Spaces:
Sleeping
Sleeping
Update src/module/Indicateurs_DQ.py
Browse files- src/module/Indicateurs_DQ.py +93 -270
src/module/Indicateurs_DQ.py
CHANGED
|
@@ -1,24 +1,8 @@
|
|
| 1 |
"""
|
| 2 |
-
MODULE: DATA QUALITY DASHBOARD - VERSION
|
| 3 |
-
=================================================
|
| 4 |
-
Responsabilité : Audit complet, détection d'anomalies
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
Fonctionnalités :
|
| 8 |
-
- ✅ Accès Google Sheets (via _client)
|
| 9 |
-
- ✅ Upload fichier Excel local
|
| 10 |
-
- ✅ 6 sections complètes d'analyse DQ
|
| 11 |
-
- ✅ Métriques hospitalières spécifiques
|
| 12 |
-
- ✅ Visualisations enrichies
|
| 13 |
-
- ✅ Analyses temporelles des anomalies
|
| 14 |
-
- ✅ Recommandations automatiques
|
| 15 |
-
- ✅ Export rapports CSV
|
| 16 |
-
|
| 17 |
-
Améliorations vs version originale :
|
| 18 |
-
- Chargement direct (pas de filtrage ETL) pour voir toutes les anomalies
|
| 19 |
-
- 6 sections au lieu de 2
|
| 20 |
-
- Analyses spécifiques au contexte hospitalier
|
| 21 |
-
- Visualisations interactives avancées
|
| 22 |
"""
|
| 23 |
|
| 24 |
import streamlit as st
|
|
@@ -41,7 +25,7 @@ def safe_int(value):
|
|
| 41 |
try:
|
| 42 |
if pd.isna(value):
|
| 43 |
return 0
|
| 44 |
-
return int(value)
|
| 45 |
except (TypeError, ValueError, OverflowError):
|
| 46 |
return 0
|
| 47 |
|
|
@@ -70,24 +54,12 @@ def safe_pct(num, den):
|
|
| 70 |
# ================= CHARGEMENT DONNÉES ================
|
| 71 |
# =====================================================
|
| 72 |
|
| 73 |
-
@st.cache_data(ttl=
|
| 74 |
def load_from_google_sheets(_client, sheet_name: str) -> dict:
|
| 75 |
-
|
| 76 |
-
"""
|
| 77 |
-
Charge les données depuis Google Sheets SANS passer par ETL.
|
| 78 |
-
Garantit qu'aucune anomalie n'est filtrée.
|
| 79 |
-
|
| 80 |
-
Args:
|
| 81 |
-
_client: _client Google Sheets
|
| 82 |
-
sheet_name: Nom de la feuille Google Sheets
|
| 83 |
-
|
| 84 |
-
Returns:
|
| 85 |
-
Dictionnaire de DataFrames
|
| 86 |
-
"""
|
| 87 |
sheets = {}
|
| 88 |
|
| 89 |
try:
|
| 90 |
-
# Liste des feuilles à charger
|
| 91 |
sheet_names = [
|
| 92 |
'patients', 'sejours', 'ressources_jour',
|
| 93 |
'stock_materiel_jour', 'admissions_jour', 'scenarios_calendrier'
|
|
@@ -95,50 +67,34 @@ def load_from_google_sheets(_client, sheet_name: str) -> dict:
|
|
| 95 |
|
| 96 |
for name in sheet_names:
|
| 97 |
try:
|
| 98 |
-
# Récupération directe depuis Google Sheets
|
| 99 |
worksheet = _client.open(sheet_name).worksheet(name)
|
| 100 |
data = worksheet.get_all_records()
|
| 101 |
df = pd.DataFrame(data)
|
| 102 |
|
| 103 |
# Conversion des dates
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
if 'date_sortie' in df.columns:
|
| 109 |
-
df['date_sortie'] = pd.to_datetime(df['date_sortie'], errors='coerce')
|
| 110 |
-
if 'date_naissance' in df.columns:
|
| 111 |
-
df['date_naissance'] = pd.to_datetime(df['date_naissance'], errors='coerce')
|
| 112 |
|
| 113 |
sheets[name] = df
|
| 114 |
|
| 115 |
except Exception as e:
|
| 116 |
-
|
| 117 |
continue
|
| 118 |
|
| 119 |
return sheets
|
| 120 |
|
| 121 |
except Exception as e:
|
| 122 |
-
st.error(f"
|
| 123 |
return {}
|
| 124 |
|
| 125 |
|
| 126 |
@st.cache_data(ttl=3600)
|
| 127 |
def load_from_excel_file(file) -> dict:
|
| 128 |
-
"""
|
| 129 |
-
Charge les données depuis un fichier Excel uploadé.
|
| 130 |
-
Garantit qu'aucune anomalie n'est filtrée.
|
| 131 |
-
|
| 132 |
-
Args:
|
| 133 |
-
file: Fichier uploadé via st.file_uploader
|
| 134 |
-
|
| 135 |
-
Returns:
|
| 136 |
-
Dictionnaire de DataFrames
|
| 137 |
-
"""
|
| 138 |
sheets = {}
|
| 139 |
-
|
| 140 |
try:
|
| 141 |
-
# Chargement de toutes les feuilles nécessaires
|
| 142 |
sheets['patients'] = pd.read_excel(file, sheet_name='patients')
|
| 143 |
sheets['sejours'] = pd.read_excel(file, sheet_name='sejours')
|
| 144 |
sheets['ressources_jour'] = pd.read_excel(file, sheet_name='ressources_jour')
|
|
@@ -146,21 +102,13 @@ def load_from_excel_file(file) -> dict:
|
|
| 146 |
sheets['admissions_jour'] = pd.read_excel(file, sheet_name='admissions_jour')
|
| 147 |
sheets['scenarios_calendrier'] = pd.read_excel(file, sheet_name='scenarios_calendrier')
|
| 148 |
|
| 149 |
-
# Conversion des dates
|
| 150 |
for sheet_name, df in sheets.items():
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
df['date_entree'] = pd.to_datetime(df['date_entree'], errors='coerce')
|
| 155 |
-
if 'date_sortie' in df.columns:
|
| 156 |
-
df['date_sortie'] = pd.to_datetime(df['date_sortie'], errors='coerce')
|
| 157 |
-
