bolade/bio-performx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add compiled Python bytecode for report generator and spirometry table extractor services

Browse Source 
- Generated bytecode for report_generator.py and spirometry_table_extractor.py
- These changes include the compiled .pyc files in the __pycache__ directory
- The report generator service handles the generation of medical reports from uploaded files
- The spirometry table extractor service extracts data from PDF files and processes it for further analysis
This commit is contained in:
bolade
2025-10-04 10:07:40 +01:00
parent 14dc64234d
commit d66f3fd18b
15 changed files with 482 additions and 3751 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/services/__pycache__/context.cpython-312.pyc
BIN
View File
Binary file not shown.
app/services/__pycache__/context_generator.cpython-312.pyc
BIN
View File
Binary file not shown.
app/services/__pycache__/graph_generator.cpython-312.pyc
BIN
View File
Binary file not shown.
app/services/__pycache__/report_generator.cpython-312.pyc
BIN
View File
Binary file not shown.
app/services/__pycache__/spirometry_table_extractor.cpython-312.pyc
BIN
View File
Binary file not shown.
app/services/context.py
-343
View File
@@ -1,343 +0,0 @@
import base64
def image_to_base64(image_path):
try:
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8")
except FileNotFoundError:
print(f"Warning: Image not found at {image_path}")
return ""
### Defining Page Contexts ###
page_1_context = {
"name": "John Doe",
"surname": "Moran",
"date": "July 29, 2025",
}
page_2_context = {
"content": "This is page 2 content",
}
page_3_context = {
"patient_name": "Keirstyn Moran",
}
page_4_context = {
"body_composition_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/body_composition_chart.png"
),
"body_fat_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/body_fat_percent_chart.png"
),
}
page_5_context = {
"metabolism_chart": "",
"fuel_source_chart": "",
"resting_calories": 1540,
"neat_calories": 310,
"weight_loss_calories": 1725,
"weight_loss_rate": "1lb/week",
"total_calories": 3575,
}
page_6_context = {
"patient_name": "Keirstyn Moran",
"age": "34",
"height": "5'4\"",
"weight": "123lbs",
"focus": "Endurance",
"deficit_calories": "1725KCals",
"deficit_protein": "120g Protein",
"deficit_carbs": "155g Carbs",
"deficit_fat": "69g Fat",
"deficit_fiber": "25g Fibre",
"refeed_weekday_calories": "1615KCals",
"refeed_weekday_protein": "120g Protein",
"refeed_weekday_carbs": "142g Carbs",
"refeed_weekday_fat": "63g Fat",
"refeed_weekday_fiber": "24g Fibre",
"refeed_weekend_calories": "2000KCals",
"refeed_weekend_protein": "120g Protein",
"refeed_weekend_carbs": "190g Carbs",
"refeed_weekend_fat": "84g Fat",
"refeed_weekend_fiber": "30g Fibre",
"protein_percentage": "28%",
"carbs_percentage": "36%",
"fats_percentage": "36%",
"page_number": "6",
}
page_7_context = {
"indication": "No Respiratory Capacity Limitation",
"peak_vt": 3.2,
"peak_vt_bpm": 198,
"peak_vt_zone": 3,
"fev1_percentage": 85,
"lung_analysis_chart": image_to_base64("/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/spirometry_chart.png"),
"respiratory_analysis_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/respiratory.png"
),
}
page_8_context = {
"vo2_max_value": "49.5",
"vo2_max_percentile": "100th percentile",
"age_range": "30-39",
"very_poor_range": "19.0-24.1",
"poor_range": "24.1-28.2",
"fair_range": "28.2-32.2",
"good_range": "32.2-35.7",
"excellent_range": "35.7-45.8",
"superior_range": "45.8+",
"zone1_percentage": "55-65% of Max Heart Rate",
"zone2_percentage": "65-75% of Max Heart Rate",
"zone3_percentage": "80-85% of Max Heart Rate",
"zone4_percentage": "85-88% of Max Heart Rate",
"zone5_percentage": "90% of Max Heart Rate",
"zone1_bpm": "81-96bpm",
"zone2_bpm": "96-100bpm",
"zone3_bpm": "100-178bpm",
"zone4_bpm": "178-188bpm",
"zone5_bpm": "188-198bpm",
"zone1_speed": "3.5mph",
"zone2_speed": "3.5-4.0mph",
"zone3_speed": "4.0-6.5mph",
"zone4_speed": "6.5-7.0mph",
"zone5_speed": "7.0-8.0mph",
"zone1_incline": "2% Incline",
"zone2_incline": "2% Incline",
"zone3_incline": "2% Incline",
"zone4_incline": "2% Incline",
"zone5_incline": "2% Incline",
"zone1_pace": "10:39min/km Pace",
"zone2_pace": "10:39-9:19min/km Pace",
"zone3_pace": "9:19-5:44min/km Pace",
"zone4_pace": "5:44-5:20min/km Pace",
"zone5_pace": "5:20-4:40min/km Pace",
"zone1_calories": "4.4kcals/minute",
"zone2_calories": "5.9kcals/minute",
"zone3_calories": "9.4kcals/minute",
"zone4_calories": "12.5kcals/minute",
"zone5_calories": "12.8kcals/minute",
"zone1_carb": "Avg: 0.4g/min Carb Utilization",
"zone2_carb": "Avg: 0.6g/min Carb Utilization",
"zone3_carb": "Avg: 1.9g/min Carb Utilization",
"zone4_carb": "Avg: 2.9g/min Carb Utilization",
"zone5_carb": "Avg: 3.1g/min Carb Utilization",
"zone1_breaths": "Avg: 27 breaths",
"zone2_breaths": "Avg: 28 breaths",
"zone3_breaths": "Avg: 31 breaths",
"zone4_breaths": "Avg: 42 breaths",
"zone5_breaths": "Avg: 51 breaths",
"zone1_breath_range": "Ideal Range: 15-20 breaths",
"zone2_breath_range": "Ideal Range: 20-25 breaths",
"zone3_breath_range": "Ideal Range: 25-30 breaths",
"zone4_breath_range": "Ideal Range: 30-35 breaths",
"zone5_breath_range": "Ideal Range: 40+ breaths",
}
page_9_context = {
"fuel_utilization_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/fuel_utilization_chart.png"
),
}
page_10_context = {
"vo2_pulse_drop_bpm": "180 bpm",
"vo2_pulse_drop_zone": "Zone 4",
"vo2_pulse_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/vo2_pulse_chart.png"
),
"vo2_breath_drop_bpm": "173 bpm",
"vo2_breath_drop_zone": "Zone 3",
"vo2_breath_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/vo2_breath_chart.png"
),
}
page_11_context = {
"fat_max_optimal": "*Optimal 10-12Kcals/minute",
"fat_max_value": "3.8Kcals/min",
"fat_max_heart_rate": "49% of Max Heart Rate",
"fat_max_bpm": "97 bpm",
"crossover_bpm": "100bpm",
"crossover_heart_rate": "51% of Max Heart Rate",
"fat_metabolism_note": "100bpm at a speed of 4.0mph and incline of 2%",
"fat_metabolism_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/fat_metabolism_chart.png"
),
"cardiac_recovery_time": "(1 minute)",
"cardiac_recovery_percentage": "33%",
"metabolic_recovery_time": "(2 minute)",
"metabolic_recovery_percentage": "65%",
"breath_recovery_time": "(2.5 minute)",
"breath_recovery_percentage": "76%",
"recovery_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/recovery_chart.png"
),
"resting_heart_rate": "53bpm",
"hr_age_range": "26-35",
"hr_poor": "82bpm +",
"hr_below_avg": "75-81bpm",
"hr_average": "71-74bpm",
"hr_above_avg": "66-70bpm",
"hr_good": "62-65bpm",
"hr_excellent": "55-61bpm",
"hr_athlete": "44-54bpm",
}
page_12_context = {
}
page_13_context = {
"patient_name": "Keirstyn Moran",
"age": "34",
"height": "5'4\"",
"weight": "123lbs",
"focus": "Endurance",
"zone2_frequency": "3-4x/week",
"zone2_duration": "40+ minutes",
"zone2_hr_range": "96-110bpm",
"zone2_speed": "3.5-4.0mph",
"zone2_incline": "2% Incline",
"zone3_frequency": "1-2x/week",
"zone3_duration": "10-20 minutes",
"zone3_hr_range": "100-178bpm",
"zone3_speed": "4.0-6.5mph",
"zone3_incline": "2% Incline",
"zone3_target_hr": "140bpm",
"zone3_recovery_speed": "3.5mph",
"zone3_recovery_incline": "2% Incline",
"zone1_hr_range": "81-96bpm",
"zone1_duration": "4-8 minutes",
"zone3_repeats": "2-3 times",
"short_sets": "8-10",
"short_duration": "10-30 seconds",
"short_zone": "5",
"short_rpe": "10",
"short_recovery": "20-60 seconds",
"medium_sets": "6-8",
"medium_duration": "30-90 seconds",
"medium_zone": "4",
"medium_rpe": "8-9",
"medium_recovery": "30-90 seconds",
"long_sets": "4-6",
"long_duration": "5-10 minutes",
"long_zone": "3/4",
"long_rpe": "7-8",
"long_recovery": "2.5-5 minutes",
"tempo_sets": "2-3",
"tempo_duration": "10-20 minutes",
"tempo_zone": "3",
"tempo_rpe": "6-7",
"tempo_recovery": "4-8 minutes",
"cardio_sets": "1",
"cardio_duration": ">40 minutes",
"cardio_zone": "2",
"cardio_rpe": "4-5",
"cardio_recovery": "N/A",
"week1_mon_zone": "Zone 2",
"week1_mon_duration": "45 mins",
"week1_tue_zone": "Zone 2",
"week1_tue_duration": "45 mins",
"week1_wed_zone": "Zone 3",
"week1_wed_duration1": "10mins On",
"week1_wed_duration2": "8mins Rest",
"week1_wed_sets": "x2",
"week1_thu_content": "",
"week1_fri_zone": "Zone 2",
"week1_fri_duration": "45 mins",
"week1_sat_content": "",
"week1_sun_content": "",
"week2_mon_zone": "Zone 2",
"week2_mon_duration": "50 mins",
"week2_tue_zone": "Zone 2",
"week2_tue_duration": "50 mins",
"week2_wed_zone": "Zone 3",
"week2_wed_duration1": "10mins On",
"week2_wed_duration2": "6mins Rest",
"week2_wed_sets": "x2",
"week2_thu_content": "",
"week2_fri_zone": "Zone 2",
"week2_fri_duration": "50 mins",
"week2_sat_content": "",
"week2_sun_content": "",
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": "13",
}
page_14_context = {
"patient_name": "Keirstyn Moran",
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": "14",
}
page_15_context = {
"patient_name": "Keirstyn Moran",
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": "15",
}
page_16_context = {
"patient_name": "Keirstyn Moran",
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": "16",
}
page_17_context = {
"patient_name": "Keirstyn Moran",
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": "17",
}
page_18_context = {
"body_fat_percentage_chart": image_to_base64(
"/home/oluwasanmi/Documents/Work/MKD/report_generation/graphs/fat_percent_master_chart.png"
),
}
page_19_context = {
"patient_name": "Keirstyn Moran",
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": "19",
}
context_list = [
page_1_context,
page_2_context,
page_3_context,
page_4_context,
page_5_context,
page_6_context,
page_7_context,
page_8_context,
page_9_context,
page_10_context,
page_11_context,
page_12_context,
page_13_context,
page_14_context,
page_15_context,
page_16_context,
page_17_context,
page_18_context,
page_19_context,
]
app/services/context_generator.py
+96 -235
View File
@@ -1,319 +1,180 @@
import base64 """
Context Generator Service
This service processes all data files and generates context dictionaries for each page
of the medical report. It performs analysis on Pnoe, Spirometry, and SECA data.
