Mise à jour de l'application Geodechets

model_paths/model_ols_Déblais_gravats.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e12a722cf964db3e110a6cdb86bc0b0a0061f0cb347c9b7996080a437b771f
+size 1178661

model_paths/model_ols_Déchets_verts.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273d5f0172243a494b2115e6bf7fa3e04d153a0dc83c2fc2f55b838490924517
+size 1178659

model_paths/model_ols_Encombrants.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f294743fd864c5f71b45bfe4b18d561a0ab4211224004c834100735e05372a3
+size 1178656

model_paths/model_ols_Matériaux_recyclables.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9940a9ee9a3aa6548bf33d1d1e27ad2db7ebbe5b893438d72d13eb17c8fc6495
+size 1178667

model_paths/model_ols_Total_autres_dechets.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daaed3339dfbe9c3ab4a2ece88b693f1d3626471a2b9269c364ec37984c9ebe8
+size 1178665

requirements.txt

@@ -1,3 +1,14 @@
+
 altair
 pandas
-streamlit
+streamlit
+matplotlib
+numpy
+openpyxl
+statsmodels
+requests
+boto3
+shap
+langchain
+langchain-mistralai
+python-dotenv

src/streamlit_app.py

@@ -1,40 +1,210 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+# import altair as alt
+# import numpy as np
+# import pandas as pd
+# import streamlit as st
+
+# """
+# # Welcome to Streamlit!
+
+# Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
+# If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
+# forums](https://discuss.streamlit.io).
+
+# In the meantime, below is an example of what you can do with just a few lines of code:
+# """
+
+# num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
+# num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+
+# indices = np.linspace(0, 1, num_points)
+# theta = 2 * np.pi * num_turns * indices
+# radius = indices
+
+# x = radius * np.cos(theta)
+# y = radius * np.sin(theta)
+
+# df = pd.DataFrame({
+#     "x": x,
+#     "y": y,
+#     "idx": indices,
+#     "rand": np.random.randn(num_points),
+# })
+
+# st.altair_chart(alt.Chart(df, height=700, width=700)
+#     .mark_point(filled=True)
+#     .encode(
+#         x=alt.X("x", axis=None),
+#         y=alt.Y("y", axis=None),
+#         color=alt.Color("idx", legend=None, scale=alt.Scale()),
+#         size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
+#     ))
+# Import des bibliothéques
 import streamlit as st
+import pandas as pd
+import pickle
+import matplotlib.pyplot as plt
+from dotenv import load_dotenv
+import os
+
+import numpy as np
+import shap
+from sklearn.linear_model import LinearRegression
+from langchain_mistralai import ChatMistralAI
+from langchain_core.output_parsers import StrOutputParser
+
+# Chargement des données
+df = pd.read_csv("https://geodechet.s3.eu-west-3.amazonaws.com/v1/dataset/df_dummies_2019.csv").drop(columns=["Unnamed: 0"], errors="ignore")
+observed_df = pd.read_excel("https://geodechet.s3.eu-west-3.amazonaws.com/v1/dataset/data_wip_v5.xlsx")
+
+# liste des départements présents dans les colonnes du df, sans le préfixe "Département_".
+departements = [col.replace("Département_", "") for col in df.columns if col.startswith("Département_")]
+
+# Mise en page
+st.set_page_config(layout="wide")
+st.markdown("<h1 style='text-align: center;'>♻️ Simulateur de production de déchets par département</h1>", unsafe_allow_html=True)
+
+# Titre + Choix département alignés
+top_col1, top_col2 = st.columns([1, 2])
+with top_col1:
+    st.markdown("<h3 style='text-align: center;'>📍 Choix du département</h3>", unsafe_allow_html=True)
+with top_col2:
+    st.markdown("<h3 style='text-align: center;'>📈 Comparaison entre valeurs observées et prédites</h3>", unsafe_allow_html=True)
+
+# Séparation en colonnes
+top_input_col, chart_col = st.columns([1, 2])
+
+with top_input_col:
+    selected_dept = st.selectbox("Sélectionner un département", sorted(departements), index=sorted(departements).index("Ain") if "Ain" in departements else 0)
+    row_default = df[df[f"Département_{selected_dept}"] == 1].iloc[0]
+    default_dict = row_default.to_dict()
+
+    st.subheader("⚙️ Paramètres modifiables")
+    form_input = {}
+
+    categories = {
+        "📊 Population": [
+            "densité", , "pop_globale",
+            "tranche_age_0-24", "tranche_age_25-59", "tranche_age_60+",
+            "csp1_agriculteurs", "csp2_artisans_commerçant_chef_entreprises",
+            "csp3_cadres_professions_intellectuelles", "csp4_professions_intermédiaires",
+            "csp5_employés", "csp6_ouvriers", "csp7_retraités", "csp8_sans_activité"
+        ],
+        "🏭 Activité économique": [
+            "nb_salaries_secteur_agricole", "nb_salaries_secteur_industrie", "nb_salaries_secteur_service",
+            "nbre_entreprises", "nbre_entreprises_agricole", "nbre_entreprises_industrie", "nbre_entreprises_service"
+        ],
+        "🗑️ Déchets": [
+            "tonnage_dechet_produit",
