Spaces:
Sleeping
Sleeping
Update src/module/Data_Exploration.py
Browse files- src/module/Data_Exploration.py +380 -0
src/module/Data_Exploration.py
CHANGED
|
@@ -0,0 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
MODULE DATA EXPLORATION - VORTEX SYSTEM
|
| 3 |
+
========================================
|
| 4 |
+
Responsabilité : Analyse exploratoire des données (EDA) avec Google Sheets
|
| 5 |
+
"""
|
| 6 |
+
import pandas as pd
|
| 7 |
+
import numpy as np
|
| 8 |
+
import streamlit as st
|
| 9 |
+
import plotly.express as px
|
| 10 |
+
import plotly.graph_objects as go
|
| 11 |
+
from plotly.subplots import make_subplots
|
| 12 |
+
import gspread
|
| 13 |
+
from datetime import datetime
|
| 14 |
+
import json
|
| 15 |
+
|
| 16 |
+
class DataExplorer:
|
| 17 |
+
"""Classe pour l'exploration et l'analyse des données hospitalières"""
|
| 18 |
+
|
| 19 |
+
def __init__(self, gspread_client, sheet_name="bdd_mvp_faker"):
|
| 20 |
+
"""
|
| 21 |
+
Initialise l'explorateur de données
|
| 22 |
+
|
| 23 |
+
Args:
|
| 24 |
+
gspread_client: Client gspread authentifié
|
| 25 |
+
sheet_name: Nom du fichier Google Sheets
|
| 26 |
+
"""
|
| 27 |
+
self.client = gspread_client
|
| 28 |
+
self.sheet_name = sheet_name
|
| 29 |
+
self.dataframes = {}
|
| 30 |
+
self.kpis = {}
|
| 31 |
+
|
| 32 |
+
def load_all_sheets(self):
|
| 33 |
+
"""Charge tous les onglets du fichier Google Sheets"""
|
| 34 |
+
try:
|
| 35 |
+
spreadsheet = self.client.open(self.sheet_name)
|
| 36 |
+
sheet_names = [worksheet.title for worksheet in spreadsheet.worksheets()]
|
| 37 |
+
|
| 38 |
+
st.info(f"📊 Onglets détectés : {', '.join(sheet_names)}")
|
| 39 |
+
|
| 40 |
+
for sheet_name in sheet_names:
|
| 41 |
+
worksheet = spreadsheet.worksheet(sheet_name)
|
| 42 |
+
data = worksheet.get_all_records()
|
| 43 |
+
|
| 44 |
+
if data:
|
| 45 |
+
# Standardisation du nom pour le dictionnaire
|
| 46 |
+
standardized_name = sheet_name.lower().replace('é', 'e').replace(' ', '_')
|
| 47 |
+
self.dataframes[standardized_name] = pd.DataFrame(data)
|
| 48 |
+
st.success(f"✅ {sheet_name} chargé ({len(data)} lignes)")
|
| 49 |
+
else:
|
| 50 |
+
st.warning(f"⚠️ {sheet_name} est vide")
|
| 51 |
+
|
| 52 |
+
return True
|
| 53 |
+
|
| 54 |
+
except Exception as e:
|
| 55 |
+
st.error(f"❌ Erreur lors du chargement : {e}")
|
| 56 |
+
return False
|
| 57 |
+
|
| 58 |
+
def get_dataframe(self, sheet_key):
|
| 59 |
+
"""Récupère un DataFrame spécifique par son nom standardisé"""
|
| 60 |
+
return self.dataframes.get(sheet_key)
|
| 61 |
+
|
| 62 |
+
def show_data_overview(self):
|
| 63 |
+
"""Affiche un aperçu général des données"""
|
| 64 |
+
st.markdown("### 📋 Aperçu Général des Données")
|
| 65 |
+
|
| 66 |
+
if not self.dataframes:
|
| 67 |
+
st.warning("⚠️ Aucune donnée chargée. Veuillez d'abord charger les données.")
