^^

Dockerfile

@@ -22,6 +22,8 @@ COPY --chown=user data/ ./data/
 COPY --chown=user .streamlit/ ./.streamlit/
 COPY --chown=user src/ ./src/
 COPY --chown=user src/pages/1_Historical_Prices.py ./src/pages/1_Historical_Prices.py
+COPY --chown=user src/pages/2_Prediction_Prices.py ./src/pages/2_Prediction_Prices.py
+COPY --chown=user src/pages/3_Historical_Risk_Score_Fire.py ./src/pages/3_Historical_Risk_Score_Fire.py
 
 EXPOSE 8501
 

src/pages/1_Historical_Prices.py

@@ -172,19 +172,17 @@ top_departements_variation_display["prixm2moyen_2024"] = (
 top_departements_variation_display["prixm2moyen_difference"] = (
     top_departements_variation_display["prixm2moyen_difference"].map("{:,.0f}€".format)
 )
-top_departements_variation_display["variation_percentage"] = (
-    top_departements_variation_display["variation_percentage"].map("{:,.2f}%".format)
-)
-
 top_departements_variation_display = top_departements_variation_display.sort_values(
     by="variation_percentage", ascending=False
 )
 
 fig = px.bar(
-    top_departements_variation_display.sort_values(by="variation_percentage", ascending=True),
+    top_departements_variation_display.sort_values(
+        by="variation_percentage", ascending=True
+    ),
     x="nom_departement",
     y="variation_percentage",
-    title="Top Departments by Price Variation (2015-2024)",
+    title=f"Top Departments by Price Variation ({selected_year_1} to {selected_year_2})",
     labels={
         "nom_departement": "Department Name",
         "variation_percentage": "Price Variation (%)",
@@ -193,6 +191,10 @@ fig = px.bar(
 )
 st.plotly_chart(fig, use_container_width=True)
 
+top_departements_variation_display["variation_percentage"] = (
+    top_departements_variation_display["variation_percentage"].map("{:,.2f}%".format)
+)
+
 st.dataframe(
     top_departements_variation_display,
     hide_index=True,
@@ -323,6 +325,7 @@ with right_co:
             "Average Price per m²": {"formatter": "currency", "currency": "EUR"}
         },
     )
+
 ###############################################################################
 
 st.subheader("Select Department(s) to View Historical Prices", divider=True)
@@ -489,6 +492,7 @@ selected_year_communes = st.selectbox(
     options=dataset_housing_prices["annee"].unique(),
     format_func=lambda x: str(x),
     key="year_communes_selectbox",
+    index=list(dataset_housing_prices["annee"].unique()).index(2024) if 2024 in dataset_housing_prices["annee"].unique() else 0
 )
 
 top_communes = (

src/pages/2_Prediction_Prices.py

@@ -3,6 +3,7 @@ import pandas as pd
 import asyncio
 import plotly.express as px
 import geopandas as gpd
+from functools import reduce
 
 from pages.utils.utils import (
     async_load_file_s3,
@@ -56,15 +57,9 @@ def load_all_data_wrapper_predictions_prices_region():
 # --- Streamlit App Layout ---
 st.set_page_config(page_title="Oasis", page_icon=":house:", layout="wide")
 
-st.header("Historical Price - France")
-st.subheader("An overview of real estate prices in France from 2015 to 2024")
+###############################################################################
 
-st.write(
-    "This map shows the average price per square meter in French departments over the years, with a focus on climatic events."
-)
-
-# Display a table of the top 10 departments with the highest average price per square meter
-st.subheader("Top 10 Departments by Average Price per Square Meter (2015-2024)")
+st.header("Forecast Prices (2024-2029)")
 
 with st.spinner("Loading data and preparing maps..."):
     (
@@ -73,10 +68,170 @@ with st.spinner("Loading data and preparing maps..."):
         insee_df,
     ) = load_all_data_wrapper_predictions_prices_country()
 
