from django.shortcuts import render, redirect, get_object_or_404
from django.http import HttpResponse, JsonResponse
from django.contrib.auth.decorators import login_required, user_passes_test
from django.contrib.auth.models import User
from django.contrib import messages
from django.contrib.auth import authenticate, login, logout
from django.core.files.storage import FileSystemStorage
from django.db.models import Q, Count
from django.views.decorators.csrf import csrf_exempt
from scipy.stats import chi2_contingency, chi2,norm,chisquare
from plotly.graph_objects import Bar, Figure
from plotly.subplots import make_subplots
import plotly.graph_objs as go
import pandas as pd
import numpy as np
import json
from urllib.parse import unquote
from .forms import PatientFilterForm
from .models import Dataset, Case, Control, ListedDatasets, UniversalPresets, Group
from .filter import Filter, Group
import math
from django.db import transaction
from django.core.files.storage import FileSystemStorage
from django.contrib import messages
from django.shortcuts import redirect, render
import pandas as pd
from django.shortcuts import get_object_or_404, render
from .models import Dataset, Group
from django.contrib.auth.decorators import login_required
from django.shortcuts import render, get_object_or_404
from urllib.parse import unquote
import json
from django.shortcuts import get_object_or_404, render
import plotly.graph_objs as go
from django.db.models import Count
from django.shortcuts import render, get_object_or_404
from django.db.models import Count, Q
from scipy.stats import chi2_contingency
from .models import Dataset, Case
import pandas as pd
from django.shortcuts import render, get_object_or_404
from django.db.models import Count, Q
from scipy.stats import chi2_contingency
from .models import Dataset, Case
from django.shortcuts import render, get_object_or_404
from django.db.models import Q
import json
from urllib.parse import unquote
import logging
from django.db.models import F, FloatField, ExpressionWrapper
from urllib.parse import quote
# Configure logging
logger = logging.getLogger(__name__)
def clean_cell(value):
if pd.isna(value) or value == 'N/A':
return None
return value
def numberToString(value):
if isinstance(value, float) and math.isnan(value):
return None # Handle NaN specifically
if isinstance(value, (int, float)):
return int(value) # Convert float/int to integer
try:
return int(float(value)) # Convert string to float, then to int
except ValueError:
return None # Handle invalid cases
def patient_information(request):
# Get the first ListedDatasets entry and its first dataset
listed_dataset = ListedDatasets.objects.prefetch_related("datasets").first()
dataset_unique_id = None
if listed_dataset and listed_dataset.datasets.exists():
dataset_unique_id = listed_dataset.datasets.first().unique_id
return render(request, "patient_information.html", {
"dataset_unique_id": dataset_unique_id,
})
def contact_us(request):
"""
Render the Contact Us page with static details for Dr. Jesmin and the department.
"""
return render(request, "contact_us.html")
def register(request):
if request.method == "POST":
first_name = request.POST.get("first_name")
last_name = request.POST.get("last_name")
email = request.POST.get("email").strip().lower() # Normalize email to lowercase
password = request.POST.get("password")
confirm_password = request.POST.get("confirm_password")
# Validation
if password != confirm_password:
messages.error(request, "Passwords do not match!")
return redirect("register")
# Check if the email is already registered
if User.objects.filter(email=email).exists():
messages.error(request, "Email is already registered!")
return redirect("register")
# Create a new user
user = User.objects.create_user(
username=email, # Using email as username
email=email,
password=password,
first_name=first_name,
last_name=last_name,
)
messages.success(request, "Registration successful! Please log in.")
return redirect("login") # Redirect to a login page or any other page
return render(request, "register.html")
def login_view(request):
if request.method == "POST":
email = request.POST.get("email").strip().lower() # Normalize email to lowercase
password = request.POST.get("password")
# Authenticate the user
user = authenticate(request, username=email, password=password)
if user is not None:
login(request, user)
messages.success(request, "Logged in successfully!")
return redirect("index") # Redirect to the homepage or dashboard
else:
messages.error(request, "Invalid email or password!")
return redirect("login")
return render(request, "login.html")
def logout_view(request):
logout(request)
messages.success(request, "You have been logged out successfully!")
return redirect("login")
@login_required
def upload_dataset(request):
if request.method == 'POST':
dataset_title = request.POST['dataset_title']
dataset_description = request.POST['dataset_description']
case_file = request.FILES.get('case_file')
control_file = request.FILES.get('control_file')
# Validate file extensions
if not (case_file and case_file.name.endswith(".xlsx")):
messages.error(request, "Invalid case file! Please upload a valid .xlsx file.")
return redirect("upload_dataset")
if not (control_file and control_file.name.endswith(".xlsx")):
messages.error(request, "Invalid control file! Please upload a valid .xlsx file.")
return redirect("upload_dataset")
if Dataset.objects.filter(title=dataset_title).exists():
messages.error(request, f"A dataset with the title '{dataset_title}' already exists. Please choose a different title.")
return redirect("upload_dataset")
# Start a database transaction
try:
with transaction.atomic():
# Create Dataset
dataset = Dataset.objects.create(
title=dataset_title,
description=dataset_description,
user=request.user
)
# Save files temporarily for processing
fs = FileSystemStorage()
case_file_path = fs.save(case_file.name, case_file)
control_file_path = fs.save(control_file.name, control_file)
# Process case file
case_data = pd.read_excel(fs.path(case_file_path))
cases = [
Case(
dataset=dataset,
sl_no=row['Sl No'],
id_no=row['ID No'],
age_years=row['Age (Years)'],
occupation=row['Occupation'],
height_m=row['Height (m)'],
weight_kg=row['Weight (Kg)'],
bmi=row['BMI (Kg/m^2)'],
waist_circum_cm=row['Waist Circum. (cm)'],
hip_circum_cm=row['Hip Circum. (cm)'],
whr=row['WHR'],
bp_sys=row['BP-Sys (mm Hg)'],
bp_dia=row['BP-Dia (mm Hg)'],
rbs=row['RBS (mmol/dl)'],
hba1c=row['HbA1c (%)'],
tg=row['TG (mg/dl)'],
hdl=row['HDL (mg/dl)'],
ldl=row['LDL (mg/dl)'],
tc=row['TC (mg/dl)'],
tg_hdl=row['TG/ HDL'],
ldl_hdl=row['LDL/ HDL'],
tc_hdl=row['TC/ HDL'],
creatinine=row['Creatinine (mg/dl)'],
education=row['Education'],
income=row['Income'],
carbohydrate=row['Carbohydrate'],
protein=row['Protein'],
fats_source=row['Fats Source'],
vegetable=row['Vegetable'],
fruits=row['Fruits'],
vitamins=row['Vitamins'],
minerals=row['Minerals'],
water_g_per_day=row['Water (G/D)'],
tea=row['Tea'],
coffee=row['Coffee'],
betal_nuts=row['Betal nuts'],
jarda=row['Jarda'],
processed_food=row['Processed food'],
fast_food=row['Fast food'],
soft_drinks=row['Soft drinks'],
walking_hours=row['Walking (h/d)'],
standing_hours=row['Standing (h/d)'],
desk_job=row['Desk job'],
shift_d_n=row['Shift (D/N)'],
regular_exercise=row['Regular exercise'],
feeling_restless=row['Felling restless'],
fatigue=row['Fatigue'],
shortness_of_breath=row['Shortness of breath'],
sleeping_hours=row['Sleeping (h/d)'],
sound_sleep=row['Sound sleep'],
family_history_with_cancer=row['Family history with cancer'],
menarche_age=clean_cell(row['Menerche age (Yrs)']),
menstrual_status=row['Menstrual status'],
menopause_age=clean_cell(row['Menopause age (Yrs)']),
parity=clean_cell(row['Parity (No)']),
age_at_first_birth=clean_cell(row['Age at 1st birth (Yrs)']),
lactation_situation=row['Lactation sitation'],
breastfeeding_duration=row['Breast feeding duration'],
use_contraceptive=row['Use contraceptive'],
thyroidism_problem=row['Thyroidism problem'],
gastric=row['Gastric'],
antibiotic_intake=row['Antibiotic intake'],
diabetes=row['Diabetes'],
age_at_diagnosis=clean_cell(row['Age at Diagnosis']),
er=row['ER'],
pr=row['PR'],
her2=row['HER-2'],
tnbc=row['TNBC'],
breast_cancer_type=row['Breast Cancer type'],
radio_therapy=row['Radio therapy'],
chemotherapy=row['Chemotherapy'],
hormone_therapy=row['Hormone therapy'],
surgery=row['Surgery'],
cancer_stage=numberToString(row['B. Cancer Stage']),
oral_medication=row['Oral medication'],
histologic_type=row['Histologic type'],
fnac=row['FNAC'],
pathology=row['Pathology'],
histopathology=row['Histopathology'],
mammography=row['Mamography'],
physical=row['Physical'],
)
for _, row in case_data.iterrows()
]
Case.objects.bulk_create(cases)
# Process control file
control_data = pd.read_excel(fs.path(control_file_path))
controls = [
Control(
dataset=dataset,
sl_no=row['Sl No'],
id_no=row['ID No'],
age_years=row['Age (Years)'],
occupation=row['Occupation'],
height_m=row['Height (m)'],
weight_kg=row['Weight (Kg)'],
bmi=row['BMI (Kg/m^2)'],
waist_circum_cm=row['Waist Circum. (cm)'],
hip_circum_cm=row['Hip Circum. (cm)'],
whr=row['WHR'],
bp_sys=row['BP-Sys (mm Hg)'],
bp_dia=row['BP-Dia (mm Hg)'],
rbs=row['RBS (mmol/dl)'],
hba1c=row['HbA1c (%)'],
tg=row['TG (mg/dl)'],
hdl=row['HDL (mg/dl)'],
ldl=row['LDL (mg/dl)'],
tc=row['TC (mg/dl)'],
tg_hdl=row['TG/ HDL'],
ldl_hdl=row['LDL/ HDL'],
tc_hdl=row['TC/ HDL'],
creatinine=row['Creatinine (mg/dl)'],
education=row['Education'],
income=row['Income'],
carbohydrate=row['Carbohydrate'],
protein=row['Protein'],
fats_source=row['Fats Source'],
vegetable=row['Vegetable'],
fruits=row['Fruits'],
vitamins=row['Vitamins'],
minerals=row['Minerals'],
water_g_per_day=row['Water (G/D)'],
tea=row['Tea'],
coffee=row['Coffee'],
betal_nuts=row['Betal nuts'],
jarda=row['Jarda'],
processed_food=row['Processed food'],
fast_food=row['Fast food'],
soft_drinks=row['Soft drinks'],
walking_hours=row['Walking (h/d)'],
standing_hours=row['Standing (h/d)'],
desk_job=row['Desk job'],
shift_d_n=row['Shift (D/N)'],
