Spaces:
Sleeping
Sleeping
Update src/module/Indicateurs_DQ.py
Browse files- src/module/Indicateurs_DQ.py +688 -169
src/module/Indicateurs_DQ.py
CHANGED
|
@@ -1,14 +1,27 @@
|
|
| 1 |
"""
|
| 2 |
-
MODULE:
|
| 3 |
-
=====================================
|
| 4 |
-
Responsabilité : Audit,
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"""
|
|
|
|
| 7 |
import streamlit as st
|
| 8 |
import pandas as pd
|
|
|
|
| 9 |
import plotly.express as px
|
| 10 |
import plotly.graph_objects as go
|
| 11 |
-
from
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
# =====================================================
|
| 14 |
# ================== OUTILS SÉCURITÉ ==================
|
|
@@ -45,203 +58,709 @@ def safe_pct(num, den):
|
|
| 45 |
|
| 46 |
|
| 47 |
# =====================================================
|
| 48 |
-
# =================
|
| 49 |
# =====================================================
|
| 50 |
|
| 51 |
-
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
-
# ================= CHARGEMENT ETL =================
|
| 55 |
-
etl = ETL_Engine(client, sheet_name)
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
-
else:
|
| 67 |
-
data = st.session_state.data_explorer.dataframes
|
| 68 |
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
df_res = data.get('ressources_jour')
|
| 73 |
-
df_stock = data.get('stock_materiel_jour')
|
| 74 |
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
# ==================================================
|
| 82 |
# ================= KPI GLOBAUX ====================
|
| 83 |
# ==================================================
|
| 84 |
st.markdown("### 📊 Synthèse de Santé des Données")
|
|
|
|
| 85 |
col1, col2, col3, col4 = st.columns(4)
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
anomalies_stock = int((df_stock['dq_is_anomaly'] == 1).sum())
|
| 121 |
-
total_stock = len(df_stock)
|
| 122 |
-
else:
|
| 123 |
-
anomalies_stock = total_stock = 0
|
| 124 |
-
|
| 125 |
-
# ---------------- POURCENTAGES -------------
|
| 126 |
-
pct_anom_pat = safe_pct(anomalies_patients, total_patients)
|
| 127 |
-
pct_anom_sej = safe_pct(anomalies_sejours, total_sejours)
|
| 128 |
-
pct_anom_res = safe_pct(anomalies_ressources, total_ressources)
|
| 129 |
-
pct_anom_stock = safe_pct(anomalies_stock, total_stock)
|
| 130 |
-
|
| 131 |
-
col1.metric("🔴 Anomalies Patients", f"{anomalies_patients:,}", f"{pct_anom_pat}%", delta_color="inverse")
|
| 132 |
-
col2.metric("🔴 Anomalies Séjours", f"{anomalies_sejours:,}", f"{pct_anom_sej}%", delta_color="inverse")
|
| 133 |
-
col3.metric("🔴 Anomalies Ressources", f"{anomalies_ressources:,}", f"{pct_anom_res}%", delta_color="inverse")
|
| 134 |
-
col4.metric("🔴 Anomalies Stock", f"{anomalies_stock:,}", f"{pct_anom_stock}%", delta_color="inverse")
|
| 135 |
-
|
| 136 |
st.divider()
|
| 137 |
-
|
| 138 |
# ==================================================
|
| 139 |
-
# ==========
|
| 140 |
# ==================================================
|
| 141 |
st.subheader("1️⃣ Complétude des Données (Missing Values)")
|
|
|
|
| 142 |
tab1, tab2, tab3, tab4 = st.tabs(["📋 Patients", "🏥 Séjours", "⚕️ Ressources", "📦 Stock"])
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
fig.update_traces(texttemplate='%{text:.1f}%', textposition='outside')
|
| 159 |
-
fig.update_layout(xaxis_tickangle=-45)
|
| 160 |
st.plotly_chart(fig, use_container_width=True)
|
| 161 |
else:
|
| 162 |
-
st.success("✅ Aucune
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
st.plotly_chart(fig, use_container_width=True)
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
if
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
|
|
|
|
|
|
|
|
|
| 196 |
st.plotly_chart(fig, use_container_width=True)
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
st.warning("Aucune donnée ressource disponible")
|
| 201 |
-
|
| 202 |
-
with tab4:
|
| 203 |
-
if df_stock is not None and not df_stock.empty:
|
| 204 |
-
missing_df = (df_stock.isnull().mean() * 100).reset_index()
|
| 205 |
-
missing_df.columns = ['Colonne', 'Pourcentage Manquant']
|
| 206 |
-
missing_df = missing_df[missing_df['Pourcentage Manquant'] > 0]
|
| 207 |
-
if not missing_df.empty:
|
| 208 |
-
st.dataframe(missing_df, use_container_width=True)
|
| 209 |
-
else:
|
| 210 |
-
st.success("✅ Aucune donnée manquante")
|
| 211 |
-
else:
|
| 212 |
-
st.warning("Aucune donnée stock disponible")
|
| 213 |
-
|
| 214 |
# ==================================================
|
| 215 |
-
# ==========
|
| 216 |
# ==================================================
|
| 217 |
-
st.
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
completeness_score = safe_pct(total_rows - total_missing, total_rows)
|
| 227 |
-
|
| 228 |
-
total_anomalies = anomalies_patients + anomalies_sejours + anomalies_ressources + anomalies_stock
|
| 229 |
-
total_all_rows = total_patients + total_sejours + total_ressources + total_stock
|
| 230 |
-
accuracy_score = safe_pct(total_all_rows - total_anomalies, total_all_rows)
|
| 231 |
-
|
| 232 |
-
global_score = round((completeness_score + accuracy_score) / 2, 2)
|
| 233 |
-
|
| 234 |
-
st.metric("Score de complétude", f"{completeness_score}%")
|
| 235 |
-
st.metric("Score d'exactitude", f"{accuracy_score}%")
|
| 236 |
-
|
| 237 |
if global_score >= 95:
|
| 238 |
status = "🟢 EXCELLENT"
|
|
|
|
| 239 |
elif global_score >= 85:
|
| 240 |
status = "🟡 BON"
|
|
|
|
| 241 |
elif global_score >= 70:
|
| 242 |
status = "🟠 MOYEN"
|
|
|
|
| 243 |
else:
|
| 244 |
status = "🔴 CRITIQUE"
|
| 245 |
-
|
| 246 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
st.progress(global_score / 100)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
"""
|
| 2 |
+
MODULE: DATA QUALITY DASHBOARD - VERSION AMÉLIORÉE
|
| 3 |
+
===================================================
|
| 4 |
+
Responsabilité : Audit complet, détection d'anomalies, analyses spécifiques hospitalières.
