Refactor code structure for improved readability and maintainability

app/api.py

@@ -0,0 +1,533 @@
+"""
+FastAPI application for report generation with file uploads.
+
+This API allows users to:
+1. Upload required files (Spirometry PDF, Pnoe CSV, SECA Excel)
+2. Generate reports with graphs and analysis
+"""
+
+import shutil
+from pathlib import Path
+from typing import Dict, Optional
+
+import pandas as pd
+from fastapi import FastAPI, File, HTTPException, UploadFile
+from fastapi.responses import FileResponse
+from pydantic import BaseModel
+
+from graph_generator import GraphGenerator
+
+app = FastAPI(
+    title="Medical Report Generation API",
+    description="API for generating medical performance reports with analysis and graphs",
+    version="1.0.0",
+)
+
+# Define upload directory
+UPLOAD_DIR = Path("uploads")
+UPLOAD_DIR.mkdir(exist_ok=True)
+
+# Define output directories
+GRAPHS_DIR = Path("graphs")
+GRAPHS_DIR.mkdir(exist_ok=True)
+REPORTS_DIR = Path("reports")
+REPORTS_DIR.mkdir(exist_ok=True)
+
+# Storage for uploaded files metadata
+uploaded_files_store: Dict[str, Dict[str, str]] = {}
+
+
+class FileUploadResponse(BaseModel):
+    message: str
+    filename: str
+    file_type: str
+    file_path: str
+
+
+class ReportRequest(BaseModel):
+    patient_name: str
+    age: int
+    height: str
+    weight: str
+    focus: str = "Endurance"
+    session_id: Optional[str] = "default"
+
+
+class ReportResponse(BaseModel):
+    message: str
+    report_path: str
+    graphs_generated: list
+    analysis_data: dict
+
+
+@app.get("/")
+async def root():
+    """Root endpoint with API information"""
+    return {
+        "message": "Medical Report Generation API",
+        "version": "1.0.0",
+        "endpoints": {
+            "upload_spirometry": "/upload/spirometry",
+            "upload_pnoe": "/upload/pnoe",
+            "upload_seca": "/upload/seca",
+            "generate_report": "/generate-report",
+            "list_uploads": "/uploads",
+            "health": "/health",
+        },
+    }
+
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint"""
+    return {"status": "healthy", "service": "report-generation-api"}
+
+
+@app.post("/upload/spirometry", response_model=FileUploadResponse)
+async def upload_spirometry_pdf(
+    file: UploadFile = File(...), session_id: str = "default"
+):
+    """
+    Upload Spirometry PDF file for analysis.
+
+    Args:
+        file: Spirometry PDF file
+        session_id: Session identifier to group files together (default: "default")
+
+    Returns:
+        FileUploadResponse with upload details
+    """
+    if not file.filename.endswith(".pdf"):
+        raise HTTPException(status_code=400, detail="Only PDF files are allowed")
+
+    # Create session directory
+    session_dir = UPLOAD_DIR / session_id
+    session_dir.mkdir(exist_ok=True)
+
+    # Save file
+    file_path = session_dir / f"spirometry_{file.filename}"
+    with open(file_path, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+
+    # Store metadata
+    if session_id not in uploaded_files_store:
+        uploaded_files_store[session_id] = {}
+
+    uploaded_files_store[session_id]["spirometry_pdf"] = str(file_path)
+
+    return FileUploadResponse(
+        message="Spirometry PDF uploaded successfully",
+        filename=file.filename,
+        file_type="spirometry_pdf",
+        file_path=str(file_path),
+    )
+
+
+@app.post("/upload/pnoe", response_model=FileUploadResponse)
+async def upload_pnoe_csv(file: UploadFile = File(...), session_id: str = "default"):
+    """
+    Upload Pnoe CSV file for metabolic analysis.