regular_exercise=row['Regular exercise'],
feeling_restless=row['Felling restless'],
fatigue=row['Fatigue'],
shortness_of_breath=row['Shortness of breath'],
sleeping_hours=row['Sleeping (h/d)'],
sound_sleep=row['Sound sleep'],
family_history_with_cancer=row['Family history with cancer'],
menarche_age=clean_cell(row['Menerche age (Yrs)']),
menstrual_status=row['Menstrual status'],
menopause_age=clean_cell(row['Menopause age (Yrs)']),
parity=clean_cell(row['Parity (No)']),
age_at_first_birth=clean_cell(row['Age at 1st birth (Yrs)']),
lactation_situation=row['Lactation sitation'],
breastfeeding_duration=row['Breast feeding duration'],
use_contraceptive=row['Use contraceptive'],
thyroidism_problem=row['Thyroidism problem'],
gastric=row['Gastric'],
antibiotic_intake=row['Antibiotic intake'],
diabetes=row['Diabetes'],
)
for _, row in control_data.iterrows()
]
Control.objects.bulk_create(controls)
# Delete temporary files
fs.delete(case_file_path)
fs.delete(control_file_path)
# Redirect to success page
return redirect("upload_success", unique_id=dataset.unique_id)
except Exception as e:
# Log the error (optional)
messages.error(request, f"Error uploading dataset: {e}")
return redirect("upload_dataset")
return render(request, 'upload_dataset.html')
def upload_success(request, unique_id):
dataset = get_object_or_404(Dataset, unique_id=unique_id)
analysis_url = request.build_absolute_uri(f"/dataset/{unique_id}/")
context = {
"dataset": dataset,
"analysis_url": analysis_url,
}
return render(request, "upload_success.html", context)
def dataset_options(request, unique_id):
dataset = get_object_or_404(Dataset, unique_id=unique_id)
sections = [
{"name": "Demographic Data", "url_name": "demographic_data"},
{"name": "Anthropometric Data", "url_name": "anthropometric_data"},
{"name": "Biochemical Parameters Data", "url_name": "biochemical_data"},
{"name": "Clinical Data", "url_name": "clinical_data"},
{"name": "Obstetric Data", "url_name": "obstetric_data"},
{"name": "Treatment Strategies Data", "url_name": "treatment_data"},
{"name": "Genetic SNPs Variation Data", "url_name": "genetic_snps_data"},
]
tools = [
{"title": "Data Visualization", "url": f"/presets/{unique_id}/", "description": "Visualize patterns and insights in your dataset."},
{"title": "OR Calculation", "url": f"/or-calculation/{unique_id}/", "description": "Analyze odds ratios and relationships."},
{"title": "Chi-Square Test (2x2)", "url": f"/chi-square-2x2/{unique_id}/", "description": "Perform categorical data analysis."},
{"title": "More Tools Coming Soon", "url": "#", "description": "Stay tuned for additional features."},
]
context = {
"dataset": dataset,
"cases_count": Case.objects.filter(dataset=dataset).count(),
"controls_count": Control.objects.filter(dataset=dataset).count(),
"sections": sections,
"tools": tools,
}
return render(request, "dataset_options.html", context)
def getUniversalPresets():
UNIVERSAL_PRESETS = [
{
"groupTitle":"Hypertension",
"rootGroups":[{"title": "Hypertension - Yes", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "bp_sys", "condition_type": "gte", "value": "130"}, {"type": "condition", "field": "bp_dia", "condition_type": "gte", "value": "80"}]}}, {"title": "Hypertension - No", "filters": {"logic": "OR", "filters": [{"type": "condition", "field": "bp_sys", "condition_type": "lt", "value": "130"}, {"type": "condition", "field": "bp_dia", "condition_type": "lt", "value": "80"}]}}]
},
{
"groupTitle":"BMI",
"rootGroups":[{"title": "NW", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "bmi", "condition_type": "gt", "value": "18.5"}, {"type": "condition", "field": "bmi", "condition_type": "lt", "value": "25.0"}]}}, {"title": "OW", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "bmi", "condition_type": "gte", "value": "25"}, {"type": "condition", "field": "bmi", "condition_type": "lt", "value": "30"}]}}, {"title": "OB", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "bmi", "condition_type": "gte", "value": "30"}]}}, {"title": "NL+OW", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "bmi", "condition_type": "gte", "value": "18.5"}, {"type": "condition", "field": "bmi", "condition_type": "lt", "value": "30"}]}}]
},
{
"groupTitle":"Hyperlipidemia",
"rootGroups":[{"title": "Hyperlipidemia - Yes", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "tg_hdl", "condition_type": "gt", "value": "2.0"}]}}]
},
{
"groupTitle":"Overall (*)",
"rootGroups":[{"title": "*", "filters": {"logic": "AND", "filters": [{"type": "condition", "field": "bmi", "condition_type": "gt", "value": "0"}]}}]
}
]
return UNIVERSAL_PRESETS
def presets(request, unique_id):
# Ensure the dataset exists
dataset = get_object_or_404(Dataset, unique_id=unique_id)
# Fetch universal presets with kid=None
# presets = UniversalPresets.objects.filter(kid__isnull=True).first()
# preset_groups = presets.groups.all() if presets else Group.objects.none()
preset_groups = getUniversalPresets()
for group in preset_groups:
group["group_logic_uriencoded"] = quote(json.dumps(group))
print(preset_groups)
# Check if user is logged in
if request.user.is_authenticated:
# Fetch presets created by the logged-in user and associated with the dataset
user_presets = Group.objects.filter(creator=request.user).order_by('-created_at')
else:
user_presets = None # No custom presets for anonymous users
return render(request, "presets.html", {
"unique_id": unique_id,
"dataset": dataset,
"preset_groups": preset_groups,
"user_presets": user_presets,
# "dataset_title": dataset.title, # Include dataset title for display
"is_logged_in": request.user.is_authenticated, # Pass login status
"cases_count": Case.objects.filter(dataset=dataset).count(),
"controls_count": Control.objects.filter(dataset=dataset).count(),
})
@login_required
def research_tools(request):
context = {
"upload_dataset_url": "/upload-dataset/",
"visualize_data_url": "/breast-cancer-resources/",
"tools": [
{
"title": "More Tools Coming Soon",
"description": "We are continuously adding new features and tools to enhance your research capabilities.",
},
{
"title": "Stay Tuned!",
"description": "Exciting new updates and tools will be available here shortly.",
},
],
}
return render(request, "research_tools.html", context)
def breast_cancer_resources(request):
dataset_groups = ListedDatasets.objects.prefetch_related("datasets").all()
annotated_groups = []
for group in dataset_groups:
datasets_with_counts = []
for dataset in group.datasets.all():
# Add cases and controls count to each dataset
dataset.cases_count = Case.objects.filter(dataset=dataset).count()
dataset.controls_count = Control.objects.filter(dataset=dataset).count()
datasets_with_counts.append(dataset)
group.annotated_datasets = datasets_with_counts
annotated_groups.append(group)
# Get user-uploaded datasets
user_datasets = []
if request.user.is_authenticated:
user_datasets = Dataset.objects.filter(user=request.user)
for dataset in user_datasets:
dataset.cases_count = Case.objects.filter(dataset=dataset).count()
dataset.controls_count = Control.objects.filter(dataset=dataset).count()
return render(request, "breast_cancer_resources.html", {
"dataset_groups": annotated_groups,
"user_datasets": user_datasets,
})
@login_required
def delete_dataset(request, dataset_id):
dataset = get_object_or_404(Dataset, id=dataset_id, user=request.user)
if request.method == "POST":
dataset.delete()
messages.success(request, "Dataset deleted successfully!")
return redirect("breast_cancer_resources")
return render(request, "confirm_delete.html", {"dataset": dataset})
def chi2x2_calculation(case1, case2, control1, control2, alpha=0.05):
# Calculate Odds Ratio (OR)
or_value = (case1 * control2) / (case2 * control1)
# Standard error of log(OR)
se_log_or = np.sqrt(1/case1 + 1/case2 + 1/control1 + 1/control2)
# Z-value for the given alpha
z_alpha = norm.ppf(1 - alpha / 2)
# Confidence intervals (CI) for log(OR)
log_or = np.log(or_value)
ci_lower = np.exp(log_or - z_alpha * se_log_or)
ci_upper = np.exp(log_or + z_alpha * se_log_or)
# Z-score for Wald test
z_score = log_or / se_log_or
# Two-tailed p-value
p_value = 2 * (1 - norm.cdf(abs(z_score)))
return or_value, ci_lower, ci_upper, p_value
def or_calculation_table(request, unique_id):
"""
Calculates Odds Ratios and related statistics for each criterion defined in CHART_CONFIG.
"""
dataset = get_object_or_404(Dataset, unique_id=unique_id)
cases = Case.objects.filter(dataset=dataset)
controls = Control.objects.filter(dataset=dataset)
table_data_by_category = {}
for chart_title, config in CHART_CONFIG.items():
# Skip fields marked as 'case_only' if applicable
if config.get("case_only", False):
continue
label = config["title"]
key = config["key"]
category = config.get("category", "Others") # Default category if not defined
labels = config["labels"]
filters = config["filters"]
# Ensure there are exactly two labels for OR calculation
if len(labels) != 2:
continue
# Retrieve counts using the filter lambdas
try:
case_counts = filters(cases)
control_counts = filters(controls)
except Exception as e:
continue
if len(case_counts) != 2 or len(control_counts) != 2:
continue
case1, case2 = case_counts
control1, control2 = control_counts
# Perform Chi-square test
try:
or_value, ci_lower, ci_upper, p_value = chi2x2_calculation(case1, control1, case2, control2)
except Exception as e:
or_value, ci_lower, ci_upper, p_value = None, None, None, None
row_data = {
"criteria": label,
"case_1": case1,
"control_1": control1,
"case_2": case2,
"control_2": control2,
"odds_ratio": or_value,
"lower_limit": ci_lower,
"upper_limit": ci_upper,
"p_value": p_value
}
# Group by category
if category not in table_data_by_category:
table_data_by_category[category] = []
table_data_by_category[category].append(row_data)
context = {
"dataset": dataset,
"cases": cases.count(),
"controls": controls.count(),
"table_data_by_category": table_data_by_category,
}
return render(request, "or_calculation_table.html", context)
def chi2x2_calculation_table(request, unique_id):
"""
Generates a Chi-square calculation table for each criterion defined in CHART_CONFIG.