+            "Total_autres_dechets",
+            "Déblais_gravats",
+            "Déchets_verts",
+            "Encombrants",
+            "Matériaux_recyclables"
+        ]
+    }
+
+    for category_name, variables in categories.items():
+        with st.expander(category_name, expanded=True):
+            for var in variables:
+                if var in default_dict:
+                    col_slider, col_input = st.columns([2, 1])
+                    with col_slider:
+                        slider_value = st.slider(
+                            f"🔧 {var}",
+                            min_value=float(default_dict[var]) * 0,
+                            max_value=float(default_dict[var]) * 1.5,
+                            value=float(default_dict[var]),
+                            step=1.0,
+                            key=f"slider_{var}"
+                        )
+                    with col_input:
+                        text_val = st.text_input(f"{var} (manuel)", value=str(slider_value), key=f"text_{var}")
+                        try:
+                            form_input[var] = float(text_val)
+                        except ValueError:
+                            form_input[var] = slider_value
+
+    input_df = pd.DataFrame([form_input])
+    input_df_complete = row_default.to_frame().T.copy()
+    for col in input_df.columns:
+        if col in input_df_complete.columns:
+            input_df_complete.at[input_df_complete.index[0], col] = input_df.at[0, col]
+
+with chart_col:
+    st.markdown("<div style='margin-top: 30px;'></div>", unsafe_allow_html=True)
+
+    btn_col = st.columns([3, 2, 3])[1]
+    with btn_col:
+        run_eval = st.button("🔍 Lancer l'évaluation")
+
+    st.markdown("<div style='margin-top: 40px;'></div>", unsafe_allow_html=True)
+
+    model_paths = {
+            "Déblais et Gravats": "src/model_paths/Déblais_gravats.pkl",
+            "Déchets verts": "src/model_paths/Déchets_verts.pkl",
+            "Encombrants": "src/model_paths/Encombrants.pkl",
+            "Matériaux recyclables": "src/model_paths/Matériaux_recyclables.pkl",
+            "Total autres déchets": "src/model_paths/Total_autres_dechets.pkl"
+        }
+
+    col_mapping = {
+        "Déblais et Gravats": "Déblais_gravats",
+        "Déchets verts": "Déchets_verts",
+        "Encombrants": "Encombrants",
+        "Matériaux recyclables": "Matériaux_recyclables",
+        "Total autres déchets": "Total_autres_dechets"
+    }
+
+    valeurs_observees = []
+    valeurs_predites = []
+    labels = []
+
+    if run_eval:
+        for typologie, path in model_paths.items():
+            try:
+                with open(path, "rb") as f:
+                    model = pickle.load(f)
+
+                expected_cols = model.model.exog_names
+                if "const" in expected_cols and "const" not in input_df_complete.columns:
+                    input_df_complete["const"] = 1.0
+
+                prediction = max(0, model.predict(input_df_complete[expected_cols]).iloc[0])
+                valeurs_predites.append(prediction)
+                labels.append(typologie)
+
+                filtered = observed_df[
+                    (observed_df["Département"] == selected_dept) & (observed_df["année"] == 2019)
+                ]
+
+                excel_col = col_mapping.get(typologie)
+                if not filtered.empty and excel_col in filtered.columns:
+                    valeurs_observees.append(filtered[excel_col].values[0])
+                else:
+                    valeurs_observees.append(0.0)
+            except Exception as e:
+                st.error(f"Erreur avec le modèle {typologie}")
+                st.exception(e)
+
+    if valeurs_observees and valeurs_predites:
+        x = np.arange(len(labels))
+        width = 0.4
+        fig, ax = plt.subplots(figsize=(10, 6))
+
+        bars1 = ax.bar(x - width / 2, valeurs_observees, width, label='Observé (2019)', color='steelblue')
+        bar_colors = [(1, 0, 0, 0.6) if pred > obs else (0, 0.6, 0, 0.6)
+                      for pred, obs in zip(valeurs_predites, valeurs_observees)]
+        bars2 = ax.bar(x + width / 2, valeurs_predites, width, label='Prévision', color=bar_colors)
+
+        for i in range(len(labels)):
+            ax.text(x[i] - width / 2, valeurs_observees[i] + max(valeurs_observees) * 0.01, f"{valeurs_observees[i]:,.0f}",
+                    ha='center', va='bottom', fontsize=9)
+            ax.text(x[i] + width / 2, valeurs_predites[i] + max(valeurs_predites) * 0.01, f"{valeurs_predites[i]:,.0f}",
+                    ha='center', va='bottom', fontsize=9)
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+        ax.set_ylabel("Tonnes")
+        ax.set_title("Comparaison Observé vs Prédit")
+        ax.set_xticks(x)
+        ax.set_xticklabels(labels, rotation=45, ha='right')
+        ax.legend()
+        st.pyplot(fig)