|
| 5 |
+
Style : Gotham UI + Analyses médicales avancées
|
| 6 |
+
|
| 7 |
+
Améliorations :
|
| 8 |
+
- Chargement direct depuis Excel (pas de filtrage ETL)
|
| 9 |
+
- 6 sections complètes d'analyse DQ
|
| 10 |
+
- Métriques hospitalières spécifiques
|
| 11 |
+
- Visualisations enrichies
|
| 12 |
+
- Analyses temporelles des anomalies
|
| 13 |
"""
|
| 14 |
+
|
| 15 |
import streamlit as st
|
| 16 |
import pandas as pd
|
| 17 |
+
import numpy as np
|
| 18 |
import plotly.express as px
|
| 19 |
import plotly.graph_objects as go
|
| 20 |
+
from plotly.subplots import make_subplots
|
| 21 |
+
from datetime import datetime
|
| 22 |
+
import warnings
|
| 23 |
+
warnings.filterwarnings('ignore')
|
| 24 |
+
|
| 25 |
|
| 26 |
# =====================================================
|
| 27 |
# ================== OUTILS SÉCURITÉ ==================
|
|
|
|
| 58 |
|
| 59 |
|
| 60 |
# =====================================================
|
| 61 |
+
# ================= CHARGEMENT DONNÉES ================
|
| 62 |
# =====================================================
|
| 63 |
|
| 64 |
+
@st.cache_data(ttl=3600)
|
| 65 |
+
def load_excel_data_direct(file_path: str) -> dict:
|
| 66 |
+
"""
|
| 67 |
+
Charge DIRECTEMENT depuis Excel sans passer par ETL.
|
| 68 |
+
Garantit qu'aucune anomalie n'est filtrée.
|
| 69 |
+
"""
|
| 70 |
+
sheets = {}
|
| 71 |
+
try:
|
| 72 |
+
# Chargement de toutes les feuilles nécessaires
|
| 73 |
+
sheets['patients'] = pd.read_excel(file_path, sheet_name='patients')
|
| 74 |
+
sheets['sejours'] = pd.read_excel(file_path, sheet_name='sejours')
|
| 75 |
+
sheets['ressources_jour'] = pd.read_excel(file_path, sheet_name='ressources_jour')
|
| 76 |
+
sheets['stock_materiel_jour'] = pd.read_excel(file_path, sheet_name='stock_materiel_jour')
|
| 77 |
+
sheets['admissions_jour'] = pd.read_excel(file_path, sheet_name='admissions_jour')
|
| 78 |
+
sheets['scenarios_calendrier'] = pd.read_excel(file_path, sheet_name='scenarios_calendrier')
|
| 79 |
+
|
| 80 |
+
# Conversion des dates
|
| 81 |
+
for sheet_name, df in sheets.items():
|
| 82 |
+
if 'date' in df.columns:
|
| 83 |
+
df['date'] = pd.to_datetime(df['date'], errors='coerce')
|
| 84 |
+
if 'date_entree' in df.columns:
|
| 85 |
+
df['date_entree'] = pd.to_datetime(df['date_entree'], errors='coerce')
|
| 86 |
+
if 'date_sortie' in df.columns:
|
| 87 |
+
df['date_sortie'] = pd.to_datetime(df['date_sortie'], errors='coerce')
|
| 88 |
+
if 'date_naissance' in df.columns:
|
| 89 |
+
df['date_naissance'] = pd.to_datetime(df['date_naissance'], errors='coerce')
|
| 90 |
+
|
| 91 |
+
return sheets
|
| 92 |
+
except Exception as e:
|
| 93 |
+
st.error(f"❌ Erreur chargement Excel : {str(e)}")
|
| 94 |
+
return {}
|
| 95 |
|
|
|
|
|
|
|
| 96 |
|
| 97 |
+
# =====================================================
|
| 98 |
+
# ============ ANALYSES DATA QUALITY ==================
|
| 99 |
+
# =====================================================
|
| 100 |
+
|
| 101 |
+
class HospitalDataQualityAnalyzer:
|
| 102 |
+
"""Analyseur complet de qualité des données hospitalières"""
|
| 103 |
+
|
| 104 |
+
def __init__(self, dataframes: dict):
|
| 105 |
+
self.df_pat = dataframes.get('patients')
|
| 106 |
+
self.df_sej = dataframes.get('sejours')
|
| 107 |
+
self.df_res = dataframes.get('ressources_jour')
|
| 108 |
+
self.df_stock = dataframes.get('stock_materiel_jour')
|
| 109 |
+
self.df_adm = dataframes.get('admissions_jour')
|
| 110 |
+
self.df_scenarios = dataframes.get('scenarios_calendrier')
|
| 111 |
+
|
| 112 |
+
self.metrics = {}
|
| 113 |
+
self._compute_all_metrics()
|
| 114 |
+
|
| 115 |
+
def _compute_all_metrics(self):
|
| 116 |
+
"""Calcul de toutes les métriques DQ"""
|
| 117 |
+
|
| 118 |
+
# ============= PATIENTS =============
|
| 119 |
+
if self.df_pat is not None and not self.df_pat.empty:
|
| 120 |
+
self.metrics['patients'] = {
|
| 121 |
+
'total': len(self.df_pat),
|
| 122 |
+
'anomalies': safe_int(self.df_pat['dq_is_anomaly'].sum()),
|
| 123 |
+
'doublons': safe_int(self.df_pat.duplicated(subset=['nom', 'prenom']).sum()),
|
| 124 |
+
'ages_negatifs': safe_int((self.df_pat['age'] < 0).sum()),
|
| 125 |
+
'ages_aberrants': safe_int((self.df_pat['age'] > 120).sum()),
|
| 126 |
+