Groups the data into separate tables based on category.
"""
dataset = get_object_or_404(Dataset, unique_id=unique_id)
cases = Case.objects.filter(dataset=dataset)
controls = Control.objects.filter(dataset=dataset)
# Dictionary to hold the table data grouped by category
categorized_data = {}
for chart_title, config in CHART_CONFIG.items():
# Skip fields marked as 'case_only' if applicable
if config.get("case_only", False):
continue
label = config["title"]
key = config["key"]
labels = config["labels"]
filters = config["filters"]
# Ensure there are exactly two labels for Chi-square calculation
if len(labels) != 2:
continue
# Retrieve counts using the filter lambdas
try:
case_counts = filters(cases)
control_counts = filters(controls)
except Exception as e:
continue
# Ensure we have two counts
if len(case_counts) != 2 or len(control_counts) != 2:
continue
# Extract counts
case1, case2 = case_counts
control1, control2 = control_counts
# Perform Chi-square test
try:
_,_,_,p = chi2x2_calculation(case1, control1, case2, control2)
except Exception as e:
p = None
# Group data by category (assuming `key` represents the category)
category = config.get("category", "General")
if category not in categorized_data:
categorized_data[category] = []
categorized_data[category].append({
"criteria": label,
"case_1": case1,
"control_1": control1,
"case_2": case2,
"control_2": control2,
"p_value": round(p, 4) if p is not None else "N/A",
})
context = {
"dataset": dataset,
"cases": cases.count(),
"controls": controls.count(),
"categorized_data": categorized_data,
}
return render(request, "chi2x2_calculation_table.html", context)
def create_filter_lambda(field, condition1, condition2, ignore_nan=False):
"""
Generates a filter function for CHART_CONFIG entries.
Args:
field (str): The model field to filter on.
condition1 (dict): The first condition as a dictionary.
condition2 (dict): The second condition as a dictionary.
ignore_nan (bool): Whether to exclude NaN (NULL) values.
Returns:
function: A lambda function that applies the filters to a queryset.
"""
def filters(cases):
if ignore_nan:
# Exclude records where the field is NULL
count1 = cases.filter(**condition1, **{f"{field}__isnull": False}).count()
count2 = cases.filter(**condition2, **{f"{field}__isnull": False}).count()
else:
count1 = cases.filter(**condition1).count()
count2 = cases.filter(**condition2).count()
return [count1, count2]
return filters
CHART_CONFIG = {
# Demographic Data
"Age": {
"key": "age_years",
"title": "Age (≥ 45 vs. < 45) Years",
"category": "Demographic data",
"labels": [">=45", "<45"],
"ignore_nan": True, # Exclude records where age_years is NULL
"filters": create_filter_lambda(
field="age_years",
condition1={"age_years__gte": 45},
condition2={"age_years__lt": 45},
ignore_nan=True
),
},
"Socio-economic Status": {
"key": "income",
"title": "Socio-economic Status (Medium vs. Low)",
"category": "Demographic data",
"labels": ["Medium", "Low"],
"ignore_nan": False, # Include records where income is NULL
"filters": create_filter_lambda(
field="income",
condition1={"income": "Medium"},
condition2={"income": "Low"},
ignore_nan=False
),
},
"Education": {
"key": "education",
"title": "Education Level (Yes vs. No)",
"category": "Demographic data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="education",
condition1={"education": "Yes"},
condition2={"education": "No"},
ignore_nan=False
),
},
"Regular Exercise": {
"key": "regular_exercise",
"title": "Regular Exercise (Yes vs. No)",
"category": "Demographic data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="regular_exercise",
condition1={"regular_exercise": "Yes"},
condition2={"regular_exercise": "No"},
ignore_nan=False
),
},
"Walking Time": {
"key": "walking_hours",
"title": "Walking Time (> 3 vs. ≤ 3) H/Day",
"category": "Demographic data",
"labels": [">3 H/Day", "≤3 H/Day"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="walking_hours",
condition1={"walking_hours__gt": 3},
condition2={"walking_hours__lte": 3},
ignore_nan=False
),
},
"Sleeping Time": {
"key": "sleeping_hours",
"title": "Sleeping Hours (≥ 6 vs. < 6) H/Day",
"category": "Demographic data",
"labels": [">=6 H/Day", "<6 H/Day"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="sleeping_hours",
condition1={"sleeping_hours__gte": 6},
condition2={"sleeping_hours__lt": 6},
ignore_nan=False
),
},
"Tea Intake": {
"key": "tea",
"title": "Tea Intake (Yes vs. No)",
"category": "Demographic data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="tea",
condition1={"tea": "Yes"},
condition2={"tea": "No"},
ignore_nan=False
),
},
"Coffee Intake": {
"key": "coffee",
"title": "Coffee Intake (Yes vs. No)",
"category": "Demographic data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="coffee",
condition1={"coffee": "Yes"},
condition2={"coffee": "No"},
ignore_nan=False
),
},
"Family History with Cancer": {
"key": "family_history_with_cancer",
"title": "Family History with Cancer (Yes vs. No)",
"category": "Demographic data",
"labels": ["Yes", "No"],
"ignore_nan": True, # Treat NaN as "No" by excluding
"filters": create_filter_lambda(
field="family_history_with_cancer",
condition1={"family_history_with_cancer": "Yes"},
condition2={"family_history_with_cancer": "No"},
ignore_nan=True
),
},
"Sound Sleep Occurrence": {
"key": "sound_sleep",
"title": "Sound Sleep Occurrence (Yes vs. No)",
"category": "Demographic data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="sound_sleep",
condition1={"sound_sleep": "Yes"},
condition2={"sound_sleep": "No"},
ignore_nan=False
),
},
"Lifestyle": {
"key": "desk_job",
"title": "Lifestyle (Active in Job vs. Sedentary)",
"category": "Demographic data",
"labels": ["Active in Job", "Sedentary"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="desk_job",
condition1={"desk_job": "No"},
condition2={"desk_job": "Yes"},
ignore_nan=False
),
},
# Anthropometric Data
"Height": {
"key": "height_m",
"title": "Height (<1.5 m vs. ≥1.5 m)",
"category": "Anthropometric data",
"labels": ["≥1.5 m", "<1.5 m"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="height_m",
condition1={"height_m__gte": 1.5},
condition2={"height_m__lt": 1.5},
ignore_nan=False
),
},
"BMI": {
"key": "bmi",
"title": "BMI (>=30 vs. <30)",
"category": "Anthropometric data",
"labels": [">=30", "<30"],
"ignore_nan": True, # Exclude records where BMI is NULL
"filters": create_filter_lambda(
field="bmi",
condition1={"bmi__gte": 30},
condition2={"bmi__lt": 30},
ignore_nan=True
),
},
"Weight": {
"key": "weight_kg",
"title": "Weight (≥59 Kg vs. <59 Kg)",
"category": "Anthropometric data",
"labels": ["≥59 Kg", "<59 Kg"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="weight_kg",
condition1={"weight_kg__gte": 59},
condition2={"weight_kg__lt": 59},
ignore_nan=False
),
},
"Waist Circumference": {
"key": "waist_circum_cm",
"title": "Waist Circumference (≥80 cm vs. <80 cm)",
"category": "Anthropometric data",
"labels": ["≥80 cm", "<80 cm"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="waist_circum_cm",
condition1={"waist_circum_cm__gte": 80},
condition2={"waist_circum_cm__lt": 80},
ignore_nan=False
),
},
"Waist-Hip Ratio": {
"key": "whr",
"title": "Waist-Hip Ratio (≥0.8 vs. <0.8)",
"category": "Anthropometric data",
"labels": ["≥0.8", "<0.8"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="whr",
condition1={"whr__gte": 0.8},
condition2={"whr__lt": 0.8},
ignore_nan=False
),
},
# Biochemical Parameters Data
"BP SYS": {
"key": "bp_sys",
"title": "Blood Pressure SYS (>120 mmHg vs. ≤120 mmHg)",
"category": "Biochemical parameters data",
"labels": [">120 mmHg", "<=120 mmHg"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="bp_sys",
condition1={"bp_sys__gt": 120},
condition2={"bp_sys__lte": 120},
ignore_nan=False
),
},
"BP DIA": {
"key": "bp_dia",
"title": "Blood Pressure DIA (>80 mmHg vs. ≤80 mmHg)",
"category": "Biochemical parameters data",
"labels": [">80 mmHg", "<=80 mmHg"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="bp_dia",
condition1={"bp_dia__gt": 80},
condition2={"bp_dia__lte": 80},
ignore_nan=False
),
},
"RBS": {
"key": "rbs",
"title": "Random Blood Sugar (>=7.8 mmol/dl vs. <7.8 mmol/dl)",
"category": "Biochemical parameters data",
"labels": [">=7.8 mmol/dl", "<7.8 mmol/dl"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="rbs",
condition1={"rbs__gte": 7.8},
condition2={"rbs__lt": 7.8},
ignore_nan=False
),
},
"HBA1C": {
"key": "hba1c",
"title": "HbA1c (>6.3% vs. ≤6.3%)",
"category": "Biochemical parameters data",
"labels": [">6.3%", "<=6.3%"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="hba1c",
condition1={"hba1c__gt": 6.3},
condition2={"hba1c__lte": 6.3},
ignore_nan=False
),
},
"Blood Creatinine Level": {
"key": "creatinine",
"title": "Blood Creatinine Level (<0.6 & >1.2 mg/dl vs. 0.6-1.2 mg/dl)",
"category": "Biochemical parameters data",
"labels": ["<0.6 & >1.2 mg/dl", "0.6-1.2 mg/dl"],
"ignore_nan": False,
"filters": lambda cases: [
cases.filter(creatinine__lt=0.6).count() + cases.filter(creatinine__gt=1.2).count(),
cases.filter(creatinine__gte=0.6, creatinine__lte=1.2).count(),
],
},
"HDL": {
"key": "hdl",
"title": "HDL (≥30 mg/dl vs. <30 mg/dl)",
"category": "Biochemical parameters data",
"labels": ["≥30 mg/dl", "<30 mg/dl"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="hdl",
condition1={"hdl__gte": 30},
condition2={"hdl__lt": 30},
ignore_nan=False
),
},
"LDL": {
"key": "ldl",
"title": "LDL (≥130 mg/dl vs. <130 mg/dl)",
"category": "Biochemical parameters data",
"labels": ["≥130 mg/dl", "<130 mg/dl"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="ldl",
condition1={"ldl__gte": 130},
condition2={"ldl__lt": 130},
ignore_nan=False
),
},
"LDL / HDL Ratio": {
"key": "ldl_hdl",