"""
from datetime import datetime
from pathlib import Path from pathlib import Path
from typing import Dict, List, Optional, Tuple from typing import Dict, List, Optional, Tuple
import matplotlib.pyplot as plt
import pandas as pd import pandas as pd
class ReportGenerator: class ContextGenerator:
"""Generate context data for report pages"""
def __init__(self): def __init__(self):
self.pnoe_df = None self.pnoe_df = None
self.patient_df = None
self.spirometry_df = None self.spirometry_df = None
self.seca_df = None self.seca_df = None
self.patient_info = {} self.patient_info = {}
self.charts_dir = Path("graphs")
self.charts_dir.mkdir(exist_ok=True)
def load_data( def load_data(
self, self,
pnoe_path: str, pnoe_path: str,
patient_path: str,
spirometry_path: str, spirometry_path: str,
seca_path: str = None, seca_path: str,
): ):
"""Load all required datasets""" """Load all required datasets"""
self.pnoe_df = pd.read_csv(pnoe_path, delimiter=";") self.pnoe_df = pd.read_csv(pnoe_path, delimiter=";")
self.patient_df = pd.read_csv(patient_path)
self.spirometry_df = pd.read_csv(spirometry_path) self.spirometry_df = pd.read_csv(spirometry_path)
if seca_path: self.seca_df = pd.read_excel(seca_path)
self.seca_df = pd.read_excel(seca_path) self._preprocess_pnoe_data()
# Apply preprocessing def _preprocess_pnoe_data(self):
self._preprocess_data() """Apply preprocessing steps to Pnoe data"""
def _preprocess_data(self):
"""Apply preprocessing steps from your notebook"""
# Convert to numeric
self.pnoe_df = self.pnoe_df.apply(pd.to_numeric, errors="ignore") self.pnoe_df = self.pnoe_df.apply(pd.to_numeric, errors="ignore")
self.pnoe_df["VO2 Pulse"] = self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["HR(bpm)"]
# Calculate derived columns self.pnoe_df["VO2 Breath"] = self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["BF(bpm)"]
self.pnoe_df["VO2 Pulse"] = ( self.pnoe_df["CHO"] = self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["CARBS(%)"] / 100
self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["HR(bpm)"] self.pnoe_df["FAT"] = self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["FAT(%)"] / 100
)
self.pnoe_df["VO2 Breath"] = (
self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["BF(bpm)"]
)
self.pnoe_df["CHO"] = (
self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["CARBS(%)"] / 100
)
self.pnoe_df["FAT"] = (
self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["FAT(%)"] / 100
)
# Apply smoothing
window_size = 10 window_size = 10
columns_to_smooth = [ columns_to_smooth = ["VO2(ml/min)", "VCO2(ml/min)", "HR(bpm)", "VT(l)", "BF(bpm)", "VE(l/min)", "VO2 Pulse", "VO2 Breath", "CHO", "FAT"]
"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: for col in columns_to_smooth:
if col in self.pnoe_df.columns: if col in self.pnoe_df.columns:
self.pnoe_df[f"{col}_smoothed"] = ( self.pnoe_df[f"{col}_smoothed"] = self.pnoe_df[col].rolling(window=window_size, min_periods=1).mean()
self.pnoe_df[col].rolling(window=window_size, min_periods=1).mean()
)
def extract_patient_info(self, last_name: str) -> Dict: def extract_patient_info(self, patient_name: str) -> Dict:
"""Extract patient information from datasets""" """Extract patient information from SECA dataset"""
if self.seca_df is not None: if self.seca_df is not None:
patient_data = self.seca_df[ patient_data = self.seca_df[self.seca_df["LastName"].str.contains(patient_name, case=False, na=False)]
self.seca_df["LastName"].str.contains(last_name, case=False, na=False)
]
if not patient_data.empty: if not patient_data.empty:
row = patient_data.iloc[0] row = patient_data.iloc[0]
weight_kg = float(row.get("Weight", 0))
fat_pct = float(row.get("Adult_FMP", 0))
self.patient_info = { self.patient_info = {
"name": f"{row.get('FirstName', '')} {last_name}", "name": f"{row.get('FirstName', '')} {row.get('LastName', '')}",
"first_name": row.get("FirstName", ""),
"last_name": row.get("LastName", ""),
"age": int(row.get("Age", 0)), "age": int(row.get("Age", 0)),
"height": f"{row.get('Height', '')}", "height": f"{row.get('Height', '')}",
"weight": float(row.get("Weight", 0)), "weight": weight_kg,
"gender": row.get("Gender", "").lower(), "gender": row.get("Gender", "").lower(),
"fat_percentage": float(row.get("Adult_FMP", 0)), "fat_percentage": fat_pct,
"fat_mass_lbs": weight_kg * fat_pct / 100 * 2.20462,
"lean_mass_lbs": weight_kg * (1 - fat_pct / 100) * 2.20462,
} }
return self.patient_info return self.patient_info
def calculate_spirometry_metrics(self) -> Dict: def calculate_spirometry_metrics(self) -> Dict:
"""Calculate spirometry-related metrics""" """Calculate spirometry-related metrics"""
metrics = {} metrics = {}
# Extract key spirometry values
for param in ["FVC", "FEV1", "FEV1/FVC%"]: for param in ["FVC", "FEV1", "FEV1/FVC%"]:
row = self.spirometry_df.loc[self.spirometry_df["Parameters"] == param] row = self.spirometry_df.loc[self.spirometry_df["Parameters"].str.strip() == param]
if not row.empty: if not row.empty:
metrics[ param_key = param.lower().replace('/', '_').replace('%', '_pct')
f"{param.lower().replace('/', '_').replace('%', '_pct')}_best" metrics[f"{param_key}_best"] = row["Best"].values[0]
] = row["Best"].values[0] metrics[f"{param_key}_pred"] = row["%Pred."].values[0]
metrics[
f"{param.lower().replace('/', '_').replace('%', '_pct')}_pred"
] = row["%Pred."].values[0]
return metrics return metrics
def calculate_pnoe_metrics(self) -> Dict: def calculate_pnoe_metrics(self) -> Dict:
"""Calculate all Pnoe-derived metrics""" """Calculate all Pnoe-derived metrics"""
metrics = {} metrics = {}
# Basic metrics
metrics["vo2_max"] = self.pnoe_df["VO2(ml/min)_smoothed"].max() metrics["vo2_max"] = self.pnoe_df["VO2(ml/min)_smoothed"].max()
metrics["vo2_max_per_kg"] = metrics["vo2_max"] / self.patient_info["weight"] metrics["vo2_max_per_kg"] = metrics["vo2_max"] / self.patient_info["weight"]
# Peak VT
peak_vt_idx = self.pnoe_df["VT(l)_smoothed"].idxmax() peak_vt_idx = self.pnoe_df["VT(l)_smoothed"].idxmax()
peak_vt_row = self.pnoe_df.loc[peak_vt_idx] peak_vt_row = self.pnoe_df.loc[peak_vt_idx]
metrics["peak_vt"] = peak_vt_row["VT(l)_smoothed"] metrics["peak_vt"] = peak_vt_row["VT(l)_smoothed"]
metrics["peak_vt_hr"] = peak_vt_row["HR(bpm)_smoothed"] metrics["peak_vt_hr"] = peak_vt_row["HR(bpm)_smoothed"]
# Fat burning metrics
fat_max_idx = self.pnoe_df["FAT_smoothed"].idxmax() fat_max_idx = self.pnoe_df["FAT_smoothed"].idxmax()
fat_max_row = self.pnoe_df.loc[fat_max_idx] fat_max_row = self.pnoe_df.loc[fat_max_idx]
metrics["fat_max_value"] = fat_max_row["FAT_smoothed"] metrics["fat_max_value"] = fat_max_row["FAT_smoothed"]
metrics["fat_max_hr"] = fat_max_row["HR(bpm)_smoothed"] metrics["fat_max_hr"] = fat_max_row["HR(bpm)_smoothed"]
# Calculate zones (simplified from your logic)
metrics.update(self._calculate_hr_zones())
# VT1/VT2 detection
vt1, vt2 = self._detect_thresholds() vt1, vt2 = self._detect_thresholds()
metrics["vt1"] = vt1 metrics["vt1"] = vt1
metrics["vt2"] = vt2 metrics["vt2"] = vt2
zones = self._calculate_hr_zones(vt1, vt2, fat_max_row)
metrics.update(zones)
return metrics return metrics
def _detect_thresholds(self) -> Tuple[Optional[Dict], Optional[Dict]]: def _detect_thresholds(self) -> Tuple[Optional[Dict], Optional[Dict]]:
"""Detect VT1 and VT2 thresholds""" """Detect VT1 and VT2 thresholds"""
# VT1: First crossover where carbs > fat
condition = self.pnoe_df["CHO_smoothed"] > self.pnoe_df["FAT_smoothed"] condition = self.pnoe_df["CHO_smoothed"] > self.pnoe_df["FAT_smoothed"]
crossover_indices = condition[condition].index crossover_indices = condition[condition].index
vt1 = None vt1 = None
if len(crossover_indices) > 0: if len(crossover_indices) > 0:
vt1_idx = crossover_indices[0] vt1_idx = crossover_indices[0]
vt1_row = self.pnoe_df.loc[vt1_idx] vt1_row = self.pnoe_df.loc[vt1_idx]
vt1 = { vt1 = {"HeartRate": vt1_row["HR(bpm)_smoothed"], "Speed": vt1_row["Speed"], "Time": vt1_row["T(sec)"]}
"HeartRate": vt1_row["HR(bpm)_smoothed"],
"Speed": vt1_row["Speed"],
"Time": vt1_row["T(sec)"],
}
# VT2: Ventilation inflection (simplified)
ve_slope = self.pnoe_df["VE(l/min)_smoothed"].diff() ve_slope = self.pnoe_df["VE(l/min)_smoothed"].diff()
second_derivative = ve_slope.diff() second_derivative = ve_slope.diff()
vt2_idx = second_derivative.idxmax() vt2_idx = second_derivative.idxmax()
vt2 = None vt2 = None
if pd.notna(vt2_idx): if pd.notna(vt2_idx):
vt2_row = self.pnoe_df.loc[vt2_idx] vt2_row = self.pnoe_df.loc[vt2_idx]
vt2 = { vt2 = {"HeartRate": vt2_row["HR(bpm)_smoothed"], "Speed": vt2_row["Speed"], "Time": vt2_row["T(sec)"]}
"HeartRate": vt2_row["HR(bpm)_smoothed"],
"Speed": vt2_row["Speed"],
"Time": vt2_row["T(sec)"],
}
return vt1, vt2 return vt1, vt2
def _calculate_hr_zones(self) -> Dict: def _calculate_hr_zones(self, vt1: Optional[Dict], vt2: Optional[Dict], fat_max_row: pd.Series) -> Dict:
"""Calculate heart rate zones""" """Calculate heart rate zones based on thresholds"""
max_hr = 220 - self.patient_info["age"] zones = {}
if vt1 and vt2:
# Simplified zone calculation - you can make this more sophisticated zone_1_start = fat_max_row["HR(bpm)_smoothed"] - 15
zones = { zone_2_start = fat_max_row["HR(bpm)_smoothed"]
"zone1_bpm": f"{int(max_hr * 0.55)}-{int(max_hr * 0.65)}bpm", zone_3_start = vt1["HeartRate"]
"zone2_bpm": f"{int(max_hr * 0.65)}-{int(max_hr * 0.75)}bpm", zone_4_start = vt2["HeartRate"] - 10
"zone3_bpm": f"{int(max_hr * 0.75)}-{int(max_hr * 0.85)}bpm", zone_5_start = vt2["HeartRate"] + 10
"zone4_bpm": f"{int(max_hr * 0.85)}-{int(max_hr * 0.95)}bpm",
"zone5_bpm": f"{int(max_hr * 0.95)}+bpm", zones["zone1_bpm"] = f"{int(zone_1_start)}-{int(zone_2_start)}bpm"
} zones["zone2_bpm"] = f"{int(zone_2_start)}-{int(vt1['HeartRate'])}bpm"
zones["zone3_bpm"] = f"{int(zone_3_start)}-{int(zone_4_start)}bpm"
zones["zone4_bpm"] = f"{int(zone_4_start)}-{int(zone_5_start)}bpm"
zones["zone5_bpm"] = f"{int(zone_5_start)}+bpm"
else:
max_hr = 220 - self.patient_info["age"]
zones["zone1_bpm"] = f"{int(max_hr * 0.55)}-{int(max_hr * 0.65)}bpm"
zones["zone2_bpm"] = f"{int(max_hr * 0.65)}-{int(max_hr * 0.75)}bpm"
zones["zone3_bpm"] = f"{int(max_hr * 0.75)}-{int(max_hr * 0.85)}bpm"
zones["zone4_bpm"] = f"{int(max_hr * 0.85)}-{int(max_hr * 0.95)}bpm"
zones["zone5_bpm"] = f"{int(max_hr * 0.95)}+bpm"
return zones return zones
def generate_charts(self) -> Dict[str, str]: def generate_all_contexts(self, patient_name: str, graphs: Dict[str, str]) -> List[Dict]:
"""Generate all charts and return base64 encoded versions"""
charts = {}
# Generate fuel utilization chart
charts["fuel_utilization_chart"] = self._create_fuel_chart()
# Generate VO2 pulse chart
charts["vo2_pulse_chart"] = self._create_vo2_pulse_chart()
# Generate body composition chart
charts["body_composition_chart"] = self._create_body_comp_chart()
# Add more chart generation methods...
return charts
def _create_fuel_chart(self) -> str:
"""Create and save fuel utilization chart"""
# Use your existing chart code but make it dynamic
speed_groups = self.pnoe_df.groupby("Speed").mean(numeric_only=True).round(1)
speed_groups = speed_groups.iloc[1:-1]
filtered_data = speed_groups[
(speed_groups.index >= 3.5) & (speed_groups.index <= 7.5)
]
plt.figure(figsize=(15, 8))
# ... your chart code here ...
chart_path = self.charts_dir / "fuel_utilization_chart.png"
plt.savefig(chart_path, dpi=300)
plt.close()
return self._image_to_base64(chart_path)
def _create_vo2_pulse_chart(self) -> str:
"""Create VO2 pulse chart"""
# Your VO2 pulse chart code here
chart_path = self.charts_dir / "vo2_pulse_chart.png"
# ... chart generation code ...
return self._image_to_base64(chart_path)
def _create_body_comp_chart(self) -> str:
"""Create body composition chart"""
# Your body composition chart code here
chart_path = self.charts_dir / "body_composition_chart.png"
# ... chart generation code ...
return self._image_to_base64(chart_path)
def _image_to_base64(self, image_path: Path) -> str:
"""Convert image to base64"""
try:
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8")
except FileNotFoundError:
return ""
def generate_all_contexts(self, last_name: str = "Moran") -> List[Dict]:
"""Main method to generate all page contexts""" """Main method to generate all page contexts"""
# Extract patient info self.extract_patient_info(patient_name)
self.extract_patient_info(last_name)
# Calculate metrics
spirometry_metrics = self.calculate_spirometry_metrics() spirometry_metrics = self.calculate_spirometry_metrics()
pnoe_metrics = self.calculate_pnoe_metrics() pnoe_metrics = self.calculate_pnoe_metrics()
# Generate charts
charts = self.generate_charts()
# Build contexts for each page
contexts = [] contexts = []
contexts.append({"name": self.patient_info["name"], "surname": self.patient_info["last_name"], "date": datetime.now().strftime("%B %d, %Y")})
# Page 1 contexts.append({"patient_name": self.patient_info["name"], "test_date": datetime.now().strftime("%B %d, %Y")})
contexts.append(
{ for i in range(4):
"name": self.patient_info["name"], contexts.append({"patient_name": self.patient_info["name"], "page_number": i + 3})
"surname": last_name,
"date": "July 29, 2025", fev1_percentage = 0
} if spirometry_metrics.get("fvc_best"):
) fev1_percentage = (pnoe_metrics["peak_vt"] / spirometry_metrics["fvc_best"]) * 100
# Page 2-6 (add as needed) contexts.append({"peak_vt": f"{pnoe_metrics['peak_vt']:.2f}", "peak_vt_bpm": f"{int(pnoe_metrics['peak_vt_hr'])}", "fev1_percentage": f"{fev1_percentage:.1f}", "lung_analysis_chart": graphs.get("spirometry_chart", ""), "respiratory_analysis_chart": graphs.get("respiratory", "")})
for i in range(5): contexts.append({"vo2_max_value": f"{pnoe_metrics['vo2_max_per_kg']:.1f}", "age_range": f"{self.patient_info['age'] // 10 * 10}-{self.patient_info['age'] // 10 * 10 + 9}", "zone1_bpm": pnoe_metrics.get("zone1_bpm", ""), "zone2_bpm": pnoe_metrics.get("zone2_bpm", ""), "zone3_bpm": pnoe_metrics.get("zone3_bpm", ""), "zone4_bpm": pnoe_metrics.get("zone4_bpm", ""), "zone5_bpm": pnoe_metrics.get("zone5_bpm", ""), "vo2_pulse_chart": graphs.get("vo2_pulse", "")})
contexts.append({}) contexts.append({"fat_max_value": f"{pnoe_metrics['fat_max_value']:.2f}", "fat_max_hr": f"{int(pnoe_metrics['fat_max_hr'])}", "fuel_utilization_chart": graphs.get("fuel_utilization", ""), "fat_metabolism_chart": graphs.get("fat_metabolism", "")})
contexts.append({"fat_percentage": f"{self.patient_info['fat_percentage']:.1f}", "fat_mass_lbs": f"{self.patient_info['fat_mass_lbs']:.1f}", "lean_mass_lbs": f"{self.patient_info['lean_mass_lbs']:.1f}", "body_composition_chart": graphs.get("body_composition", ""), "body_fat_percent_chart": graphs.get("body_fat_percent", "")})
# Page 7 - Spirometry
contexts.append( for i in range(9):
{ contexts.append({"patient_name": self.patient_info["name"], "page_number": i + 11, "vo2_breath_chart": graphs.get("vo2_breath", ""), "recovery_chart": graphs.get("recovery", "")})
"peak_vt": pnoe_metrics["peak_vt"],
"peak_vt_bpm": pnoe_metrics["peak_vt_hr"],
"fev1_percentage": (
pnoe_metrics["peak_vt"] / spirometry_metrics["fvc_best"]
)
* 100,
"lung_analysis_chart": charts.get("spirometry_chart", ""),
"respiratory_analysis_chart": charts.get("respiratory_chart", ""),
}
)
# Page 8 - VO2 Max and Zones
contexts.append(
{
"vo2_max_value": f"{pnoe_metrics['vo2_max_per_kg']:.1f}",
"age_range": f"{self.patient_info['age'] // 10 * 10}-{self.patient_info['age'] // 10 * 10 + 9}",
**pnoe_metrics, # Include all zone calculations
}
)