if 'date_naissance' in df.columns:
|
| 158 |
-
df['date_naissance'] = pd.to_datetime(df['date_naissance'], errors='coerce')
|
| 159 |
-
|
| 160 |
return sheets
|
| 161 |
-
|
| 162 |
except Exception as e:
|
| 163 |
-
st.error(f"
|
| 164 |
return {}
|
| 165 |
|
| 166 |
|
|
@@ -182,20 +130,33 @@ class HospitalDataQualityAnalyzer:
|
|
| 182 |
self.metrics = {}
|
| 183 |
self._compute_all_metrics()
|
| 184 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 185 |
def _compute_all_metrics(self):
|
| 186 |
"""Calcul de toutes les métriques DQ"""
|
| 187 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
# ============= PATIENTS =============
|
| 189 |
if self.df_pat is not None and not self.df_pat.empty:
|
| 190 |
self.metrics['patients'] = {
|
| 191 |
'total': len(self.df_pat),
|
| 192 |
-
'anomalies':
|
| 193 |
-
'doublons':
|
| 194 |
-
'ages_negatifs':
|
| 195 |
-
'ages_aberrants':
|
| 196 |
-
'missing_birth':
|
| 197 |
-
'missing_ville':
|
| 198 |
-
'missing_total':
|
| 199 |
}
|
| 200 |
else:
|
| 201 |
self.metrics['patients'] = {k: 0 for k in ['total', 'anomalies', 'doublons', 'ages_negatifs',
|
|
@@ -203,16 +164,17 @@ class HospitalDataQualityAnalyzer:
|
|
| 203 |
|
| 204 |
# ============= SÉJOURS =============
|
| 205 |
if self.df_sej is not None and not self.df_sej.empty:
|
| 206 |
-
dates_inversees =
|
| 207 |
-
|
|
|
|
| 208 |
|
| 209 |
self.metrics['sejours'] = {
|
| 210 |
'total': len(self.df_sej),
|
| 211 |
-
'anomalies':
|
| 212 |
'dates_inversees': dates_inversees,
|
| 213 |
'gravite_aberrante': gravite_aberrante,
|
| 214 |
-
'equipement_manquant':
|
| 215 |
-
'missing_total':
|
| 216 |
}
|
| 217 |
else:
|
| 218 |
self.metrics['sejours'] = {k: 0 for k in ['total', 'anomalies', 'dates_inversees',
|
|
@@ -222,13 +184,14 @@ class HospitalDataQualityAnalyzer:
|
|
| 222 |
if self.df_res is not None and not self.df_res.empty:
|
| 223 |
df_res_temp = self.df_res.copy()
|
| 224 |
df_res_temp['lits_occupes_num'] = pd.to_numeric(df_res_temp['lits_occupes'], errors='coerce').fillna(0)
|
| 225 |
-
|
|
|
|
| 226 |
|
| 227 |
self.metrics['ressources'] = {
|
| 228 |
'total': len(self.df_res),
|
| 229 |
-
'anomalies':
|
| 230 |
'suroccupation': suroccupation,
|
| 231 |
-
'missing_total':
|
| 232 |
}
|
| 233 |
else:
|
| 234 |
self.metrics['ressources'] = {k: 0 for k in ['total', 'anomalies', 'suroccupation', 'missing_total']}
|
|
@@ -237,9 +200,9 @@ class HospitalDataQualityAnalyzer:
|
|
| 237 |
if self.df_stock is not None and not self.df_stock.empty:
|
| 238 |
self.metrics['stock'] = {
|
| 239 |
'total': len(self.df_stock),
|
| 240 |
-
'anomalies':
|
| 241 |
-
'alertes':
|
| 242 |
-
'missing_total':
|
| 243 |
}
|
| 244 |
else:
|
| 245 |
self.metrics['stock'] = {k: 0 for k in ['total', 'anomalies', 'alertes', 'missing_total']}
|
|
@@ -297,25 +260,25 @@ class HospitalDataQualityAnalyzer:
|
|
| 297 |
|
| 298 |
# Complétude
|
| 299 |
total_rows = (self.metrics['patients']['total'] +
|
| 300 |
-
|
| 301 |
-
|
| 302 |
|
| 303 |
total_missing = (self.metrics['patients']['missing_total'] +
|
| 304 |
-
|
| 305 |
-
|
| 306 |
|
| 307 |
completeness_score = safe_pct(total_rows - total_missing, total_rows)
|
| 308 |
|
| 309 |
# Exactitude
|
| 310 |
total_all_rows = (self.metrics['patients']['total'] +
|
| 311 |
-
|
| 312 |
-
|
| 313 |
-
|
| 314 |
|
| 315 |
total_anomalies = (self.metrics['patients']['anomalies'] +
|
| 316 |
-
|
| 317 |
-
|
| 318 |
-
|
| 319 |
|
| 320 |
accuracy_score = safe_pct(total_all_rows - total_anomalies, total_all_rows)
|
| 321 |
|
|
@@ -459,11 +422,11 @@ def plot_completeness_radar(analyzer: HospitalDataQualityAnalyzer):
|
|
| 459 |
patient_completeness = 100 - safe_pct(metrics['patients']['missing_total'],
|
| 460 |
metrics['patients']['total'] * len(analyzer.df_pat.columns) if analyzer.df_pat is not None else 1)
|
| 461 |
sejour_completeness = 100 - safe_pct(metrics['sejours']['missing_total'],
|
| 462 |
-
|
| 463 |
ressource_completeness = 100 - safe_pct(metrics['ressources']['missing_total'],
|
| 464 |
-
|
| 465 |
stock_completeness = 100 - safe_pct(metrics['stock']['missing_total'],
|
| 466 |
-
|
| 467 |
|
| 468 |
categories = ['Patients', 'Séjours', 'Ressources', 'Stock']
|
| 469 |
values = [patient_completeness, sejour_completeness, ressource_completeness, stock_completeness]
|
|
@@ -501,10 +464,6 @@ def plot_completeness_radar(analyzer: HospitalDataQualityAnalyzer):
|
|
| 501 |
def show_dq_dashboard(_client=None, sheet_name=None):
|
| 502 |
"""
|
| 503 |
Dashboard Data Quality complet avec support Google Sheets et Upload Fichier.