"title": "LDL / HDL Ratio (≥2.5 vs. <2.5)",
"category": "Biochemical parameters data",
"labels": ["≥2.5", "<2.5"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="ldl_hdl",
condition1={"ldl_hdl__gte": 2.5},
condition2={"ldl_hdl__lt": 2.5},
ignore_nan=False
),
},
# Clinical Data
"Subtype": {
"key": "breast_cancer_type",
"title": "Subtype (ER+ vs. ER-)",
"category": "Clinical Data",
"labels": ["ER+", "ER-"],
"ignore_nan": False, # Assuming subtype is always provided
"filters": lambda cases: [
cases.filter(er="Positive").count(),
cases.filter(er="Negative").count(),
],
"case_only": True, # This field is only available in the Case model
},
"Age at Diagnosis": {
"key": "age_at_diagnosis",
"title": "Age at Diagnosis (<40 vs. >=40)",
"category": "Clinical Data",
"labels": ["<40", ">=40"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="age_at_diagnosis",
condition1={"age_at_diagnosis__lt": 40},
condition2={"age_at_diagnosis__gte": 40},
ignore_nan=False
),
},
"Cancer Stage": {
"key": "cancer_stage",
"title": "Cancer Stage (II vs. III)",
"category": "Clinical Data",
"labels": ["II", "III"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="cancer_stage",
condition1={"cancer_stage": "2"},
condition2={"cancer_stage": "3"},
ignore_nan=False
),
},
"Cancer Type": {
"key": "breast_cancer_type",
"title": "Cancer Type",
"category": "Clinical Data",
"labels": ["TNBC", "Ductal cell carcinoma"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="breast_cancer_type",
condition1={"breast_cancer_type__icontains": "TNBC"},
condition2={"breast_cancer_type__icontains": "Ductal Cell Carcinoma"},
ignore_nan=False
),
},
"Physical": {
"key": "physical",
"title": "Physical (Yes vs. No)",
"category": "Clinical Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="physical",
condition1={"physical": "Yes"},
condition2={"physical": "No"},
ignore_nan=False
),
},
"Mammography": {
"key": "mammography",
"title": "Mammography (Yes vs. No)",
"category": "Clinical Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="mammography",
condition1={"mammography": "Yes"},
condition2={"mammography": "No"},
ignore_nan=False
),
},
"FNAC": {
"key": "fnac",
"title": "FNAC (Yes vs. No)",
"category": "Clinical Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="fnac",
condition1={"fnac": "Yes"},
condition2={"fnac": "No"},
ignore_nan=False
),
},
"Pathology": {
"key": "pathology",
"title": "Pathology (Yes vs. No)",
"category": "Clinical Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="pathology",
condition1={"pathology": "Yes"},
condition2={"pathology": "No"},
ignore_nan=False
),
},
"Histopathology": {
"key": "histopathology",
"title": "Histopathology (Yes vs. No)",
"category": "Clinical Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="histopathology",
condition1={"histopathology": "Yes"},
condition2={"histopathology": "No"},
ignore_nan=False
),
},
# Obstetric Data
"Menarche Age": {
"key": "menarche_age",
"title": "Menarche Age (≥12 vs. <12 Years)",
"category": "Obstetric data",
"labels": ["≥12", "<12"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="menarche_age",
condition1={"menarche_age__gte": 12},
condition2={"menarche_age__lt": 12},
ignore_nan=False
),
},
"Menopause Age": {
"key": "menopause_age",
"title": "Menopause Age (≥45 vs. <45 Years)",
"category": "Obstetric data",
"labels": ["≥45", "<45"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="menopause_age",
condition1={"menopause_age__gte": 45},
condition2={"menopause_age__lt": 45},
ignore_nan=False
),
},
"First Child-Bearing Age": {
"key": "age_at_first_birth",
"title": "First Child-Bearing Age (≥18 vs. <18 Years)",
"category": "Obstetric data",
"labels": ["≥18", "<18"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="age_at_first_birth",
condition1={"age_at_first_birth__gte": 18},
condition2={"age_at_first_birth__lt": 18},
ignore_nan=False
),
},
"Parity": {
"key": "parity",
"title": "Parity (>2 vs. ≤2)",
"category": "Obstetric data",
"labels": [">2", "≤2"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="parity",
condition1={"parity__gt": 2},
condition2={"parity__lte": 2},
ignore_nan=False
),
},
"Breastfeeding Duration": {
"key": "breastfeeding_duration",
"title": "Breastfeeding Duration (>4 vs. ≤4 Years)",
"category": "Obstetric data",
"labels": [">4", "≤4"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="breastfeeding_duration",
condition1={"breastfeeding_duration__gt": 4},
condition2={"breastfeeding_duration__lte": 4},
ignore_nan=False
),
},
"Contraceptive Use": {
"key": "use_contraceptive",
"title": "Contraceptive Use (Yes vs. No)",
"category": "Obstetric data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="use_contraceptive",
condition1={"use_contraceptive": "Yes"},
condition2={"use_contraceptive": "No"},
ignore_nan=False
),
},
# Treatment Data
"Radiotherapy": {
"key": "radio_therapy",
"title": "Radiotherapy (Yes vs. No)",
"category": "Treatment Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="radio_therapy",
condition1={"radio_therapy": "Yes"},
condition2={"radio_therapy": "No"},
ignore_nan=False
),
},
"Chemotherapy": {
"key": "chemotherapy",
"title": "Chemotherapy (Yes vs. No)",
"category": "Treatment Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="chemotherapy",
condition1={"chemotherapy": "Yes"},
condition2={"chemotherapy": "No"},
ignore_nan=False
),
},
"Surgery": {
"key": "surgery",
"title": "Surgery (Yes vs. No)",
"category": "Treatment Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="surgery",
condition1={"surgery": "Yes"},
condition2={"surgery": "No"},
ignore_nan=False
),
},
"Hormone Therapy": {
"key": "hormone_therapy",
"title": "Hormone Therapy (Yes vs. No)",
"category": "Treatment Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="hormone_therapy",
condition1={"hormone_therapy": "Yes"},
condition2={"hormone_therapy": "No"},
ignore_nan=False
),
},
"Oral Medication": {
"key": "oral_medication",
"title": "Oral Medication (Yes vs. No)",
"category": "Treatment Data",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="oral_medication",
condition1={"oral_medication": "Yes"},
condition2={"oral_medication": "No"},
ignore_nan=False
),
},
# Special Data
"NL vs OW": {
"key": "bmi",
"title": "NL vs OW",
"category": "NL vs OW vs OB",
"labels": ["NL", "OW"],
"ignore_nan": False, # Include records where bmi is NULL
"filters": create_filter_lambda(
field="bmi",
condition1={"bmi__gte": 18.5, "bmi__lt": 25}, # Normal weight (NL)
condition2={"bmi__gte": 25, "bmi__lt": 30}, # Overweight (OW)
ignore_nan=False
),
},
"NL vs OB": {
"key": "bmi",
"title": "NL vs OB",
"category": "NL vs OW vs OB",
"labels": ["NL", "OB"],
"ignore_nan": False, # Include records where bmi is NULL
"filters": create_filter_lambda(
field="bmi",
condition1={"bmi__gte": 18.5, "bmi__lt": 25}, # Normal weight (NL)
condition2={"bmi__gte": 30}, # Obese (OB)
ignore_nan=False
),
},
"OW vs OB":{
"key": "bmi",
"title": "OW vs OB",
"category": "NL vs OW vs OB",
"labels": ["OW", "OB"],
"ignore_nan": False, # Include records where bmi is NULL
"filters": create_filter_lambda(
field="bmi",
condition1={"bmi__gte": 25, "bmi__lt": 30},
condition2={"bmi__gte": 30},
ignore_nan=False
),
},
"NL+OW vs OB": {
"key": "bmi",
"title": "NL+OW vs OB",
"category": "NL vs OW vs OB",
"labels": ["NL+OW", "OB"],
"ignore_nan": False, # Include records where bmi is NULL
"filters": create_filter_lambda(
field="bmi",
condition1 = {"bmi__gte": 18.5, "bmi__lt": 30}, # NL+OW: BMI between 18.5 and 30
condition2 = {"bmi__gte": 30}, # OB: BMI >= 30
ignore_nan=False
),
},
# Extra Data
"antibiotic_intake": {
"key": "antibiotic_intake",
"title": "Antibiotic Intake (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="antibiotic_intake",
condition1={"antibiotic_intake": "Yes"},
condition2={"antibiotic_intake": "No"},
ignore_nan=False
),
},
"betal_nuts": {
"key": "betal_nuts",
"title": "Betel Nut Intake (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="betal_nuts",
condition1={"betal_nuts": "Yes"},
condition2={"betal_nuts": "No"},
ignore_nan=False
),
},
"carbohydrate": {
"key": "carbohydrate",
"title": "Carbohydrates (> 2 vs. ≤ 2) Times/Day",
"labels": [">2 Times/Day", "≤2 Times/Day"],
"ignore_nan": True,
"filters": create_filter_lambda(
field="carbohydrate",
condition1={"carbohydrate__gt": 2.0},
condition2={"carbohydrate__lte": 2.0},
ignore_nan=True
),
},
"gastric": {
"key": "gastric",
"title": "Gastric Problem (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="gastric",
condition1={"gastric": "Yes"},
condition2={"gastric": "No"},
ignore_nan=False
),
},
"jarda": {
"key": "jarda",
"title": "Jorda Intake (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="jarda",
condition1={"jarda": "Yes"},
condition2={"jarda": "No"},
ignore_nan=False
),
},
"menstrual_status": {
"key": "menstrual_status",
"title": "Menstrual Status (No vs. Yes)",
"labels": ["No", "Yes"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="menstrual_status",
condition1={"menstrual_status": "No"},
condition2={"menstrual_status": "Yes"},
ignore_nan=False
),
},
"processed_fastfood_softdrinks": {
"key": "processed_fastfood_softdrinks",
"title": "Processed/Fastfood/Soft Drinks (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": lambda cases: [
cases.filter(Q(processed_food="Yes") | Q(fast_food="Yes") | Q(soft_drinks="Yes")).count(),
cases.filter(processed_food="No", fast_food="No", soft_drinks="No").count(),
],
},
"protein": {
"key": "protein",
"title": "Proteins (≤ 2 vs. > 2) Times/Day",
"labels": ["≤2 Times/Day", ">2 Times/Day"],
"ignore_nan": True,
"filters": create_filter_lambda(
field="protein",
condition1={"protein__lte": 2.0},
condition2={"protein__gt": 2.0},
ignore_nan=True
),
},