'missing_birth': safe_int(self.df_pat['date_naissance'].isnull().sum()),
|
| 127 |
+
'missing_ville': safe_int(self.df_pat['ville'].isnull().sum()),
|
| 128 |
+
'missing_total': safe_int(self.df_pat.isnull().sum().sum())
|
| 129 |
+
}
|
| 130 |
+
else:
|
| 131 |
+
self.metrics['patients'] = {k: 0 for k in ['total', 'anomalies', 'doublons', 'ages_negatifs',
|
| 132 |
+
'ages_aberrants', 'missing_birth', 'missing_ville', 'missing_total']}
|
| 133 |
+
|
| 134 |
+
# ============= SÉJOURS =============
|
| 135 |
+
if self.df_sej is not None and not self.df_sej.empty:
|
| 136 |
+
dates_inversees = safe_int((self.df_sej['date_sortie'] < self.df_sej['date_entree']).sum())
|
| 137 |
+
gravite_aberrante = safe_int(((self.df_sej['gravite_1_5'] > 5) | (self.df_sej['gravite_1_5'] < 0)).sum())
|
| 138 |
+
|
| 139 |
+
self.metrics['sejours'] = {
|
| 140 |
+
'total': len(self.df_sej),
|
| 141 |
+
'anomalies': safe_int(self.df_sej['dq_is_anomaly'].sum()),
|
| 142 |
+
'dates_inversees': dates_inversees,
|
| 143 |
+
'gravite_aberrante': gravite_aberrante,
|
| 144 |
+
'equipement_manquant': safe_int(self.df_sej['equipement_principal_code'].isnull().sum()),
|
| 145 |
+
'missing_total': safe_int(self.df_sej.isnull().sum().sum())
|
| 146 |
+
}
|
| 147 |
+
else:
|
| 148 |
+
self.metrics['sejours'] = {k: 0 for k in ['total', 'anomalies', 'dates_inversees',
|
| 149 |
+
'gravite_aberrante', 'equipement_manquant', 'missing_total']}
|
| 150 |
+
|
| 151 |
+
# ============= RESSOURCES =============
|
| 152 |
+
if self.df_res is not None and not self.df_res.empty:
|
| 153 |
+
df_res_temp = self.df_res.copy()
|
| 154 |
+
df_res_temp['lits_occupes_num'] = pd.to_numeric(df_res_temp['lits_occupes'], errors='coerce').fillna(0)
|
| 155 |
+
suroccupation = safe_int((df_res_temp['lits_occupes_num'] > df_res_temp['lits_total']).sum())
|
| 156 |
+
|
| 157 |
+
self.metrics['ressources'] = {
|
| 158 |
+
'total': len(self.df_res),
|
| 159 |
+
'anomalies': safe_int(self.df_res['dq_is_anomaly'].sum()),
|
| 160 |
+
'suroccupation': suroccupation,
|
| 161 |
+
'missing_total': safe_int(self.df_res.isnull().sum().sum())
|
| 162 |
+
}
|
| 163 |
+
else:
|
| 164 |
+
self.metrics['ressources'] = {k: 0 for k in ['total', 'anomalies', 'suroccupation', 'missing_total']}
|
| 165 |
+
|
| 166 |
+
# ============= STOCK =============
|
| 167 |
+
if self.df_stock is not None and not self.df_stock.empty:
|
| 168 |
+
self.metrics['stock'] = {
|
| 169 |
+
'total': len(self.df_stock),
|
| 170 |
+
'anomalies': safe_int(self.df_stock['dq_is_anomaly'].sum()),
|
| 171 |
+
'alertes': safe_int((self.df_stock['alerte_stock'] == 1).sum()),
|
| 172 |
+
'missing_total': safe_int(self.df_stock.isnull().sum().sum())
|
| 173 |
+
}
|
| 174 |
+
else:
|
| 175 |
+
self.metrics['stock'] = {k: 0 for k in ['total', 'anomalies', 'alertes', 'missing_total']}
|
| 176 |
+
|
| 177 |
+
def get_anomalies_by_type(self, df_name: str):
|
| 178 |
+
"""Récupère le détail des anomalies par type"""
|
| 179 |
+
df = getattr(self, f'df_{df_name}', None)
|
| 180 |
+
|
| 181 |
+
if df is None or 'dq_anomaly_type' not in df.columns:
|
| 182 |
+
return pd.DataFrame()
|
| 183 |
+
|
| 184 |
+
anomalies = df[df['dq_is_anomaly'] == 1]
|
| 185 |
+
|
| 186 |
+
if anomalies.empty:
|
| 187 |
+
return pd.DataFrame()
|
| 188 |
|
| 189 |
+
anomaly_counts = anomalies['dq_anomaly_type'].value_counts().reset_index()
|
| 190 |
+
anomaly_counts.columns = ['Type Anomalie', 'Nombre']
|
| 191 |
+
|
| 192 |
+
return anomaly_counts
|
| 193 |
+
|
| 194 |
+
def get_temporal_anomalies(self, df_name: str):
|
| 195 |
+
"""Analyse temporelle des anomalies"""
|
| 196 |
+
df = getattr(self, f'df_{df_name}', None)
|
| 197 |
+
|
| 198 |
+
if df is None or 'date' not in df.columns or 'dq_is_anomaly' not in df.columns:
|
| 199 |
+
return None
|
| 200 |
+
|
| 201 |
+
# Groupement par date
|
| 202 |
+
temp_anomalies = df.groupby(df['date'].dt.to_period('M'))['dq_is_anomaly'].agg(['sum', 'count']).reset_index()
|
| 203 |
+
temp_anomalies['date'] = temp_anomalies['date'].dt.to_timestamp()
|
| 204 |
+
temp_anomalies['pourcentage'] = (temp_anomalies['sum'] / temp_anomalies['count']) * 100
|
| 205 |
+
|
| 206 |
+
return temp_anomalies
|
| 207 |
+
|
| 208 |
+
def get_service_quality_stats(self):
|
| 209 |
+
"""Statistiques de qualité par service"""