# Continue for all pages...
# Add remaining pages as needed
return contexts return contexts
# Usage for backend service
def generate_report(
pnoe_file, patient_file, spirometry_file, seca_file=None, patient_name="Moran"
):
"""Main function for backend service"""
generator = ReportGenerator()
generator.load_data(pnoe_file, patient_file, spirometry_file, seca_file)
return generator.generate_all_contexts(patient_name)
# Example usage
if __name__ == "__main__":
contexts = generate_report(
"data/Pnoe_20250729_1550-Moran_Keirstyn.csv",
"data/patient_data.csv",
"data/spirometry_data.csv",
"data/SECA body comp for all patients.xlsx",
)
print(f"Generated {len(contexts)} page contexts")
app/services/graph_generator.py
+288 -295
View File
@@ -1,6 +1,12 @@
"""
Graph Generator Service
This service generates all the charts and visualizations required for the medical report.
Based on the analysis notebooks in services_dfdf/.
"""
import base64 import base64
from pathlib import Path from pathlib import Path
from typing import Dict
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import matplotlib.transforms as mtransforms import matplotlib.transforms as mtransforms
@@ -11,13 +17,28 @@ from matplotlib.patches import FancyBboxPatch
class GraphGenerator: class GraphGenerator:
"""Generate all charts for medical reports"""
def __init__(self, charts_dir: str = "graphs"): def __init__(self, charts_dir: str = "graphs"):
"""Initialize the GraphGenerator with output directory for charts""" """
Initialize the graph generator.
Args:
charts_dir: Directory to save generated charts
"""
self.charts_dir = Path(charts_dir) self.charts_dir = Path(charts_dir)
self.charts_dir.mkdir(exist_ok=True) self.charts_dir.mkdir(exist_ok=True)
def _image_to_base64(self, image_path: Path) -> str: def _image_to_base64(self, image_path: Path) -> str:
"""Convert image to base64 string""" """
Convert image file to base64 string.
Args:
image_path: Path to image file
Returns:
Base64 encoded string
"""
try: try:
with open(image_path, "rb") as image_file: with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8") return base64.b64encode(image_file.read()).decode("utf-8")
@@ -25,27 +46,35 @@ class GraphGenerator:
return "" return ""
def generate_respiratory_chart( def generate_respiratory_chart(
self, df: pd.DataFrame, save_as_base64: bool = False self, df: pd.DataFrame, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate respiratory chart showing VT and Speed over time""" """
# Get phase times for background regions Generate respiratory chart (VT and Speed over time).
Args:
df: Processed DataFrame with smoothed columns
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
first_unique_phase = df.drop_duplicates(subset="PHASE") first_unique_phase = df.drop_duplicates(subset="PHASE")
phase_times = first_unique_phase["T(sec)"].tolist() phase_times = first_unique_phase["T(sec)"].tolist()
plt.figure(figsize=(18, 5)) plt.figure(figsize=(18, 5))
ax1 = plt.subplot() ax1 = plt.subplot()
# Plot VT with step-like appearance # Plot VT
sns.lineplot(data=df, x="T(sec)", y="VT(l)_smoothed", label="VT (L)") sns.lineplot(data=df, x="T(sec)", y="VT(l)_smoothed", label="VT (L)")
ax1.set_xlabel("Time (sec)") ax1.set_xlabel("Time (sec)")
ax1.set_ylabel("VT (L)") ax1.set_ylabel("VT (L)")
ax1.grid(True, alpha=0.1) ax1.grid(True, alpha=0.1)
ax1.set_ylim(0, min(8, df["VT(l)_smoothed"].max())) ax1.set_ylim(0, min(8, df["VT(l)_smoothed"].max()))
# Plot speed as step function on secondary y-axis # Plot speed on secondary y-axis
ax2 = ax1.twinx() ax2 = ax1.twinx()
ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200)) ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200))
line2 = sns.lineplot( sns.lineplot(
data=df, data=df,
x="T(sec)", x="T(sec)",
y="Speed", y="Speed",
@@ -58,11 +87,9 @@ class GraphGenerator:
ax2.set_ylabel("Speed") ax2.set_ylabel("Speed")
ax2.set_ylim(0, min(30, df["Speed"].max()) + 1) ax2.set_ylim(0, min(30, df["Speed"].max()) + 1)
# Remove default legends first # Combine legends
ax1.get_legend().remove() ax1.get_legend().remove()
ax2.get_legend().remove() ax2.get_legend().remove()
# Combine legends from both axes in the top left
lines1, labels1 = ax1.get_legend_handles_labels() lines1, labels1 = ax1.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels() lines2, labels2 = ax2.get_legend_handles_labels()
ax1.legend(lines1 + lines2, labels1 + labels2, loc="upper left") ax1.legend(lines1 + lines2, labels1 + labels2, loc="upper left")
@@ -81,12 +108,23 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_fuel_utilization_chart( def generate_fuel_utilization_chart(
self, df: pd.DataFrame, save_as_base64: bool = False self, df: pd.DataFrame, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate fuel utilization chart with stacked bars showing fat vs carbs""" """
# Group by speed and calculate mean for numeric columns only Generate fuel utilization chart (CHO vs FAT by stage).
Args:
df: Processed DataFrame with smoothed columns
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
# Group by speed and calculate mean
speed_groups = df.groupby("Speed").mean(numeric_only=True).round(1) speed_groups = df.groupby("Speed").mean(numeric_only=True).round(1)
speed_groups = speed_groups.iloc[1:-1] speed_groups = speed_groups.iloc[1:-1]
# Filter data
filtered_data = speed_groups[ filtered_data = speed_groups[
(speed_groups.index >= 3.5) & (speed_groups.index <= 7.5) (speed_groups.index >= 3.5) & (speed_groups.index <= 7.5)
] ]
@@ -94,19 +132,24 @@ class GraphGenerator:
plt.figure(figsize=(15, 8)) plt.figure(figsize=(15, 8))
plt.style.use("default") plt.style.use("default")
# Create stage labels and positions
stage_labels = [f"Stage {i}" for i in range(1, len(filtered_data) + 1)] stage_labels = [f"Stage {i}" for i in range(1, len(filtered_data) + 1)]
x_positions = np.arange(len(filtered_data)) x_positions = np.arange(len(filtered_data))
# Calculate fat and carbs energy expenditure from percentages # Calculate fat and carbs energy expenditure
fat_ee = filtered_data["EE(kcal/min)"] * filtered_data["FAT(%)"] / 100 fat_ee = filtered_data["EE(kcal/min)"] * filtered_data["FAT(%)"] / 100
carbs_ee = filtered_data["EE(kcal/min)"] * filtered_data["CARBS(%)"] / 100 carbs_ee = filtered_data["EE(kcal/min)"] * filtered_data["CARBS(%)"] / 100
# Create the main axis for the stacked bars
ax1 = plt.gca() ax1 = plt.gca()
# Create stacked bar chart with colors # Create stacked bar chart
ax1.bar(x_positions, fat_ee, color="#1f77b4", alpha=0.8, width=0.6, label="Fat") ax1.bar(
x_positions,
fat_ee,
color="#1f77b4",
alpha=0.8,
width=0.6,
label="Fat",
)
ax1.bar( ax1.bar(
x_positions, x_positions,
carbs_ee, carbs_ee,
@@ -117,16 +160,15 @@ class GraphGenerator:
label="Carbs", label="Carbs",
) )
# Set labels and formatting for primary axis
ax1.set_xlabel("", fontsize=12) ax1.set_xlabel("", fontsize=12)
ax1.set_ylabel("Fuel (kcal/min)", fontsize=12) ax1.set_ylabel("Fuel (kcal/min)", fontsize=12)
ax1.set_ylim(0, 20) ax1.set_ylim(0, 20)
# Add individual values on each bar segment # Add values on bars
for i, (fat_val, carb_val, total_val) in enumerate( for i, (fat_val, carb_val, total_val) in enumerate(
zip(fat_ee, carbs_ee, filtered_data["EE(kcal/min)"]) zip(fat_ee, carbs_ee, filtered_data["EE(kcal/min)"])
): ):
if fat_val > 0.3: # Fat value if fat_val > 0.3:
ax1.text( ax1.text(
i, i,
fat_val / 2, fat_val / 2,
@@ -137,7 +179,7 @@ class GraphGenerator:
fontweight="bold", fontweight="bold",
color="white", color="white",
) )
if carb_val > 0.3: # Carbs value if carb_val > 0.3:
ax1.text( ax1.text(
i, i,
fat_val + carb_val / 2, fat_val + carb_val / 2,
@@ -148,7 +190,6 @@ class GraphGenerator:
fontweight="bold", fontweight="bold",
color="white", color="white",
) )
# Total EE
ax1.text( ax1.text(
i, i,
total_val + 0.5, total_val + 0.5,
@@ -160,7 +201,7 @@ class GraphGenerator:
color="black", color="black",
) )
# Add speed labels below x-axis # Add speed labels
for i, speed in enumerate(filtered_data.index): for i, speed in enumerate(filtered_data.index):
ax1.text(i, -1.5, f"{speed:.1f} mph", ha="center", va="top", fontsize=9) ax1.text(i, -1.5, f"{speed:.1f} mph", ha="center", va="top", fontsize=9)
ax1.text( ax1.text(
@@ -175,8 +216,6 @@ class GraphGenerator:
# Create secondary y-axis for heart rate # Create secondary y-axis for heart rate
ax2 = ax1.twinx() ax2 = ax1.twinx()
# Plot heart rate line
ax2.plot( ax2.plot(
x_positions, x_positions,
filtered_data["HR(bpm)"], filtered_data["HR(bpm)"],
@@ -187,12 +226,11 @@ class GraphGenerator:
label="Heart Rate", label="Heart Rate",
) )
# Set heart rate axis formatting
ax2.set_ylabel("Heart Rate (bpm)", fontsize=12, color="red") ax2.set_ylabel("Heart Rate (bpm)", fontsize=12, color="red")
ax2.tick_params(axis="y", labelcolor="red") ax2.tick_params(axis="y", labelcolor="red")
ax2.set_ylim(0, 220) ax2.set_ylim(0, 220)
# Add HR values above the points # Add HR values
for i, hr in enumerate(filtered_data["HR(bpm)"]): for i, hr in enumerate(filtered_data["HR(bpm)"]):
ax2.text( ax2.text(
i, i,
@@ -205,7 +243,6 @@ class GraphGenerator:
color="red", color="red",
) )
# Set x-axis formatting
ax1.set_xticks(x_positions) ax1.set_xticks(x_positions)
ax1.set_xticklabels(stage_labels, fontsize=11) ax1.set_xticklabels(stage_labels, fontsize=11)
@@ -221,11 +258,9 @@ class GraphGenerator:
shadow=True, shadow=True,
) )
# Add grid
ax1.grid(True, alpha=0.3, linestyle="-", linewidth=0.5) ax1.grid(True, alpha=0.3, linestyle="-", linewidth=0.5)
ax1.set_axisbelow(True) ax1.set_axisbelow(True)
# Adjust layout
plt.tight_layout() plt.tight_layout()
plt.subplots_adjust(bottom=0.1, top=0.9) plt.subplots_adjust(bottom=0.1, top=0.9)
@@ -236,9 +271,18 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_vo2_pulse_chart( def generate_vo2_pulse_chart(
self, df: pd.DataFrame, save_as_base64: bool = False self, df: pd.DataFrame, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate VO2 Pulse chart with heart rate and speed""" """
Generate VO2 Pulse chart with HR and Speed.
Args:
df: Processed DataFrame with smoothed columns
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
first_unique_phase = df.drop_duplicates(subset="PHASE") first_unique_phase = df.drop_duplicates(subset="PHASE")
phase_times = first_unique_phase["T(sec)"].tolist() phase_times = first_unique_phase["T(sec)"].tolist()
@@ -292,12 +336,14 @@ class GraphGenerator:
ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200)) ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200))
# Remove default legends first # Combine legends
for ax in [ax1, ax2, ax3]: if ax1.get_legend():
if ax.get_legend(): ax1.get_legend().remove()
ax.get_legend().remove() if ax2.get_legend():
ax2.get_legend().remove()
if ax3.get_legend():
ax3.get_legend().remove()
# Combine legends from all axes
lines1, labels1 = ax1.get_legend_handles_labels() lines1, labels1 = ax1.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels() lines2, labels2 = ax2.get_legend_handles_labels()
lines3, labels3 = ax3.get_legend_handles_labels() lines3, labels3 = ax3.get_legend_handles_labels()
@@ -319,16 +365,24 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_vo2_breath_chart( def generate_vo2_breath_chart(
self, df: pd.DataFrame, save_as_base64: bool = False self, df: pd.DataFrame, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate VO2 per Breath chart""" """
Generate VO2 per Breath chart.
