Exploration des relations binaires
|
Before Width: | Height: | Size: 117 KiB After Width: | Height: | Size: 117 KiB |
|
Before Width: | Height: | Size: 112 KiB |
|
Before Width: | Height: | Size: 116 KiB After Width: | Height: | Size: 119 KiB |
|
Before Width: | Height: | Size: 114 KiB |
|
Before Width: | Height: | Size: 497 KiB |
|
Before Width: | Height: | Size: 432 KiB |
|
Before Width: | Height: | Size: 83 KiB |
|
Before Width: | Height: | Size: 610 KiB |
|
Before Width: | Height: | Size: 587 KiB |
|
Before Width: | Height: | Size: 379 KiB |
|
Before Width: | Height: | Size: 235 KiB |
|
Before Width: | Height: | Size: 364 KiB |
|
Before Width: | Height: | Size: 351 KiB |
|
Before Width: | Height: | Size: 390 KiB |
|
Before Width: | Height: | Size: 102 KiB |
|
Before Width: | Height: | Size: 505 KiB |
|
Before Width: | Height: | Size: 479 KiB |
|
Before Width: | Height: | Size: 325 KiB |
|
Before Width: | Height: | Size: 88 KiB |
|
Before Width: | Height: | Size: 111 KiB |
|
Before Width: | Height: | Size: 108 KiB |
|
Before Width: | Height: | Size: 97 KiB |
|
Before Width: | Height: | Size: 445 KiB |
|
Before Width: | Height: | Size: 430 KiB |
|
Before Width: | Height: | Size: 363 KiB |
|
Before Width: | Height: | Size: 92 KiB |
|
Before Width: | Height: | Size: 512 KiB |
|
Before Width: | Height: | Size: 471 KiB |
|
Before Width: | Height: | Size: 340 KiB |
|
Before Width: | Height: | Size: 574 KiB |
|
Before Width: | Height: | Size: 403 KiB |
|
Before Width: | Height: | Size: 201 KiB |
@@ -60,74 +60,18 @@ python "docs/04 - Corrélations binaires/scripts/plot_pairwise_time_series.py"
|
||||
|
||||
|
||||
|
||||
## Nuages de points
|
||||
|
||||
```shell
|
||||
python "docs/04 - Corrélations binaires/scripts/plot_all_pairwise_scatter.py"
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Matrices de corrélation (instantané, signé)
|
||||
|
||||
Le calcul des coefficients de Pearson et de Spearman peut nous donner une indication numérique des corrélations entre les différentes variables.
|
||||
Cette information peut nous aiguiller sur des relations spécifiques (ou au contraire, nous induire en erreur...).
|
||||
|
||||
```shell
|
||||
python "docs/04 - Corrélations binaires/scripts/plot_correlation_heatmap.py" --transform absolute --upper-only
|
||||
python "docs/04 - Corrélations binaires/scripts/plot_correlation_heatmap.py" --transform=identity --upper-only
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Le signe et l'intensité des coefficients montrent à quel point deux variables bougent ensemble au même instant (co-mouvement linéaire pour Pearson, monotone pour Spearman).
|
||||
Cette matrice sert donc surtout de carte globale : repérer rapidement les couples très corrélés ou indiquer un lien physique évident, mettre en alerte des variables à forte corrélation qui pourraient masquer d'autres effets (saisonnalité, cycle jour/nuit), et choisir quelles paires méritent qu'on teste des décalages temporels ou des relations non linéaires dans la suite.
|
||||
|
||||
@@ -1,52 +0,0 @@
|
||||
# scripts/plot_all_pairwise_scatter.py
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
import sys
|
||||
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parents[3]
|
||||
if str(PROJECT_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from meteo.dataset import load_raw_csv
|
||||
from meteo.variables import iter_variable_pairs
|
||||
from meteo.plots import plot_scatter_pair
|
||||
|
||||
|
||||
CSV_PATH = Path("data/weather_minutely.csv")
|
||||
DOC_DIR = Path(__file__).resolve().parent.parent
|
||||
OUTPUT_DIR = DOC_DIR / "figures" / "pairwise_scatter"
|
||||
|
||||
|
||||
def main() -> None:
|
||||
if not CSV_PATH.exists():
|
||||
print(f"⚠ Fichier introuvable : {CSV_PATH}")
|
||||
return
|
||||
|
||||
df = load_raw_csv(CSV_PATH)
|
||||
print(f"Dataset minuté chargé : {CSV_PATH}")
|
||||
print(f" Lignes : {len(df)}")
|
||||
print(f" Colonnes : {list(df.columns)}")
|
||||
|
||||
pairs = iter_variable_pairs()
|
||||
print(f"Nombre de paires de variables : {len(pairs)}")
|
||||
|
||||
for var_x, var_y in pairs:
|
||||
filename = f"scatter_{var_x.key}_vs_{var_y.key}.png"
|
||||
output_path = OUTPUT_DIR / filename
|
||||
|
||||
print(f"→ Trace {var_y.key} en fonction de {var_x.key} → {output_path}")
|
||||
plot_scatter_pair(
|
||||
df=df,
|
||||
var_x=var_x,
|
||||
var_y=var_y,
|
||||
output_path=output_path,
|
||||
sample_step=10, # un point sur 10 : ≈ 32k points au lieu de 320k
|
||||
)
|
||||
|
||||
print("✔ Tous les graphiques de nuages de points ont été générés.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||