"restless_fatigue_shortness_breath": {
"key": "restless_fatigue_shortness_breath",
"title": "Restless/Fatigue/Shortness of Breath (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": lambda cases: [
cases.filter(Q(feeling_restless="Yes") | Q(fatigue="Yes") | Q(shortness_of_breath="Yes")).count(),
cases.filter(feeling_restless="No", fatigue="No", shortness_of_breath="No").count(),
],
},
"standing_hours": {
"key": "standing_hours",
"title": "Standing (> 3 vs. ≤ 3) Hours/Day",
"labels": [">3 Hours/Day", "≤3 Hours/Day"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="standing_hours",
condition1={"standing_hours__gt": 3},
condition2={"standing_hours__lte": 3},
ignore_nan=False
),
},
"tc": {
"key": "tc",
"title": "TC (≥200 vs. <200) mg/dl",
"labels": [">=200 mg/dl", "<200 mg/dl"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="tc",
condition1={"tc__gte": 200},
condition2={"tc__lt": 200},
ignore_nan=False
),
},
"tc_hdl": {
"key": "tc_hdl",
"title": "TC / HDL Ratio (≥3 vs. <3)",
"labels": [">=3", "<3"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="tc_hdl",
condition1={"tc_hdl__gte": 3},
condition2={"tc_hdl__lt": 3},
ignore_nan=False
),
},
"tea_coffee_intake": {
"key": "tea_coffee_intake",
"title": "Tea/Coffee Intake (No vs. Yes)",
"labels": ["No", "Yes"],
"ignore_nan": False,
"filters": lambda cases: [
cases.filter(Q(tea="No") & Q(coffee="No")).count(),
cases.filter(Q(tea="Yes") | Q(coffee="Yes")).count(),
],
},
"tg": {
"key": "tg",
"title": "TG (≥150 vs. <150) mg/dl",
"labels": [">=150 mg/dl", "<150 mg/dl"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="tg",
condition1={"tg__gte": 150},
condition2={"tg__lt": 150},
ignore_nan=False
),
},
"tg_hdl": {
"key": "tg_hdl",
"title": "TG / HDL Ratio (≥2 vs. <2)",
"labels": [">=2", "<2"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="tg_hdl",
condition1={"tg_hdl__gte": 2},
condition2={"tg_hdl__lt": 2},
ignore_nan=False
),
},
"thyroidism_problem": {
"key": "thyroidism_problem",
"title": "Thyroidism (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="thyroidism_problem",
condition1={"thyroidism_problem": "Yes"},
condition2={"thyroidism_problem": "No"},
ignore_nan=False
),
},
"vegetable_fruits": {
"key": "vegetable_fruits",
"title": "Vegetable/Fruits (≤2 vs. >2) Times/Day",
"labels": ["≤2 Times/Day", ">2 Times/Day"],
"ignore_nan": False,
"filters": lambda cases: [
cases.annotate(total=F('vegetable') + F('fruits')).filter(total__lte=2).count(),
cases.annotate(total=F('vegetable') + F('fruits')).filter(total__gt=2).count(),
],
},
"vitamin_mineral_intake": {
"key": "vitamin_mineral_intake",
"title": "Vitamin/Mineral Intake (Yes vs. No)",
"labels": ["Yes", "No"],
"ignore_nan": False,
"filters": lambda cases: [
cases.filter(Q(vitamins="Yes") | Q(minerals="Yes")).count(),
cases.filter(Q(vitamins="No") & Q(minerals="No")).count(),
],
},
"water_g_per_day": {
"key": "water_g_per_day",
"title": "Water Intake (<8 vs. ≥8) Glass/Day",
"labels": ["<8 Glasses/Day", "≥8 Glasses/Day"],
"ignore_nan": False,
"filters": create_filter_lambda(
field="water_g_per_day",
condition1={"water_g_per_day__lt": 8},
condition2={"water_g_per_day__gte": 8},
ignore_nan=False
),
},
}
def get_combined_condition(filters):
logic = filters["logic"]
conditions = Q()
for filter_obj in filters["filters"]:
if filter_obj["type"] == "condition":
field = filter_obj["field"]
condition_type = filter_obj["condition_type"]
value = filter_obj["value"]
if condition_type == "gte":
condition = Q(**{f"{field}__gte": value})
elif condition_type == "lte":
condition = Q(**{f"{field}__lte": value})
elif condition_type == "gt":
condition = Q(**{f"{field}__gt": value})
elif condition_type == "lt":
condition = Q(**{f"{field}__lt": value})
elif condition_type == "exact":
condition = Q(**{f"{field}__in": value})
else:
raise ValueError(f"Unsupported condition type: {condition_type}")
elif filter_obj["type"] == "group":
condition = get_combined_condition(filter_obj)
else:
raise ValueError(f"Unsupported filter type: {filter_obj['type']}")
if logic == "AND":
conditions &= condition
elif logic == "OR":
conditions |= condition
else:
raise ValueError(f"Unsupported logic: {logic}")
return conditions
def generate_grouped_bar_chart(title, labels, cases_values, controls_values, cases_counts, controls_counts, p_value=None):
chart = go.Figure()
# Add bars for Cases
chart.add_trace(go.Bar(
x=labels,
y=cases_values,
width=0.35, # Narrower bars
name="Cases",
marker=dict(color="#1f77b4"),
text=[f"{value}%" for value in cases_values],
textposition="outside",
customdata=cases_counts,
hovertemplate="Cases - %{x}
Count: %{customdata}
Percentage: %{y}%",
))
# Add bars for Controls
chart.add_trace(go.Bar(
x=labels,
y=controls_values,
width=0.35, # Narrower bars
name="Controls",
marker=dict(color="#ff7f0e"),
text=[f"{value}%" for value in controls_values],
textposition="outside",
customdata=controls_counts,
hovertemplate="Controls - %{x}
Count: %{customdata}
Percentage: %{y}%",
))
try:
# Calculate the range dynamically if values are available
y_axis_range = [0, max(max(cases_values), max(controls_values)) + 20]
except (ValueError, TypeError) as e:
# Fallback range in case of empty or invalid values
print(f"Error calculating range: {e}")
y_axis_range = [0, 100] # Default range
# Update layout
chart.update_layout(
title=dict(
text=f"P-value: {p_value:.4f}" if p_value else "",
x=0.5,
font=dict(size=10, color="#B71C1C"),
),
yaxis=dict(
# title="Percentage (%)",
tickfont=dict(size=10),
range=y_axis_range,
),
xaxis=dict(tickfont=dict(size=10)),
barmode="group",
template="plotly_white",
showlegend=True,
legend=dict(
orientation="h",
yanchor="bottom",
y=-0.5,
xanchor="center",
x=0.5
),
margin=dict(l=0, r=30, t=80, b=10),
# height=250, # Reduced height
width=180, # Reduced width
modebar=dict(orientation='v')
)
config = {
'responsive': True,
'displaylogo': False,
'displayModeBar': True,
'modeBarButtonsToRemove': [
'lasso2d', 'select2d', 'toggleSpikelines',
'hoverCompareCartesian', 'hoverClosestCartesian',
'pan2d', "zoom2d", "zoomIn2d", "zoomOut2d", "autoScale2d"
],
'toImageButtonOptions': {
'filename': title,
'width': 600,
'scale': 2,
},
}
return chart.to_html(full_html=False, include_plotlyjs=False, include_mathjax=False, config=config)
def generate_bar_chart_main(title, labels, values, counts, colors, p_value=None):
chart = Figure()
chart.add_trace(
Bar(
x=labels,
y=values,
width=0.4, # Adjusted for narrower bars
text=[f"{value}%" for value in values],
textposition="inside",
marker=dict(color=colors),
customdata=counts,
hovertemplate='%{x}
Count: %{customdata}
Percentage: %{y}%',
)
)
chart.update_layout(
title={
"text": title,
"x": 0.5,
"font": {"size": 14}, # Slightly smaller font
},
# yaxis_title="Percentage (%)",
yaxis=dict(tickfont=dict(size=10)),
xaxis=dict(tickfont=dict(size=10)),
showlegend=False,
margin=dict(t=30, b=20, l=20, r=30),
width=200, # Reduced width
height=250, # Reduced height
modebar=dict(orientation='v')
)
config = {
'responsive': True,
'displaylogo': False,
'displayModeBar': True,
'modeBarButtonsToRemove': [
'lasso2d', 'select2d', 'toggleSpikelines',
'hoverCompareCartesian', 'hoverClosestCartesian',
'pan2d', "zoom2d", "zoomIn2d", "zoomOut2d"
],
'toImageButtonOptions': {
'filename': title,
'width': 600,
'scale': 2,
},
}
return chart.to_html(full_html=False, include_plotlyjs=False,include_mathjax=False, config=config)
def generate_chart_from_config(chart_title, group_title, filtered_cases, total_cases, filtered_controls=None, total_controls=None):
if chart_title not in CHART_CONFIG:
return None # Return None if chart_title is not configured
config = CHART_CONFIG[chart_title]
# Handle cases
try:
case_counts = config["filters"](filtered_cases)
case_percentages = [round((count / total_cases) * 100) if total_cases > 0 else 0 for count in case_counts]
except Exception as e:
# logger.warning(f"Error in case data for chart '{chart_title}': {e}")
case_counts = [0, 0]
case_percentages = [0, 0]
# Handle controls
control_counts = []
control_percentages = []
if filtered_controls and total_controls:
try:
control_counts = config["filters"](filtered_controls)
control_percentages = [round((count / total_controls) * 100) if total_controls > 0 else 0 for count in control_counts]
except Exception as e:
# logger.warning(f"Error in control data for chart '{chart_title}': {e}")
control_counts = [0, 0]
control_percentages = [0, 0]
# **Use original labels without interleaving**
labels = config["labels"]
cases_values = case_percentages
controls_values = control_percentages
cases_counts = case_counts
controls_counts = control_counts
try:
# Perform chi-square test for comparison, if both cases and controls are available
if case_counts and control_counts:
_, _, _, p_value = chi2x2_calculation(case_counts[0], control_counts[0], case_counts[1], control_counts[1])
else:
p_value = None
except Exception:
p_value = None
# print(f"title: {chart_title}, labels: {labels}, cases_values: {cases_values}, controls_values: {controls_values}, cases_counts: {cases_counts}, controls_counts: {controls_counts}")
# **Call the new grouped bar chart generation function**
return generate_grouped_bar_chart(
title=chart_title,
labels=labels,
cases_values=cases_values,
controls_values=controls_values,
cases_counts=cases_counts,
controls_counts=controls_counts,
p_value=p_value,
)
def data_visualization(request, unique_id):
dataset = get_object_or_404(Dataset, unique_id=unique_id)
groups_param = request.GET.get('groups')
if groups_param:
try:
data = json.loads(unquote(groups_param))
group_title = data.get("groupTitle", "Unnamed Group")
root_groups = data.get("rootGroups", [])
except json.JSONDecodeError:
logger.error("Failed to decode 'groups' parameter.")