|
| 504 |
-
|
| 505 |
-
Args:
|
| 506 |
-
_client: _client Google Sheets (optionnel)
|
| 507 |
-
sheet_name: Nom de la feuille Google Sheets (optionnel)
|
| 508 |
"""
|
| 509 |
st.markdown("## 🛡️ CENTRE DE CONTRÔLE DATA QUALITY")
|
| 510 |
st.caption("Analyse complète de la qualité des données hospitalières")
|
|
@@ -513,16 +472,13 @@ def show_dq_dashboard(_client=None, sheet_name=None):
|
|
| 513 |
|
| 514 |
# ================= MODE DE CHARGEMENT =================
|
| 515 |
if _client is not None and sheet_name is not None:
|
| 516 |
-
# Mode Google Sheets (prioritaire si _client fourni)
|
| 517 |
st.info("📊 **Mode : Google Sheets**")
|
| 518 |
|
| 519 |
with st.spinner("🔄 Chargement depuis Google Sheets..."):
|
| 520 |
dataframes = load_from_google_sheets(_client, sheet_name)
|
| 521 |
|
| 522 |
else:
|
| 523 |
-
# Mode Upload Fichier
|
| 524 |
st.sidebar.header("⚙️ Configuration")
|
| 525 |
-
|
| 526 |
uploaded_file = st.sidebar.file_uploader(
|
| 527 |
"Charger le fichier Excel",
|
| 528 |
type=['xlsx'],
|
|
@@ -531,7 +487,6 @@ def show_dq_dashboard(_client=None, sheet_name=None):
|
|
| 531 |
|
| 532 |
if uploaded_file is not None:
|
| 533 |
st.info("📁 **Mode : Fichier Excel Local**")
|
| 534 |
-
|
| 535 |
with st.spinner("🔄 Chargement du fichier Excel..."):
|
| 536 |
dataframes = load_from_excel_file(uploaded_file)
|
| 537 |
else:
|
|
@@ -556,40 +511,14 @@ def show_dq_dashboard(_client=None, sheet_name=None):
|
|
| 556 |
st.markdown("### 📊 Synthèse de Santé des Données")
|
| 557 |
|
| 558 |
col1, col2, col3, col4 = st.columns(4)
|
| 559 |
-
|
| 560 |
metrics = analyzer.metrics
|
| 561 |
|
| 562 |
-
col1.metric(
|
| 563 |
-
|
| 564 |
-
|
| 565 |
-
|
| 566 |
-
delta_color="inverse"
|
| 567 |
-
)
|
| 568 |
-
|
| 569 |
-
col2.metric(
|
| 570 |
-
"🔴 Anomalies Séjours",
|
| 571 |
-
f"{metrics['sejours']['anomalies']:,}",
|
| 572 |
-
f"{safe_pct(metrics['sejours']['anomalies'], metrics['sejours']['total'])}%",
|
| 573 |
-
delta_color="inverse"
|
| 574 |
-
)
|
| 575 |
-
|
| 576 |
-
col3.metric(
|
| 577 |
-
"🔴 Anomalies Ressources",
|
| 578 |
-
f"{metrics['ressources']['anomalies']:,}",
|
| 579 |
-
f"{safe_pct(metrics['ressources']['anomalies'], metrics['ressources']['total'])}%",
|
| 580 |
-
delta_color="inverse"
|
| 581 |
-
)
|
| 582 |
-
|
| 583 |
-
col4.metric(
|
| 584 |
-
"🔴 Anomalies Stock",
|
| 585 |
-
f"{metrics['stock']['anomalies']:,}",
|
| 586 |
-
f"{safe_pct(metrics['stock']['anomalies'], metrics['stock']['total'])}%",
|
| 587 |
-
delta_color="inverse"
|
| 588 |
-
)
|
| 589 |
|
| 590 |
-
# Graphique distribution anomalies
|
| 591 |
st.plotly_chart(plot_anomalies_distribution(analyzer), use_container_width=True)
|
| 592 |
-
|
| 593 |
st.divider()
|
| 594 |
|
| 595 |
# ==================================================
|
|
@@ -611,16 +540,10 @@ def show_dq_dashboard(_client=None, sheet_name=None):
|
|
| 611 |
|
| 612 |
if not missing_df.empty:
|
| 613 |
st.caption(f"📊 {len(missing_df)} colonnes avec données manquantes")
|
| 614 |
-
|
| 615 |
-
|
| 616 |
-
|
| 617 |
-
|
| 618 |
-
y='Pourcentage Manquant',
|
| 619 |
-
title=f"Données manquantes - {df_name}",
|
| 620 |
-
color='Pourcentage Manquant',
|
| 621 |
-
color_continuous_scale='Reds',
|
| 622 |
-
text='Pourcentage Manquant'
|
| 623 |
-
)
|
| 624 |
fig.update_traces(texttemplate='%{text:.1f}%', textposition='outside')
|
| 625 |
fig.update_layout(xaxis_tickangle=-45, height=400)
|
| 626 |
st.plotly_chart(fig, use_container_width=True)
|
|
@@ -629,226 +552,126 @@ def show_dq_dashboard(_client=None, sheet_name=None):
|
|
| 629 |
else:
|
| 630 |
st.warning(f"⚠️ Aucune donnée {df_name} disponible")
|
| 631 |
|
| 632 |
-
# Radar de complétude
|
| 633 |
st.plotly_chart(plot_completeness_radar(analyzer), use_container_width=True)
|
| 634 |
-
|
| 635 |
st.divider()
|
| 636 |
|
| 637 |
# ==================================================
|
| 638 |
# ========== 2️⃣ COHÉRENCE DES DONNÉES =============
|
| 639 |
# ==================================================
|
| 640 |
st.subheader("2️⃣ Cohérence et Validité des Données")
|
| 641 |
-
|
| 642 |
col1, col2 = st.columns(2)
|
| 643 |
-
|
| 644 |
with col1:
|
| 645 |
st.markdown("#### 👥 Cohérence Patients")
|
| 646 |
st.metric("Âges négatifs", metrics['patients']['ages_negatifs'], delta_color="inverse")
|
| 647 |
st.metric("Âges aberrants (>120 ans)", metrics['patients']['ages_aberrants'], delta_color="inverse")
|
| 648 |
st.metric("Doublons (nom+prénom)", metrics['patients']['doublons'], delta_color="inverse")
|
| 649 |
-
|
| 650 |
with col2:
|
| 651 |
st.markdown("#### 🏥 Cohérence Séjours")
|
| 652 |
st.metric("Dates inversées (sortie < entrée)", metrics['sejours']['dates_inversees'], delta_color="inverse")
|
| 653 |
st.metric("Gravité aberrante (<0 ou >5)", metrics['sejours']['gravite_aberrante'], delta_color="inverse")
|
| 654 |
st.metric("Équipement manquant", metrics['sejours']['equipement_manquant'], delta_color="inverse")
|
| 655 |
|
| 656 |
-
# Graphique qualité par service
|
| 657 |
fig_service = plot_service_quality_heatmap(analyzer)
|
| 658 |
-
if fig_service:
|
| 659 |
-
st.plotly_chart(fig_service, use_container_width=True)
|
| 660 |
-
|
| 661 |
st.divider()
|
| 662 |
|
| 663 |
# ==================================================
|
| 664 |
# ========== 3️⃣ ANALYSE DES ANOMALIES =============
|
| 665 |
# ==================================================
|
| 666 |
st.subheader("3️⃣ Analyse Détaillée des Anomalies")
|
| 667 |
-
|
| 668 |
tab1, tab2, tab3, tab4 = st.tabs(["📋 Patients", "🏥 Séjours", "⚕️ Ressources", "📦 Stock"])
|
| 669 |
-
|
| 670 |
for tab, df_label in [(tab1, 'pat'), (tab2, 'sej'), (tab3, 'res'), (tab4, 'stock')]:
