingface",
                         interactive=False,
                     )

modules/db.py

@@ -220,17 +220,24 @@ class SheamiDB:
 
     async def delete_patient(self, patient_id: str):
         try:
+            yield "⌛Deleting patient PDFs ... "
+            deleted_count = await self.delete_pdfs_by_patient_id(patient_id)
+            yield f"✅Deleted {deleted_count} patient PDFs ... "
             yield "⌛Deleting patient reports ... "
             result = await self.reports.delete_one({"patient_id": ObjectId(patient_id)})
             yield f"✅Deleted {result.deleted_count} patient reports ... "
             yield "⌛Deleting patient trends ... "
-            result = await self.trends.delete_one({"patient_id": ObjectId(patient_id)})            
+            result = await self.trends.delete_one({"patient_id": ObjectId(patient_id)})
             yield f"✅Deleted {result.deleted_count} patient trends ... "
             yield "⌛Deleting patient final reports ... "
-            result = await self.final_reports.delete_one({"patient_id": ObjectId(patient_id)})
+            result = await self.final_reports.delete_one(
+                {"patient_id": ObjectId(patient_id)}
+            )
             yield f"✅Deleted {result.deleted_count} patient final reports ... "
             yield "⌛Deleting patient run stats ... "
-            result = await self.run_stats.delete_one({"patient_id": ObjectId(patient_id)})
+            result = await self.run_stats.delete_one(
+                {"patient_id": ObjectId(patient_id)}
+            )
             yield f"✅Deleted {result.deleted_count} patient run stats ... "
             yield "⌛Deleting patient ... "
             result = await self.patients.delete_one({"_id": ObjectId(patient_id)})
@@ -537,3 +544,15 @@ class SheamiDB:
         )
         run_stats = await cursor.to_list(length=None)
         return run_stats
+
+    async def delete_pdfs_by_patient_id(self, patient_id: str) -> int:
+        # Find all files with the specified patient_id in metadata
+        cursor = self.db.fs.files.find(
+            {"metadata.patient_id": ObjectId(patient_id)}, projection={"_id": 1}
+        )
+        deleted_count = 0
+        async for file_doc in cursor:
+            file_id = file_doc["_id"]
+            await self.fs.delete(file_id)
+            deleted_count += 1
+        return deleted_count

tests/dedup_trends.py

@@ -0,0 +1,41 @@
+from modules.db import SheamiDB
+
+db = None  # global placeholder
+
+
+async def deduplicate_trend_data():
+    global db
+    if db is None:
+        db = SheamiDB()
+    cursor = db.trends.find({})
+    updated_count = 0
+    async for doc in cursor:
+        # Create a dict to keep max value for each date
+        date_max = {}
+        for entry in doc.get("trend_data", []):
+            date = entry["date"]
+            try:
+                value = float(entry["value"])
+            except ValueError as e:
+                # Skip this entry because value is not a valid float
+                print("Error converting str to float ", e)
+                continue
+            print("entry = ", entry)
+            print("date_max = ", date_max)
+            if date not in date_max or value > float(date_max[date]["value"]):
+                date_max[date] = entry
+        deduped_trend_data = list(date_max.values())
+        # Only update if changes are made
+        if len(deduped_trend_data) != len(doc.get("trend_data", [])):
+            await db.trends.update_one(
+                {"_id": doc["_id"]}, {"$set": {"trend_data": deduped_trend_data}}
+            )
+            updated_count += 1
+    print(f"Updated {updated_count} documents.")
+
+
+# Usage:
+if __name__ == "__main__":
+    import asyncio
+
+    asyncio.run(deduplicate_trend_data())