Args:
df: Processed DataFrame with smoothed columns
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
first_unique_phase = df.drop_duplicates(subset="PHASE") first_unique_phase = df.drop_duplicates(subset="PHASE")
phase_times = first_unique_phase["T(sec)"].tolist() phase_times = first_unique_phase["T(sec)"].tolist()
plt.figure(figsize=(18, 5)) plt.figure(figsize=(18, 5))
ax1 = plt.subplot() ax1 = plt.subplot()
# Plot VO2 per Breath
sns.lineplot( sns.lineplot(
data=df, data=df,
x="T(sec)", x="T(sec)",
@@ -340,7 +394,7 @@ class GraphGenerator:
ax1.set_ylim(0, df["VO2 Breath_smoothed"].max() + 1) ax1.set_ylim(0, df["VO2 Breath_smoothed"].max() + 1)
ax1.grid(True, alpha=0.1) ax1.grid(True, alpha=0.1)
# Plot speed as step function on secondary y-axis # Plot speed on secondary y-axis
ax2 = ax1.twinx() ax2 = ax1.twinx()
ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200)) ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200))
sns.lineplot( sns.lineplot(
@@ -356,11 +410,9 @@ class GraphGenerator:
ax2.set_ylim(0, df["Speed"].max() + 1) ax2.set_ylim(0, df["Speed"].max() + 1)
ax2.set_ylabel("Speed") ax2.set_ylabel("Speed")
# Remove default legends first # Combine legends
ax1.get_legend().remove() ax1.get_legend().remove()
ax2.get_legend().remove() ax2.get_legend().remove()
# Combine legends from both axes in the top left
lines1, labels1 = ax1.get_legend_handles_labels() lines1, labels1 = ax1.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels() lines2, labels2 = ax2.get_legend_handles_labels()
ax1.legend(lines1 + lines2, labels1 + labels2, loc="upper left") ax1.legend(lines1 + lines2, labels1 + labels2, loc="upper left")
@@ -379,9 +431,18 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_fat_metabolism_chart( def generate_fat_metabolism_chart(
self, df: pd.DataFrame, save_as_base64: bool = False self, df: pd.DataFrame, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate CHO and FAT metabolism chart""" """
Generate fat metabolism chart (CHO vs FAT over time).
Args:
df: Processed DataFrame with smoothed columns
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
first_unique_phase = df.drop_duplicates(subset="PHASE") first_unique_phase = df.drop_duplicates(subset="PHASE")
phase_times = first_unique_phase["T(sec)"].tolist() phase_times = first_unique_phase["T(sec)"].tolist()
@@ -391,7 +452,7 @@ class GraphGenerator:
# Plot CHO # Plot CHO
sns.lineplot(data=df, x="T(sec)", y="CHO_smoothed", label="CHO (kcal/min)") sns.lineplot(data=df, x="T(sec)", y="CHO_smoothed", label="CHO (kcal/min)")
ax1.set_xlabel("Time (sec)") ax1.set_xlabel("Time (sec)")
ax1.set_ylabel("CHO (kcal/min)") ax1.set_ylabel("CHO (g/min)")
ax1.grid(True, alpha=0.1) ax1.grid(True, alpha=0.1)
# Plot FAT on secondary y-axis # Plot FAT on secondary y-axis
@@ -408,11 +469,9 @@ class GraphGenerator:
ax2.set_ylabel("FAT (kcal/min)") ax2.set_ylabel("FAT (kcal/min)")
ax2.set_ylim(0, 15) ax2.set_ylim(0, 15)
# Remove default legends first # Combine legends
ax1.get_legend().remove() ax1.get_legend().remove()
ax2.get_legend().remove() ax2.get_legend().remove()
# Combine legends from both axes in the top left
lines1, labels1 = ax1.get_legend_handles_labels() lines1, labels1 = ax1.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels() lines2, labels2 = ax2.get_legend_handles_labels()
ax1.legend(lines1 + lines2, labels1 + labels2, loc="upper left") ax1.legend(lines1 + lines2, labels1 + labels2, loc="upper left")
@@ -431,9 +490,18 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_recovery_chart( def generate_recovery_chart(
self, df: pd.DataFrame, save_as_base64: bool = False self, df: pd.DataFrame, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate recovery chart with VCO2, HR, and BF""" """
Generate recovery chart (VCO2, HR, and BF).
Args:
df: Processed DataFrame with smoothed columns
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
first_unique_phase = df.drop_duplicates(subset="PHASE") first_unique_phase = df.drop_duplicates(subset="PHASE")
phase_times = first_unique_phase["T(sec)"].tolist() phase_times = first_unique_phase["T(sec)"].tolist()
@@ -449,7 +517,7 @@ class GraphGenerator:
color="blue", color="blue",
) )
ax1.set_xlabel("Time (sec)") ax1.set_xlabel("Time (sec)")
ax1.set_ylabel("VCO2 (ml/min)") ax1.set_ylabel("VO2 Pulse (mL/beat)")
ax1.set_ylim(0, df["VCO2(ml/min)"].max()) ax1.set_ylim(0, df["VCO2(ml/min)"].max())
ax1.grid(True, alpha=0.1) ax1.grid(True, alpha=0.1)
@@ -468,7 +536,7 @@ class GraphGenerator:
ax2.set_ylim(df["HR(bpm)_smoothed"].min(), df["HR(bpm)_smoothed"].max() + 1) ax2.set_ylim(df["HR(bpm)_smoothed"].min(), df["HR(bpm)_smoothed"].max() + 1)
ax2.tick_params(axis="y", labelcolor="red") ax2.tick_params(axis="y", labelcolor="red")
# Create third y-axis for breathing frequency # Create third y-axis for BF
ax3 = ax1.twinx() ax3 = ax1.twinx()
ax3.spines["right"].set_position(("outward", 60)) ax3.spines["right"].set_position(("outward", 60))
sns.lineplot( sns.lineplot(
@@ -485,12 +553,14 @@ class GraphGenerator:
ax3.set_ylim(0, df["BF(bpm)_smoothed"].max() + 1) ax3.set_ylim(0, df["BF(bpm)_smoothed"].max() + 1)
ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200)) ax1.set_xticks(np.arange(0, df["T(sec)"].max() + 200, 200))
# Remove default legends first # Combine legends
for ax in [ax1, ax2, ax3]: if ax1.get_legend():
if ax.get_legend(): ax1.get_legend().remove()
ax.get_legend().remove() if ax2.get_legend():
ax2.get_legend().remove()
if ax3.get_legend():
ax3.get_legend().remove()
# Combine legends from all axes in the top left
lines1, labels1 = ax1.get_legend_handles_labels() lines1, labels1 = ax1.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels() lines2, labels2 = ax2.get_legend_handles_labels()
lines3, labels3 = ax3.get_legend_handles_labels() lines3, labels3 = ax3.get_legend_handles_labels()
@@ -511,129 +581,41 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_body_fat_percentage_chart(
self,
gender: str,
age: int,
body_fat_percentage: float,
save_as_base64: bool = False,
) -> str:
"""Generate body fat percentage chart with ranges"""
# Define the segments with muted colors
segments = [
("#F8A8A8", 0, 15), # Muted Red/Salmon: 0% to 15%
("#FFEECC", 15, 5), # Pale Yellow/Cream: 15% to 20%
("#D0F0C0", 20, 15), # Pale Green/Mint: 20% to 35%
("#FFEECC", 35, 5), # Pale Yellow/Cream: 35% to 40%
("#F8A8A8", 40, 10), # Muted Red/Salmon: 40% to 50%
]
# Determine age group
if 20 <= age <= 39:
age_group = "20-39"
elif 40 <= age <= 59:
age_group = "40-59"
elif 60 <= age <= 79:
age_group = "60-79"
else:
age_group = "N/A"
demographic = f"{age_group}\n({gender[0].upper()})"
fig, ax = plt.subplots(figsize=(10, 2))
# Create the Segmented Bar
for color, start, length in segments:
ax.barh(
y=0,
width=length,
left=start,
height=1,
color=color,
edgecolor="black",
linewidth=0.5,
)
# Add the Indicator (Triangle)
ax.plot(
body_fat_percentage,
1.05,
marker="v",
color="black",
markersize=10,
clip_on=False,
transform=ax.get_xaxis_transform(),
)
# Set Axis Properties and Labels
ax.set_xlim(0, 50)
ax.set_xticks(range(0, 51, 5))
ax.set_yticks([])
ax.text(
-0.05,
0,
demographic,
transform=ax.get_yaxis_transform(),
va="center",
ha="right",
fontsize=12,
)
ax.set_xlim(0, 50)
ticks = range(0, 51, 5)
ax.set_xticks(ticks)
labels = [f"{t}%" for t in ticks]
ax.set_xticklabels(labels)
# Clean up spines and add small ticks
ax.spines["right"].set_visible(False)
ax.spines["top"].set_visible(False)
ax.spines["left"].set_visible(False)
ax.spines["bottom"].set_visible(True)
for x in range(0, 51, 5):
ax.plot(
[x, x],
[-0.05, -0.01],
color="black",
transform=ax.get_xaxis_transform(),
clip_on=False,
)
plt.tight_layout()
chart_path = self.charts_dir / "body_fat_percentage_chart.png"
plt.savefig(chart_path, bbox_inches="tight", dpi=300)
plt.close()
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_body_composition_chart( def generate_body_composition_chart(
self, fat_mass_lbs: float, lean_mass_lbs: float, save_as_base64: bool = False self, fat_mass_lbs: float, lean_mass_lbs: float, save_as_base64: bool = True
) -> str: ) -> str:
"""Generate donut chart for body composition""" """
Generate body composition donut chart.
Args:
fat_mass_lbs: Fat mass in pounds
lean_mass_lbs: Lean mass in pounds
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
# Calculate percentages # Calculate percentages
total_weight = fat_mass_lbs + lean_mass_lbs total_weight = fat_mass_lbs + lean_mass_lbs
fat_percentage = (fat_mass_lbs / total_weight) * 100 fat_percentage = (fat_mass_lbs / total_weight) * 100
lean_percentage = (lean_mass_lbs / total_weight) * 100 lean_percentage = (lean_mass_lbs / total_weight) * 100
# Data for the chart
sizes = [fat_percentage, lean_percentage] sizes = [fat_percentage, lean_percentage]
colors = ["#fde3ac", "#ff9966"] # Light yellow/tan and orange colors = ["#fde3ac", "#ff9966"]
plt.figure(figsize=(8, 8)) plt.figure(figsize=(8, 8))
# Create the donut chart without labels first # Create donut chart
wedges, texts, autotexts = plt.pie( plt.pie(
sizes, sizes,
autopct="", # Remove auto percentages autopct="",
startangle=90, startangle=90,
wedgeprops=dict(width=0.5, edgecolor="w"), wedgeprops=dict(width=0.5, edgecolor="w"),
colors=colors, colors=colors,
labels=["", ""], labels=["", ""],
) # Remove default labels )
# Add custom text annotations positioned manually # Add custom text annotations
plt.text( plt.text(
-1, -1,
1, 1,
@@ -656,8 +638,7 @@ class GraphGenerator:
bbox=dict(boxstyle="round,pad=0.3", facecolor="white", alpha=0.8), bbox=dict(boxstyle="round,pad=0.3", facecolor="white", alpha=0.8),
) )
# Set the title plt.axis("equal")
plt.axis("equal") # Equal aspect ratio ensures that pie is drawn as a circle
chart_path = self.charts_dir / "body_composition_chart.png" chart_path = self.charts_dir / "body_composition_chart.png"
plt.savefig(chart_path, bbox_inches="tight", dpi=600) plt.savefig(chart_path, bbox_inches="tight", dpi=600)
@@ -665,16 +646,142 @@ class GraphGenerator:
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_spirometry_chart( def generate_body_fat_percent_chart(
self, spirometry_df: pd.DataFrame, save_as_base64: bool = False self,
fat_percentage: float,
age: int,
gender: str,
save_as_base64: bool = True,
) -> str: ) -> str:
"""Generate spirometry chart with Z-scores and ranges""" """
Generate body fat percentage chart.
Args:
fat_percentage: Body fat percentage
age: Patient age
gender: Patient gender ('male' or 'female')
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
# Determine age group
if 20 <= age <= 39:
age_group = "20-39"
elif 40 <= age <= 59:
age_group = "40-59"
elif 60 <= age <= 79:
age_group = "60-79"
else:
age_group = "20-39" # Default
demographic = f"{age_group}\n({gender[0].upper()})"
# Define segments based on gender (female example)
if gender.lower() == "female":
segments = [
("#F8A8A8", 0, 15), # Muted Red: 0% to 15%
("#FFEECC", 15, 5), # Pale Yellow: 15% to 20%
("#D0F0C0", 20, 15), # Pale Green: 20% to 35%
("#FFEECC", 35, 5), # Pale Yellow: 35% to 40%
("#F8A8A8", 40, 10), # Muted Red: 40% to 50%
]
else: # male
segments = [
("#F8A8A8", 0, 5), # Muted Red: 0% to 5%
("#FFEECC", 5, 5), # Pale Yellow: 5% to 10%
("#D0F0C0", 10, 10), # Pale Green: 10% to 20%
("#FFEECC", 20, 5), # Pale Yellow: 20% to 25%
("#F8A8A8", 25, 25), # Muted Red: 25% to 50%
]
fig, ax = plt.subplots(figsize=(10, 2))
# Create the segmented bar
for color, start, length in segments:
ax.barh(
y=0,
width=length,
left=start,
height=1,
color=color,
edgecolor="black",
linewidth=0.5,
)
# Add the indicator (triangle)
ax.plot(
fat_percentage,
1.05,
marker="v",
color="black",
markersize=10,
clip_on=False,
transform=ax.get_xaxis_transform(),
)
# Set axis properties
ax.set_xlim(0, 50)
ax.set_xticks(range(0, 51, 5))
ax.set_yticks([])
ax.text(
-0.05,
0,
demographic,
transform=ax.get_yaxis_transform(),
va="center",
ha="right",
fontsize=12,
)
ticks = range(0, 51, 5)
ax.set_xticks(ticks)
labels = [f"{t}%" for t in ticks]
ax.set_xticklabels(labels)
# Clean up spines
ax.spines["right"].set_visible(False)
ax.spines["top"].set_visible(False)
ax.spines["left"].set_visible(False)
ax.spines["bottom"].set_visible(True)
# Add tick marks
for x in range(0, 51, 5):
ax.plot(
[x, x],
[-0.05, -0.01],
color="black",
transform=ax.get_xaxis_transform(),
clip_on=False,
)
plt.tight_layout()
chart_path = self.charts_dir / "body_fat_percent_chart.png"
plt.savefig(chart_path, bbox_inches="tight", dpi=300)
plt.close()
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_spirometry_chart(
self, spirometry_df: pd.DataFrame, save_as_base64: bool = True
) -> str:
"""
Generate spirometry chart with Z-scores.
