feat: implement data loading from SQLite (Task 3.2)
- Add load_data() method to AppState that connects to SQLite database - Populate available_drugs, available_directorates, available_indications from DB - Detect latest date in dataset and set filter defaults accordingly - Load KPI values: total_records, unique_patients, total_drugs, total_cost - Add on_load handler to trigger data loading on page initialization - Handle database errors gracefully with meaningful error messages
This commit is contained in:
Andrew Charlwood
@@ -115,11 +115,11 @@ cd pathways_app && timeout 60 python -m reflex run 2>&1 | head -30
|
||||
- `current_chart: str = "icicle"`
|
||||
|
||||
### 3.2 Data Loading
|
||||
- [ ] Create `load_data()` method that reads from SQLite
|
||||
- [ ] Populate available options for dropdowns (drugs, indications, directorates)
|
||||
- [ ] Detect latest date in dataset for "to" date defaults
|
||||
- [ ] Calculate total records and last updated timestamp
|
||||
- [ ] Call on app initialization
|
||||
- [x] Create `load_data()` method that reads from SQLite
|
||||
- [x] Populate available options for dropdowns (drugs, indications, directorates)
|
||||
- [x] Detect latest date in dataset for "to" date defaults
|
||||
- [x] Calculate total records and last updated timestamp
|
||||
- [x] Call on app initialization
|
||||
|
||||
### 3.3 Filter Logic
|
||||
- [ ] Create `apply_filters()` computed method that filters the data based on current state
|
||||
|
||||
+114
-2
@@ -6,6 +6,7 @@ Design reference: DESIGN_SYSTEM.md
|
||||
"""
|
||||
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import reflex as rx
|
||||
@@ -349,6 +350,117 @@ class AppState(rx.State):
|
||||
except (ValueError, TypeError):
|
||||
return "Unknown"
|
||||
|
||||
# =========================================================================
|
||||
# Data Loading Methods
|
||||
# =========================================================================
|
||||
|
||||
def load_data(self):
|
||||
"""
|
||||
Load data from SQLite database on app initialization.
|
||||
|
||||
This method:
|
||||
1. Connects to the SQLite database (data/pathways.db)
|
||||
2. Loads available drugs, indications, directorates from actual data
|
||||
3. Detects the latest date in the dataset for "to" date defaults
|
||||
4. Updates total_records, last_updated, and data_loaded state
|
||||
"""
|
||||
import sqlite3
|
||||
|
||||
db_path = Path("data/pathways.db")
|
||||
|
||||
if not db_path.exists():
|
||||
self.error_message = "Database not found. Please run data migration first."
|
||||
return
|
||||
|
||||
try:
|
||||
conn = sqlite3.connect(str(db_path))
|
||||
cursor = conn.cursor()
|
||||
|
||||
# Get total records
|
||||
cursor.execute("SELECT COUNT(*) FROM fact_interventions")
|
||||
self.total_records = cursor.fetchone()[0]
|
||||
|
||||
if self.total_records == 0:
|
||||
self.error_message = "No data in database. Please run data migration."
|
||||
conn.close()
|
||||
return
|
||||
|
||||
# Get available drugs (distinct, sorted)
|
||||
cursor.execute("""
|
||||
SELECT DISTINCT drug_name_std
|
||||
FROM fact_interventions
|
||||
WHERE drug_name_std IS NOT NULL AND drug_name_std != ''
|
||||
ORDER BY drug_name_std
|
||||
""")
|
||||
self.available_drugs = [row[0] for row in cursor.fetchall()]
|
||||
|
||||
# Get available directories (distinct, sorted)
|
||||
cursor.execute("""
|
||||
SELECT DISTINCT directory
|
||||
FROM fact_interventions
|
||||
WHERE directory IS NOT NULL AND directory != ''
|
||||
ORDER BY directory
|
||||
""")
|
||||
self.available_directorates = [row[0] for row in cursor.fetchall()]
|
||||
|
||||
# Get available indications from ref_drug_indication_clusters
|
||||
cursor.execute("""
|
||||
SELECT DISTINCT indication
|
||||
FROM ref_drug_indication_clusters
|
||||
WHERE indication IS NOT NULL AND indication != ''
|
||||
ORDER BY indication
|
||||
""")
|
||||
self.available_indications = [row[0] for row in cursor.fetchall()]
|
||||
|
||||
# If no indications in reference table, use placeholder
|
||||
if not self.available_indications:
|
||||
self.available_indications = ["(No indications available)"]
|
||||
|
||||
# Get date range from data
|
||||
cursor.execute("""
|
||||
SELECT MIN(intervention_date), MAX(intervention_date)
|
||||
FROM fact_interventions
|
||||
""")
|
||||
date_range = cursor.fetchone()
|
||||
min_date, max_date = date_range
|
||||
|
||||
# Update latest_date_in_data and set "to" date defaults
|
||||
if max_date:
|
||||
self.latest_date_in_data = max_date
|
||||
self.last_seen_to_date = max_date
|
||||
self.initiated_to_date = max_date
|
||||
|
||||
# Set "from" date for last_seen filter (6 months before max_date)
|
||||
max_dt = datetime.strptime(max_date, "%Y-%m-%d")
|
||||
six_months_ago = max_dt - timedelta(days=180)
|
||||
self.last_seen_from_date = six_months_ago.strftime("%Y-%m-%d")
|
||||
|
||||