|
| 210 |
+
if self.df_sej is None:
|
| 211 |
+
return None
|
| 212 |
+
|
| 213 |
+
service_stats = self.df_sej.groupby('service_code').agg({
|
| 214 |
+
'stay_id': 'count',
|
| 215 |
+
'dq_is_anomaly': 'sum',
|
| 216 |
+
'duree_sejour_jours': 'mean',
|
| 217 |
+
'gravite_1_5': 'mean'
|
| 218 |
+
}).reset_index()
|
| 219 |
+
|
| 220 |
+
service_stats.columns = ['Service', 'Nb Séjours', 'Anomalies', 'Durée Moy', 'Gravité Moy']
|
| 221 |
+
service_stats['Taux Anomalie %'] = (service_stats['Anomalies'] / service_stats['Nb Séjours']) * 100
|
| 222 |
+
|
| 223 |
+
return service_stats.round(2)
|
| 224 |
+
|
| 225 |
+
def compute_global_score(self):
|
| 226 |
+
"""Calcul du score global DQ"""
|
| 227 |
+
|
| 228 |
+
# Complétude
|
| 229 |
+
total_rows = (self.metrics['patients']['total'] +
|
| 230 |
+
self.metrics['sejours']['total'] +
|
| 231 |
+
self.metrics['ressources']['total'])
|
| 232 |
+
|
| 233 |
+
total_missing = (self.metrics['patients']['missing_total'] +
|
| 234 |
+
self.metrics['sejours']['missing_total'] +
|
| 235 |
+
self.metrics['ressources']['missing_total'])
|
| 236 |
+
|
| 237 |
+
completeness_score = safe_pct(total_rows - total_missing, total_rows)
|
| 238 |
+
|
| 239 |
+
# Exactitude
|
| 240 |
+
total_all_rows = (self.metrics['patients']['total'] +
|
| 241 |
+
self.metrics['sejours']['total'] +
|
| 242 |
+
self.metrics['ressources']['total'] +
|
| 243 |
+
self.metrics['stock']['total'])
|
| 244 |
+
|
| 245 |
+
total_anomalies = (self.metrics['patients']['anomalies'] +
|
| 246 |
+
self.metrics['sejours']['anomalies'] +
|
| 247 |
+
self.metrics['ressources']['anomalies'] +
|
| 248 |
+
self.metrics['stock']['anomalies'])
|
| 249 |
+
|
| 250 |
+
accuracy_score = safe_pct(total_all_rows - total_anomalies, total_all_rows)
|
| 251 |
+
|
| 252 |
+
# Score global
|
| 253 |
+
global_score = round((completeness_score + accuracy_score) / 2, 2)
|
| 254 |
+
|
| 255 |
+
return {
|
| 256 |
+
'completeness': completeness_score,
|
| 257 |
+
'accuracy': accuracy_score,
|
| 258 |
+
'global': global_score
|
| 259 |
+
}
|
| 260 |
|
|
|
|
|
|
|
| 261 |
|
| 262 |
+
# =====================================================
|
| 263 |
+
# ============== VISUALISATIONS =======================
|
| 264 |
+
# =====================================================
|
|
|
|
|
|
|
| 265 |
|
| 266 |
+
def plot_anomalies_distribution(analyzer: HospitalDataQualityAnalyzer):
|
| 267 |
+
"""Graphique de distribution des anomalies par table"""
|
| 268 |
+
|
| 269 |
+
data = {
|
| 270 |
+
'Table': ['Patients', 'Séjours', 'Ressources', 'Stock'],
|
| 271 |
+
'Anomalies': [
|
| 272 |
+
analyzer.metrics['patients']['anomalies'],
|
| 273 |
+
analyzer.metrics['sejours']['anomalies'],
|
| 274 |
+
analyzer.metrics['ressources']['anomalies'],
|
| 275 |
+
analyzer.metrics['stock']['anomalies']
|
| 276 |
+
],
|
| 277 |
+
'Total': [
|
| 278 |
+
analyzer.metrics['patients']['total'],
|
| 279 |
+
analyzer.metrics['sejours']['total'],
|
| 280 |
+
analyzer.metrics['ressources']['total'],
|
| 281 |
+
analyzer.metrics['stock']['total']
|
| 282 |
+
]
|
| 283 |
+
}
|
| 284 |
+
|
| 285 |
+
df_plot = pd.DataFrame(data)
|
| 286 |
+
df_plot['Pourcentage'] = (df_plot['Anomalies'] / df_plot['Total']) * 100
|
| 287 |
+
|
| 288 |
+
fig = make_subplots(
|
| 289 |
+
rows=1, cols=2,
|
| 290 |
+
subplot_titles=('Nombre d\'Anomalies', 'Taux d\'Anomalies (%)'),
|
| 291 |
+
specs=[[{"type": "bar"}, {"type": "bar"}]]
|
| 292 |
+
)
|
| 293 |
+
|
| 294 |
+
# Nombre absolu
|
| 295 |
+
fig.add_trace(
|
| 296 |
+
go.Bar(
|
| 297 |
+
x=df_plot['Table'],
|
| 298 |
+
y=df_plot['Anomalies'],
|
| 299 |
+
text=df_plot['Anomalies'],
|
| 300 |
+
textposition='outside',
|
| 301 |
+
marker_color='crimson',
|
| 302 |
+
name='Anomalies'
|
| 303 |
+
),
|
| 304 |
+
row=1, col=1
|
| 305 |
+
)
|
| 306 |
+
|
| 307 |
+
# Pourcentage
|
| 308 |
+
fig.add_trace(
|
| 309 |
+
go.Bar(
|
| 310 |
+
x=df_plot['Table'],
|
| 311 |
+
y=df_plot['Pourcentage'],
|
| 312 |
+
text=[f"{x:.2f}%" for x in df_plot['Pourcentage']],
|
| 313 |
+
textposition='outside',
|
| 314 |
+
marker_color='orange',
|
| 315 |
+
name='Taux %'
|
| 316 |
+
),
|
| 317 |
+
row=1, col=2
|
| 318 |
+
)
|
| 319 |
+
|
| 320 |
+
fig.update_layout(
|
| 321 |
+
height=400,
|
| 322 |