Args:
spirometry_df: Spirometry DataFrame with parameters
save_as_base64: If True, return base64 string, else return file path
Returns:
Base64 string or file path
"""
# Coerce numeric columns # Coerce numeric columns
for col in ["Best", "LLN", "Pred.", "%Pred.", "ZScore"]: for col in ["Best", "LLN", "Pred.", "%Pred.", "ZScore"]:
if col in spirometry_df.columns: if col in spirometry_df.columns:
spirometry_df[col] = pd.to_numeric(spirometry_df[col], errors="coerce") spirometry_df[col] = pd.to_numeric(spirometry_df[col], errors="coerce")
# Select rows of interest and prepare display values # Select rows of interest
rows_map = { rows_map = {
"Lung Volume": "FVC", "Lung Volume": "FVC",
"Lung Power": "FEV1", "Lung Power": "FEV1",
@@ -707,7 +814,7 @@ class GraphGenerator:
) )
x_min, x_max = -5, 3 x_min, x_max = -5, 3
# Segment colors: red -> orange -> yellow -> green # Segment colors
segments = [ segments = [
(-5, -4, "#f4a7a7"), # red-ish (-5, -4, "#f4a7a7"), # red-ish
(-4, -3, "#f7c49a"), # orange-ish (-4, -3, "#f7c49a"), # orange-ish
@@ -726,10 +833,10 @@ class GraphGenerator:
0, width=b - a, left=a, height=0.6, color=color, edgecolor="none" 0, width=b - a, left=a, height=0.6, color=color, edgecolor="none"
) )
# LLN (-1) and Predicted (0) markers # LLN and Predicted markers
ax.axvline(0, color="black", lw=1) ax.axvline(0, color="black", lw=1)
# Z-score pointer (downward triangle) at top of each panel # Z-score pointer
if pd.notna(rec["z"]): if pd.notna(rec["z"]):
trans = mtransforms.blended_transform_factory( trans = mtransforms.blended_transform_factory(
ax.transData, ax.transAxes ax.transData, ax.transAxes
@@ -744,7 +851,7 @@ class GraphGenerator:
clip_on=False, clip_on=False,
) )
# Labels, ticks, and styling # Labels and styling
ax.set_title( ax.set_title(
rec["label"], loc="left", fontsize=11, fontweight="bold", pad=2 rec["label"], loc="left", fontsize=11, fontweight="bold", pad=2
) )
@@ -760,15 +867,11 @@ class GraphGenerator:
# Right-side summary boxes # Right-side summary boxes
fig.subplots_adjust(right=0.78) fig.subplots_adjust(right=0.78)
box_ax = fig.add_axes( box_ax = fig.add_axes([0.805, 0.06, 0.18, 0.90])
[0.805, 0.06, 0.18, 0.90]
) # [left, bottom, width, height]
box_ax.axis("off") box_ax.axis("off")
# Helper to draw a pill-shaped text box
def pill(ax, xy, text): def pill(ax, xy, text):
x, y = xy x, y = xy
# Draw rounded rectangle background
bbox = FancyBboxPatch( bbox = FancyBboxPatch(
(x - 0.48, y - 0.09), (x - 0.48, y - 0.09),
0.96, 0.96,
@@ -801,7 +904,7 @@ class GraphGenerator:
box_ax.set_xlim(0, 1) box_ax.set_xlim(0, 1)
box_ax.set_ylim(0, 1) box_ax.set_ylim(0, 1)
# Prepare display strings and positions (top to bottom) # Prepare display strings
right_items = [] right_items = []
for rec in records: for rec in records:
name = ( name = (
@@ -814,7 +917,7 @@ class GraphGenerator:
pct_fmt = f"{rec['pct']:.1f}%" pct_fmt = f"{rec['pct']:.1f}%"
right_items.append((name, value_fmt, pct_fmt)) right_items.append((name, value_fmt, pct_fmt))
# Sort to match image order on the right (FVC, FEV1, FEV1/FVC) # Sort to match order
order = ["FVC", "FEV1", "FEV1/FVC"] order = ["FVC", "FEV1", "FEV1/FVC"]
right_items_sorted = [ right_items_sorted = [
next(item for item in right_items if item[0] == k) for k in order next(item for item in right_items if item[0] == k) for k in order
@@ -830,113 +933,3 @@ class GraphGenerator:
plt.close() plt.close()
return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path) return self._image_to_base64(chart_path) if save_as_base64 else str(chart_path)
def generate_all_charts(
self,
pnoe_df: pd.DataFrame,
spirometry_df: pd.DataFrame,
patient_data: Dict,
save_as_base64: bool = False,
) -> Dict[str, str]:
"""Generate all charts at once and return dictionary of paths/base64 strings"""
charts = {}
# Generate physiological charts
charts["respiratory"] = self.generate_respiratory_chart(pnoe_df, save_as_base64)
charts["fuel_utilization_chart"] = self.generate_fuel_utilization_chart(
pnoe_df, save_as_base64
)
charts["vo2_pulse_chart"] = self.generate_vo2_pulse_chart(
pnoe_df, save_as_base64
)
charts["vo2_breath_chart"] = self.generate_vo2_breath_chart(
pnoe_df, save_as_base64
)
charts["fat_metabolism_chart"] = self.generate_fat_metabolism_chart(
pnoe_df, save_as_base64
)
charts["recovery_chart"] = self.generate_recovery_chart(pnoe_df, save_as_base64)
# Generate body composition charts
if (
"gender" in patient_data
and "age" in patient_data
and "fat_percentage" in patient_data
):
charts["body_fat_percentage_chart"] = (
self.generate_body_fat_percentage_chart(
patient_data["gender"],
patient_data["age"],
patient_data["fat_percentage"],
save_as_base64,
)
)
if "fat_mass_lbs" in patient_data and "lean_mass_lbs" in patient_data:
charts["body_composition_chart"] = self.generate_body_composition_chart(
patient_data["fat_mass_lbs"],
patient_data["lean_mass_lbs"],
save_as_base64,
)
# Generate spirometry chart
charts["spirometry_chart"] = self.generate_spirometry_chart(
spirometry_df, save_as_base64
)
return charts
# Example usage
if __name__ == "__main__":
# Initialize graph generator
generator = GraphGenerator()
# Load sample data (you would pass your actual dataframes)
pnoe_df = pd.read_csv("data/Pnoe_20250729_1550-Moran_Keirstyn.csv", delimiter=";")
spirometry_df = pd.read_csv("data/spirometry_data.csv")
# Preprocess pnoe data (same as in your notebook)
pnoe_df = pnoe_df.apply(pd.to_numeric, errors="ignore")
pnoe_df["VO2 Pulse"] = pnoe_df["VO2(ml/min)"] / pnoe_df["HR(bpm)"]
pnoe_df["VO2 Breath"] = pnoe_df["VO2(ml/min)"] / pnoe_df["BF(bpm)"]
pnoe_df["CHO"] = pnoe_df["EE(kcal/min)"] * pnoe_df["CARBS(%)"] / 100
pnoe_df["FAT"] = pnoe_df["EE(kcal/min)"] * pnoe_df["FAT(%)"] / 100
# Apply smoothing
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 pnoe_df.columns:
pnoe_df[f"{col}_smoothed"] = (
pnoe_df[col].rolling(window=window_size, min_periods=1).mean()
)
# Patient data
patient_data = {
"gender": "female",
"age": 25,
"fat_percentage": 22.4,
"fat_mass_lbs": 27.6,
"lean_mass_lbs": 95.4,
}
# Generate all charts
charts = generator.generate_all_charts(
pnoe_df, spirometry_df, patient_data, save_as_base64=True
)
print(f"Generated {len(charts)} charts:")
for chart_name in charts.keys():
print(f"- {chart_name}")
app/services/page_generator.py
-191
View File
@@ -1,191 +0,0 @@
import datetime
import pandas as pd
import matplotlib.pyplot as plt
class PageGenerator:
def __init__(self, pnoe_df: pd.DataFrame, seca_df: pd.DataFrame, spirometry_df: pd.DataFrame, patient_info: dict):
self.pnoe_df = pnoe_df
self.seca_df = seca_df
self.spirometry_df = spirometry_df
self.patient_info = patient_info
def page_1_context(self):
# Extract patient information
patient_name = self.patient_info.get("patient_name", "N/A")
context = {
"first_name": patient_name.split()[0] if patient_name else "N/A",
"surname": patient_name.split()[-1] if patient_name else "N/A",
"date": datetime.datetime.now().strftime("%B %d, %Y"),
}
return context
def page_3_context(self):
# Example: Extract detailed PNOE data for page 3
pnoe_details = self.pnoe_df.head(10).to_dict(orient="records")
context = {
"pnoe_details": pnoe_details,
}
return context
def page_4_context(self):
# Example: Extract detailed Spirometry data for page 4
# Filter df_2 for Keirstyn Moran
patient_data = self.patient_info[self.patient_info['LastName'].str.contains('Moran', case=False, na=False)]
fat_percentage = patient_data['Adult_FMP'].iloc[0]
weight_kg = patient_data['Weight'].iloc[0]
lean_percentage = 100 - fat_percentage
fat_mass_lbs = weight_kg * (fat_percentage / 100) * 2.20462
lean_mass_lbs = weight_kg * (lean_percentage / 100) * 2.20462
total_weight = fat_mass_lbs + lean_mass_lbs
fat_percentage = (fat_mass_lbs / total_weight) * 100
lean_percentage = (lean_mass_lbs / total_weight) * 100
sizes = [fat_percentage, lean_percentage]
colors = ['#fde3ac', '#ff9966'] # Light yellow/tan and orange from the image
plt.figure(figsize=(8, 8))
wedges, texts, autotexts = plt.pie(sizes, autopct='', startangle=90, wedgeprops=dict(width=0.5, edgecolor='w'), colors=colors, labels=['', '']) # Remove default labels
plt.text(-1, 1, f'Fat Mass ({fat_mass_lbs:.1f}lbs)\n{fat_percentage:.1f}%',
fontsize=14, fontweight='bold', ha='center', va='center',
bbox=dict(boxstyle="round,pad=0.3", facecolor='white', alpha=0.8))
plt.text(1, -1, f'Lean Mass ({lean_mass_lbs:.1f}lbs)\n{lean_percentage:.1f}%',
fontsize=14, fontweight='bold', ha='center', va='center',
bbox=dict(boxstyle="round,pad=0.3", facecolor='white', alpha=0.8))
plt.axis('equal') # Equal aspect ratio ensures that pie is drawn as a circle
spirometry_details = self.spirometry_df.head(10).to_dict(orient="records")
context = {
"spirometry_details": spirometry_details,
}
return context
def page_5_context(self):
# Example: Summary and conclusions for page 5
summary = {
"pnoe_summary": self.pnoe_df.describe().to_dict(),
"seca_summary": self.seca_df.describe().to_dict(),
"spirometry_summary": self.spirometry_df.describe().to_dict(),
}
context = {
"summary": summary,
}
return context
def page_6_context(self):
# Example: Recommendations based on data for page 6
recommendations = [
"Increase cardiovascular training.",
"Incorporate strength training twice a week.",
"Monitor respiratory function regularly.",
]
context = {
"recommendations": recommendations,
}
return context
def page_7_context(self):
# Example: Additional notes or references for page 7
notes = "This report is generated based on the provided data. Consult a healthcare professional for personalized advice."
context = {
"notes": notes,
}
return context
def page_8_context(self):
# Example: Contact information and disclaimers for page 8
contact_info = {
"clinic_name": "Health Clinic",
"address": "123 Wellness St, Healthy City, HC 12345",
"phone": "(123) 456-7890",
"email": "contact@healthclinic.com"
}
context = {
"contact_info": contact_info,
}
return context
def page_9_context(self):
# Example: Graphs and visualizations for page 9
graphs = [
"graph1.png",
"graph2.png",
"graph3.png"
]
context = {
"graphs": graphs,
}
return context
def page_10_context(self):
# Example: Final remarks and next steps for page 10
final_remarks = "Thank you for using our health assessment services. We look forward to assisting you in your health journey."
context = {
"final_remarks": final_remarks,
}
return context
def page_11_context(self):
# Example: Additional resources and references for page 11
resources = [
{"title": "Healthy Living Guide", "link": "http://example.com/healthy-living"},
{"title": "Exercise Tips", "link": "http://example.com/exercise-tips"},
{"title": "Nutrition Advice", "link": "http://example.com/nutrition-advice"}
]
context = {
"resources": resources,
}
return context
def page_12_context(self):
# Example: Feedback and survey information for page 12
feedback_info = "We value your feedback. Please visit http://example.com/feedback to share your experience."
context = {
"feedback_info": feedback_info,
}
return context
def page_13_context(self):
# Example: Acknowledgments and credits for page 13
acknowledgments = "This report was generated using data analysis techniques and the expertise of our medical team."
context = {
"acknowledgments": acknowledgments,
}
return context
def page_18_context(self):
# Example: Legal disclaimers and terms for page 18
legal_disclaimer = "This report is for informational purposes only and does not constitute medical advice."
context = {
"legal_disclaimer": legal_disclaimer,
}
return context
app/services/report_generator.py
+98 -12
View File
@@ -12,8 +12,9 @@ import pandas as pd
from jinja2 import Environment, FileSystemLoader from jinja2 import Environment, FileSystemLoader
from playwright.sync_api import sync_playwright from playwright.sync_api import sync_playwright
from app.services.context import context_list from app.services.context_generator import ContextGenerator
from app.services.graph_generator import GraphGenerator from app.services.graph_generator import GraphGenerator
from app.services.spirometry_table_extractor import extract_spirometry_table_from_pdf
class ReportGeneratorService: class ReportGeneratorService:
@@ -24,6 +25,7 @@ class ReportGeneratorService:
template_dir: str = "app/report_gen", template_dir: str = "app/report_gen",
graphs_dir: str = "graphs", graphs_dir: str = "graphs",
reports_dir: str = "reports", reports_dir: str = "reports",
data_dir: str = "data",
): ):
""" """
Initialize the report generator service. Initialize the report generator service.