+
+    Args:
+        file: Pnoe CSV file
+        session_id: Session identifier to group files together (default: "default")
+
+    Returns:
+        FileUploadResponse with upload details
+    """
+    if not file.filename.endswith(".csv"):
+        raise HTTPException(status_code=400, detail="Only CSV files are allowed")
+
+    # Create session directory
+    session_dir = UPLOAD_DIR / session_id
+    session_dir.mkdir(exist_ok=True)
+
+    # Save file
+    file_path = session_dir / f"pnoe_{file.filename}"
+    with open(file_path, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+
+    # Store metadata
+    if session_id not in uploaded_files_store:
+        uploaded_files_store[session_id] = {}
+
+    uploaded_files_store[session_id]["pnoe_csv"] = str(file_path)
+
+    return FileUploadResponse(
+        message="Pnoe CSV uploaded successfully",
+        filename=file.filename,
+        file_type="pnoe_csv",
+        file_path=str(file_path),
+    )
+
+
+@app.post("/upload/seca", response_model=FileUploadResponse)
+async def upload_seca_excel(file: UploadFile = File(...), session_id: str = "default"):
+    """
+    Upload SECA body composition Excel file.
+
+    Args:
+        file: SECA Excel file (.xlsx)
+        session_id: Session identifier to group files together (default: "default")
+
+    Returns:
+        FileUploadResponse with upload details
+    """
+    if not file.filename.endswith((".xlsx", ".xls")):
+        raise HTTPException(
+            status_code=400, detail="Only Excel files (.xlsx, .xls) are allowed"
+        )
+
+    # Create session directory
+    session_dir = UPLOAD_DIR / session_id
+    session_dir.mkdir(exist_ok=True)
+
+    # Save file
+    file_path = session_dir / f"seca_{file.filename}"
+    with open(file_path, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+
+    # Store metadata
+    if session_id not in uploaded_files_store:
+        uploaded_files_store[session_id] = {}
+
+    uploaded_files_store[session_id]["seca_excel"] = str(file_path)
+
+    return FileUploadResponse(
+        message="SECA Excel uploaded successfully",
+        filename=file.filename,
+        file_type="seca_excel",
+        file_path=str(file_path),
+    )
+
+
+@app.get("/uploads")
+async def list_uploads(session_id: str = "default"):
+    """
+    List all uploaded files for a session.
+
+    Args:
+        session_id: Session identifier (default: "default")
+
+    Returns:
+        Dictionary of uploaded files
+    """
+    if session_id not in uploaded_files_store:
+        return {"session_id": session_id, "files": {}, "message": "No files uploaded"}
+
+    return {
+        "session_id": session_id,
+        "files": uploaded_files_store[session_id],
+        "files_count": len(uploaded_files_store[session_id]),
+    }
+
+
+@app.post("/generate-report", response_model=ReportResponse)
+async def generate_report(report_request: ReportRequest):
+    """
+    Generate a comprehensive medical report with graphs and analysis.
+
+    Args:
+        report_request: Report configuration including patient details
+
+    Returns:
+        ReportResponse with report path and analysis data
+    """
+    session_id = report_request.session_id
+
+    # Check if all required files are uploaded
+    if session_id not in uploaded_files_store:
+        raise HTTPException(
+            status_code=400,
+            detail=f"No files found for session '{session_id}'. Please upload files first.",
+        )
+
+    files = uploaded_files_store[session_id]
+    required_files = ["spirometry_pdf", "pnoe_csv", "seca_excel"]
+    missing_files = [f for f in required_files if f not in files]
+
+    if missing_files:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Missing required files: {', '.join(missing_files)}. Please upload all files first.",
+        )
+
+    try:
+        # Initialize graph generator
+        graph_gen = GraphGenerator(charts_dir=str(GRAPHS_DIR))
+
+        # Load and process Pnoe data
+        df = pd.read_csv(files["pnoe_csv"], delimiter=";")