|
| 68 |
+
return
|
| 69 |
+
|
| 70 |
+
# Tableau récapitulatif
|
| 71 |
+
overview_data = []
|
| 72 |
+
for name, df in self.dataframes.items():
|
| 73 |
+
overview_data.append({
|
| 74 |
+
"Onglet": name,
|
| 75 |
+
"Lignes": len(df),
|
| 76 |
+
"Colonnes": len(df.columns),
|
| 77 |
+
"Mémoire (KB)": round(df.memory_usage(deep=True).sum() / 1024, 2),
|
| 78 |
+
"Valeurs manquantes": df.isnull().sum().sum()
|
| 79 |
+
})
|
| 80 |
+
|
| 81 |
+
overview_df = pd.DataFrame(overview_data)
|
| 82 |
+
st.dataframe(overview_df, use_container_width=True)
|
| 83 |
+
|
| 84 |
+
def show_detailed_inspection(self, sheet_key):
|
| 85 |
+
"""Affiche une inspection détaillée d'un DataFrame spécifique"""
|
| 86 |
+
df = self.get_dataframe(sheet_key)
|
| 87 |
+
|
| 88 |
+
if df is None:
|
| 89 |
+
st.error(f"❌ Onglet '{sheet_key}' non trouvé")
|
| 90 |
+
return
|
| 91 |
+
|
| 92 |
+
st.markdown(f"### 🔍 Inspection Détaillée : `{sheet_key}`")
|
| 93 |
+
|
| 94 |
+
# Onglets d'inspection
|
| 95 |
+
tab1, tab2, tab3, tab4 = st.tabs(["📊 Aperçu", "📈 Statistiques", "🔎 Qualité", "🧹 Colonnes"])
|
| 96 |
+
|
| 97 |
+
with tab1:
|
| 98 |
+
st.markdown("#### Premières lignes")
|
| 99 |
+
st.dataframe(df.head(10), use_container_width=True)
|
| 100 |
+
|
| 101 |
+
st.markdown("#### Dernières lignes")
|
| 102 |
+
st.dataframe(df.tail(5), use_container_width=True)
|
| 103 |
+
|
| 104 |
+
with tab2:
|
| 105 |
+
st.markdown("#### Statistiques Descriptives")
|
| 106 |
+
st.dataframe(df.describe(include='all').T, use_container_width=True)
|
| 107 |
+
|
| 108 |
+
st.markdown("#### Types de Données")
|
| 109 |
+
types_df = pd.DataFrame({
|
| 110 |
+
'Colonne': df.columns,
|
| 111 |
+
'Type': df.dtypes.values,
|
| 112 |
+
'Non-Null': df.count().values,
|
| 113 |
+
'Null': df.isnull().sum().values
|
| 114 |
+
})
|
| 115 |
+
st.dataframe(types_df, use_container_width=True)
|
| 116 |
+
|
| 117 |
+
with tab3:
|
| 118 |
+
st.markdown("#### Analyse de Qualité")
|
| 119 |
+
|
| 120 |
+
# Valeurs manquantes
|
| 121 |
+
missing_data = df.isnull().sum()
|
| 122 |
+
missing_percent = (missing_data / len(df)) * 100
|
| 123 |
+
|
| 124 |
+
quality_df = pd.DataFrame({
|
| 125 |
+
'Colonne': missing_data.index,
|
| 126 |
+
'Valeurs Manquantes': missing_data.values,
|
| 127 |
+
'Pourcentage (%)': missing_percent.values.round(2)
|
| 128 |
+
})
|
| 129 |
+
quality_df = quality_df[quality_df['Valeurs Manquantes'] > 0].sort_values('Valeurs Manquantes', ascending=False)
|
| 130 |
+
|
| 131 |
+
if not quality_df.empty:
|
| 132 |
+
st.dataframe(quality_df, use_container_width=True)
|
| 133 |
+
|
| 134 |
+
# Graphique
|
| 135 |
+
fig = px.bar(quality_df, x='Colonne', y='Pourcentage (%)',
|
| 136 |
+
title='Pourcentage de Valeurs Manquantes par Colonne',
|
| 137 |
+
color='Pourcentage (%)',
|
| 138 |
+
color_continuous_scale='Reds')
|
| 139 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 140 |
+
else:
|
| 141 |
+
st.success("✅ Aucune valeur manquante détectée !")