|
| 671 |
with tab:
|
| 672 |
anomaly_details = analyzer.get_anomalies_by_type(df_label)
|
| 673 |
-
|
| 674 |
if not anomaly_details.empty:
|
| 675 |
st.dataframe(anomaly_details, use_container_width=True)
|
| 676 |
-
|
| 677 |
-
fig = px.pie(
|
| 678 |
-
anomaly_details,
|
| 679 |
-
values='Nombre',
|
| 680 |
-
names='Type Anomalie',
|
| 681 |
-
title=f"Répartition des Types d'Anomalies"
|
| 682 |
-
)
|
| 683 |
st.plotly_chart(fig, use_container_width=True)
|
| 684 |
else:
|
| 685 |
st.success(f"✅ Aucune anomalie détectée")
|
| 686 |
|
| 687 |
-
# Évolution temporelle
|
| 688 |
fig_temporal = plot_temporal_anomalies(analyzer)
|
| 689 |
-
if fig_temporal:
|
| 690 |
-
st.plotly_chart(fig_temporal, use_container_width=True)
|
| 691 |
-
|
| 692 |
st.divider()
|
| 693 |
|
| 694 |
# ==================================================
|
| 695 |
# ========== 4️⃣ SPÉCIFICITÉS HOSPITALIÈRES ========
|
| 696 |
# ==================================================
|
| 697 |
st.subheader("4️⃣ Analyses Spécifiques Hospitalières")
|
| 698 |
-
|
| 699 |
col1, col2 = st.columns(2)
|
| 700 |
-
|
| 701 |
with col1:
|
| 702 |
st.markdown("#### 🛏️ Ressources")
|
| 703 |
if analyzer.df_res is not None:
|
| 704 |
st.metric("Cas de suroccupation", metrics['ressources']['suroccupation'], delta_color="inverse")
|
| 705 |
-
|
| 706 |
-
# Taux occupation moyen par service
|
| 707 |
if 'service_code' in analyzer.df_res.columns and 'taux_occupation' in analyzer.df_res.columns:
|
| 708 |
taux_moy = analyzer.df_res.groupby('service_code')['taux_occupation'].mean().reset_index()
|
| 709 |
taux_moy.columns = ['Service', 'Taux Occupation Moyen']
|
| 710 |
-
|
| 711 |
-
|
| 712 |
-
fig = px.bar(
|
| 713 |
-
taux_moy.head(10),
|
| 714 |
-
x='Service',
|
| 715 |
-
y='Taux Occupation Moyen',
|
| 716 |
-
title="Top 10 Services - Taux Occupation",
|
| 717 |
-
color='Taux Occupation Moyen',
|
| 718 |
-
color_continuous_scale='RdYlGn_r'
|
| 719 |
-
)
|
| 720 |
st.plotly_chart(fig, use_container_width=True)
|
| 721 |
-
|
| 722 |
with col2:
|
| 723 |
st.markdown("#### 📦 Stock")
|
| 724 |
st.metric("Alertes stock actives", metrics['stock']['alertes'], delta_color="inverse")
|
| 725 |
-
|
| 726 |
-
# Distribution des alertes par matériel
|
| 727 |
if analyzer.df_stock is not None and 'alerte_stock' in analyzer.df_stock.columns:
|
| 728 |
-
alertes = analyzer.df_stock[analyzer.df_stock['alerte_stock'] == 1]
|
| 729 |
if not alertes.empty and 'materiel_code' in alertes.columns:
|
| 730 |
alert_counts = alertes['materiel_code'].value_counts().reset_index()
|
| 731 |
alert_counts.columns = ['Matériel', 'Nombre Alertes']
|
| 732 |
-
|
| 733 |
-
fig = px.bar(
|
| 734 |
-
alert_counts.head(10),
|
| 735 |
-
x='Matériel',
|
| 736 |
-
y='Nombre Alertes',
|
| 737 |
-
title="Top 10 Matériels en Alerte",
|
| 738 |
-
color='Nombre Alertes',
|
| 739 |
-
color_continuous_scale='Oranges'
|
| 740 |
-
)
|
| 741 |
st.plotly_chart(fig, use_container_width=True)
|
| 742 |
-
|
| 743 |
st.divider()
|
| 744 |
|
| 745 |
# ==================================================
|
| 746 |
# ========== 5️⃣ RÉSUMÉ EXÉCUTIF ===================
|
| 747 |
# ==================================================
|
| 748 |
st.subheader("5️⃣ Résumé Exécutif Data Quality")
|
| 749 |
-
|
| 750 |
col1, col2, col3 = st.columns(3)
|
| 751 |
-
|
| 752 |
col1.metric("Score de Complétude", f"{scores['completeness']:.2f}%")
|
| 753 |
col2.metric("Score d'Exactitude", f"{scores['accuracy']:.2f}%")
|
| 754 |
-
|
| 755 |
global_score = scores['global']
|
| 756 |
-
|
| 757 |
-
|
| 758 |
-
|
| 759 |
-
|
| 760 |
-
elif global_score >= 85:
|
| 761 |
-
status = "🟡 BON"
|
| 762 |
-
color = "blue"
|
| 763 |
-
elif global_score >= 70:
|
| 764 |
-
status = "🟠 MOYEN"
|
| 765 |
-
color = "orange"
|
| 766 |
-
else:
|
| 767 |
-
status = "🔴 CRITIQUE"
|
| 768 |
-
color = "red"
|
| 769 |
-
|
| 770 |
col3.markdown(f"**Score Global**")
|
| 771 |
col3.markdown(f"<h2 style='color: {color};'>{global_score:.2f}%</h2>", unsafe_allow_html=True)
|
| 772 |
-
|
| 773 |
st.markdown(f"### {status}")
|
| 774 |
st.progress(global_score / 100)
|
| 775 |
|
| 776 |
-
# Recommandations
|
| 777 |
st.markdown("#### 💡 Recommandations")
|
| 778 |
-
|
| 779 |
recommendations = []
|
| 780 |
-
|
| 781 |
-
if metrics['
|
| 782 |
-
|
| 783 |
-
|
| 784 |
-
if
|
| 785 |
-
recommendations.append(f"🔴 **{metrics['sejours']['dates_inversees']} séjours avec dates inversées** - Corriger les dates d'entrée/sortie")
|
| 786 |
-
|
| 787 |
-
if metrics['ressources']['suroccupation'] > 0:
|
| 788 |
-
recommendations.append(f"🚨 **{metrics['ressources']['suroccupation']} cas de suroccupation** - Revoir la capacité des services")
|
| 789 |
-
|
| 790 |
-
if metrics['stock']['alertes'] > 0:
|
| 791 |
-
recommendations.append(f"📦 **{metrics['stock']['alertes']} alertes stock** - Réapprovisionner les matériels critiques")
|
| 792 |
-
|
| 793 |
-
if global_score < 85:
|
| 794 |
-
recommendations.append("📊 **Score global < 85%** - Lancer un plan d'action Data Quality urgent")
|
| 795 |
|
| 796 |
if recommendations:
|
| 797 |
-
for rec in recommendations:
|
| 798 |
-
|
| 799 |
-
else:
|
| 800 |
-
st.success("✅ Aucune action critique nécessaire - Qualité des données satisfaisante")
|
| 801 |
-
|
| 802 |
st.divider()
|
| 803 |
|
| 804 |
# ==================================================
|
| 805 |
# ========== 6️⃣ EXPORT DES RÉSULTATS ==============
|
| 806 |
# ==================================================
|
| 807 |
st.subheader("6️⃣ Export et Documentation")
|
| 808 |
-
|
| 809 |
-
# Création du rapport
|
| 810 |
-
report_data = {
|
| 811 |
-
'Métrique': [],
|
| 812 |
-