+        df = df.apply(pd.to_numeric, errors="ignore")
+
+        # Calculate derived columns
+        df["VO2 Pulse"] = df["VO2(ml/min)"] / df["HR(bpm)"]
+        df["VO2 Breath"] = df["VO2(ml/min)"] / df["BF(bpm)"]
+        df["CHO"] = df["EE(kcal/min)"] * df["CARBS(%)"] / 100
+        df["FAT"] = df["EE(kcal/min)"] * df["FAT(%)"] / 100
+
+        # Smooth columns
+        window_size = 10
+        columns_to_smooth = [
+            "VO2(ml/min)",
+            "VCO2(ml/min)",
+            "HR(bpm)",
+            "VT(l)",
+            "BF(bpm)",
+            "VE(l/min)",
+            "VO2 Pulse",
+            "VO2 Breath",
+            "CHO",
+            "FAT",
+        ]
+
+        for col in columns_to_smooth:
+            if col in df.columns:
+                df[f"{col}_smoothed"] = (
+                    df[col].rolling(window=window_size, min_periods=1).mean()
+                )
+
+        # Generate graphs
+        graphs_generated = []
+
+        # Generate all available graphs from the graph generator
+        try:
+            respiratory_path = graph_gen.generate_respiratory_chart(
+                df, save_as_base64=False
+            )
+            graphs_generated.append(
+                {"name": "respiratory", "path": str(respiratory_path)}
+            )
+        except Exception as e:
+            print(f"Warning: Could not generate respiratory chart: {e}")
+
+        try:
+            fuel_util_path = graph_gen.generate_fuel_utilization_chart(
+                df, save_as_base64=False
+            )
+            graphs_generated.append(
+                {"name": "fuel_utilization", "path": str(fuel_util_path)}
+            )
+        except Exception as e:
+            print(f"Warning: Could not generate fuel utilization chart: {e}")
+
+        try:
+            vo2_pulse_path = graph_gen.generate_vo2_pulse_chart(
+                df, save_as_base64=False
+            )
+            graphs_generated.append({"name": "vo2_pulse", "path": str(vo2_pulse_path)})
+        except Exception as e:
+            print(f"Warning: Could not generate VO2 pulse chart: {e}")
+
+        try:
+            vo2_breath_path = graph_gen.generate_vo2_breath_chart(
+                df, save_as_base64=False
+            )
+            graphs_generated.append(
+                {"name": "vo2_breath", "path": str(vo2_breath_path)}
+            )
+        except Exception as e:
+            print(f"Warning: Could not generate VO2 breath chart: {e}")
+
+        try:
+            fat_metabolism_path = graph_gen.generate_fat_metabolism_chart(
+                df, save_as_base64=False
+            )
+            graphs_generated.append(
+                {"name": "fat_metabolism", "path": str(fat_metabolism_path)}
+            )
+        except Exception as e:
+            print(f"Warning: Could not generate fat metabolism chart: {e}")
+
+        try:
+            recovery_path = graph_gen.generate_recovery_chart(df, save_as_base64=False)
+            graphs_generated.append({"name": "recovery", "path": str(recovery_path)})
+        except Exception as e:
+            print(f"Warning: Could not generate recovery chart: {e}")
+
+        # Calculate basic analysis metrics
+        analysis_data = {
+            "vo2_max": float(df["VO2(ml/min)_smoothed"].max())
+            if "VO2(ml/min)_smoothed" in df.columns
+            else 0,
+            "peak_vt": float(df["VT(l)_smoothed"].max())
+            if "VT(l)_smoothed" in df.columns
+            else 0,
+            "max_hr": float(df["HR(bpm)_smoothed"].max())
+            if "HR(bpm)_smoothed" in df.columns
+            else 0,
+            "graphs_count": len(graphs_generated),
+        }
+
+        # Generate PDF report using existing main.py logic
+        from jinja2 import Environment, FileSystemLoader
+
+        from context import context_list
+        from main import html_string_to_pdf
+
+        env = Environment(loader=FileSystemLoader("report_gen"))
+        html_pages = []
+
+        header_context = {
+            "patient_name": report_request.patient_name,