+
showlegend=False,
|
| 323 |
+
title_text="📊 Distribution des Anomalies par Table"
|
| 324 |
+
)
|
| 325 |
+
|
| 326 |
+
return fig
|
| 327 |
+
|
| 328 |
+
|
| 329 |
+
def plot_temporal_anomalies(analyzer: HospitalDataQualityAnalyzer):
|
| 330 |
+
"""Évolution temporelle des anomalies pour séjours"""
|
| 331 |
+
|
| 332 |
+
temp_data = analyzer.get_temporal_anomalies('sej')
|
| 333 |
+
|
| 334 |
+
if temp_data is None or temp_data.empty:
|
| 335 |
+
return None
|
| 336 |
+
|
| 337 |
+
fig = go.Figure()
|
| 338 |
+
|
| 339 |
+
fig.add_trace(go.Scatter(
|
| 340 |
+
x=temp_data['date'],
|
| 341 |
+
y=temp_data['pourcentage'],
|
| 342 |
+
mode='lines+markers',
|
| 343 |
+
name='Taux Anomalies',
|
| 344 |
+
line=dict(color='red', width=2),
|
| 345 |
+
marker=dict(size=8)
|
| 346 |
+
))
|
| 347 |
+
|
| 348 |
+
fig.update_layout(
|
| 349 |
+
title="📈 Évolution Temporelle des Anomalies (Séjours)",
|
| 350 |
+
xaxis_title="Date",
|
| 351 |
+
yaxis_title="Taux d'Anomalies (%)",
|
| 352 |
+
height=400,
|
| 353 |
+
hovermode='x unified'
|
| 354 |
+
)
|
| 355 |
+
|
| 356 |
+
return fig
|
| 357 |
+
|
| 358 |
+
|
| 359 |
+
def plot_service_quality_heatmap(analyzer: HospitalDataQualityAnalyzer):
|
| 360 |
+
"""Heatmap de qualité par service"""
|
| 361 |
+
|
| 362 |
+
service_stats = analyzer.get_service_quality_stats()
|
| 363 |
+
|
| 364 |
+
if service_stats is None or service_stats.empty:
|
| 365 |
+
return None
|
| 366 |
+
|
| 367 |
+
fig = px.bar(
|
| 368 |
+
service_stats.sort_values('Taux Anomalie %', ascending=False).head(10),
|
| 369 |
+
x='Service',
|
| 370 |
+
y='Taux Anomalie %',
|
| 371 |
+
color='Taux Anomalie %',
|
| 372 |
+
color_continuous_scale='Reds',
|
| 373 |
+
title="🏥 Taux d'Anomalies par Service (Top 10)",
|
| 374 |
+
text='Taux Anomalie %'
|
| 375 |
+
)
|
| 376 |
+
|
| 377 |
+
fig.update_traces(texttemplate='%{text:.1f}%', textposition='outside')
|
| 378 |
+
fig.update_layout(height=450)
|
| 379 |
+
|
| 380 |
+
return fig
|
| 381 |
+
|
| 382 |
+
|
| 383 |
+
def plot_completeness_radar(analyzer: HospitalDataQualityAnalyzer):
|
| 384 |
+
"""Radar chart de complétude par dimension"""
|
| 385 |
+
|
| 386 |
+
metrics = analyzer.metrics
|
| 387 |
+
|
| 388 |
+
# Calcul des complétudes
|
| 389 |
+
patient_completeness = 100 - safe_pct(metrics['patients']['missing_total'],
|
| 390 |
+
metrics['patients']['total'] * len(analyzer.df_pat.columns) if analyzer.df_pat is not None else 1)
|
| 391 |
+
sejour_completeness = 100 - safe_pct(metrics['sejours']['missing_total'],
|
| 392 |
+
metrics['sejours']['total'] * len(analyzer.df_sej.columns) if analyzer.df_sej is not None else 1)
|
| 393 |
+
ressource_completeness = 100 - safe_pct(metrics['ressources']['missing_total'],
|
| 394 |
+
metrics['ressources']['total'] * len(analyzer.df_res.columns) if analyzer.df_res is not None else 1)
|
| 395 |
+
stock_completeness = 100 - safe_pct(metrics['stock']['missing_total'],
|
| 396 |
+
metrics['stock']['total'] * len(analyzer.df_stock.columns) if analyzer.df_stock is not None else 1)
|
| 397 |
+
|
| 398 |
+
categories = ['Patients', 'Séjours', 'Ressources', 'Stock']
|
| 399 |
+
values = [patient_completeness, sejour_completeness, ressource_completeness, stock_completeness]
|
| 400 |
+
values.append(values[0]) # Fermeture
|
| 401 |
+
|
| 402 |
+
fig = go.Figure()
|
| 403 |
+
|
| 404 |
+
fig.add_trace(go.Scatterpolar(
|
| 405 |
+
r=values,
|
| 406 |
+
theta=categories + [categories[0]],
|
| 407 |
+
fill='toself',
|
| 408 |
+
name='Complétude',
|
| 409 |
+
line_color='cyan'
|
| 410 |
+
))
|
| 411 |
+
|
| 412 |
+
fig.update_layout(
|
| 413 |
+
polar=dict(
|
| 414 |
+
radialaxis=dict(
|
| 415 |
+
visible=True,
|
| 416 |
+
range=[0, 100]
|
| 417 |
+
)
|
| 418 |
+
),
|
| 419 |
+
showlegend=False,
|
| 420 |
+
title="🎯 Radar de Complétude des Données",
|
| 421 |
+
height=400
|
| 422 |
+
)
|
| 423 |
+
|
| 424 |
+
return fig
|
| 425 |
|
| 426 |
|
| 427 |
+
# =====================================================
|
| 428 |
+
# ================= DASHBOARD PRINCIPAL ===============
|
| 429 |
+
# =====================================================
|
| 430 |
+
|
| 431 |
+
def show_enhanced_dq_dashboard():
|
| 432 |
+
"""
|
| 433 |
+
Dashboard Data Quality amélioré avec toutes les sections.