@@ -32,16 +34,20 @@ class ReportGeneratorService:
template_dir: Directory containing Jinja2 templates template_dir: Directory containing Jinja2 templates
graphs_dir: Directory to save generated graphs graphs_dir: Directory to save generated graphs
reports_dir: Directory to save generated reports reports_dir: Directory to save generated reports
data_dir: Directory to store extracted/processed data
""" """
self.template_dir = template_dir self.template_dir = template_dir
self.graphs_dir = Path(graphs_dir) self.graphs_dir = Path(graphs_dir)
self.reports_dir = Path(reports_dir) self.reports_dir = Path(reports_dir)
self.graph_generator = GraphGenerator(charts_dir=str(graphs_dir)) self.data_dir = Path(data_dir)
self.graph_generator = GraphGenerator(charts_dir=str(self.graphs_dir))
self.context_generator = ContextGenerator()
self.env = Environment(loader=FileSystemLoader(template_dir)) self.env = Environment(loader=FileSystemLoader(template_dir))
# Ensure directories exist # Ensure directories exist
self.graphs_dir.mkdir(exist_ok=True) self.graphs_dir.mkdir(exist_ok=True)
self.reports_dir.mkdir(exist_ok=True) self.reports_dir.mkdir(exist_ok=True)
self.data_dir.mkdir(exist_ok=True)
def process_pnoe_data(self, pnoe_csv_path: str) -> pd.DataFrame: def process_pnoe_data(self, pnoe_csv_path: str) -> pd.DataFrame:
""" """
@@ -139,13 +145,16 @@ class ReportGeneratorService:
else 0, else 0,
} }
def generate_html(self, patient_info: Dict[str, Any]) -> str: def generate_html(
self, patient_info: Dict[str, Any], context_list: List[Dict[str, Any]]
) -> str:
""" """
Generate HTML content for the report. Generate HTML content for the report.
Args: Args:
patient_info: Dictionary containing patient information patient_info: Dictionary containing patient information
(patient_name, age, height, weight, focus) (patient_name, age, height, weight, focus)
context_list: List of context dictionaries for each page
Returns: Returns:
Complete HTML document as string Complete HTML document as string
@@ -277,35 +286,112 @@ class ReportGeneratorService:
""" """
Generate complete medical report from uploaded files. Generate complete medical report from uploaded files.
This follows the complete workflow:
1. Extract spirometry data from PDF
2. Store all data in data directory
3. Generate all graphs
4. Generate context for each page
5. Generate final HTML and PDF report
Args: Args:
spirometry_pdf_path: Path to Spirometry PDF file spirometry_pdf_path: Path to Spirometry PDF file
pnoe_csv_path: Path to Pnoe CSV file pnoe_csv_path: Path to Pnoe CSV file
seca_excel_path: Path to SECA Excel file seca_excel_path: Path to SECA Excel file
patient_info: Dictionary containing patient information patient_info: Dictionary containing patient information
output_filename: Optional custom output filename output_filename: Optional custom output filename
n
Returns: Returns:
Dictionary containing report path, graphs generated, and analysis data Dictionary containing report path, graphs generated, and analysis data
""" """
# Process data # Step 1: Extract spirometry table from PDF
spirometry_csv_path = self.data_dir / "extracted_spirometry_table.csv"
extract_spirometry_table_from_pdf(spirometry_pdf_path)
# The extraction saves to current directory, move it to data_dir
import shutil
if Path("extracted_spirometry_table.csv").exists():
shutil.move("extracted_spirometry_table.csv", spirometry_csv_path)
# Step 2: Process Pnoe data
df = self.process_pnoe_data(pnoe_csv_path) df = self.process_pnoe_data(pnoe_csv_path)
# Generate graphs # Step 3: Generate all graphs
graphs_generated = self.generate_graphs(df) graphs_generated = self.generate_graphs(df)
# Calculate analysis metrics # Create graph dictionary with base64 encoded images
graphs_dict = {}
for graph in graphs_generated:
# Read the graph file and convert to base64
graph_path = Path(graph["path"])
if graph_path.exists():
import base64
with open(graph_path, "rb") as f:
graphs_dict[graph["name"]] = base64.b64encode(f.read()).decode(
"utf-8"
)
# Also generate body composition charts
# Extract patient data for these charts
patient_name = patient_info.get("patient_name", "").split()[-1] # Get last name
# Load SECA data to get body composition info
seca_df = pd.read_excel(seca_excel_path)
patient_data = seca_df[
seca_df["LastName"].str.contains(patient_name, case=False, na=False)
]
if not patient_data.empty:
row = patient_data.iloc[0]
weight_kg = float(row.get("Weight", 0))
fat_pct = float(row.get("Adult_FMP", 0))
age = int(row.get("Age", patient_info.get("age", 25)))
gender = row.get("Gender", "female").lower()
fat_mass_lbs = weight_kg * fat_pct / 100 * 2.20462
lean_mass_lbs = weight_kg * (1 - fat_pct / 100) * 2.20462
# Generate body composition chart
body_comp_b64 = self.graph_generator.generate_body_composition_chart(
fat_mass_lbs, lean_mass_lbs, save_as_base64=True
)
graphs_dict["body_composition"] = body_comp_b64
# Generate body fat percent chart
body_fat_b64 = self.graph_generator.generate_body_fat_percent_chart(
fat_pct, age, gender, save_as_base64=True
)
graphs_dict["body_fat_percent"] = body_fat_b64
# Generate spirometry chart
spirometry_df = pd.read_csv(spirometry_csv_path)
spirometry_chart_b64 = self.graph_generator.generate_spirometry_chart(
spirometry_df, save_as_base64=True
)
graphs_dict["spirometry_chart"] = spirometry_chart_b64
# Step 4: Generate context for all pages
self.context_generator.load_data(
pnoe_csv_path, str(spirometry_csv_path), seca_excel_path
)
context_list = self.context_generator.generate_all_contexts(
patient_name, graphs_dict
)
# Step 5: Calculate analysis metrics
analysis_data = self.calculate_analysis_metrics(df) analysis_data = self.calculate_analysis_metrics(df)
analysis_data["graphs_count"] = len(graphs_generated) analysis_data["graphs_count"] = len(graphs_generated)
# Generate HTML # Step 6: Generate HTML
html_content = self.generate_html(patient_info) html_content = self.generate_html(patient_info, context_list)
# Generate PDF # Step 7: Generate PDF
if output_filename is None: if output_filename is None:
patient_name = patient_info.get("patient_name", "Unknown") patient_name_full = patient_info.get("patient_name", "Unknown")
session_id = patient_info.get("session_id", "default") session_id = patient_info.get("session_id", "default")
output_filename = ( output_filename = (
f"report_{patient_name.replace(' ', '_')}_{session_id}.pdf" f"report_{patient_name_full.replace(' ', '_')}_{session_id}.pdf"
) )
report_path = self.reports_dir / output_filename report_path = self.reports_dir / output_filename
app/services_dfdf/__init__.py
View File
app/services_dfdf/analysis.ipynb
-807
View File
@@ -1,807 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "b18c1027",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'id': 'gen-1759135172-DIhs7TMuaaVY0h3T2ibV', 'provider': 'Google', 'model': 'google/gemini-2.5-flash-lite', 'object': 'chat.completion', 'created': 1759135172, 'choices': [{'logprobs': None, 'finish_reason': 'stop', 'native_finish_reason': 'STOP', 'index': 0, 'message': {'role': 'assistant', 'content': 'Parameters,Best,LLN,Pred.,%Pred.,ZScore,PRE#1,PRE#2,PRE#3\\nFVC,L,4.24,3.03,3.79,112.0,0.95,4.24,4.17,4.15\\nFEV1,L,3.26,2.53,3.16,103.3,0.28,3.26,3.21,3.14\\nFEV1/FVC%,76.89,72.47,83.78,91.8,-1.05,76.9,77.0,75.7\\nPEF,L/m,684,222,384,178.7,-,444,438,684\\nFEF2575,L/s,2.74,2.15,3.42,80.2,-0.84,2.74,2.68,2.48\\nFEF25,L/s,6.08,-,-,-,6.08,6.0,5.53\\nFEF50,L/s,3.06,-,-,-,3.06,3.1,2.77\\nFEF75,L/s,1.06,0.71,1.41,75.1,-0.72,1.06,1.12,0.94\\nPEFTime,ms,-,-,79,-,79,49,39\\nEvol,mL,-,-,78.0,-,78.0,77.0,197.0\\nFEV6,L,4.22,3.03,3.79,111.4,-,4.22,4.17,4.13', 'refusal': None, 'reasoning': None}}], 'usage': {'prompt_tokens': 1350, 'completion_tokens': 454, 'total_tokens': 1804, 'prompt_tokens_details': {'cached_tokens': 0}, 'completion_tokens_details': {'reasoning_tokens': 0, 'image_tokens': 0}}}\n",
"Content saved to extracted_table.csv\n"
]
}
],
"source": [
"\n",
"import requests\n",
"import json\n",
"import base64\n",
"from pathlib import Path\n",
"\n",
"API_KEY_REF = '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'\n",
"def encode_pdf_to_base64(pdf_path):\n",
" with open(pdf_path, \"rb\") as pdf_file:\n",
" return base64.b64encode(pdf_file.read()).decode('utf-8')\n",
"\n",
"url = \"https://openrouter.ai/api/v1/chat/completions\"\n",
"headers = {\n",
" \"Authorization\": f\"Bearer {API_KEY_REF}\",\n",
" \"Content-Type\": \"application/json\"\n",
"}\n",
"\n",
"# Read and encode the PDF\n",
"pdf_path = \"data/~Moran~K~19910201~Spirometry Exam~20250729~20250729032843.pdf\"\n",
"base64_pdf = encode_pdf_to_base64(pdf_path)\n",
"data_url = f\"data:application/pdf;base64,{base64_pdf}\"\n",
"\n",
"messages = [\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [\n",
" {\n",
" \"type\": \"text\",\n",
" \"text\": \"Please extract the Spirometry table from the pdf and return the values in csv format, \"\n",
" \"note that it is the unit of parameter that is beside it and it should not be a column. \"\n",
" \"The '-' Should be treated as empty values.\"\n",
" \"do not add 'csv' at the start or end of the response\"\n",
" },\n",
" {\n",
" \"type\": \"file\",\n",
" \"file\": {\n",
" \"filename\": \"document.pdf\",\n",
" \"file_data\": data_url\n",
" }\n",
" },\n",
" ]\n",
" }\n",
"]\n",
"\n",
"# Optional: Configure PDF processing engine\n",
"# PDF parsing will still work even if the plugin is not explicitly set\n",
"plugins = [\n",
" {\n",
" \"id\": \"file-parser\",\n",
" \"pdf\": {\n",
" \"engine\": \"pdf-text\" # defaults to \"mistral-ocr\". See Pricing above\n",
" }\n",
" }\n",
"]\n",
"\n",
"payload = {\n",
" \"model\": \"google/gemini-2.5-flash-lite\",\n",
" \"messages\": messages,\n",
"}\n",
"\n",
"response = requests.post(url, headers=headers, json=payload)\n",
"# Get the response content\n",
"response_data = response.json()\n",
"print(response_data)\n",
"\n",
"# Extract the content from the response\n",
"if 'choices' in response_data and len(response_data['choices']) > 0:\n",
" content = response_data['choices'][0]['message']['content']\n",
" \n",
" # Save to a CSV file\n",
" output_file = \"extracted_table.csv\"\n",
" with open(output_file, 'w', encoding='utf-8') as f:\n",
" f.write(content)\n",
" \n",
" print(f\"Content saved to {output_file}\")\n",
"else:\n",
" print(\"No content found in response\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "56a9d655",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"FVC Best: 4.24, FVC Pred: 112.0\n",
"FEV1 Best: 3.26, FEV1 Pred: 103.3\n",
"FEV1/FVC% Best: 76.89, FEV1/FVC% Pred: 91.8\n"
]
}
],
"source": [
"import pandas as pd\n",
"spirometry_df = pd.read_csv(\"extracted_table.csv\")\n",
"\n",
"fvc_best = spirometry_df.loc[spirometry_df['Parameters'] == 'FVC', 'Best'].values[0]\n",
"fvc_pred = spirometry_df.loc[spirometry_df['Parameters'] == 'FVC', '%Pred.'].values[0]\n",
"\n",
"fev1_best = spirometry_df.loc[spirometry_df['Parameters'] == 'FEV1', 'Best'].values[0]\n",
"fev1_pred = spirometry_df.loc[spirometry_df['Parameters'] == 'FEV1', '%Pred.'].values[0]\n",
"\n",
"fev1_fevc_best = spirometry_df.loc[spirometry_df['Parameters'] == 'FEV1/FVC%', 'Best'].values[0]\n",
"fev1_fevc_pred = spirometry_df.loc[spirometry_df['Parameters'] == 'FEV1/FVC%', '%Pred.'].values[0]\n",
"\n",
"print(f\"FVC Best: {fvc_best}, FVC Pred: {fvc_pred}\")\n",
"print(f\"FEV1 Best: {fev1_best}, FEV1 Pred: {fev1_pred}\")\n",
"print(f\"FEV1/FVC% Best: {fev1_fevc_best}, FEV1/FVC% Pred: {fev1_fevc_pred}\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "990f4b4f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Peak VT: 2.75\n",
"HR at Peak VT: 155.0\n"
]
}
],
"source": [
"df = pd.read_csv('data/Pnoe_20250729_1550-Moran_Keirstyn.csv', delimiter=';')\n",
"peak_vt = df['VT(l)'].max()\n",
"max_vt_row = df.loc[df['VT(l)'].idxmax()]\n",
"print(f\"Peak VT: {peak_vt}\")\n",
"hr = max_vt_row['HR(bpm)']\n",
"print(f\"HR at Peak VT: {hr}\")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "041cbc3d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Peak VT: 2.3770000000000002\n",
"HR at Peak VT: 171.525\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_301535/4157056299.py:3: FutureWarning: errors='ignore' is deprecated and will raise in a future version. Use to_numeric without passing `errors` and catch exceptions explicitly instead\n",