+st.subheader("An overview of real estate forecasted prices in France", divider=True)
+
+st.write(
+    "This map shows the average price per square meter in French departments over the years, with a focus on climatic events."
+)
+
+fig_france = display_choropleth_map_country(
+    dataset_departements_housing_prices,
+    departements_geojson,
+    metric_name="prixm2moyen",
+    metric_description="Average Price per Square Meter",
+    title="Average Forecasted Price in French Departments",
+)
+st.plotly_chart(fig_france, use_container_width=False)
+st.write(
+    "Missing values are represented in light grey, while actual data is shown in a gradient from red (high prices) to green (low prices)."
+)
+
+###############################################################################
+
+st.subheader(
+    "Top 7 Departments with Highest Variation",
+    divider=True,
+)
+
+st.write(
+    "Select the period to view the top 7 departments with the highest variation in average price."
+)
+
+left_co, right_co = st.columns(2)
+with left_co:
+    selected_year_1 = st.selectbox(
+        "Select Year 1", options=range(2024, 2030), index=0, key="year_select_1"
+    )
+with right_co:
+    selected_year_2 = st.selectbox(
+        "Select Year 2", options=range(2024, 2030), index=5, key="year_select_2"
+    )
+
+# 1. Get prices for 2024 and 2030
+prices_2024 = dataset_departements_housing_prices[
+    dataset_departements_housing_prices["annee"] == selected_year_1
+][["code_departement", "prixm2moyen"]].rename(
+    columns={"prixm2moyen": "prixm2moyen_2024"}
+)
+
+prices_2030 = dataset_departements_housing_prices[
+    dataset_departements_housing_prices["annee"] == selected_year_2
+][["code_departement", "prixm2moyen"]].rename(
+    columns={"prixm2moyen": "prixm2moyen_2030"}
+)
+
+# 2. Merge them based on department code
+# Use an outer merge to keep departments even if they are missing data for one of the years
+variation_data = pd.merge(prices_2024, prices_2030, on="code_departement", how="outer")
+
+# 3. Calculate absolute difference and percentage variation
+variation_data["prixm2moyen_difference"] = (
+    variation_data["prixm2moyen_2030"] - variation_data["prixm2moyen_2024"]
+)
+variation_data["variation_percentage"] = (
+    variation_data["prixm2moyen_difference"] / variation_data["prixm2moyen_2024"]
+) * 100
+
+# Handle cases where prixm2moyen_2024 might be 0 or NaN, leading to Inf or NaN percentage
+variation_data.replace([float("inf"), -float("inf")], pd.NA, inplace=True)
+variation_data.fillna(
+    0, inplace=True
+)  # Or pd.NA for missing values depending on how you want to display
+
+# 4. Sort and select top N
+# Sort by the absolute difference for "highest variation"
+# If "highest variation" means biggest absolute change (up or down), use abs()
+# If it means biggest increase, sort by prixm2moyen_difference directly
+top_departements_variation = variation_data.sort_values(
+    by="prixm2moyen_difference",
+    ascending=False,  # For highest increase
+    # by="prixm2moyen_difference".abs(), ascending=False # For highest absolute change (increase or decrease)
+).head(7)
+
+# add the department name to the dataframe
+top_departements_variation = top_departements_variation.assign(
+    nom_departement=lambda x: x["code_departement"].apply(
+        lambda code: insee_df[
+            _format_department_code(insee_df)["code_departement"] == code
+        ]["nom_departement"].values[0]
+        if code in _format_department_code(insee_df)["code_departement"].values
+        else "Unknown"
+    )
+)
+
+# Select and reorder columns for display
+display_cols = [
+    "nom_departement",
+    "code_departement",
+    "prixm2moyen_2024",
+    "prixm2moyen_2030",
+    "prixm2moyen_difference",
+    "variation_percentage",
+]
+top_departements_variation_display = top_departements_variation[display_cols].copy()
+
+# Format the numerical columns for better display in Streamlit
+top_departements_variation_display["prixm2moyen_2024"] = (
+    top_departements_variation_display["prixm2moyen_2024"].map("{:,.0f}€".format)
+)
+top_departements_variation_display["prixm2moyen_2030"] = (
+    top_departements_variation_display["prixm2moyen_2030"].map("{:,.0f}€".format)
+)
+top_departements_variation_display["prixm2moyen_difference"] = (
+    top_departements_variation_display["prixm2moyen_difference"].map("{:,.0f}€".format)
+)
+top_departements_variation_display = top_departements_variation_display.sort_values(
+    by="variation_percentage", ascending=False
+)
+
+fig = px.bar(
+    top_departements_variation_display.sort_values(
+        by="variation_percentage", ascending=True
+    ),
+    x="nom_departement",
+    y="variation_percentage",
+    title=f"Top Departments by Price Variation ({selected_year_1} to {selected_year_2})",
+    labels={
+        "nom_departement": "Department Name",
+        "variation_percentage": "Price Variation (%)",
+    },
+    color_continuous_scale=px.colors.sequential.Reds,
+)
+st.plotly_chart(fig, use_container_width=True)
+
+top_departements_variation_display["variation_percentage"] = (
+    top_departements_variation_display["variation_percentage"].map("{:,.2f}%".format)
+)
+
+st.dataframe(
+    top_departements_variation_display,
+    hide_index=True,
+    # You can explicitly set column headers if you want more user-friendly names
+    column_config={
+        "nom_departement": "Department Name",
+        "code_departement": "Dept. Code",
+        "prixm2moyen_2024": "Avg. Price 2024",
+        "prixm2moyen_2030": "Avg. Price 2030",
+        "prixm2moyen_difference": "Abs. Change (€)",
+        "variation_percentage": "Change (%)",
+    },
+)
+
+###############################################################################
+
+st.subheader("Top & Bottom 5 Departments", divider=True)
+
+st.write(
+    "Select a year to view the top and bottom departments by average price per square meter."
+)
+
 selected_year = st.selectbox(
     "Select a Year",
     options=dataset_departements_housing_prices["annee"].unique(),
     format_func=lambda x: f"{x}",
+    index=list(dataset_departements_housing_prices["annee"].unique()).index(2024)
+    if 2024 in dataset_departements_housing_prices["annee"].unique()
+    else 0,
 )
 