|
| 434 |
+
"""
|
| 435 |
+
st.markdown("## 🛡️ CENTRE DE CONTRÔLE DATA QUALITY")
|
| 436 |
+
st.caption("Analyse complète de la qualité des données hospitalières")
|
| 437 |
+
|
| 438 |
+
# ================= UPLOAD FICHIER =================
|
| 439 |
+
st.sidebar.header("⚙️ Configuration")
|
| 440 |
+
|
| 441 |
+
uploaded_file = st.sidebar.file_uploader(
|
| 442 |
+
"Charger le fichier Excel",
|
| 443 |
+
type=['xlsx'],
|
| 444 |
+
help="Fichier bdd_mvp_faker.xlsx"
|
| 445 |
+
)
|
| 446 |
+
|
| 447 |
+
if uploaded_file is None:
|
| 448 |
+
st.info("👈 Veuillez charger le fichier Excel dans la barre latérale")
|
| 449 |
+
return
|
| 450 |
+
|
| 451 |
+
# ================= CHARGEMENT =================
|
| 452 |
+
with st.spinner("🔄 Chargement des données..."):
|
| 453 |
+
dataframes = load_excel_data_direct(uploaded_file)
|
| 454 |
+
|
| 455 |
+
if not dataframes:
|
| 456 |
+
st.error("❌ Erreur lors du chargement des données")
|
| 457 |
+
return
|
| 458 |
+
|
| 459 |
+
# ================= ANALYSE =================
|
| 460 |
+
analyzer = HospitalDataQualityAnalyzer(dataframes)
|
| 461 |
+
scores = analyzer.compute_global_score()
|
| 462 |
+
|
| 463 |
+
st.success(f"✅ Données chargées : {sum(m['total'] for m in analyzer.metrics.values()):,} lignes au total")
|
| 464 |
+
|
| 465 |
# ==================================================
|
| 466 |
# ================= KPI GLOBAUX ====================
|
| 467 |
# ==================================================
|
| 468 |
st.markdown("### 📊 Synthèse de Santé des Données")
|
| 469 |
+
|
| 470 |
col1, col2, col3, col4 = st.columns(4)
|
| 471 |
+
|
| 472 |
+
metrics = analyzer.metrics
|
| 473 |
+
|
| 474 |
+
col1.metric(
|
| 475 |
+
"🔴 Anomalies Patients",
|
| 476 |
+
f"{metrics['patients']['anomalies']:,}",
|
| 477 |
+
f"{safe_pct(metrics['patients']['anomalies'], metrics['patients']['total'])}%",
|
| 478 |
+
delta_color="inverse"
|
| 479 |
+
)
|
| 480 |
+
|
| 481 |
+
col2.metric(
|
| 482 |
+
"🔴 Anomalies Séjours",
|
| 483 |
+
f"{metrics['sejours']['anomalies']:,}",
|
| 484 |
+
f"{safe_pct(metrics['sejours']['anomalies'], metrics['sejours']['total'])}%",
|
| 485 |
+
delta_color="inverse"
|
| 486 |
+
)
|
| 487 |
+
|
| 488 |
+
col3.metric(
|
| 489 |
+
"🔴 Anomalies Ressources",
|
| 490 |
+
f"{metrics['ressources']['anomalies']:,}",
|
| 491 |
+
f"{safe_pct(metrics['ressources']['anomalies'], metrics['ressources']['total'])}%",
|
| 492 |
+
delta_color="inverse"
|
| 493 |
+
)
|
| 494 |
+
|
| 495 |
+
col4.metric(
|
| 496 |
+
"🔴 Anomalies Stock",
|
| 497 |
+
f"{metrics['stock']['anomalies']:,}",
|
| 498 |
+
f"{safe_pct(metrics['stock']['anomalies'], metrics['stock']['total'])}%",
|
| 499 |
+
delta_color="inverse"
|
| 500 |
+
)
|
| 501 |
+
|
| 502 |
+
# Graphique distribution anomalies
|
| 503 |
+
st.plotly_chart(plot_anomalies_distribution(analyzer), use_container_width=True)
|
| 504 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 505 |
st.divider()
|
| 506 |
+
|
| 507 |
# ==================================================
|
| 508 |
+
# ========== 1️⃣ COMPLÉTUDE DES DONNÉES ============
|
| 509 |
# ==================================================
|
| 510 |
st.subheader("1️⃣ Complétude des Données (Missing Values)")
|
| 511 |
+
|
| 512 |
tab1, tab2, tab3, tab4 = st.tabs(["📋 Patients", "🏥 Séjours", "⚕️ Ressources", "📦 Stock"])
|
| 513 |
+
|
| 514 |
+
for tab, df_name, df in [(tab1, 'Patients', analyzer.df_pat),
|
| 515 |
+
(tab2, 'Séjours', analyzer.df_sej),
|
| 516 |
+
(tab3, 'Ressources', analyzer.df_res),
|
| 517 |
+
(tab4, 'Stock', analyzer.df_stock)]:
|
| 518 |
+
with tab:
|
| 519 |
+
if df is not None and not df.empty:
|
| 520 |
+
missing_df = (df.isnull().mean() * 100).reset_index()
|
| 521 |
+
missing_df.columns = ['Colonne', 'Pourcentage Manquant']
|
| 522 |
+
missing_df = missing_df[missing_df['Pourcentage Manquant'] > 0]
|
| 523 |
+
|
| 524 |
+
if not missing_df.empty:
|
| 525 |
+
st.caption(f"📊 {len(missing_df)} colonnes avec données manquantes")
|
| 526 |
+
|
| 527 |
+
fig = px.bar(
|
| 528 |
+
missing_df.sort_values('Pourcentage Manquant', ascending=False),
|
| 529 |
+
x='Colonne',
|
| 530 |
+
y='Pourcentage Manquant',
|
| 531 |
+
title=f"Données manquantes - {df_name}",
|
| 532 |
+
color='Pourcentage Manquant',
|
| 533 |
+
color_continuous_scale='Reds',
|
| 534 |
+
text='Pourcentage Manquant'
|
| 535 |
+
)
|
| 536 |
+
fig.update_traces(texttemplate='%{text:.1f}%', textposition='outside')
|
| 537 |
+
fig.update_layout(xaxis_tickangle=-45, height=400)
|
| 538 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 539 |
+
else:
|
| 540 |
+
st.success(f"✅ Aucune donnée manquante dans {df_name}")
|
| 541 |
+
else:
|
| 542 |
+
st.warning(f"⚠️ Aucune donnée {df_name} disponible")
|
| 543 |
+
|
| 544 |
+
# Radar de complétude
|
| 545 |
+
st.plotly_chart(plot_completeness_radar(analyzer), use_container_width=True)
|
| 546 |
+
|
| 547 |
+
st.divider()
|
| 548 |
+
|
| 549 |
+
