pyreverte/luce
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

final commit

Browse Source
This commit is contained in:
Pierre-Yves REVERTE
2026-06-19 11:15:39 +02:00
parent e2b1b20913
commit d095840037
975 changed files with 1232523 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
2025_07_23/data.xlsx
BIN
View File
Binary file not shown.
2025_07_23/main.py
+116
View File
@@ -0,0 +1,116 @@
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from scipy.interpolate import make_interp_spline, BSpline
# === Chargement des données ===
chemin_fichier = "data.xlsx"
df = pd.read_excel(chemin_fichier)
# === Filtrer les sources ===
df = df[df["type"].str.lower() == "source"]
df = df.dropna(subset=["c25°C ", "Nom"])
# === Couleurs par source ===
couleurs_sources = {
"Bullac": "#D77D00",
"Corn": "#A1C935",
"Bual": "#F5D200",
"La diège": "#9271EA",
"Ayrissac": "#EB64C3",
"Pito": "#D52117",
"Ressel": "#1DC6C3",
"Marchepied": "#3FB94D",
"Anglades": "#0084C9",
"Liauzu": "#431D84",
"Pescalerie": "#D8676B",
"Sagne": "tab:purple",
}
# === Calcul des fréquences normalisées ===
freq_absolue = df.groupby(["Nom", "c25°C "]).size().reset_index(name="frequence")
freq_totale = freq_absolue.groupby("Nom")["frequence"].transform("sum")
freq_absolue["frequence_normalisee"] = freq_absolue["frequence"] / freq_totale
# === Sources à afficher dans l'ordre souhaité ===
noms_ordonnes = [
"Sagne", "Ressel", "Pito", "Pescalerie", "Marchepied",
"Liauzu", "La diège", "Corn", "Bullac", "Bual", "Ayrissac", "Anglades"
]
sources_disponibles = set(freq_absolue["Nom"].unique())
noms_valides = [nom for nom in noms_ordonnes if nom in sources_disponibles]
# === Graphique 3D ===
fig = plt.figure(figsize=(20, 12))
ax = fig.add_subplot(111, projection='3d')
y_spacing = 4.0
for idx, nom in enumerate(reversed(noms_valides)):
df_nom = freq_absolue[freq_absolue["Nom"] == nom].sort_values("c25°C ")
if df_nom.empty:
continue
xs = df_nom["c25°C "].to_numpy()
ys = df_nom["frequence_normalisee"].to_numpy()
color = couleurs_sources.get(nom, "gray")
y_val = (len(noms_valides) - 1 - idx) * y_spacing
# === Courbe type histogramme ===
x_curve = []
y_curve = []
for i in range(len(xs)):
x_curve.extend([xs[i] - 0.5, xs[i], xs[i] + 0.5])
y_curve.extend([0, ys[i], 0])
# Relier à la suivante si proche
if i < len(xs) - 1 and xs[i + 1] - xs[i] <= 1.5:
x_curve.extend([xs[i] + 0.5, xs[i + 1] - 0.5])
y_curve.extend([0, 0])
# X_Y_Spline = make_interp_spline(x_curve, y_curve)
# X_ = np.linspace(x_curve.min(), x_curve.max(), 500)
# Y_ = X_Y_Spline(X_)
# ax.plot(X_, [y_val] * len(Y_), Y_, color=color, linewidth=2, alpha=0.8)
res = {key: value for key, value in zip(x_curve, y_curve)}
x_curve = list(res.keys())
y_curve = list(res.values())
# Interpolation pour lisser la courbe
spline = make_interp_spline(x_curve, y_curve, k=1)
x_curve = np.linspace(min(x_curve), max(x_curve), 100)
y_curve = spline(x_curve)
ax.plot(x_curve, [y_val] * len(x_curve), y_curve, color=color, linewidth=2, alpha=0.8)
# Nom de la source à gauche
ax.text(
x=freq_absolue["c25°C "].min() - 30,
y=y_val,
z=0,
s=nom,
color=color,
fontsize=10,
ha='right',
va='center'
)
# === Configuration du graphique ===
ax.set_yticks([])
ax.set_xlabel("Conductivité (c25°C, µS/cm)", labelpad=15)
ax.set_ylabel("")
ax.set_zlabel("Fréquence normalisée", labelpad=10)
ax.set_title("Courbes 3D type histogrammes par source", pad=20)
ax.set_xlim(freq_absolue["c25°C "].min() - 35, freq_absolue["c25°C "].max() + 10)
ax.set_ylim(-y_spacing, len(noms_valides) * y_spacing)
ax.set_zlim(0, 0.4)
ax.view_init(elev=25, azim=-140)
# ax.autoscale()
plt.tight_layout()
plt.show()
2025_07_23/main2.py
+140
View File
@@ -0,0 +1,140 @@
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from scipy.interpolate import make_interp_spline