# Get unique patient count for KPIs
|
||||
cursor.execute("SELECT COUNT(DISTINCT upid) FROM fact_interventions")
|
||||
self.unique_patients = cursor.fetchone()[0]
|
||||
|
||||
# Get unique drug count
|
||||
self.total_drugs = len(self.available_drugs)
|
||||
|
||||
# Get total cost
|
||||
cursor.execute("SELECT SUM(price_actual) FROM fact_interventions")
|
||||
total_cost_result = cursor.fetchone()[0]
|
||||
self.total_cost = float(total_cost_result) if total_cost_result else 0.0
|
||||
|
||||
conn.close()
|
||||
|
||||
# Set data_loaded and last_updated
|
||||
self.data_loaded = True
|
||||
self.last_updated = datetime.now().isoformat()
|
||||
self.error_message = ""
|
||||
|
||||
except sqlite3.Error as e:
|
||||
self.error_message = f"Database error: {str(e)}"
|
||||
self.data_loaded = False
|
||||
except Exception as e:
|
||||
self.error_message = f"Failed to load data: {str(e)}"
|
||||
self.data_loaded = False
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Layout Components
|
||||
@@ -1332,5 +1444,5 @@ app = rx.App(
|
||||
],
|
||||
)
|
||||
|
||||
# Register page
|
||||
app.add_page(index, route="/", title="HCD Analysis | Patient Pathways")
|
||||
# Register page with on_load handler to load data on app initialization
|
||||
app.add_page(index, route="/", title="HCD Analysis | Patient Pathways", on_load=AppState.load_data)
|
||||
|
||||
@@ -440,3 +440,54 @@ Use `rx.cond(condition, true_value, false_value)` not Python `if`.
|
||||
- `pathways_app/pathways_app.py` — existing load patterns (search for "def load_")
|
||||
### Blocked items:
|
||||
- None
|
||||
|
||||
## Iteration 8 - 2026-02-04
|
||||
### Task: 3.2 Data Loading
|
||||
### Why this task:
|
||||
- Previous iteration (7) explicitly recommended continuing with Task 3.2
|
||||
- Natural progression through Phase 3: State Management
|
||||
- Data loading is foundational for filter logic (Task 3.3) and KPI calculations (Task 3.4)
|
||||
- No dependencies blocking this task
|
||||
### Status: COMPLETE
|
||||
### What was done:
|
||||
- Added `Path` import from pathlib to app_v2.py
|
||||
- Created comprehensive `load_data()` method in AppState that:
|
||||
- Connects to SQLite database (data/pathways.db)
|
||||
- Loads available_drugs from DISTINCT drug_name_std in fact_interventions (552 unique drugs)
|
||||
- Loads available_directorates from DISTINCT directory in fact_interventions (29 unique)
|
||||
- Loads available_indications from ref_drug_indication_clusters table (32 unique)
|
||||
- Detects date range (2019-04-01 to 2025-02-28) and sets last_seen_to_date to max date
|
||||
- Sets last_seen_from_date to 6 months before max date
|
||||
- Populates KPI values: total_records (440,069), unique_patients, total_drugs, total_cost
|
||||
- Sets data_loaded=True and last_updated timestamp on success
|
||||
- Handles errors gracefully with meaningful error messages
|
||||
- Added on_load handler to app.add_page() to trigger load_data on page load
|
||||
### Validation results:
|
||||
- Tier 1 (Code):
|
||||
- `python -m py_compile pathways_app/app_v2.py` PASSED
|
||||
- `python -c "from pathways_app.app_v2 import app, AppState"` PASSED
|
||||
- AppState.load_data method exists and is callable
|
||||
- Database queries tested independently — all return expected data
|
||||
- Tier 2 (Visual): Deferred - requires running reflex with modified rxconfig
|
||||
- Tier 3 (Functional): Database queries verified — 552 drugs, 29 directories, 32 indications, 440K records
|
||||
### Files changed:
|
||||
- Modified: pathways_app/app_v2.py (+80 lines - load_data method, on_load handler, Path import)
|
||||
- Modified: IMPLEMENTATION_PLAN.md (marked 3.2 subtasks complete)
|
||||
### Committed: [pending]
|
||||
### Patterns discovered:
|
||||
- Reflex on_load: Use `app.add_page(..., on_load=AppState.method_name)` to trigger method on page load
|
||||
- SQLite in Reflex state: Import sqlite3 inside method to avoid issues with state serialization
|
||||
- Date handling: Parse SQLite dates with datetime.strptime(date_str, "%Y-%m-%d")
|
||||
- Reference tables: ref_drug_indication_clusters has 32 unique indications for dropdown
|
||||
- Path handling: Use `Path("data/pathways.db")` for cross-platform compatibility
|
||||
### Next iteration should:
|
||||
- Continue with Task 3.3: Filter Logic
|
||||
- Create `apply_filters()` computed method that filters data based on current filter state
|
||||
- Handle initiated date filter (when enabled)
|
||||
- Handle last seen date filter (when enabled)
|
||||
- Handle drug/indication/directorate multi-select filters
|
||||
- Return filtered data for chart generation
|
||||
- Consider implementing as @rx.var computed property that returns filtered record count
|
||||
- May need to store raw_data list in state or re-query SQLite based on filters
|
||||
### Blocked items:
|
||||
- None
|
||||
|
||||
Reference in New Issue
Block a user