# ==================================================
|
| 550 |
+
# ========== 2️⃣ COHÉRENCE DES DONNÉES =============
|
| 551 |
+
# ==================================================
|
| 552 |
+
st.subheader("2️⃣ Cohérence et Validité des Données")
|
| 553 |
+
|
| 554 |
+
col1, col2 = st.columns(2)
|
| 555 |
+
|
| 556 |
+
with col1:
|
| 557 |
+
st.markdown("#### 👥 Cohérence Patients")
|
| 558 |
+
st.metric("Âges négatifs", metrics['patients']['ages_negatifs'], delta_color="inverse")
|
| 559 |
+
st.metric("Âges aberrants (>120 ans)", metrics['patients']['ages_aberrants'], delta_color="inverse")
|
| 560 |
+
st.metric("Doublons (nom+prénom)", metrics['patients']['doublons'], delta_color="inverse")
|
| 561 |
+
|
| 562 |
+
with col2:
|
| 563 |
+
st.markdown("#### 🏥 Cohérence Séjours")
|
| 564 |
+
st.metric("Dates inversées (sortie < entrée)", metrics['sejours']['dates_inversees'], delta_color="inverse")
|
| 565 |
+
st.metric("Gravité aberrante (<0 ou >5)", metrics['sejours']['gravite_aberrante'], delta_color="inverse")
|
| 566 |
+
st.metric("Équipement manquant", metrics['sejours']['equipement_manquant'], delta_color="inverse")
|
| 567 |
+
|
| 568 |
+
# Graphique qualité par service
|
| 569 |
+
fig_service = plot_service_quality_heatmap(analyzer)
|
| 570 |
+
if fig_service:
|
| 571 |
+
st.plotly_chart(fig_service, use_container_width=True)
|
| 572 |
+
|
| 573 |
+
st.divider()
|
| 574 |
+
|
| 575 |
+
# ==================================================
|
| 576 |
+
# ========== 3️⃣ ANALYSE DES ANOMALIES =============
|
| 577 |
+
# ==================================================
|
| 578 |
+
st.subheader("3️⃣ Analyse Détaillée des Anomalies")
|
| 579 |
+
|
| 580 |
+
tab1, tab2, tab3, tab4 = st.tabs(["📋 Patients", "🏥 Séjours", "⚕️ Ressources", "📦 Stock"])
|
| 581 |
+
|
| 582 |
+
for tab, df_label in [(tab1, 'pat'), (tab2, 'sej'), (tab3, 'res'), (tab4, 'stock')]:
|
| 583 |
+
with tab:
|
| 584 |
+
anomaly_details = analyzer.get_anomalies_by_type(df_label)
|
| 585 |
|
| 586 |
+
if not anomaly_details.empty:
|
| 587 |
+
st.dataframe(anomaly_details, use_container_width=True)
|
| 588 |
+
|
| 589 |
+
fig = px.pie(
|
| 590 |
+
anomaly_details,
|
| 591 |
+
values='Nombre',
|
| 592 |
+
names='Type Anomalie',
|
| 593 |
+
title=f"Répartition des Types d'Anomalies"
|
| 594 |
+
)
|
|
|
|
|
|
|
| 595 |
st.plotly_chart(fig, use_container_width=True)
|
| 596 |
else:
|
| 597 |
+
st.success(f"✅ Aucune anomalie détectée")
|
| 598 |
+
|
| 599 |
+
# Évolution temporelle
|
| 600 |
+
fig_temporal = plot_temporal_anomalies(analyzer)
|
| 601 |
+
if fig_temporal:
|
| 602 |
+
st.plotly_chart(fig_temporal, use_container_width=True)
|
| 603 |
+
|
| 604 |
+
st.divider()
|
| 605 |
+
|
| 606 |
+
# ==================================================
|
| 607 |
+
# ========== 4️⃣ SPÉCIFICITÉS HOSPITALIÈRES ========
|
| 608 |
+
# ==================================================
|
| 609 |
+
st.subheader("4️⃣ Analyses Spécifiques Hospitalières")
|
| 610 |
+
|
| 611 |
+
col1, col2 = st.columns(2)
|
| 612 |
+
|
| 613 |
+
with col1:
|
| 614 |
+
st.markdown("#### 🛏️ Ressources")
|
| 615 |
+
if analyzer.df_res is not None:
|
| 616 |
+
st.metric("Cas de suroccupation", metrics['ressources']['suroccupation'], delta_color="inverse")
|
| 617 |
+
|
| 618 |
+
# Taux occupation moyen par service
|
| 619 |
+
if 'service_code' in analyzer.df_res.columns and 'taux_occupation' in analyzer.df_res.columns:
|
| 620 |
+
taux_moy = analyzer.df_res.groupby('service_code')['taux_occupation'].mean().reset_index()
|
| 621 |
+
taux_moy.columns = ['Service', 'Taux Occupation Moyen']
|
| 622 |
+
taux_moy = taux_moy.sort_values('Taux Occupation Moyen', ascending=False)
|
| 623 |
+
|
| 624 |
+
fig = px.bar(
|
| 625 |
+
taux_moy.head(10),
|
| 626 |
+
x='Service',
|
| 627 |
+
y='Taux Occupation Moyen',
|
| 628 |
+
title="Top 10 Services - Taux Occupation",
|
| 629 |
+
color='Taux Occupation Moyen',
|
| 630 |
+
color_continuous_scale='RdYlGn_r'
|
| 631 |
+
)
|
| 632 |
st.plotly_chart(fig, use_container_width=True)
|
| 633 |
+
|
| 634 |
+
with col2:
|
| 635 |
+
st.markdown("#### 📦 Stock")
|
| 636 |
+
st.metric("Alertes stock actives", metrics['stock']['alertes'], delta_color="inverse")
|
| 637 |
+
|
| 638 |
+
# Distribution des alertes par matériel
|
| 639 |
+
if analyzer.df_stock is not None and 'alerte_stock' in analyzer.df_stock.columns:
|
| 640 |
+
alertes = analyzer.df_stock[analyzer.df_stock['alerte_stock'] == 1]
|
| 641 |
+
if not alertes.empty and 'materiel_code' in alertes.columns:
|
| 642 |
+
alert_counts = alertes['materiel_code'].value_counts().reset_index()
|
| 643 |
+
alert_counts.columns = ['Matériel', 'Nombre Alertes']
|
| 644 |
+
|
| 645 |
+
fig = px.bar(
|
| 646 |
+
alert_counts.head(10),
|
| 647 |
+
x='Matériel',
|
| 648 |
+
y='Nombre Alertes',
|
| 649 |
+
title="Top 10 Matériels en Alerte",
|
| 650 |
+
color='Nombre Alertes',
|
| 651 |
+
color_continuous_scale='Oranges'
|
| 652 |
+
)