|
| 142 |
+
|
| 143 |
+
# Doublons
|
| 144 |
+
duplicates = df.duplicated().sum()
|
| 145 |
+
st.metric("Lignes Dupliquées", duplicates)
|
| 146 |
+
|
| 147 |
+
with tab4:
|
| 148 |
+
st.markdown("#### Liste des Colonnes")
|
| 149 |
+
cols_info = []
|
| 150 |
+
for col in df.columns:
|
| 151 |
+
unique_count = df[col].nunique()
|
| 152 |
+
cols_info.append({
|
| 153 |
+
'Colonne': col,
|
| 154 |
+
'Type': str(df[col].dtype),
|
| 155 |
+
'Valeurs Uniques': unique_count,
|
| 156 |
+
'Exemple': str(df[col].iloc[0]) if len(df) > 0 else 'N/A'
|
| 157 |
+
})
|
| 158 |
+
|
| 159 |
+
st.dataframe(pd.DataFrame(cols_info), use_container_width=True)
|
| 160 |
+
|
| 161 |
+
def analyze_patients(self):
|
| 162 |
+
"""Analyse spécifique des patients"""
|
| 163 |
+
df_patients = self.get_dataframe('patients')
|
| 164 |
+
|
| 165 |
+
if df_patients is None:
|
| 166 |
+
st.warning("⚠️ Onglet 'patients' non disponible")
|
| 167 |
+
return
|
| 168 |
+
|
| 169 |
+
st.markdown("### 👥 Analyse Démographique des Patients")
|
| 170 |
+
|
| 171 |
+
col1, col2, col3 = st.columns(3)
|
| 172 |
+
|
| 173 |
+
with col1:
|
| 174 |
+
total_patients = len(df_patients)
|
| 175 |
+
st.metric("Total Patients", f"{total_patients:,}")
|
| 176 |
+
|
| 177 |
+
with col2:
|
| 178 |
+
if 'age' in df_patients.columns:
|
| 179 |
+
avg_age = df_patients['age'].mean()
|
| 180 |
+
st.metric("Âge Moyen", f"{avg_age:.1f} ans")
|
| 181 |
+
|
| 182 |
+
with col3:
|
| 183 |
+
if 'sexe' in df_patients.columns:
|
| 184 |
+
gender_dist = df_patients['sexe'].value_counts()
|
| 185 |
+
st.metric("Répartition H/F", f"{gender_dist.get('M', 0)}/{gender_dist.get('F', 0)}")
|
| 186 |
+
|
| 187 |
+
# Pyramide des âges
|
| 188 |
+
if 'age' in df_patients.columns:
|
| 189 |
+
st.markdown("#### 📊 Pyramide des Âges")
|
| 190 |
+
|
| 191 |
+
# Détection des outliers
|
| 192 |
+
q1 = df_patients['age'].quantile(0.25)
|
| 193 |
+
q3 = df_patients['age'].quantile(0.75)
|
| 194 |
+
iqr = q3 - q1
|
| 195 |
+
outlier_threshold = q3 + 1.5 * iqr
|
| 196 |
+
|
| 197 |
+
outliers = df_patients[df_patients['age'] > outlier_threshold]
|
| 198 |
+
if not outliers.empty:
|
| 199 |
+
st.warning(f"⚠️ {len(outliers)} outliers détectés (âge > {outlier_threshold:.0f} ans)")
|
| 200 |
+
|
| 201 |
+
fig = px.histogram(df_patients, x='age', nbins=30,
|
| 202 |
+
title='Distribution des Âges',
|
| 203 |
+
labels={'age': 'Âge', 'count': 'Nombre de patients'},
|
| 204 |
+
color_discrete_sequence=['#58a6ff'])
|
| 205 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 206 |
+
|
| 207 |
+
# Répartition par sexe
|
| 208 |
+
if 'sexe' in df_patients.columns:
|
| 209 |
+
st.markdown("#### ⚥ Répartition par Sexe")
|
| 210 |
+
|
| 211 |
+
gender_counts = df_patients['sexe'].value_counts()
|
| 212 |
+
fig = px.pie(values=gender_counts.values, names=gender_counts.index,
|
| 213 |
+
title='Répartition Hommes/Femmes',
|
| 214 |
+
color_discrete_sequence=['#58a6ff', '#ff6b9d'])
|
| 215 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 216 |
+
|
| 217 |
+
def analyze_data_quality(self):
|
| 218 |
+
"""Analyse la qualité des données (colonnes dq_)"""
|
| 219 |
+
st.markdown("### 🔬 Audit de Qualité des Données")
|
| 220 |
+
|
| 221 |
+
dq_results = {}
|
| 222 |
+
|
| 223 |
+
for name, df in self.dataframes.items():
|
| 224 |
+
if 'dq_is_anomaly' in df.columns:
|
| 225 |
+
anomalies = df[df['dq_is_anomaly'] == 1]
|
| 226 |
+
|
| 227 |
+
dq_results[name] = {
|
| 228 |
+
"total_rows": len(df),
|
| 229 |
+
"anomaly_count": len(anomalies),
|
| 230 |
+
"anomaly_rate": (len(anomalies) / len(df) * 100) if len(df) > 0 else 0
|
| 231 |
+
}
|
| 232 |
+
|
| 233 |
+