group_title = "Unnamed Group"
root_groups = []
else:
group_title = "Unnamed Group"
root_groups = []
chart_titles = CHART_CONFIG.keys()
group_results = {}
categorized_charts = {}
total_cases = Case.objects.filter(dataset=dataset).count()
total_controls = Control.objects.filter(dataset=dataset).count()
for group in root_groups:
title = group.get("title", "Unnamed Group")
filters = group.get("filters", {})
combined_condition = get_combined_condition(filters)
try:
filtered_cases = Case.objects.filter(dataset=dataset).filter(combined_condition)
except:
filtered_cases = None
try:
filtered_controls = Control.objects.filter(dataset=dataset).filter(combined_condition)
except:
filtered_controls = None
try:
cases_count = filtered_cases.count()
except:
cases_count = 0
try:
controls_count = filtered_controls.count()
except:
controls_count = 0
cases_percent = round((cases_count / total_cases) * 100) if total_cases else 0
controls_percent = round((controls_count / total_controls) * 100) if total_controls else 0
try:
_,_,_, p_value = chi2x2_calculation(cases_count, total_cases, controls_count, total_controls)
except Exception as e:
logger.error(f"Chi-square test failed for group '{title}': {e}")
p_value = None
bar_chart_html = generate_bar_chart_main(
title=f"{title}",
labels=["Cases", "Controls"],
values=[cases_percent, controls_percent],
counts=[cases_count, controls_count],
colors=["#1f77b4", "#ff7f0e"],
)
for chart_title in chart_titles:
chart_html = generate_chart_from_config(chart_title, title, filtered_cases, total_cases, filtered_controls, total_controls)
if chart_html:
category = CHART_CONFIG[chart_title].get("category", "Uncategorized")
if category == "Uncategorized":
continue
if category not in categorized_charts:
categorized_charts[category] = []
chart_entry = next((item for item in categorized_charts[category] if item["title"] == chart_title), None)
if not chart_entry:
chart_entry = {"title": chart_title, "charts": {}}
categorized_charts[category].append(chart_entry)
chart_entry["charts"][title] = chart_html
group_results[title] = {
"label": title,
"cases_count": cases_count,
"total_cases": total_cases,
"cases_percent": cases_percent,
"controls_count": controls_count,
"total_controls": total_controls,
"controls_percent": controls_percent,
"bar_chart_html": bar_chart_html,
}
context = {
"dataset": dataset,
"unique_id": unique_id,
"group_title": group_title,
"group_results": group_results,
"categorized_charts": categorized_charts,
}
return render(request, "data_visualization.html", context)
@csrf_exempt
def add_groups(request, unique_id):
def get_options(dataset_id,variable):
cases = Case.objects.filter(dataset__unique_id=dataset_id).values_list(variable, flat=True).distinct()
return [option for option in cases if option]
dataset = get_object_or_404(Dataset, unique_id=unique_id)
variables = [
{"field": "age_years", "name": "Age (Years)", "type": "integer", "category": "Demographic data"},
{"field": "occupation", "name": "Occupation", "type": "checkbox", "options": get_options(unique_id, "occupation"), "category": "Demographic data"},
{"field": "education", "name": "Education", "type": "checkbox", "options": get_options(unique_id, "education"), "category": "Demographic data"},
{"field": "income", "name": "Income", "type": "checkbox", "options": get_options(unique_id, "income"), "category": "Demographic data"},
{"field": "family_history_with_cancer", "name": "Family history with cancer", "type": "checkbox", "options": get_options(unique_id, "family_history_with_cancer"), "category": "Demographic data"},
{"field": "regular_exercise", "name": "Regular exercise", "type": "checkbox", "options": get_options(unique_id, "regular_exercise"), "category": "Demographic data"},
{"field": "feeling_restless", "name": "Feeling restless", "type": "checkbox", "options": get_options(unique_id, "feeling_restless"), "category": "Demographic data"},
{"field": "fatigue", "name": "Fatigue", "type": "checkbox", "options": get_options(unique_id, "fatigue"), "category": "Demographic data"},
{"field": "shortness_of_breath", "name": "Shortness of breath", "type": "checkbox", "options": get_options(unique_id, "shortness_of_breath"), "category": "Demographic data"},
{"field": "sleeping_hours", "name": "Sleeping (h/d)", "type": "float", "category": "Demographic data"},
{"field": "sound_sleep", "name": "Sound sleep", "type": "checkbox", "options": get_options(unique_id, "sound_sleep"), "category": "Demographic data"},
{"field": "height_m", "name": "Height (m)", "type": "float", "category": "Anthropometric data"},
{"field": "weight_kg", "name": "Weight (Kg)", "type": "float", "category": "Anthropometric data"},
{"field": "bmi", "name": "BMI (Kg/m^2)", "type": "float", "category": "Anthropometric data"},
{"field": "waist_circum_cm", "name": "Waist Circum. (cm)", "type": "float", "category": "Anthropometric data"},
{"field": "hip_circum_cm", "name": "Hip Circum. (cm)", "type": "float", "category": "Anthropometric data"},
{"field": "whr", "name": "WHR", "type": "float", "category": "Anthropometric data"},
{"field": "bp_sys", "name": "BP-Sys (mm Hg)", "type": "integer", "category": "Biochemical parameters data"},
{"field": "bp_dia", "name": "BP-Dia (mm Hg)", "type": "integer", "category": "Biochemical parameters data"},
{"field": "rbs", "name": "RBS (mmol/dl)", "type": "float", "category": "Biochemical parameters data"},
{"field": "hba1c", "name": "HbA1c (%)", "type": "float", "category": "Biochemical parameters data"},
{"field": "tg", "name": "TG (mg/dl)", "type": "float", "category": "Biochemical parameters data"},
{"field": "hdl", "name": "HDL (mg/dl)", "type": "float", "category": "Biochemical parameters data"},
{"field": "ldl", "name": "LDL (mg/dl)", "type": "float", "category": "Biochemical parameters data"},
{"field": "tc", "name": "TC (mg/dl)", "type": "float", "category": "Biochemical parameters data"},
{"field": "tg_hdl", "name": "TG/ HDL", "type": "float", "category": "Biochemical parameters data"},
{"field": "ldl_hdl", "name": "LDL/ HDL", "type": "float", "category": "Biochemical parameters data"},
{"field": "tc_hdl", "name": "TC/ HDL", "type": "float", "category": "Biochemical parameters data"},
{"field": "creatinine", "name": "Creatinine (mg/dl)", "type": "float", "category": "Biochemical parameters data"},
{"field": "menarche_age", "name": "Menerche age (Yrs)", "type": "integer", "category": "Obstetric data"},
{"field": "menstrual_status", "name": "Menstrual status", "type": "checkbox", "options": get_options(unique_id, "menstrual_status"), "category": "Obstetric data"},
{"field": "menopause_age", "name": "Menopause age (Yrs)", "type": "integer", "category": "Obstetric data"},
{"field": "parity", "name": "Parity (No)", "type": "integer", "category": "Obstetric data"},
{"field": "age_at_first_birth", "name": "Age at 1st birth (Yrs)", "type": "integer", "category": "Obstetric data"},
{"field": "lactation_situation", "name": "Lactation situation", "type": "checkbox", "options": get_options(unique_id, "lactation_situation"), "category": "Obstetric data"},
{"field": "breastfeeding_duration", "name": "Breastfeeding duration", "type": "float", "category": "Obstetric data"},
{"field": "use_contraceptive", "name": "Use contraceptive", "type": "checkbox", "options": get_options(unique_id, "use_contraceptive"), "category": "Obstetric data"},
{"field": "er", "name": "ER+/-", "type": "checkbox", "options": get_options(unique_id, "er"), "category": "Clinical Data"},
{"field": "her2", "name": "HER2+/-", "type": "checkbox", "options": get_options(unique_id, "her2"), "category": "Clinical Data"},
{"field": "age_at_diagnosis", "name": "Age at diagnosis (Yrs)", "type": "integer", "category": "Clinical Data"},
{"field": "cancer_stage", "name": "Cancer stage", "type": "checkbox", "options": get_options(unique_id, "cancer_stage"), "category": "Clinical Data"},
{"field": "physical", "name": "Physical", "type": "checkbox", "options": get_options(unique_id, "physical"), "category": "Clinical Data"},
{"field": "mammography", "name": "Mammography", "type": "checkbox", "options": get_options(unique_id, "mammography"), "category": "Clinical Data"},
{"field": "fnac", "name": "FNAC", "type": "checkbox", "options": get_options(unique_id, "fnac"), "category": "Clinical Data"},
{"field": "pathology", "name": "Pathology", "type": "checkbox", "options": get_options(unique_id, "pathology"), "category": "Clinical Data"},