|
| 653 |
st.plotly_chart(fig, use_container_width=True)
|
| 654 |
+
|
| 655 |
+
st.divider()
|
| 656 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 657 |
# ==================================================
|
| 658 |
+
# ========== 5️⃣ RÉSUMÉ EXÉCUTIF ===================
|
| 659 |
# ==================================================
|
| 660 |
+
st.subheader("5️⃣ Résumé Exécutif Data Quality")
|
| 661 |
+
|
| 662 |
+
col1, col2, col3 = st.columns(3)
|
| 663 |
+
|
| 664 |
+
col1.metric("Score de Complétude", f"{scores['completeness']:.2f}%")
|
| 665 |
+
col2.metric("Score d'Exactitude", f"{scores['accuracy']:.2f}%")
|
| 666 |
+
|
| 667 |
+
global_score = scores['global']
|
| 668 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 669 |
if global_score >= 95:
|
| 670 |
status = "🟢 EXCELLENT"
|
| 671 |
+
color = "green"
|
| 672 |
elif global_score >= 85:
|
| 673 |
status = "🟡 BON"
|
| 674 |
+
color = "blue"
|
| 675 |
elif global_score >= 70:
|
| 676 |
status = "🟠 MOYEN"
|
| 677 |
+
color = "orange"
|
| 678 |
else:
|
| 679 |
status = "🔴 CRITIQUE"
|
| 680 |
+
color = "red"
|
| 681 |
+
|
| 682 |
+
col3.markdown(f"**Score Global**")
|
| 683 |
+
col3.markdown(f"<h2 style='color: {color};'>{global_score:.2f}%</h2>", unsafe_allow_html=True)
|
| 684 |
+
|
| 685 |
+
st.markdown(f"### {status}")
|
| 686 |
st.progress(global_score / 100)
|
| 687 |
+
|
| 688 |
+
# Recommandations
|
| 689 |
+
st.markdown("#### 💡 Recommandations")
|
| 690 |
+
|
| 691 |
+
recommendations = []
|
| 692 |
+
|
| 693 |
+
if metrics['patients']['anomalies'] > 0:
|
| 694 |
+
recommendations.append(f"⚠️ **{metrics['patients']['anomalies']} anomalies patients** détectées - Vérifier les données de naissance et villes manquantes")
|
| 695 |
+
|
| 696 |
+
if metrics['sejours']['dates_inversees'] > 0:
|
| 697 |
+
recommendations.append(f"🔴 **{metrics['sejours']['dates_inversees']} séjours avec dates inversées** - Corriger les dates d'entrée/sortie")
|
| 698 |
+
|
| 699 |
+
if metrics['ressources']['suroccupation'] > 0:
|
| 700 |
+
recommendations.append(f"🚨 **{metrics['ressources']['suroccupation']} cas de suroccupation** - Revoir la capacité des services")
|
| 701 |
+
|
| 702 |
+
if metrics['stock']['alertes'] > 0:
|
| 703 |
+
recommendations.append(f"📦 **{metrics['stock']['alertes']} alertes stock** - Réapprovisionner les matériels critiques")
|
| 704 |
+
|
| 705 |
+
if global_score < 85:
|
| 706 |
+
recommendations.append("📊 **Score global < 85%** - Lancer un plan d'action Data Quality urgent")
|
| 707 |
+
|
| 708 |
+
if recommendations:
|
| 709 |
+
for rec in recommendations:
|
| 710 |
+
st.markdown(rec)
|
| 711 |
+
else:
|
| 712 |
+
st.success("✅ Aucune action critique nécessaire - Qualité des données satisfaisante")
|
| 713 |
+
|
| 714 |
+
st.divider()
|
| 715 |
+
|
| 716 |
+
# ==================================================
|
| 717 |
+
# ========== 6️⃣ EXPORT DES RÉSULTATS ==============
|
| 718 |
+
# ==================================================
|
| 719 |
+
st.subheader("6️⃣ Export et Documentation")
|
| 720 |
+
|
| 721 |
+
# Création du rapport
|
| 722 |
+
report_data = {
|
| 723 |
+
'Métrique': [],
|
| 724 |
+
'Valeur': []
|
| 725 |
+
}
|
| 726 |
+
|
| 727 |
+
for category, cat_metrics in analyzer.metrics.items():
|
| 728 |
+
for metric_name, value in cat_metrics.items():
|
| 729 |
+
report_data['Métrique'].append(f"{category}_{metric_name}")
|
| 730 |
+
report_data['Valeur'].append(value)
|
| 731 |
+
|
| 732 |
+
# Ajout scores
|
| 733 |
+
report_data['Métrique'].extend(['score_completeness', 'score_accuracy', 'score_global'])
|
| 734 |
+
report_data['Valeur'].extend([scores['completeness'], scores['accuracy'], scores['global']])
|
| 735 |
+
|
| 736 |
+
report_df = pd.DataFrame(report_data)
|
| 737 |
+
|
| 738 |
+
col1, col2 = st.columns(2)
|
| 739 |
+
|
| 740 |
+
with col1:
|
| 741 |
+
csv = report_df.to_csv(index=False).encode('utf-8')
|
| 742 |
+
st.download_button(
|
| 743 |
+
label="📥 Télécharger Rapport DQ (CSV)",
|
| 744 |
+
data=csv,
|
| 745 |
+
file_name=f'data_quality_report_{datetime.now().strftime("%Y%m%d_%H%M%S")}.csv',
|
| 746 |
+
mime='text/csv'
|
| 747 |
+
)
|
| 748 |
+
|
| 749 |
+
with col2:
|
| 750 |
+
# Export des anomalies détectées
|
| 751 |
+
if metrics['patients']['anomalies'] > 0:
|
| 752 |
+
anomalies_df = analyzer.df_pat[analyzer.df_pat['dq_is_anomaly'] == 1][
|
| 753 |
+
['patient_id', 'nom', 'prenom', 'dq_anomaly_type', 'dq_anomaly_detail']
|
| 754 |
+
]
|
| 755 |
+
anomalies_csv = anomalies_df.to_csv(index=False).encode('utf-8')
|
| 756 |
+
st.download_button(
|
| 757 |
+
label="📥 Télécharger Anomalies Patients (CSV)",
|
| 758 |
+
data=anomalies_csv,
|
| 759 |
+
file_name=f'anomalies_patients_{datetime.now().strftime("%Y%m%d_%H%M%S")}.csv',
|
| 760 |
+
mime='text/csv'
|
| 761 |
+
)
|
| 762 |
+
|
| 763 |
+
|
| 764 |
+
# Point d'entrée
|
| 765 |
+
if __name__ == "__main__":
|
| 766 |
+
show_enhanced_dq_dashboard()
|