'Valeur': []
|
| 813 |
-
}
|
| 814 |
-
|
| 815 |
for category, cat_metrics in analyzer.metrics.items():
|
| 816 |
for metric_name, value in cat_metrics.items():
|
| 817 |
report_data['Métrique'].append(f"{category}_{metric_name}")
|
| 818 |
report_data['Valeur'].append(value)
|
| 819 |
-
|
| 820 |
-
# Ajout scores
|
| 821 |
report_data['Métrique'].extend(['score_completeness', 'score_accuracy', 'score_global'])
|
| 822 |
report_data['Valeur'].extend([scores['completeness'], scores['accuracy'], scores['global']])
|
| 823 |
-
|
| 824 |
report_df = pd.DataFrame(report_data)
|
| 825 |
|
| 826 |
col1, col2 = st.columns(2)
|
| 827 |
-
|
| 828 |
with col1:
|
| 829 |
csv = report_df.to_csv(index=False).encode('utf-8')
|
| 830 |
-
st.download_button(
|
| 831 |
-
label="📥 Télécharger Rapport DQ (CSV)",
|
| 832 |
-
data=csv,
|
| 833 |
-
file_name=f'data_quality_report_{datetime.now().strftime("%Y%m%d_%H%M%S")}.csv',
|
| 834 |
-
mime='text/csv'
|
| 835 |
-
)
|
| 836 |
-
|
| 837 |
with col2:
|
| 838 |
-
# Export des anomalies détectées
|
| 839 |
if metrics['patients']['anomalies'] > 0 and analyzer.df_pat is not None:
|
| 840 |
-
anomalies_df = analyzer.df_pat[analyzer.df_pat['dq_is_anomaly'] == 1][
|
| 841 |
-
['patient_id', 'nom', 'prenom', 'dq_anomaly_type', 'dq_anomaly_detail']
|
| 842 |
-
]
|
| 843 |
anomalies_csv = anomalies_df.to_csv(index=False).encode('utf-8')
|
| 844 |
-
st.download_button(
|
| 845 |
-
label="📥 Télécharger Anomalies Patients (CSV)",
|
| 846 |
-
data=anomalies_csv,
|
| 847 |
-
file_name=f'anomalies_patients_{datetime.now().strftime("%Y%m%d_%H%M%S")}.csv',
|
| 848 |
-
mime='text/csv'
|
| 849 |
-
)
|
| 850 |
-
|
| 851 |
|
| 852 |
-
# Point d'entrée
|
| 853 |
if __name__ == "__main__":
|
| 854 |
show_dq_dashboard()
|
|
|
|
| 1 |
"""
|
| 2 |
+
MODULE: DATA QUALITY DASHBOARD - VERSION CORRIGÉE
|
| 3 |
+
=================================================
|
| 4 |
+
Responsabilité : Audit complet, détection d'anomalies.
|
| 5 |
+
Correction : Gestion stricte des types numériques pour éviter les crashs (int/str).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"""
|
| 7 |
|
| 8 |
import streamlit as st
|
|
|
|
| 25 |
try:
|
| 26 |
if pd.isna(value):
|
| 27 |
return 0
|
| 28 |
+
return int(float(value)) # Double cast pour gérer les strings '1.0'
|
| 29 |
except (TypeError, ValueError, OverflowError):
|
| 30 |
return 0
|
| 31 |
|
|
|
|
| 54 |
# ================= CHARGEMENT DONNÉES ================
|
| 55 |
# =====================================================
|
| 56 |
|
| 57 |
+
@st.cache_data(ttl=60) # TTL court pour voir les nouvelles données injectées
|
| 58 |
def load_from_google_sheets(_client, sheet_name: str) -> dict:
|
| 59 |
+
"""Charge les données depuis Google Sheets SANS passer par ETL."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
sheets = {}
|
| 61 |
|
| 62 |
try:
|
|
|
|
| 63 |
sheet_names = [
|
| 64 |
'patients', 'sejours', 'ressources_jour',
|
| 65 |
'stock_materiel_jour', 'admissions_jour', 'scenarios_calendrier'
|
|
|
|
| 67 |
|
| 68 |
for name in sheet_names:
|
| 69 |
try:
|
|
|
|
| 70 |
worksheet = _client.open(sheet_name).worksheet(name)
|
| 71 |
data = worksheet.get_all_records()
|
| 72 |
df = pd.DataFrame(data)
|
| 73 |
|
| 74 |
# Conversion des dates
|
| 75 |
+
date_cols = ['date', 'date_entree', 'date_sortie', 'date_naissance']
|
| 76 |
+
for col in date_cols:
|
| 77 |
+
if col in df.columns:
|
| 78 |
+
df[col] = pd.to_datetime(df[col], errors='coerce')
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
sheets[name] = df
|
| 81 |
|
| 82 |
except Exception as e:
|
| 83 |
+
# On continue même si une feuille manque
|
| 84 |
continue
|
| 85 |
|
| 86 |
return sheets
|
| 87 |
|
| 88 |
except Exception as e:
|
| 89 |
+
st.error(f"Erreur lors du chargement depuis Google Sheets : {str(e)}")
|
| 90 |
return {}
|
| 91 |
|
| 92 |
|
| 93 |
@st.cache_data(ttl=3600)
|
| 94 |
def load_from_excel_file(file) -> dict:
|
| 95 |
+
"""Charge les données depuis un fichier Excel uploadé."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
sheets = {}
|
|
|
|
| 97 |
try:
|
|
|
|
| 98 |
sheets['patients'] = pd.read_excel(file, sheet_name='patients')
|
| 99 |
sheets['sejours'] = pd.read_excel(file, sheet_name='sejours')
|
| 100 |
sheets['ressources_jour'] = pd.read_excel(file, sheet_name='ressources_jour')
|
|
|
|
| 102 |
sheets['admissions_jour'] = pd.read_excel(file, sheet_name='admissions_jour')
|
| 103 |
sheets['scenarios_calendrier'] = pd.read_excel(file, sheet_name='scenarios_calendrier')
|
| 104 |
|
|
|
|
| 105 |
for sheet_name, df in sheets.items():
|
| 106 |
+
for col in df.columns:
|
| 107 |
+
if 'date' in col.lower():
|
| 108 |
+
df[col] = pd.to_datetime(df[col], errors='coerce')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
return sheets
|
|
|
|
| 110 |
except Exception as e:
|
| 111 |
+
st.error(f"Erreur lors du chargement du fichier Excel : {str(e)}")
|
| 112 |
return {}
|
| 113 |
|
| 114 |
|
|
|
|
| 130 |
self.metrics = {}
|
| 131 |
self._compute_all_metrics()
|
| 132 |
|
| 133 |
+
def _force_numeric_anomaly(self, df):
|
| 134 |
+
"""Force la colonne dq_is_anomaly en numérique pour éviter les crashs"""
|
| 135 |
+
if df is not None and not df.empty and 'dq_is_anomaly' in df.columns:
|
| 136 |
+
# Conversion robuste : force tout en nombre, remplace les erreurs par 0
|
| 137 |
+
df['dq_is_anomaly'] = pd.to_numeric(df['dq_is_anomaly'], errors='coerce').fillna(0).astype(int)
|
| 138 |
+
return df
|
| 139 |
+
|
| 140 |
def _compute_all_metrics(self):
|
| 141 |
"""Calcul de toutes les métriques DQ"""
|
| 142 |
|
| 143 |
+
# NETTOYAGE PRÉALABLE : Conversion des types pour éviter le crash int+str
|