{"field": "histopathology", "name": "Histopathology", "type": "checkbox", "options": get_options(unique_id, "histopathology"), "category": "Clinical Data"},
{"field": "thyroidism_problem", "name": "Thyroidism problem", "type": "checkbox", "options": get_options(unique_id, "thyroidism_problem"), "category": "Clinical Data"},
{"field": "gastric", "name": "Gastric", "type": "checkbox", "options": get_options(unique_id, "gastric"), "category": "Clinical Data"},
{"field": "antibiotic_intake", "name": "Antibiotic intake", "type": "checkbox", "options": get_options(unique_id, "antibiotic_intake"), "category": "Clinical Data"},
{"field": "diabetes", "name": "Diabetes", "type": "checkbox", "options": get_options(unique_id, "diabetes"), "category": "Clinical Data"},
{"field": "chemotherapy", "name": "Chemotherapy", "type": "checkbox", "options": get_options(unique_id, "chemotherapy"), "category": "Treatment Data"},
{"field": "radio_therapy", "name": "Radiotherapy", "type": "checkbox", "options": get_options(unique_id, "radio_therapy"), "category": "Treatment Data"},
{"field": "surgery", "name": "Surgery", "type": "checkbox", "options": get_options(unique_id, "surgery"), "category": "Treatment Data"},
{"field": "hormone_therapy", "name": "Hormone therapy", "type": "checkbox", "options": get_options(unique_id, "hormone_therapy"), "category": "Treatment Data"},
{"field": "oral_medication", "name": "Oral medication", "type": "checkbox", "options": get_options(unique_id, "oral_medication"), "category": "Treatment Data"},
{"field": "carbohydrate", "name": "Carbohydrate", "type": "checkbox", "options": get_options(unique_id, "carbohydrate"), "category": "Extra Class"},
{"field": "protein", "name": "Protein", "type": "checkbox", "options": get_options(unique_id, "protein"), "category": "Extra Class"},
{"field": "fats_source", "name": "Fats Source", "type": "checkbox", "options": get_options(unique_id, "fats_source"), "category": "Extra Class"},
{"field": "vegetable", "name": "Vegetable", "type": "checkbox", "options": get_options(unique_id, "vegetable"), "category": "Extra Class"},
{"field": "fruits", "name": "Fruits", "type": "checkbox", "options": get_options(unique_id, "fruits"), "category": "Extra Class"},
{"field": "vitamins", "name": "Vitamins", "type": "checkbox", "options": get_options(unique_id, "vitamins"), "category": "Extra Class"},
{"field": "minerals", "name": "Minerals", "type": "checkbox", "options": get_options(unique_id, "minerals"), "category": "Extra Class"},
{"field": "water_g_per_day", "name": "Water (G/D)", "type": "float", "category": "Extra Class"},
{"field": "tea", "name": "Tea", "type": "checkbox", "options": get_options(unique_id, "tea"), "category": "Extra Class"},
{"field": "coffee", "name": "Coffee", "type": "checkbox", "options": get_options(unique_id, "coffee"), "category": "Extra Class"},
{"field": "betal_nuts", "name": "Betal nuts", "type": "checkbox", "options": get_options(unique_id, "betal_nuts"), "category": "Extra Class"},
{"field": "jarda", "name": "Jarda", "type": "checkbox", "options": get_options(unique_id, "jarda"), "category": "Extra Class"},
{"field": "processed_food", "name": "Processed food", "type": "checkbox", "options": get_options(unique_id, "processed_food"), "category": "Extra Class"},
{"field": "fast_food", "name": "Fast food", "type": "checkbox", "options": get_options(unique_id, "fast_food"), "category": "Extra Class"},
{"field": "soft_drinks", "name": "Soft drinks", "type": "checkbox", "options": get_options(unique_id, "soft_drinks"), "category": "Extra Class"},
{"field": "walking_hours", "name": "Walking (h/d)", "type": "float", "category": "Extra Class"},
{"field": "standing_hours", "name": "Standing (h/d)", "type": "float", "category": "Extra Class"},
{"field": "desk_job", "name": "Desk job", "type": "checkbox", "options": get_options(unique_id, "desk_job"), "category": "Extra Class"},
{"field": "shift_d_n", "name": "Shift (D/N)", "type": "checkbox", "options": get_options(unique_id, "shift_d_n"), "category": "Extra Class"},
]
return render(request, "add_groups.html", {
"unique_id": unique_id,
"variables": json.dumps(variables),
})
def save_preset(request):
if request.method == "POST":
try:
print("Saving preset...")
data = json.loads(request.body)
name = data.get("name")
group_logic = data.get("group_logic")
uri_encoded = data.get("uri_encoded")
save = data.get("save")
update = data.get("update")
print(save,update)
if request.user.is_anonymous:
return JsonResponse({"success": False, "error": "You are not logged in. Please log in to save/update a custom preset."}, status=400)
# Check for empty name
if not name or name.strip() == "":
print("Group title cannot be empty.")
return JsonResponse({"success": False, "error": "Group title cannot be empty."}, status=400)
# Check if the user already has a preset with the same name
if Group.objects.filter(creator=request.user, name=name).exists() and update == False:
print(f"User already has a custom preset with the title '{name}'.")
return JsonResponse({"success": False, "error": "You already have a custom preset with the same name. Please use the update operation."}, status=400)
# Save the preset
if save == True:
Group.objects.create(
creator=request.user,
name=name,
group_logic=group_logic,
group_logic_uriencoded=uri_encoded,
description="Custom preset saved by user."
)
elif update == True:
if Group.objects.filter(creator=request.user, name=name).exists() == False:
return JsonResponse({"success": False, "error": "You do not have a custom preset with the same name. Please use the save operation."}, status=400)
else:
group = Group.objects.get(creator=request.user, name=name)
group.group_logic = group_logic
group.group_logic_uriencoded = uri_encoded
group.save()
print("Preset saved successfully!")
return JsonResponse({"success": True, "message": "Preset saved successfully!"})
except Exception as e:
print(f"Error saving preset: {str(e)}")
return JsonResponse({"success": False, "error": str(e)}, status=500)
return JsonResponse({"success": False, "error": "Invalid request method"}, status=405)
@csrf_exempt
@login_required
def delete_preset(request, preset_id):
if request.method == "DELETE":
try:
preset = get_object_or_404(Group, id=preset_id, creator=request.user)
preset.delete()
return JsonResponse({"success": True, "message": "Preset deleted successfully!"})
except Exception as e:
return JsonResponse({"success": False, "error": str(e)}, status=500)
return JsonResponse({"success": False, "error": "Invalid request method."}, status=405)
@user_passes_test(lambda u: u.is_superuser)
def list_universal_presets(request):
# Get the first object in UniversalPresets (or create if it doesn't exist)
universal_preset, created = UniversalPresets.objects.get_or_create()
# Get all groups created by superusers
groups = Group.objects.filter(creator__is_superuser=True)
# Get selected groups in the current preset
selected_groups = universal_preset.groups.all()
if request.method == "POST":
# Update the universal preset with selected groups
selected_group_ids = request.POST.getlist('selected_groups')
universal_preset.groups.set(Group.objects.filter(id__in=selected_group_ids))
return redirect('list_universal_presets') # Redirect to the same page
return render(request, 'list_universal_presets.html', {
'groups': groups,
'selected_groups': selected_groups,
})
def generate_category_charts(request, unique_id, category, template_name):
# Fetch the dataset or return 404 if not found
dataset = get_object_or_404(Dataset, unique_id=unique_id)
charts = []
# Filter CHART_CONFIG for the specified category
category_charts = {
name: config for name, config in CHART_CONFIG.items()
if config.get("category") == category
}
# Total counts for Cases and Controls
cases_queryset = Case.objects.filter(dataset=dataset)
controls_queryset = Control.objects.filter(dataset=dataset)
total_cases = cases_queryset.count()
total_controls = controls_queryset.count()
for name, config in category_charts.items():
title = config.get("title", name)
labels = config.get("labels", ["Condition 1", "Condition 2"])
filters = config.get("filters", lambda qs: [0, 0]) # Default to [0, 0] if no filters provided
# Apply filters to Cases and Controls using the provided lambda functions
case_counts = filters(cases_queryset)
control_counts = filters(controls_queryset)
# Ensure that filters return exactly two counts
if len(case_counts) != 2 or len(control_counts) != 2:
print(f"Skipping {title} due to unexpected filter counts.")