" df = df.apply(pd.to_numeric, errors='ignore')\n"
]
}
],
"source": [
"df = pd.read_csv('data/Pnoe_20250729_1550-Moran_Keirstyn.csv', delimiter=';')\n",
"# Convert all columns to numeric where possible, coercing errors to NaN\n",
"df = df.apply(pd.to_numeric, errors='ignore')\n",
"df['VO2 Pulse'] = df['VO2(ml/min)'] / df['HR(bpm)'] # VO2 Pulse in mL/beat\n",
"df['VO2 Breath'] = df['VO2(ml/min)'] / df['BF(bpm)'] # VO2 per Breath in mL/breath\n",
"df['CHO'] = df['EE(kcal/min)'] * df['CARBS(%)']/100\n",
"df['FAT'] = df['EE(kcal/min)'] * df['FAT(%)']/100\n",
"# Smooth key columns using rolling window\n",
"window_size = 10\n",
"\n",
"# List of columns to smooth\n",
"columns_to_smooth = ['VO2(ml/min)', 'VCO2(ml/min)', 'HR(bpm)', 'VT(l)', 'BF(bpm)', 'VE(l/min)', 'VO2 Pulse', 'VO2 Breath', 'CHO', 'FAT']\n",
"\n",
"# Apply smoothing to each column\n",
"for col in columns_to_smooth:\n",
" if col in df.columns:\n",
" df[f'{col}_smoothed'] = df[col].rolling(window=window_size).mean()\n",
" \n",
"peak_vt = df['VT(l)_smoothed'].max()\n",
"max_vt_row = df.loc[df['VT(l)_smoothed'].idxmax()]\n",
"print(f\"Peak VT: {peak_vt}\")\n",
"hr = max_vt_row['HR(bpm)_smoothed']\n",
"print(f\"HR at Peak VT: {hr}\")"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "de7cadd1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Percent FEV: 72.91411042944786\n"
]
}
],
"source": [
"percent_fev = (peak_vt / fev1_best) * 100\n",
"print(f\"Percent FEV: {percent_fev}\")"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "cb972ed3",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>MeasurementDate</th>\n",
" <th>Comment</th>\n",
" <th>ExternalDeviceId</th>\n",
" <th>ExternalPatientId</th>\n",
" <th>FirstName</th>\n",
" <th>LastName</th>\n",
" <th>BirthDate</th>\n",
" <th>Age</th>\n",
" <th>Ethnicity</th>\n",
" <th>Gender</th>\n",
" <th>...</th>\n",
" <th>Child_XC</th>\n",
" <th>Child_XC_Unit</th>\n",
" <th>Child_BIVA_ZRh</th>\n",
" <th>Child_BIVA_ZXcH</th>\n",
" <th>Child_PhA</th>\n",
" <th>Child_PhA_Unit</th>\n",
" <th>Child_REE_Kcal</th>\n",
" <th>Child_REE_MJ</th>\n",
" <th>Child_TEE_Kcal</th>\n",
" <th>Child_TEE_MJ</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>2025-07-29T18:58:54.0000000Z</td>\n",
" <td>NaN</td>\n",
" <td>10000001583275_0055003f5631501320313557</td>\n",
" <td>KM6479696509</td>\n",
" <td>Keirstyn</td>\n",
" <td>Moran</td>\n",
" <td>1991-02-01T00:00:00.0000000Z</td>\n",
" <td>34</td>\n",
" <td>Caucasian</td>\n",
" <td>Female</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 147 columns</p>\n",
"</div>"
],
"text/plain": [
" MeasurementDate Comment \\\n",
"13 2025-07-29T18:58:54.0000000Z NaN \n",
"\n",
" ExternalDeviceId ExternalPatientId FirstName \\\n",
"13 10000001583275_0055003f5631501320313557 KM6479696509 Keirstyn \n",
"\n",
" LastName BirthDate Age Ethnicity Gender ... \\\n",
"13 Moran 1991-02-01T00:00:00.0000000Z 34 Caucasian Female ... \n",
"\n",
" Child_XC Child_XC_Unit Child_BIVA_ZRh Child_BIVA_ZXcH Child_PhA \\\n",
"13 NaN NaN NaN NaN NaN \n",
"\n",
" Child_PhA_Unit Child_REE_Kcal Child_REE_MJ Child_TEE_Kcal Child_TEE_MJ \n",
"13 NaN NaN NaN NaN NaN \n",
"\n",
"[1 rows x 147 columns]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"personal_df = pd.read_excel('data/SECA body comp for all patients.xlsx')\n",
"\n",
"keirstyn_data = personal_df[personal_df['LastName'].str.contains('Moran', case=False, na=False)]\n",
"keirstyn_data"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "98d9295a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"VO2 Max: 47.906290322580645\n"
]
}
],
"source": [
"v02_max = df['VO2(ml/min)_smoothed'].max()\n",
"weight = keirstyn_data['Weight'].iloc[0]\n",
"print(f\"VO2 Max: {v02_max/weight}\")"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "cdfeb309",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==================================================\n",
"Optimal Fat Burning Zone (highest fat:carb ratio):\n",
"Time: 164.0 seconds\n",
"Fat burn rate: 3.894 kcal/min\n",
"Carb burn rate: 1.575 kcal/min\n",
"Fat:Carb ratio: 2.47\n",
"Heart Rate: 96.7 bpm\n",
"VO2: 1147.9 ml/min\n"
]
}
],
"source": [
"# Find the point where fat burning is highest and carb burning is lowest\n",
"# Using the smoothed data for more stable results\n",
"fat_burn_max_idx = df['FAT_smoothed'].idxmax()\n",
"carb_burn_min_idx = df['CHO_smoothed'].idxmin()\n",
"\n",
"# # Get the data at maximum fat burning point\n",
"# max_fat_row = df.loc[fat_burn_max_idx]\n",
"# print(f\"Maximum Fat Burning Point:\")\n",
"# print(f\"Time: {max_fat_row['T(sec)']} seconds\")\n",
"# print(f\"Fat burn rate: {max_fat_row['FAT_smoothed']:.3f} kcal/min\")\n",
"# print(f\"Carb burn rate: {max_fat_row['CHO_smoothed']:.3f} kcal/min\")\n",
"# print(f\"Heart Rate: {max_fat_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
"# print(f\"VO2: {max_fat_row['VO2(ml/min)_smoothed']:.1f} ml/min\")\n",
"\n",
"# print(\"\\n\" + \"=\"*50)\n",
"\n",
"# # Get the data at minimum carb burning point\n",
"# min_carb_row = df.loc[carb_burn_min_idx]\n",
"# print(f\"Minimum Carbohydrate Burning Point:\")\n",
"# print(f\"Time: {min_carb_row['T(sec)']} seconds\")\n",
"# print(f\"Fat burn rate: {min_carb_row['FAT_smoothed']:.3f} kcal/min\")\n",
"# print(f\"Carb burn rate: {min_carb_row['CHO_smoothed']:.3f} kcal/min\")\n",
"# print(f\"Heart Rate: {min_carb_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
"# print(f\"VO2: {min_carb_row['VO2(ml/min)_smoothed']:.1f} ml/min\")\n",
"\n",
"print(\"\\n\" + \"=\"*50)\n",
"\n",
"# Find the optimal fat burning zone (highest fat:carb ratio)\n",
"df['fat_carb_ratio'] = df['FAT_smoothed'] / (df['CHO_smoothed'] + 0.00000001) # Add small value to avoid division by zero\n",
"optimal_fat_idx = df['fat_carb_ratio'].idxmax()\n",
"optimal_row = df.loc[optimal_fat_idx]\n",
"\n",
"print(f\"Optimal Fat Burning Zone (highest fat:carb ratio):\")\n",
"print(f\"Time: {optimal_row['T(sec)']} seconds\")\n",
"print(f\"Fat burn rate: {optimal_row['FAT_smoothed']:.3f} kcal/min\")\n",
"print(f\"Carb burn rate: {optimal_row['CHO_smoothed']:.3f} kcal/min\")\n",
"print(f\"Fat:Carb ratio: {optimal_row['fat_carb_ratio']:.2f}\")\n",
"print(f\"Heart Rate: {optimal_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
"print(f\"VO2: {optimal_row['VO2(ml/min)_smoothed']:.1f} ml/min\")"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "4420cfea",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 2 intersections at indices: [18, 47]\n",
"\n",
"Last intersection at index 47:\n",
"Time: 251.0 seconds\n",
"Fat burn rate: 3.040 kcal/min\n",
"Carb burn rate: 3.166 kcal/min\n",
"Heart Rate: 100.5 bpm\n",
"VO2: 1283.0 ml/min\n"
]
}
],
"source": [
"# Find intersections where FAT_smoothed and CHO_smoothed cross each other\n",
"intersections = []\n",
"\n",
"for i in range(1, len(df)):\n",
" # Check if there's a crossover between consecutive points\n",
" prev_fat = df.iloc[i-1]['FAT_smoothed']\n",
" prev_cho = df.iloc[i-1]['CHO_smoothed']\n",
" curr_fat = df.iloc[i]['FAT_smoothed']\n",
" curr_cho = df.iloc[i]['CHO_smoothed']\n",
" \n",
" # Skip if any values are NaN\n",
" if pd.isna(prev_fat) or pd.isna(prev_cho) or pd.isna(curr_fat) or pd.isna(curr_cho):\n",
" continue\n",
" \n",
" # Check if lines cross (fat was above/below cho and now it's below/above)\n",
" if ((prev_fat > prev_cho and curr_fat < curr_cho) or \n",
" (prev_fat < prev_cho and curr_fat > curr_cho)):\n",
" intersections.append(i)\n",
"\n",
"print(f\"Found {len(intersections)} intersections at indices: {intersections}\")\n",
"\n",
"if intersections:\n",
" # Get the last intersection\n",
" last_intersection_idx = intersections[-1]\n",
" last_intersection_row = df.iloc[last_intersection_idx]\n",
" \n",
" print(f\"\\nLast intersection at index {last_intersection_idx}:\")\n",
" print(f\"Time: {last_intersection_row['T(sec)']} seconds\")\n",
" print(f\"Fat burn rate: {last_intersection_row['FAT_smoothed']:.3f} kcal/min\")\n",
" print(f\"Carb burn rate: {last_intersection_row['CHO_smoothed']:.3f} kcal/min\")\n",
" print(f\"Heart Rate: {last_intersection_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
" print(f\"VO2: {last_intersection_row['VO2(ml/min)_smoothed']:.1f} ml/min\")\n",
"else:\n",
" print(\"No intersections found between FAT and CHO curves\")"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "62803668",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"VT1: {'HeartRate': 100.5, 'Speed': 4.0, 'Time': 251.0}\n",
"VT2: {'HeartRate': 189.71300000000002, 'Speed': 7.5, 'Time': 1524.0}\n"
]
}
],
"source": [
"def detect_vt1(df, fat_col=\"FAT_smoothed\", carb_col=\"CHO_smoothed\"):\n",
" \"\"\"\n",
" Detect VT1 as the first index where carb burn > fat burn and remains higher.\n",
" \"\"\"\n",
" condition = df[carb_col] > df[fat_col]\n",
" crossover_indices = condition[condition].index\n",
"\n",
" if len(crossover_indices) == 0:\n",
" return None # No crossover found\n",
" \n",
" # Find first crossover where carbs remain higher for the rest\n",
" for idx in crossover_indices:\n",
" if all(df.loc[idx:][carb_col] > df.loc[idx:][fat_col]):\n",
" return idx\n",
" return None\n",
"\n",
"\n",
"def detect_vt2(df, vent_col=\"VE(l/min)_smoothed\", bf_col=\"BF(bpm)_smoothed\", smooth_window=5):\n",
" \"\"\"\n",
" Detect VT2 using slope/inflection method.\n",
" Works with either Ventilation (VE) or Breathing Frequency (Bf).\n",
" \"\"\"\n",
" col = vent_col if vent_col in df.columns else bf_col\n",
" \n",
" # Use already smoothed data\n",
" smoothed_col = col\n",
" \n",
" # Compute slope (first derivative)\n",
" df[\"slope\"] = df[smoothed_col].diff()\n",
" \n",
" # Detect inflection: largest change in slope (second derivative peak)\n",
" df[\"second_derivative\"] = df[\"slope\"].diff()\n",
" inflection_idx = df[\"second_derivative\"].idxmax()\n",
" \n",
" return inflection_idx\n",
"\n",
"\n",
"def analyze_thresholds(df_input):\n",
" # Use the existing dataframe\n",
" df_copy = df_input.copy()\n",
" \n",
" # --- Detect VT1 ---\n",
" vt1_idx = detect_vt1(df_copy)\n",
" vt1 = None\n",
" if vt1_idx is not None:\n",
" vt1 = {\n",
" \"HeartRate\": df_copy.loc[vt1_idx, \"HR(bpm)_smoothed\"],\n",
" \"Speed\": df_copy.loc[vt1_idx, \"Speed\"],\n",
" \"Time\": df_copy.loc[vt1_idx, \"T(sec)\"]\n",
" }\n",
" \n",
" # --- Detect VT2 ---\n",
" vt2_idx = detect_vt2(df_copy)\n",
" vt2 = None\n",
" if vt2_idx is not None:\n",
" vt2 = {\n",
" \"HeartRate\": df_copy.loc[vt2_idx, \"HR(bpm)_smoothed\"],\n",
" \"Speed\": df_copy.loc[vt2_idx, \"Speed\"],\n",
" \"Time\": df_copy.loc[vt2_idx, \"T(sec)\"]\n",
" }\n",
" \n",
" return vt1, vt2\n",
"\n",
"\n",
"vt1, vt2 = analyze_thresholds(df)\n",
"print(\"VT1:\", vt1)\n",
"print(\"VT2:\", vt2)\n"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "07593b56",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Zone 1 (Active Recovery): 81.7 - 96.7 bpm\n",
"Zone 2 (Aerobic Base): 96.7 - 100.5 bpm\n",
"Zone 3 (Aerobic): 100.5 - 179.7 bpm\n",
"Zone 4 (Lactate Threshold): 179.7 - 199.7 bpm\n",
"Zone 5 (VO2 Max): 199.7+ bpm\n"
]
}
],
"source": [
"zone_1_start = optimal_row['HR(bpm)_smoothed'] - 15\n",
"zone_2_start = optimal_row['HR(bpm)_smoothed']\n",
"zone_3_start = vt1\n",
"zone_4_start = vt2['HeartRate'] - 10\n",
"zone_5_start = vt2['HeartRate'] + 10\n",
"\n",
"zone_1_end = zone_2_start\n",
"zone_2_end = vt1['HeartRate']\n",
"zone_3_end = zone_4_start\n",
"zone_4_end = zone_5_start\n",
"\n",
"print(f\"Zone 1 (Active Recovery): {zone_1_start:.1f} - {zone_1_end:.1f} bpm\")\n",
"print(f\"Zone 2 (Aerobic Base): {zone_2_start:.1f} - {zone_2_end:.1f} bpm\")\n",
"print(f\"Zone 3 (Aerobic): {zone_3_start['HeartRate']:.1f} - {zone_3_end:.1f} bpm\")\n",
"print(f\"Zone 4 (Lactate Threshold): {zone_4_start:.1f} - {zone_4_end:.1f} bpm\")\n",
"print(f\"Zone 5 (VO2 Max): {zone_5_start:.1f}+ bpm\")"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "c90415b2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"VO2 Max detected at index 202:\n",
"Time: 985.0 seconds\n",
"VO2 Breath: 58.2 ml/breath\n",
"VO2: 2167.8 ml/min\n",
"VO2 per kg: 38.8 ml/kg/min\n",
"Heart Rate: 170.5 bpm\n",
"Speed: 6.0 km/h\n",
"VO2 Breath Slope: -0.02\n"
]
}
],
"source": [
"# Calculate the slope of VO2 Breath (first derivative)\n",
"df['vo2_breath_slope'] = df['VO2 Breath_smoothed'].diff()\n",
"\n",
"# Find points where slope is consistently zero or negative\n",