if 'dq_anomaly_type' in df.columns and not anomalies.empty:
|
| 234 |
+
dq_results[name]["types"] = anomalies['dq_anomaly_type'].value_counts().to_dict()
|
| 235 |
+
|
| 236 |
+
if not dq_results:
|
| 237 |
+
st.info("ℹ️ Aucune colonne de qualité (dq_) détectée dans les données")
|
| 238 |
+
return
|
| 239 |
+
|
| 240 |
+
# Affichage des résultats
|
| 241 |
+
for sheet_name, results in dq_results.items():
|
| 242 |
+
with st.expander(f"📋 {sheet_name.upper()}", expanded=True):
|
| 243 |
+
col1, col2, col3 = st.columns(3)
|
| 244 |
+
|
| 245 |
+
with col1:
|
| 246 |
+
st.metric("Total Lignes", f"{results['total_rows']:,}")
|
| 247 |
+
with col2:
|
| 248 |
+
st.metric("Anomalies", results['anomaly_count'])
|
| 249 |
+
with col3:
|
| 250 |
+
st.metric("Taux d'Anomalies", f"{results['anomaly_rate']:.2f}%")
|
| 251 |
+
|
| 252 |
+
if "types" in results and results["types"]:
|
| 253 |
+
st.markdown("**Types d'Anomalies :**")
|
| 254 |
+
types_df = pd.DataFrame(list(results["types"].items()),
|
| 255 |
+
columns=['Type', 'Count'])
|
| 256 |
+
st.dataframe(types_df, use_container_width=True)
|
| 257 |
+
|
| 258 |
+
def calculate_kpis(self):
|
| 259 |
+
"""Calcule les KPIs par service"""
|
| 260 |
+
st.markdown("### 📊 Indicateurs de Performance (KPIs)")
|
| 261 |
+
|
| 262 |
+
# Exemple de KPIs - à adapter selon vos données réelles
|
| 263 |
+
kpis = {}
|
| 264 |
+
|
| 265 |
+
# KPI 1: Taux d'occupation
|
| 266 |
+
df_ressources = self.get_dataframe('ressources_jour')
|
| 267 |
+
if df_ressources is not None and 'lits_total' in df_ressources.columns:
|
| 268 |
+
total_lits = df_ressources['lits_total'].sum()
|
| 269 |
+
lits_occupes = df_ressources['lits_occupes'].sum() if 'lits_occupes' in df_ressources.columns else 0
|
| 270 |
+
kpis['taux_occupation'] = (lits_occupes / total_lits * 100) if total_lits > 0 else 0
|
| 271 |
+
|
| 272 |
+
# KPI 2: Durée moyenne de séjour
|
| 273 |
+
df_sejours = self.get_dataframe('sejours')
|
| 274 |
+
if df_sejours is not None and 'duree_sejour' in df_sejours.columns:
|
| 275 |
+
kpis['duree_moyenne_sejour'] = df_sejours['duree_sejour'].mean()
|
| 276 |
+
|
| 277 |
+
# KPI 3: Nombre de patients
|
| 278 |
+
df_patients = self.get_dataframe('patients')
|
| 279 |
+
if df_patients is not None:
|
| 280 |
+
kpis['total_patients'] = len(df_patients)
|
| 281 |
+
|
| 282 |
+
# Affichage
|
| 283 |
+
if kpis:
|
| 284 |
+
cols = st.columns(len(kpis))
|
| 285 |
+
for idx, (key, value) in enumerate(kpis.items()):
|
| 286 |
+
with cols[idx]:
|
| 287 |
+
st.metric(key.replace('_', ' ').title(), f"{value:.2f}")
|
| 288 |
+
|
| 289 |
+
# Export JSON
|
| 290 |
+
if st.button("💾 Exporter les KPIs (JSON)"):
|
| 291 |
+
kpis_json = json.dumps(kpis, indent=2)
|
| 292 |
+
st.download_button(
|
| 293 |
+
label="Télécharger KPIs.json",
|
| 294 |
+
data=kpis_json,
|
| 295 |
+
file_name=f"kpis_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
| 296 |
+
mime="application/json"
|
| 297 |
+
)
|
| 298 |
+
else:
|
| 299 |
+
st.info("ℹ️ Impossible de calculer les KPIs avec les données actuelles")
|
| 300 |
+
|
| 301 |
+
def show_stock_alerts(self):
|
| 302 |
+
"""Affiche les alertes de stock"""
|
| 303 |
+
df_stock = self.get_dataframe('materiel')
|
| 304 |
+
|
| 305 |
+
if df_stock is None:
|
| 306 |
+
st.warning("⚠️ Onglet 'materiel' non disponible")
|
| 307 |
+
return
|
| 308 |
+
|
| 309 |
+
st.markdown("### 🚨 Alertes Stock & Matériel")
|
| 310 |
+
|
| 311 |
+
if 'tension_stock' in df_stock.columns:
|
| 312 |
+
alerts = df_stock[df_stock['tension_stock'] > 0.8]
|
| 313 |
+
|
| 314 |
+
if not alerts.empty:
|
| 315 |
+
st.error(f"⚠️ {len(alerts)} alertes de tension de stock détectées !")