from sklearn.cluster import DBSCAN
# === Chargement des données ===
chemin_fichier = "data.xlsx"
df = pd.read_excel(chemin_fichier)
# === Filtrer les sources ===
df = df[df["type"].str.lower() == "source"]
df = df.dropna(subset=["c25°C ", "Nom"])
# === Couleurs par source ===
couleurs_sources = {
"Bullac": "#D77D00",
"Corn": "#A1C935",
"Bual": "#F5D200",
"La diège": "#9271EA",
"Ayrissac": "#EB64C3",
"Pito": "#D52117",
"Ressel": "#1DC6C3",
"Marchepied": "#3FB94D",
"Anglades": "#0084C9",
"Liauzu": "#431D84",
"Pescalerie": "#D8676B",
"Sagne": "tab:purple",
}
# === Paramètres DBSCAN ===
eps_val = 5
min_samples_val = 1
# === Clustering dynamique par source ===
clusters_data = []
for nom in df["Nom"].unique():
sub_df = df[df["Nom"] == nom].copy()
X = sub_df[["c25°C "]].to_numpy()
db = DBSCAN(eps=eps_val, min_samples=min_samples_val).fit(X)
sub_df["cluster"] = db.labels_
grouped = (
sub_df.groupby("cluster")
.agg(
conductivite_min=("c25°C ", "min"),
conductivite_max=("c25°C ", "max"),
conductivite_moyenne=("c25°C ", "mean"),
effectif=("c25°C ", "count")
)
.reset_index(drop=True)
)
grouped["frequence_normalisee"] = grouped["effectif"] / grouped["effectif"].sum()
grouped["Nom"] = nom
clusters_data.append(grouped)
# === Fusion des résultats ===
df_clusters = pd.concat(clusters_data, ignore_index=True)
# === Ordre des sources ===
noms_ordonnes = [
"Sagne", "Ressel", "Pito", "Pescalerie", "Marchepied",
"Liauzu", "La diège", "Corn", "Bullac", "Bual", "Ayrissac", "Anglades"
]
sources_disponibles = set(df_clusters["Nom"].unique())
noms_valides = [nom for nom in noms_ordonnes if nom in sources_disponibles]
# === Tracé du graphique 3D ===
fig = plt.figure(figsize=(20, 12))
ax = fig.add_subplot(111, projection='3d')
y_spacing = 4.0
for idx, nom in enumerate(reversed(noms_valides)):
df_nom = df_clusters[df_clusters["Nom"] == nom].sort_values("conductivite_moyenne")
if df_nom.empty:
continue
xs_min = df_nom["conductivite_min"].to_numpy()
xs_max = df_nom["conductivite_max"].to_numpy()
xs_center = df_nom["conductivite_moyenne"].to_numpy()
ys = df_nom["frequence_normalisee"].to_numpy()
color = couleurs_sources.get(nom, "gray")
y_val = (len(noms_valides) - 1 - idx) * y_spacing
x_curve = []
y_curve = []
for i in range(len(xs_center)):
# Pic trapézoïdal
x_curve.extend([xs_min[i], xs_center[i], xs_max[i]])
y_curve.extend([0, ys[i], 0])
# Relier à la suivante si les clusters sont très proches
if i < len(xs_center) - 1 and xs_min[i + 1] - xs_max[i] <= 1.5:
x_curve.extend([xs_max[i], xs_min[i + 1]])
y_curve.extend([0, 0])
# Ajout d'un point d’ancrage à gauche (252 µS/cm) à z=0
x_curve = [525] + x_curve
y_curve = [0] + y_curve
# Ajouter un point final à la courbe à droite (limite max de l'axe X)
xlim_max = df_clusters["conductivite_max"].max() + 10
x_curve.append(xlim_max)
y_curve.append(0)
# Tracé 3D
ax.plot(x_curve, [y_val] * len(x_curve), y_curve, color=color, linewidth=2, alpha=0.8)
# Affichage du nom de la source
ax.text(
x=df_clusters["conductivite_moyenne"].min() - 30,
y=y_val,
z=0,
s=nom,
color=color,
fontsize=10,
ha='right',
va='center'
)
# === Configuration finale du graphique ===
ax.set_yticks([])
ax.set_xlabel("Conductivité (c25°C, µS/cm)", labelpad=15)
ax.set_ylabel("")
ax.set_zlabel("Fréquence normalisée", labelpad=10)
ax.set_title("Courbes 3D type histogrammes par source (pics trapézoïdaux DBSCAN)", pad=20)
ax.set_xlim(525, df_clusters["conductivite_max"].max() + 10)
ax.set_ylim(-y_spacing, len(noms_valides) * y_spacing)
ax.set_zlim(0, 1)
ax.view_init(elev=10, azim=-120)
plt.tight_layout()
plt.show()
2025_07_23/requirements.txt
+7
View File
@@ -0,0 +1,7 @@
pandas==2.3.1
numpy==2.3.1
matplotlib==3.10.3
mpl-tools==0.4.1
openpyxl==3.1.5
scipy==1.16.0
scikit-learn==1.7.1