+            "age": report_request.age,
+            "height": report_request.height,
+            "weight": report_request.weight,
+            "focus": report_request.focus,
+        }
+
+        footer_context = [
+            {
+                "contact_email": "info@ishplabs.com",
+                "website": "www.ishplabs.com",
+                "social": "@ishplabs",
+                "page_number": i + 1,
+            }
+            for i in range(len(context_list))
+        ]
+
+        header_html = env.get_template("header.html").render(header_context)
+        footer_html_list = [
+            env.get_template("footer.html").render(context)
+            for context in footer_context
+        ]
+
+        for i, context in enumerate(context_list):
+            template = env.get_template(f"page_{i + 1}.html").render(context)
+
+            if (i + 1) > 2:
+                full_html = f"""
+                <div class="page flex flex-col justify-between">
+                    <div>
+                        {header_html}
+                    </div>
+                    <main class="flex-grow p-4">
+                        {template}
+                    </main>
+                    <div class="border-t text-center text-sm text-gray-600">
+                        {footer_html_list[i]}
+                    </div>
+                </div>
+                """
+                html_pages.append(full_html)
+            else:
+                html_pages.append(template)
+
+        # Combine with page breaks
+        final_html = "<div class='page-break'></div>".join(html_pages)
+
+        # Wrap in full HTML document
+        html_doc = f"""
+        <!DOCTYPE html>
+        <html>
+        <head>
+          <meta charset="utf-8">
+          <link href="https://cdn.jsdelivr.net/npm/tailwindcss/dist/tailwind.min.css" rel="stylesheet">
+          <style>
+            html, body {{
+                height: 100%;
+                margin: 0;
+                padding: 0;
+            }}
+            .page-break {{ page-break-after: always; }}
+            .page {{
+              height: 100vh;
+              min-height: 100vh;
+              display: flex;
+              flex-direction: column;
+            }}
+            .page main {{
+              flex: 1;
+              overflow: hidden;
+            }}
+            * {{
+              margin: 0;
+              padding: 0;
+              box-sizing: border-box;
+            }}
+            img {{
+              max-height: 300px;
+            }}
+            .chart-large {{
+              max-height: 500px !important;
+            }}
+          </style>
+        </head>
+        <body class="m-0 p-0">
+          {final_html}
+        </body>
+        </html>
+        """
+
+        # Generate PDF
+        report_filename = (
+            f"report_{report_request.patient_name.replace(' ', '_')}_{session_id}.pdf"
+        )
+        report_path = REPORTS_DIR / report_filename
+        html_string_to_pdf(html_doc, str(report_path))
+
+        return ReportResponse(
+            message="Report generated successfully",
+            report_path=str(report_path),
+            graphs_generated=graphs_generated,
+            analysis_data=analysis_data,
+        )
+
+    except Exception as e:
+        raise HTTPException(
+            status_code=500, detail=f"Error generating report: {str(e)}"
+        )
+
+
+@app.get("/download-report/{filename}")
+async def download_report(filename: str):
+    """
+    Download a generated report.
+
+    Args:
+        filename: Name of the report file
+
+    Returns:
+        PDF file
+    """
+    file_path = REPORTS_DIR / filename
+
+    if not file_path.exists():
+        raise HTTPException(status_code=404, detail="Report not found")
+
+    return FileResponse(
+        path=file_path,
+        media_type="application/pdf",
+        filename=filename,
+    )
+
+
+@app.delete("/uploads/{session_id}")
+async def delete_session_uploads(session_id: str):
+    """
+    Delete all uploaded files for a session.