|
| 316 |
+
|
| 317 |
+
# Colonnes à afficher
|
| 318 |
+
display_cols = [col for col in ['date', 'service_code', 'materiel_code', 'tension_stock']
|
| 319 |
+
if col in alerts.columns]
|
| 320 |
+
st.dataframe(alerts[display_cols], use_container_width=True)
|
| 321 |
+
else:
|
| 322 |
+
st.success("✅ Aucune alerte de stock")
|
| 323 |
+
else:
|
| 324 |
+
st.info("ℹ️ Colonne 'tension_stock' non trouvée dans les données")
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
def show_terminal(gspread_client, sheet_name="bdd_mvp_faker"):
|
| 328 |
+
"""
|
| 329 |
+
Fonction principale à appeler depuis Streamlit pour afficher l'interface EDA
|
| 330 |
+
|
| 331 |
+
Args:
|
| 332 |
+
gspread_client: Client gspread authentifié
|
| 333 |
+
sheet_name: Nom du fichier Google Sheets
|
| 334 |
+
"""
|
| 335 |
+
st.markdown("## 🔬 EXPLORATEUR DE DONNÉES")
|
| 336 |
+
|
| 337 |
+
# Initialisation
|
| 338 |
+
if 'data_explorer' not in st.session_state:
|
| 339 |
+
st.session_state.data_explorer = DataExplorer(gspread_client, sheet_name)
|
| 340 |
+
|
| 341 |
+
explorer = st.session_state.data_explorer
|
| 342 |
+
|
| 343 |
+
# Bouton de chargement
|
| 344 |
+
if st.button("📥 Charger les Données", type="primary"):
|
| 345 |
+
with st.spinner("Chargement en cours..."):
|
| 346 |
+
success = explorer.load_all_sheets()
|
| 347 |
+
if success:
|
| 348 |
+
st.success("✅ Données chargées avec succès !")
|
| 349 |
+
|
| 350 |
+
# Menu d'analyse
|
| 351 |
+
if explorer.dataframes:
|
| 352 |
+
st.divider()
|
| 353 |
+
|
| 354 |
+
analysis_mode = st.selectbox(
|
| 355 |
+
"Mode d'Analyse",
|
| 356 |
+
["Aperçu Général", "Inspection Détaillée", "Analyse Patients",
|
| 357 |
+
"Qualité des Données", "KPIs", "Alertes Stock"]
|
| 358 |
+
)
|
| 359 |
+
|
| 360 |
+
if analysis_mode == "Aperçu Général":
|
| 361 |
+
explorer.show_data_overview()
|
| 362 |
+
|
| 363 |
+
elif analysis_mode == "Inspection Détaillée":
|
| 364 |
+
sheet_to_inspect = st.selectbox(
|
| 365 |
+
"Sélectionner un onglet",
|
| 366 |
+
list(explorer.dataframes.keys())
|
| 367 |
+
)
|
| 368 |
+
explorer.show_detailed_inspection(sheet_to_inspect)
|
| 369 |
+
|
| 370 |
+
elif analysis_mode == "Analyse Patients":
|
| 371 |
+
explorer.analyze_patients()
|
| 372 |
+
|
| 373 |
+
elif analysis_mode == "Qualité des Données":
|
| 374 |
+
explorer.analyze_data_quality()
|
| 375 |
+
|
| 376 |
+
elif analysis_mode == "KPIs":
|
| 377 |
+
explorer.calculate_kpis()
|
| 378 |
+
|
| 379 |
+
elif analysis_mode == "Alertes Stock":
|
| 380 |
+
explorer.show_stock_alerts()
|