| 144 |
+
self.df_pat = self._force_numeric_anomaly(self.df_pat)
|
| 145 |
+
self.df_sej = self._force_numeric_anomaly(self.df_sej)
|
| 146 |
+
self.df_res = self._force_numeric_anomaly(self.df_res)
|
| 147 |
+
self.df_stock = self._force_numeric_anomaly(self.df_stock)
|
| 148 |
+
|
| 149 |
# ============= PATIENTS =============
|
| 150 |
if self.df_pat is not None and not self.df_pat.empty:
|
| 151 |
self.metrics['patients'] = {
|
| 152 |
'total': len(self.df_pat),
|
| 153 |
+
'anomalies': int(self.df_pat['dq_is_anomaly'].sum()),
|
| 154 |
+
'doublons': int(self.df_pat.duplicated(subset=['nom', 'prenom']).sum()),
|
| 155 |
+
'ages_negatifs': int((pd.to_numeric(self.df_pat['age'], errors='coerce') < 0).sum()),
|
| 156 |
+
'ages_aberrants': int((pd.to_numeric(self.df_pat['age'], errors='coerce') > 120).sum()),
|
| 157 |
+
'missing_birth': int(self.df_pat['date_naissance'].isnull().sum()),
|
| 158 |
+
'missing_ville': int(self.df_pat['ville'].isnull().sum()),
|
| 159 |
+
'missing_total': int(self.df_pat.isnull().sum().sum())
|
| 160 |
}
|
| 161 |
else:
|
| 162 |
self.metrics['patients'] = {k: 0 for k in ['total', 'anomalies', 'doublons', 'ages_negatifs',
|
|
|
|
| 164 |
|
| 165 |
# ============= SÉJOURS =============
|
| 166 |
if self.df_sej is not None and not self.df_sej.empty:
|
| 167 |
+
dates_inversees = int((self.df_sej['date_sortie'] < self.df_sej['date_entree']).sum())
|
| 168 |
+
gravite = pd.to_numeric(self.df_sej['gravite_1_5'], errors='coerce').fillna(3)
|
| 169 |
+
gravite_aberrante = int(((gravite > 5) | (gravite < 0)).sum())
|
| 170 |
|
| 171 |
self.metrics['sejours'] = {
|
| 172 |
'total': len(self.df_sej),
|
| 173 |
+
'anomalies': int(self.df_sej['dq_is_anomaly'].sum()),
|
| 174 |
'dates_inversees': dates_inversees,
|
| 175 |
'gravite_aberrante': gravite_aberrante,
|
| 176 |
+
'equipement_manquant': int(self.df_sej['equipement_principal_code'].isnull().sum()),
|
| 177 |
+
'missing_total': int(self.df_sej.isnull().sum().sum())
|
| 178 |
}
|
| 179 |
else:
|
| 180 |
self.metrics['sejours'] = {k: 0 for k in ['total', 'anomalies', 'dates_inversees',
|
|
|
|
| 184 |
if self.df_res is not None and not self.df_res.empty:
|
| 185 |
df_res_temp = self.df_res.copy()
|
| 186 |
df_res_temp['lits_occupes_num'] = pd.to_numeric(df_res_temp['lits_occupes'], errors='coerce').fillna(0)
|
| 187 |
+
df_res_temp['lits_total_num'] = pd.to_numeric(df_res_temp['lits_total'], errors='coerce').fillna(1)
|
| 188 |
+
suroccupation = int((df_res_temp['lits_occupes_num'] > df_res_temp['lits_total_num']).sum())
|
| 189 |
|
| 190 |
self.metrics['ressources'] = {
|
| 191 |
'total': len(self.df_res),
|
| 192 |
+
'anomalies': int(self.df_res['dq_is_anomaly'].sum()),
|
| 193 |
'suroccupation': suroccupation,
|
| 194 |
+
'missing_total': int(self.df_res.isnull().sum().sum())
|
| 195 |
}
|
| 196 |
else:
|
| 197 |
self.metrics['ressources'] = {k: 0 for k in ['total', 'anomalies', 'suroccupation', 'missing_total']}
|
|
|
|
| 200 |
if self.df_stock is not None and not self.df_stock.empty:
|
| 201 |
self.metrics['stock'] = {
|
| 202 |
'total': len(self.df_stock),
|
| 203 |
+
'anomalies': int(self.df_stock['dq_is_anomaly'].sum()),
|
| 204 |
+
'alertes': int((self.df_stock['alerte_stock'].astype(str) == '1').sum()),
|
| 205 |
+
'missing_total': int(self.df_stock.isnull().sum().sum())
|
| 206 |
}
|
| 207 |
else:
|
| 208 |
self.metrics['stock'] = {k: 0 for k in ['total', 'anomalies', 'alertes', 'missing_total']}
|
|
|
|
| 260 |
|
| 261 |
# Complétude
|
| 262 |
total_rows = (self.metrics['patients']['total'] +
|
| 263 |
+
self.metrics['sejours']['total'] +
|
| 264 |
+
self.metrics['ressources']['total'])
|
| 265 |
|
| 266 |
total_missing = (self.metrics['patients']['missing_total'] +
|
| 267 |
+
self.metrics['sejours']['missing_total'] +
|
| 268 |
+
self.metrics['ressources']['missing_total'])
|
| 269 |
|
| 270 |
completeness_score = safe_pct(total_rows - total_missing, total_rows)
|
| 271 |
|
| 272 |
# Exactitude
|
| 273 |
total_all_rows = (self.metrics['patients']['total'] +
|
| 274 |
+
self.metrics['sejours']['total'] +
|
| 275 |
+
self.metrics['ressources']['total'] +
|
| 276 |
+
self.metrics['stock']['total'])
|
| 277 |
|
| 278 |
total_anomalies = (self.metrics['patients']['anomalies'] +
|
| 279 |
+
self.metrics['sejours']['anomalies'] +
|
| 280 |
+
self.metrics['ressources']['anomalies'] +
|
| 281 |
+
self.metrics['stock']['anomalies'])
|
| 282 |
|
| 283 |
accuracy_score = safe_pct(total_all_rows - total_anomalies, total_all_rows)
|
| 284 |
|
|
|
|
| 422 |
patient_completeness = 100 - safe_pct(metrics['patients']['missing_total'],
|
| 423 |
metrics['patients']['total'] * len(analyzer.df_pat.columns) if analyzer.df_pat is not None else 1)
|
| 424 |
sejour_completeness = 100 - safe_pct(metrics['sejours']['missing_total'],
|
| 425 |
+
metrics['sejours']['total'] * len(analyzer.df_sej.columns) if analyzer.df_sej is not None else 1)
|
| 426 |
ressource_completeness = 100 - safe_pct(metrics['ressources']['missing_total'],
|
| 427 |
+
metrics['ressources']['total'] * len(analyzer.df_res.columns) if analyzer.df_res is not None else 1)
|
| 428 |
stock_completeness = 100 - safe_pct(metrics['stock']['missing_total'],
|
| 429 |
+
metrics['stock']['total'] * len(analyzer.df_stock.columns) if analyzer.df_stock is not None else 1)
|
| 430 |
|
| 431 |
categories = ['Patients', 'Séjours', 'Ressources', 'Stock']
|
| 432 |
values = [patient_completeness, sejour_completeness, ressource_completeness, stock_completeness]
|
|
|
|
| 464 |
def show_dq_dashboard(_client=None, sheet_name=None):
|
| 465 |
"""
|
| 466 |