continue # Skip this chart or handle appropriately
# Extract counts
case1_count, case2_count = case_counts
control1_count, control2_count = control_counts
# Calculate percentages
case1_pct = (case1_count / total_cases * 100) if total_cases > 0 else 0
control1_pct = (control1_count / total_controls * 100) if total_controls > 0 else 0
case2_pct = (case2_count / total_cases * 100) if total_cases > 0 else 0
control2_pct = (control2_count / total_controls * 100) if total_controls > 0 else 0
# Prepare data for Cases and Controls
cases_percentages = [case1_pct, case2_pct]
controls_percentages = [control1_pct, control2_pct]
cases_counts = [case1_count, case2_count]
controls_counts = [control1_count, control2_count]
# Determine the maximum y-value for dynamic y-axis scaling
current_max = max(cases_percentages + controls_percentages)
max_y = current_max + 10 if (current_max + 10) < 100 else 100 # Adjust as needed
_,_,_,p_value = chi2x2_calculation(case1_count, case2_count, control1_count, control2_count)
# Create the bar chart
fig = go.Figure()
# Trace for Cases
fig.add_trace(go.Bar(
x=labels,
y=cases_percentages,
name="Cases",
marker=dict(
color="#538BD5", # Blue for Cases
line=dict(color="black", width=1)
),
hovertemplate=(
"Condition: %{x}
"
"Cases: %{y:.1f}%
"
"Count: %{customdata}"
),
customdata=cases_counts,
text=[f"{pct:.1f}%" for pct in cases_percentages],
textposition='outside',
insidetextanchor='middle',
cliponaxis=False
))
# Trace for Controls
fig.add_trace(go.Bar(
x=labels,
y=controls_percentages,
name="Controls",
marker=dict(
color="#E36C09", # Orange for Controls
line=dict(color="black", width=1)
),
hovertemplate=(
"Condition: %{x}
"
"Controls: %{y:.1f}%
"
"Count: %{customdata}"
),
customdata=controls_counts,
text=[f"{pct:.1f}%" for pct in controls_percentages],
textposition='outside',
insidetextanchor='middle',
cliponaxis=False # Ensure text is clipped within the bar
))
# Update layout
fig.update_layout(
title=dict(
text=f"P-value: {p_value:.4f}" if p_value else "",
x=0.5,
font=dict(size=10, color="#B71C1C"),
),
yaxis=dict(
# title="Percentage (%)",
range=[0, max_y], # Adjusted to fit labels inside bars
tickformat=".1f" # One decimal place
),
barmode="group",
bargap=0.3,
bargroupgap=0,
template="plotly_white",
showlegend=True,
legend=dict(
orientation="h",
yanchor="top",
y=-0.2,
xanchor="center",
x=0.5
),
margin=dict(l=20, r=40, t=20, b=60), # Adjust margins as needed
# height=350, # Increased height for better visibility
modebar=dict(orientation='v')
)
# Plotly configuration
config_plot = {
'responsive': True,
'displaylogo': False,
'displayModeBar': True,
'modeBarButtonsToAdd': [],
'modeBarButtonsToRemove': [
'lasso2d', 'select2d', 'toggleSpikelines',
'hoverCompareCartesian', 'hoverClosestCartesian',
'hoverClosest3d', 'toggleHover', 'zoom2d',
'pan2d', 'zoomIn2d', 'zoomOut2d', 'autoScale2d',
'zoom3d', 'pan3d', 'orbitRotation', 'tableRotation',
'zoomInGeo', 'zoomOutGeo', 'hoverClosestGeo'
],
'toImageButtonOptions': {
'filename': title,
'width': 260, # Match the chart width
'scale': 2
},
}
# Convert chart to HTML
chart_html = fig.to_html(
full_html=False,
config=config_plot,
include_plotlyjs=False, # Assume Plotly JS is included globally in your base template
include_mathjax=False
)
# Append the chart to the charts list
charts.append({
"title": title,
"chart_html": chart_html,
})
context = {
"dataset": dataset,
"charts": charts,
}
return render(request, template_name, context)
def generate_only_case_chart(cases, clinical_variables):
charts = []
total_cases = cases.count()
for var in clinical_variables:
# Extract labels and counts
labels = []
counts = []
for category in var['categories']:
count = cases.filter(category["filter"]).count()
labels.append(category["label"])
counts.append(count)
# Calculate percentages
percentages = [(count / total_cases * 100) if total_cases else 0 for count in counts]
percentages = [round(p, 2) for p in percentages]
# Perform Chi-square test if there are 2 or more categories
if len(var['categories']) >= 2:
obs = counts
# Validate observed counts
if sum(obs) > 0 and all(count >= 0 for count in obs):
try:
# Perform Chi-square goodness-of-fit test
chi_stat, p_value = chisquare(f_obs=obs)
p_value = round(p_value, 3)
except ValueError as ve:
print(f"ValueError for {var['label']}: {ve}")
p_value = None
except Exception as e:
print(f"Error performing Chi-square test for {var['label']}: {e}")
p_value = None
else:
print(f"Invalid observed counts for {var['label']}: {obs}")
p_value = None
else:
p_value = None
# Create Plotly Bar Chart with Black Borders
fig = go.Figure(data=[
go.Bar(
x=labels, # Categories on X-axis
y=percentages, # Percentages on Y-axis
width=0.4, # Narrower bars
customdata=counts, # Pass counts for hover
text=[f"{p}%" for p in percentages], # Percentage text on bars
textfont=dict(
size=14, # Increased text size
color='black' # Optional: Change text color if needed
),
textposition='outside',
marker=dict(
color='#538BD5', # Bar fill color
line=dict(
color='black', # Border color
width=1 # Border width in pixels
)
),
hovertemplate='%{x}: %{y}% (%{customdata} counts)',
hoverlabel=dict(
bgcolor='white', # Set hover background color to white
font=dict(
color='black' # Set hover text color to black for readability
)
)
)
])
# Customize layout for responsiveness
fig.update_layout(
title={
# 'text': var['label'],
'y': 0.9,
'x': 0.5,
'xanchor': 'center',
'yanchor': 'top'
},
xaxis_title="", # Remove X-axis title
yaxis_title="Percentage (%)", # Y-axis represents percentages
template="plotly_white",
margin=dict(l=20, r=20, t=60, b=60), # Adjust margins as needed
autosize=True # Enable autosizing
)
# Define Plotly configuration
config_plot = {
'responsive': True,
'displaylogo': False,
'displayModeBar': True,
'modeBarButtonsToAdd': [],
'modeBarButtonsToRemove': [
'lasso2d', 'select2d', 'toggleSpikelines',
'hoverCompareCartesian', 'hoverClosestCartesian',
'hoverClosest3d', 'toggleHover', 'zoom2d',
'pan2d', 'zoomIn2d', 'zoomOut2d', 'autoScale2d',
'zoom3d', 'pan3d', 'orbitRotation', 'tableRotation',
'zoomInGeo', 'zoomOutGeo', 'hoverClosestGeo'
],
'toImageButtonOptions': {
'filename': var['label'],
'width': 600, # Match the chart width if fixed
'scale': 2
},
}
# Convert Plotly figure to HTML
chart_html = fig.to_html(
full_html=False,
config=config_plot,
include_plotlyjs=False, # Plotly JS is included globally
include_mathjax=False
)
# Append chart details to the charts list
charts.append({
"title": var['label'], # Ensure 'title' key is used in the template
"chart_html": chart_html,
"p_value": p_value if p_value is not None else "N/A"
})
return charts
def demographic_data(request, unique_id):
return generate_category_charts(
request=request,
unique_id=unique_id,
category="Demographic data",
template_name='sections/demographic_data.html'
)
def anthropometric_data(request, unique_id):
return generate_category_charts(
request=request,
unique_id=unique_id,
category="Anthropometric data",
template_name='sections/anthropometric_data.html'
)
def biochemical_data(request, unique_id):
return generate_category_charts(
request=request,
unique_id=unique_id,
category="Biochemical parameters data",
template_name='sections/biochemical_data.html'
)
def obstetric_data(request, unique_id):
return generate_category_charts(
request=request,
unique_id=unique_id,
category="Obstetric data",
template_name='sections/obstetric_data.html'
)
def treatment_data(request, unique_id):
# Get the dataset object using the unique_id
dataset = get_object_or_404(Dataset, unique_id=unique_id)
# Query the Case data related to this dataset
cases = Case.objects.filter(dataset=dataset)
# Prepare clinical data for the charts
clinical_variables = [
{
"label": "Radiotherapy",
"query": "radio_therapy",
"categories": [
{"label": "Yes", "filter": Q(radio_therapy="Yes")},
{"label": "No", "filter": Q(radio_therapy="No")},
],
},
{
"label": "Chemotherapy",
"query": "chemotherapy",
"categories": [
{"label": "Yes", "filter": Q(chemotherapy="Yes")},
{"label": "No", "filter": Q(chemotherapy="No")},
],
},
{
"label": "Surgery",
"query": "surgery",
"categories": [
{"label": "Yes", "filter": Q(surgery="Yes")},
{"label": "No", "filter": Q(surgery="No")},
],
},
{
"label": "Hormone therapy",
"query": "hormone_therapy",
"categories": [
{"label": "Yes", "filter": Q(hormone_therapy="Yes")},
{"label": "No", "filter": Q(hormone_therapy="No")},
]
},
{
"label": "Oral medication",
"query": "oral_medication",
"categories": [
{"label": "Yes", "filter": Q(oral_medication="Yes")},
{"label": "No", "filter": Q(oral_medication="No")},
]
},
]
charts = generate_only_case_chart(cases,clinical_variables)
context = {
"dataset": dataset,
"charts": charts
}
return render(request, 'sections/treatment_data.html', context)
def genetic_snps_data(request, unique_id):
dataset = get_object_or_404(Dataset, unique_id=unique_id)
return render(request, 'sections/genetic_snps_data.html', {'dataset': dataset})
def clinical_data(request, unique_id):
# Get the dataset object using the unique_id
dataset = get_object_or_404(Dataset, unique_id=unique_id)
# Query the Case data related to this dataset
cases = Case.objects.filter(dataset=dataset)
# Prepare clinical data for the charts
clinical_variables = [
{
"label": "Age at diagnosis",
"query": "age_at_diagnosis",
"categories": [
{"label": "<40", "filter": Q(age_at_diagnosis__lt=40)},
{"label": ">=40", "filter": Q(age_at_diagnosis__gte=40)},
],
},
{
"label": "Cancer stage",
"query": "cancer_stage",
"categories": [
{"label": "II", "filter": Q(cancer_stage="2")},
{"label": "III", "filter": Q(cancer_stage="3")},
],
},
{
"label": "Cancer type",
"query": "breast_cancer_type",
"categories": [
{"label": "TNBC", "filter": Q(breast_cancer_type__icontains="TNBC")},
{"label": "Invasive ductal cell carcinoma", "filter": Q(breast_cancer_type__icontains="Invasive ductal cell carcinoma") | Q(breast_cancer_type__icontains="IDCC")},
{"label": "Ductal cell carcinoma", "filter": Q(breast_cancer_type="Ductal Cell Carcinoma") | Q(breast_cancer_type__icontains="DCC")},
],
},
{
"label": "Physical",
"query": "physical",
"categories": [
{"label": "Yes", "filter": Q(physical="Yes")},
{"label": "No", "filter": Q(physical="No")},
],
},
{
"label": "Mammography",
"query": "mammography",
"categories": [
{"label": "Yes", "filter": Q(mammography="Yes")},
{"label": "No", "filter": Q(mammography="No")},
],
},
{
"label": "FNAC",
"query": "fnac",
"categories": [
{"label": "Yes", "filter": Q(fnac="Yes")},
{"label": "No", "filter": Q(fnac="No")},
],
},
{
"label": "Pathology",
"query": "pathology",
"categories": [
{"label": "Yes", "filter": Q(pathology="Yes")},
{"label": "No", "filter": Q(pathology="No")},
],
},
{
"label": "Histopathology",
"query": "histopathology",
"categories": [
{"label": "Yes", "filter": Q(histopathology="Yes")},
{"label": "No", "filter": Q(histopathology="No")},
]
},
]
charts = generate_only_case_chart(cases,clinical_variables)
context = {
"dataset": dataset,
"charts": charts
}
return render(request, 'sections/clinical_data.html', context)