+
+    Args:
+        session_id: Session identifier
+
+    Returns:
+        Success message
+    """
+    if session_id not in uploaded_files_store:
+        raise HTTPException(status_code=404, detail="Session not found")
+
+    # Delete files
+    session_dir = UPLOAD_DIR / session_id
+    if session_dir.exists():
+        shutil.rmtree(session_dir)
+
+    # Remove from store
+    del uploaded_files_store[session_id]
+
+    return {"message": f"Session '{session_id}' deleted successfully"}
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=8000)

extracted_table.csv

@@ -1,12 +0,0 @@
-Parameters,Best,LLN,Pred.,%Pred.,ZScore,PRE#1,PRE#2,PRE#3
-FVC,L,4.24,3.03,3.79,112.0,0.95,4.24,4.17,4.15
-FEV1,L,3.26,2.53,3.16,103.3,0.28,3.26,3.21,3.14
-FEV1/FVC%,76.89,72.47,83.78,91.8,-1.05,76.9,77.0,75.7
-PEF,L/m,684,222,384,178.7,-,444,438,684
-FEF2575,L/s,2.74,2.15,3.42,80.2,-0.84,2.74,2.68,2.48
-FEF25,L/s,6.08,-,-,-,6.08,6.0,5.53
-FEF50,L/s,3.06,-,-,-,3.06,3.1,2.77
-FEF75,L/s,1.06,0.71,1.41,75.1,-0.72,1.06,1.12,0.94
-PEFTime,ms,-,-,79,-,79,49,39
-Evol,mL,-,-,78.0,-,78.0,77.0,197.0
-FEV6,L,4.22,3.03,3.79,111.4,-,4.22,4.17,4.13

requirements.txt

@@ -1,5 +1,8 @@
+annotated-types==0.7.0
+anyio==4.11.0
 asttokens==3.0.0
 brotli==1.1.0
+certifi==2025.8.3
 cffi==2.0.0
 chardet==5.2.0
 charset-normalizer==3.4.3
@@ -11,24 +14,39 @@ cssselect2==0.8.0
 cycler==0.12.1
 debugpy==1.8.17
 decorator==5.2.1
+dnspython==2.8.0
+email-validator==2.3.0
 et-xmlfile==2.0.0
 executing==2.2.1
+fastapi==0.118.0
+fastapi-cli==0.0.13
+fastapi-cloud-cli==0.3.0
 fonttools==4.60.0
+greenlet==3.2.4
+h11==0.16.0
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+idna==3.10
 ipykernel==6.30.1
 ipython==9.5.0
 ipython-pygments-lexers==1.1.1
+itsdangerous==2.2.0
 jedi==0.19.2
 jinja2==3.1.6
 jupyter-client==8.6.3
 jupyter-core==5.8.1
 kiwisolver==1.4.9
+markdown-it-py==4.0.0
 markupsafe==3.0.2
 matplotlib==3.10.6
 matplotlib-inline==0.1.7
+mdurl==0.1.2
 nest-asyncio==1.6.0
 numpy==2.3.3
 opencv-python-headless==4.11.0.86
 openpyxl==3.1.5
+orjson==3.11.3
 packaging==25.0
 pandas==2.3.2
 pango==0.0.1
@@ -38,12 +56,18 @@ pdfminer-six==20250506
 pexpect==4.9.0
 pillow==11.3.0
 platformdirs==4.4.0
+playwright==1.55.0
 prompt-toolkit==3.0.52
 psutil==7.1.0
 ptyprocess==0.7.0
 pure-eval==0.2.3
 pycparser==2.23
+pydantic==2.11.9
+pydantic-core==2.33.2
+pydantic-extra-types==2.10.5
+pydantic-settings==2.11.0
 pydyf==0.11.0
+pyee==13.0.0
 pygments==2.19.2
 pymupdf==1.26.4
 pyparsing==3.2.5
@@ -51,17 +75,36 @@ pypdf==5.9.0
 pypdfium2==4.30.0
 pyphen==0.17.2
 python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+python-multipart==0.0.20
 pytz==2025.2
+pyyaml==6.0.3
 pyzmq==27.1.0
+rich==14.1.0
+rich-toolkit==0.15.1
+rignore==0.7.0
 seaborn==0.13.2
+sentry-sdk==2.39.0
+shellingham==1.5.4
 six==1.17.0
+sniffio==1.3.1
 stack-data==0.6.3
+starlette==0.48.0
 tabulate==0.9.0
 tinycss2==1.4.0
 tinyhtml5==2.0.0
 tornado==6.5.2
 traitlets==5.14.3
+typer==0.19.2
+typing-extensions==4.15.0
+typing-inspection==0.4.2
 tzdata==2025.2
+ujson==5.11.0
+urllib3==2.5.0
+uvicorn==0.37.0
+uvloop==0.21.0
+watchfiles==1.1.0
 wcwidth==0.2.14
 webencodings==0.5.1
+websockets==15.0.1
 zopfli==0.2.3.post1