Dashboard Data Quality complet avec support Google Sheets et Upload Fichier.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 467 |
"""
|
| 468 |
st.markdown("## 🛡️ CENTRE DE CONTRÔLE DATA QUALITY")
|
| 469 |
st.caption("Analyse complète de la qualité des données hospitalières")
|
|
|
|
| 472 |
|
| 473 |
# ================= MODE DE CHARGEMENT =================
|
| 474 |
if _client is not None and sheet_name is not None:
|
|
|
|
| 475 |
st.info("📊 **Mode : Google Sheets**")
|
| 476 |
|
| 477 |
with st.spinner("🔄 Chargement depuis Google Sheets..."):
|
| 478 |
dataframes = load_from_google_sheets(_client, sheet_name)
|
| 479 |
|
| 480 |
else:
|
|
|
|
| 481 |
st.sidebar.header("⚙️ Configuration")
|
|
|
|
| 482 |
uploaded_file = st.sidebar.file_uploader(
|
| 483 |
"Charger le fichier Excel",
|
| 484 |
type=['xlsx'],
|
|
|
|
| 487 |
|
| 488 |
if uploaded_file is not None:
|
| 489 |
st.info("📁 **Mode : Fichier Excel Local**")
|
|
|
|
| 490 |
with st.spinner("🔄 Chargement du fichier Excel..."):
|
| 491 |
dataframes = load_from_excel_file(uploaded_file)
|
| 492 |
else:
|
|
|
|
| 511 |
st.markdown("### 📊 Synthèse de Santé des Données")
|
| 512 |
|
| 513 |
col1, col2, col3, col4 = st.columns(4)
|
|
|
|
| 514 |
metrics = analyzer.metrics
|
| 515 |
|
| 516 |
+
col1.metric("🔴 Anomalies Patients", f"{metrics['patients']['anomalies']:,}", delta_color="inverse")
|
| 517 |
+
col2.metric("🔴 Anomalies Séjours", f"{metrics['sejours']['anomalies']:,}", delta_color="inverse")
|
| 518 |
+
col3.metric("🔴 Anomalies Ressources", f"{metrics['ressources']['anomalies']:,}", delta_color="inverse")
|
| 519 |
+
col4.metric("🔴 Anomalies Stock", f"{metrics['stock']['anomalies']:,}", delta_color="inverse")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 520 |
|
|
|
|
| 521 |
st.plotly_chart(plot_anomalies_distribution(analyzer), use_container_width=True)
|
|
|
|
| 522 |
st.divider()
|
| 523 |
|
| 524 |
# ==================================================
|
|
|
|
| 540 |
|
| 541 |
if not missing_df.empty:
|
| 542 |
st.caption(f"📊 {len(missing_df)} colonnes avec données manquantes")
|
| 543 |
+
fig = px.bar(missing_df.sort_values('Pourcentage Manquant', ascending=False),
|
| 544 |
+
x='Colonne', y='Pourcentage Manquant',
|
| 545 |
+
title=f"Données manquantes - {df_name}",
|
| 546 |
+
color='Pourcentage Manquant', color_continuous_scale='Reds', text='Pourcentage Manquant')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 547 |
fig.update_traces(texttemplate='%{text:.1f}%', textposition='outside')
|
| 548 |
fig.update_layout(xaxis_tickangle=-45, height=400)
|
| 549 |
st.plotly_chart(fig, use_container_width=True)
|
|
|
|
| 552 |
else:
|
| 553 |
st.warning(f"⚠️ Aucune donnée {df_name} disponible")
|
| 554 |
|
|
|
|
| 555 |
st.plotly_chart(plot_completeness_radar(analyzer), use_container_width=True)
|
|
|
|
| 556 |
st.divider()
|
| 557 |
|
| 558 |
# ==================================================
|
| 559 |
# ========== 2️⃣ COHÉRENCE DES DONNÉES =============
|
| 560 |
# ==================================================
|
| 561 |
st.subheader("2️⃣ Cohérence et Validité des Données")
|
|
|
|
| 562 |
col1, col2 = st.columns(2)
|
|
|
|
| 563 |
with col1:
|
| 564 |
st.markdown("#### 👥 Cohérence Patients")
|
| 565 |
st.metric("Âges négatifs", metrics['patients']['ages_negatifs'], delta_color="inverse")
|
| 566 |
st.metric("Âges aberrants (>120 ans)", metrics['patients']['ages_aberrants'], delta_color="inverse")
|
| 567 |
st.metric("Doublons (nom+prénom)", metrics['patients']['doublons'], delta_color="inverse")
|
|
|
|
| 568 |
with col2:
|
| 569 |
st.markdown("#### 🏥 Cohérence Séjours")
|
| 570 |
st.metric("Dates inversées (sortie < entrée)", metrics['sejours']['dates_inversees'], delta_color="inverse")
|
| 571 |
st.metric("Gravité aberrante (<0 ou >5)", metrics['sejours']['gravite_aberrante'], delta_color="inverse")
|
| 572 |
st.metric("Équipement manquant", metrics['sejours']['equipement_manquant'], delta_color="inverse")
|
| 573 |
|
|
|
|
| 574 |
fig_service = plot_service_quality_heatmap(analyzer)
|
| 575 |
+
if fig_service: st.plotly_chart(fig_service, use_container_width=True)
|
|
|
|
|
|
|
| 576 |
st.divider()
|
| 577 |
|
| 578 |
# ==================================================
|
| 579 |
# ========== 3️⃣ ANALYSE DES ANOMALIES =============
|
| 580 |
# ==================================================
|
| 581 |
st.subheader("3️⃣ Analyse Détaillée des Anomalies")
|
|
|
|
| 582 |
tab1, tab2, tab3, tab4 = st.tabs(["📋 Patients", "🏥 Séjours", "⚕️ Ressources", "📦 Stock"])
|
|
|
|
| 583 |
for tab, df_label in [(tab1, 'pat'), (tab2, 'sej'), (tab3, 'res'), (tab4, 'stock')]:
|
| 584 |
with tab:
|
| 585 |
anomaly_details = analyzer.get_anomalies_by_type(df_label)
|
|
|
|
| 586 |
if not anomaly_details.empty:
|
| 587 |
st.dataframe(anomaly_details, use_container_width=True)
|
| 588 |
+
fig = px.pie(anomaly_details, values='Nombre', names='Type Anomalie', title=f"Répartition des Types d'Anomalies")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 589 |
st.plotly_chart(fig, use_container_width=True)
|
| 590 |
else:
|
| 591 |
st.success(f"✅ Aucune anomalie détectée")
|
| 592 |
|
|
|
|
| 593 |
fig_temporal = plot_temporal_anomalies(analyzer)
|
| 594 |
+
if fig_temporal: st.plotly_chart(fig_temporal, use_container_width=True)
|
|
|
|
|
|
|
| 595 |
st.divider()
|
| 596 |
|
| 597 |
# ==================================================
|
| 598 |
# ========== 4️⃣ SPÉCIFICITÉS HOSPITALIÈRES ========
|
| 599 |
# ==================================================
|
| 600 |
st.subheader("4️⃣ Analyses Spécifiques Hospitalières")
|
|
|
|
| 601 |
col1, col2 = st.columns(2)
|
|
|
|
| 602 |
with col1:
|
| 603 |