"# We'll use a rolling window to check for consistent negative/zero slope\n",
"window = len(df) // 3 # Number of consecutive points to check\n",
"\n",
"# Calculate rolling mean of slope to smooth out noise\n",
"df['vo2_breath_slope_smoothed'] = df['vo2_breath_slope'].rolling(window=window).mean()\n",
"\n",
"# Find where slope becomes consistently zero or negative\n",
"mask = df['vo2_breath_slope_smoothed'] <= 0\n",
"consistent_negative_indices = mask[mask].index\n",
"\n",
"if len(consistent_negative_indices) > 0:\n",
" # Find the first point where slope becomes consistently negative/zero\n",
" vo2_max_idx = consistent_negative_indices[0]\n",
" vo2_max_row = df.loc[vo2_max_idx]\n",
" \n",
" print(f\"VO2 Max detected at index {vo2_max_idx}:\")\n",
" print(f\"Time: {vo2_max_row['T(sec)']} seconds\")\n",
" print(f\"VO2 Breath: {vo2_max_row['VO2 Breath_smoothed']:.1f} ml/breath\")\n",
" print(f\"VO2: {vo2_max_row['VO2(ml/min)_smoothed']:.1f} ml/min\")\n",
" print(f\"VO2 per kg: {vo2_max_row['VO2(ml/min)_smoothed']/weight:.1f} ml/kg/min\")\n",
" print(f\"Heart Rate: {vo2_max_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
" print(f\"Speed: {vo2_max_row['Speed']} km/h\")\n",
" print(f\"VO2 Breath Slope: {vo2_max_row['vo2_breath_slope_smoothed']:.2f}\")\n",
"else:\n",
" # If no consistent negative slope found, use the maximum VO2 Breath value\n",
" vo2_max_idx = df['VO2 Breath_smoothed'].idxmax()\n",
" vo2_max_row = df.loc[vo2_max_idx]\n",
" \n",
" print(f\"No consistent negative slope found. Using peak VO2 Breath at index {vo2_max_idx}:\")\n",
" print(f\"Time: {vo2_max_row['T(sec)']} seconds\")\n",
" print(f\"VO2 Breath: {vo2_max_row['VO2 Breath_smoothed']:.1f} ml/breath\")\n",
" print(f\"VO2: {vo2_max_row['VO2(ml/min)_smoothed']:.1f} ml/min\")\n",
" print(f\"VO2 per kg: {vo2_max_row['VO2(ml/min)_smoothed']/weight:.1f} ml/kg/min\")\n",
" print(f\"Heart Rate: {vo2_max_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
" print(f\"Speed: {vo2_max_row['Speed']} km/h\")"
]
},
{
"cell_type": "code",
"execution_count": 66,
"id": "c3b2cc59",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"VO2 Pulse and HR slopes diverge consistently starting at index 89:\n",
"Time: 485.0 seconds\n",
"VO2 Pulse (smoothed): 13.91\n",
"Heart Rate (smoothed): 136.2 bpm\n",
"VO2 Pulse Slope: 0.672\n",
"HR Slope: 1.000\n",
"Slope Difference: 1.006\n",
"VO2: 1897.8 ml/min\n",
"Speed: 4.5 km/h\n",
"Threshold used: 0.615\n"
]
}
],
"source": [
"# Calculate slopes for both VO2 Pulse and HR\n",
"df['vo2_pulse_slope'] = df['VO2 Pulse_smoothed'].diff()\n",
"df['hr_slope'] = df['HR(bpm)_smoothed'].diff()\n",
"\n",
"# Calculate the difference between the slopes\n",
"df['slope_difference'] = abs(df['vo2_pulse_slope'] - df['hr_slope'])\n",
"\n",
"# Find where the slope difference becomes consistently large (slopes diverge)\n",
"# Use a rolling window to smooth out noise\n",
"window_size = len(df) // 5 # Adjust window size as needed\n",
"df['slope_difference_smoothed'] = df['slope_difference'].rolling(window=window_size).mean()\n",
"\n",
"# Find the threshold - we'll use the 75th percentile of slope differences as threshold\n",
"threshold = df['slope_difference_smoothed'].quantile(0.75)\n",
"\n",
"# Find points where slope difference exceeds threshold\n",
"divergence_mask = df['slope_difference_smoothed'] > threshold\n",
"divergence_indices = divergence_mask[divergence_mask].index\n",
"\n",
"if len(divergence_indices) > 0:\n",
" # Find the first sustained divergence point\n",
" min_consecutive_points = 5\n",
" consistent_divergence_idx = None\n",
" \n",
" for start_idx in divergence_indices:\n",
" # Check if divergence is sustained for consecutive points\n",
" consecutive_count = 0\n",
" for j in range(start_idx, min(start_idx + min_consecutive_points, len(df))):\n",
" if j in divergence_indices:\n",
" consecutive_count += 1\n",
" else:\n",
" break\n",
" \n",
" if consecutive_count >= min_consecutive_points:\n",
" consistent_divergence_idx = start_idx\n",
" break\n",
" \n",
" if consistent_divergence_idx is not None:\n",
" divergence_row = df.iloc[consistent_divergence_idx]\n",
" \n",
" print(f\"VO2 Pulse and HR slopes diverge consistently starting at index {consistent_divergence_idx}:\")\n",
" print(f\"Time: {divergence_row['T(sec)']} seconds\")\n",
" print(f\"VO2 Pulse (smoothed): {divergence_row['VO2 Pulse_smoothed']:.2f}\")\n",
" print(f\"Heart Rate (smoothed): {divergence_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
" print(f\"VO2 Pulse Slope: {divergence_row['vo2_pulse_slope']:.3f}\")\n",
" print(f\"HR Slope: {divergence_row['hr_slope']:.3f}\")\n",
" print(f\"Slope Difference: {divergence_row['slope_difference_smoothed']:.3f}\")\n",
" print(f\"VO2: {divergence_row['VO2(ml/min)_smoothed']:.1f} ml/min\")\n",
" print(f\"Speed: {divergence_row['Speed']} km/h\")\n",
" print(f\"Threshold used: {threshold:.3f}\")\n",
" else:\n",
" print(f\"No sustained divergence found. Threshold: {threshold:.3f}\")\n",
" # Show the point with maximum slope difference instead\n",
" max_diff_idx = df['slope_difference_smoothed'].idxmax()\n",
" max_diff_row = df.iloc[max_diff_idx]\n",
" \n",
" print(f\"\\nPoint with maximum slope difference at index {max_diff_idx}:\")\n",
" print(f\"Time: {max_diff_row['T(sec)']} seconds\")\n",
" print(f\"VO2 Pulse (smoothed): {max_diff_row['VO2 Pulse_smoothed']:.2f}\")\n",
" print(f\"Heart Rate (smoothed): {max_diff_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
" print(f\"Slope Difference: {max_diff_row['slope_difference_smoothed']:.3f}\")\n",
"else:\n",
" print(\"No significant slope divergence found between VO2 Pulse and HR\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "672d68f3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Maximum FAT_smoothed occurs at index 30:\n",
"Heart Rate (smoothed): 96.7 bpm\n",
"FAT (smoothed): 3.894 kcal/min\n"
]
}
],
"source": [
"max_fat_smoothed_idx = df['FAT_smoothed'].idxmax()\n",
"max_fat_smoothed_row = df.loc[max_fat_smoothed_idx]\n",
"max_heart_rate = 220 - keirstyn_data['Age'].iloc[0]\n",
"\n",
"print(f\"Maximum FAT_smoothed occurs at index {max_fat_smoothed_idx}:\")\n",
"print(f\"Heart Rate (smoothed): {max_fat_smoothed_row['HR(bpm)_smoothed']:.1f} bpm\")\n",
"print(f\"FAT (smoothed): {max_fat_smoothed_row['FAT_smoothed']:.3f} kcal/min\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fe3b7605",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "report_generation",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
app/services_dfdf/context_generator.py
View File
app/services_dfdf/notebook.ipynb
-1550
View File
File diff suppressed because one or more lines are too long
app/services_dfdf/report_generator.py
-318
View File
@@ -1,318 +0,0 @@
"""
Report Generator Service
This service handles the generation of medical reports from uploaded files.
It processes data, generates graphs, and creates PDF reports.
"""
from pathlib import Path
from typing import Any, Dict, List
import pandas as pd
from jinja2 import Environment, FileSystemLoader
from playwright.sync_api import sync_playwright
from app.services.context import context_list
from app.services.graph_generator import GraphGenerator
class ReportGeneratorService:
"""Service for generating medical performance reports"""
def __init__(
self,
template_dir: str = "app/report_gen",
graphs_dir: str = "graphs",
reports_dir: str = "reports",
):
"""
Initialize the report generator service.
Args:
template_dir: Directory containing Jinja2 templates
graphs_dir: Directory to save generated graphs
reports_dir: Directory to save generated reports
"""
self.template_dir = template_dir
self.graphs_dir = Path(graphs_dir)
self.reports_dir = Path(reports_dir)
self.graph_generator = GraphGenerator(charts_dir=str(graphs_dir))
self.env = Environment(loader=FileSystemLoader(template_dir))
# Ensure directories exist
self.graphs_dir.mkdir(exist_ok=True)
self.reports_dir.mkdir(exist_ok=True)
def process_pnoe_data(self, pnoe_csv_path: str) -> pd.DataFrame:
"""
Load and process Pnoe CSV data.
Args:
pnoe_csv_path: Path to Pnoe CSV file
Returns:
Processed DataFrame with smoothed columns
"""
# Load data
df = pd.read_csv(pnoe_csv_path, 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()
)
return df
def generate_graphs(self, df: pd.DataFrame) -> List[Dict[str, str]]:
"""
Generate all required graphs from processed data.
Args:
df: Processed DataFrame with smoothed columns
Returns:
List of dictionaries containing graph names and paths
"""
graphs_generated = []
# List of graphs to generate
graph_methods = [
("respiratory", self.graph_generator.generate_respiratory_chart),
("fuel_utilization", self.graph_generator.generate_fuel_utilization_chart),
("vo2_pulse", self.graph_generator.generate_vo2_pulse_chart),
("vo2_breath", self.graph_generator.generate_vo2_breath_chart),
("fat_metabolism", self.graph_generator.generate_fat_metabolism_chart),
("recovery", self.graph_generator.generate_recovery_chart),
]
for name, method in graph_methods:
try:
path = method(df, save_as_base64=False)
graphs_generated.append({"name": name, "path": str(path)})
except Exception as e:
print(f"Warning: Could not generate {name} chart: {e}")
return graphs_generated
def calculate_analysis_metrics(self, df: pd.DataFrame) -> Dict[str, Any]:
"""
Calculate basic analysis metrics from processed data.
Args:
df: Processed DataFrame with smoothed columns
Returns:
Dictionary containing analysis metrics
"""
return {
"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,
}
def generate_html(self, patient_info: Dict[str, Any]) -> str:
"""
Generate HTML content for the report.
Args:
patient_info: Dictionary containing patient information
(patient_name, age, height, weight, focus)
Returns:
Complete HTML document as string
"""
html_pages = []
# Header context
header_context = {
"patient_name": patient_info.get("patient_name", ""),
"age": patient_info.get("age", ""),
"height": patient_info.get("height", ""),
"weight": patient_info.get("weight", ""),
"focus": patient_info.get("focus", "Endurance"),
}
# Footer context
footer_context = [
{
"contact_email": "info@ishplabs.com",
"website": "www.ishplabs.com",
"social": "@ishplabs",
"page_number": i + 1,
}
for i in range(len(context_list))
]
# Render header
header_html = self.env.get_template("header.html").render(header_context)
# Render footers
footer_html_list = [
self.env.get_template("footer.html").render(context)
for context in footer_context
]
# Render pages
for i, context in enumerate(context_list):
template = self.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>
"""
return html_doc
def html_to_pdf(self, html_content: str, pdf_path: str) -> None:
"""
Convert HTML content to PDF file.
Args:
html_content: HTML content as string
pdf_path: Path where PDF should be saved
"""
with sync_playwright() as p:
browser = p.chromium.launch()
page = browser.new_page()
page.set_content(html_content)
page.pdf(path=pdf_path, format="A4", print_background=True)
browser.close()
def generate_report(
self,
spirometry_pdf_path: str,
pnoe_csv_path: str,
seca_excel_path: str,
patient_info: Dict[str, Any],
output_filename: str = None,
) -> Dict[str, Any]:
"""
Generate complete medical report from uploaded files.
Args:
spirometry_pdf_path: Path to Spirometry PDF file
pnoe_csv_path: Path to Pnoe CSV file
seca_excel_path: Path to SECA Excel file
patient_info: Dictionary containing patient information
output_filename: Optional custom output filename
Returns:
Dictionary containing report path, graphs generated, and analysis data
"""
# Process data
df = self.process_pnoe_data(pnoe_csv_path)
# Generate graphs
graphs_generated = self.generate_graphs(df)
# Calculate analysis metrics
analysis_data = self.calculate_analysis_metrics(df)
analysis_data["graphs_count"] = len(graphs_generated)
# Generate HTML
html_content = self.generate_html(patient_info)
# Generate PDF
if output_filename is None:
patient_name = patient_info.get("patient_name", "Unknown")
session_id = patient_info.get("session_id", "default")
output_filename = (
f"report_{patient_name.replace(' ', '_')}_{session_id}.pdf"
)
report_path = self.reports_dir / output_filename
self.html_to_pdf(html_content, str(report_path))
return {
"report_path": str(report_path),
"graphs_generated": graphs_generated,
"analysis_data": analysis_data,
}