st.markdown("#### 🛏️ Ressources")
|
| 604 |
if analyzer.df_res is not None:
|
| 605 |
st.metric("Cas de suroccupation", metrics['ressources']['suroccupation'], delta_color="inverse")
|
|
|
|
|
|
|
| 606 |
if 'service_code' in analyzer.df_res.columns and 'taux_occupation' in analyzer.df_res.columns:
|
| 607 |
taux_moy = analyzer.df_res.groupby('service_code')['taux_occupation'].mean().reset_index()
|
| 608 |
taux_moy.columns = ['Service', 'Taux Occupation Moyen']
|
| 609 |
+
fig = px.bar(taux_moy.head(10), x='Service', y='Taux Occupation Moyen', title="Top 10 Services - Taux Occupation", color='Taux Occupation Moyen', color_continuous_scale='RdYlGn_r')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 610 |
st.plotly_chart(fig, use_container_width=True)
|
|
|
|
| 611 |
with col2:
|
| 612 |
st.markdown("#### 📦 Stock")
|
| 613 |
st.metric("Alertes stock actives", metrics['stock']['alertes'], delta_color="inverse")
|
|
|
|
|
|
|
| 614 |
if analyzer.df_stock is not None and 'alerte_stock' in analyzer.df_stock.columns:
|
| 615 |
+
alertes = analyzer.df_stock[analyzer.df_stock['alerte_stock'].astype(str) == '1']
|
| 616 |
if not alertes.empty and 'materiel_code' in alertes.columns:
|
| 617 |
alert_counts = alertes['materiel_code'].value_counts().reset_index()
|
| 618 |
alert_counts.columns = ['Matériel', 'Nombre Alertes']
|
| 619 |
+
fig = px.bar(alert_counts.head(10), x='Matériel', y='Nombre Alertes', title="Top 10 Matériels en Alerte", color='Nombre Alertes', color_continuous_scale='Oranges')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 620 |
st.plotly_chart(fig, use_container_width=True)
|
|
|
|
| 621 |
st.divider()
|
| 622 |
|
| 623 |
# ==================================================
|
| 624 |
# ========== 5️⃣ RÉSUMÉ EXÉCUTIF ===================
|
| 625 |
# ==================================================
|
| 626 |
st.subheader("5️⃣ Résumé Exécutif Data Quality")
|
|
|
|
| 627 |
col1, col2, col3 = st.columns(3)
|
|
|
|
| 628 |
col1.metric("Score de Complétude", f"{scores['completeness']:.2f}%")
|
| 629 |
col2.metric("Score d'Exactitude", f"{scores['accuracy']:.2f}%")
|
|
|
|
| 630 |
global_score = scores['global']
|
| 631 |
+
if global_score >= 95: status, color = "🟢 EXCELLENT", "green"
|
| 632 |
+
elif global_score >= 85: status, color = "🟡 BON", "blue"
|
| 633 |
+
elif global_score >= 70: status, color = "🟠 MOYEN", "orange"
|
| 634 |
+
else: status, color = "🔴 CRITIQUE", "red"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 635 |
col3.markdown(f"**Score Global**")
|
| 636 |
col3.markdown(f"<h2 style='color: {color};'>{global_score:.2f}%</h2>", unsafe_allow_html=True)
|
|
|
|
| 637 |
st.markdown(f"### {status}")
|
| 638 |
st.progress(global_score / 100)
|
| 639 |
|
|
|
|
| 640 |
st.markdown("#### 💡 Recommandations")
|
|
|
|
| 641 |
recommendations = []
|
| 642 |
+
if metrics['patients']['anomalies'] > 0: recommendations.append(f"⚠️ **{metrics['patients']['anomalies']} anomalies patients** détectées")
|
| 643 |
+
if metrics['sejours']['dates_inversees'] > 0: recommendations.append(f"🔴 **{metrics['sejours']['dates_inversees']} séjours avec dates inversées**")
|
| 644 |
+
if metrics['ressources']['suroccupation'] > 0: recommendations.append(f"🚨 **{metrics['ressources']['suroccupation']} cas de suroccupation**")
|
| 645 |
+
if metrics['stock']['alertes'] > 0: recommendations.append(f"📦 **{metrics['stock']['alertes']} alertes stock**")
|
| 646 |
+
if global_score < 85: recommendations.append("📊 **Score global < 85%** - Plan Data Quality requis")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 647 |
|
| 648 |
if recommendations:
|
| 649 |
+
for rec in recommendations: st.markdown(rec)
|
| 650 |
+
else: st.success("✅ Qualité des données satisfaisante")
|
|
|
|
|
|
|
|
|
|
| 651 |
st.divider()
|
| 652 |
|
| 653 |
# ==================================================
|
| 654 |
# ========== 6️⃣ EXPORT DES RÉSULTATS ==============
|
| 655 |
# ==================================================
|
| 656 |
st.subheader("6️⃣ Export et Documentation")
|
| 657 |
+
report_data = {'Métrique': [], 'Valeur': []}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 658 |
for category, cat_metrics in analyzer.metrics.items():
|
| 659 |
for metric_name, value in cat_metrics.items():
|
| 660 |
report_data['Métrique'].append(f"{category}_{metric_name}")
|
| 661 |
report_data['Valeur'].append(value)
|
|
|
|
|
|
|
| 662 |
report_data['Métrique'].extend(['score_completeness', 'score_accuracy', 'score_global'])
|
| 663 |
report_data['Valeur'].extend([scores['completeness'], scores['accuracy'], scores['global']])
|
|
|
|
| 664 |
report_df = pd.DataFrame(report_data)
|
| 665 |
|
| 666 |
col1, col2 = st.columns(2)
|
|
|
|
| 667 |
with col1:
|
| 668 |
csv = report_df.to_csv(index=False).encode('utf-8')
|
| 669 |
+
st.download_button(label="📥 Télécharger Rapport DQ (CSV)", data=csv, file_name=f'dq_report_{datetime.now().strftime("%Y%m%d")}.csv', mime='text/csv')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 670 |
with col2:
|
|
|
|
| 671 |
if metrics['patients']['anomalies'] > 0 and analyzer.df_pat is not None:
|
| 672 |
+
anomalies_df = analyzer.df_pat[analyzer.df_pat['dq_is_anomaly'] == 1][['patient_id', 'nom', 'prenom', 'dq_anomaly_type']]
|
|
|
|
|
|
|
| 673 |
anomalies_csv = anomalies_df.to_csv(index=False).encode('utf-8')
|
| 674 |
+
st.download_button(label="📥 Télécharger Anomalies Patients (CSV)", data=anomalies_csv, file_name=f'anomalies_pat_{datetime.now().strftime("%Y%m%d")}.csv', mime='text/csv')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 675 |
|
|
|
|
| 676 |
if __name__ == "__main__":
|
| 677 |
show_dq_dashboard()
|