 top_departements = (
@@ -104,36 +259,89 @@ top_departements = (
             )
         }
     )
+    .head(5)
+)
+
+bottom_departements = (
+    dataset_departements_housing_prices[
+        (dataset_departements_housing_prices["annee"] == selected_year)
+        & (dataset_departements_housing_prices["prixm2moyen"] > 0)
+    ]
+    .groupby("code_departement")["prixm2moyen"]
+    .mean()
+    .reset_index()
+    .sort_values(by="prixm2moyen", ascending=True)
+    .rename(
+        columns={
+            "code_departement": "Department Code",
+            "prixm2moyen": "Average Price per m²",
+        }
+    )
     .assign(
         **{
-            "Average Price per m²": lambda x: x["Average Price per m²"].apply(
-                lambda y: f"{y:,.2f} €"
+            "Department Name": lambda x: x["Department Code"].apply(
+                lambda code: insee_df[
+                    _format_department_code(insee_df)["code_departement"] == code
+                ]["nom_departement"].values[0]
+                if code in _format_department_code(insee_df)["code_departement"].values
+                else "Unknown"
             )
         }
     )
-    .head(10)
+    .head(5)
 )
-st.dataframe(top_departements)
+left_co, right_co = st.columns(2)
 
-fig_france = display_choropleth_map_country(
-    dataset_departements_housing_prices,
-    departements_geojson,
-    metric_name="prixm2moyen",
-    metric_description="Average Price per Square Meter",
-    title="Average Predicted Price per Square Meter in French Departments",
-    height=1400,
-    width=1400,
-)
-st.plotly_chart(fig_france, use_container_width=False)
-st.write("Hover over the map to see detailed information for each department and year.")
-st.write(
-    "Missing values are represented in light grey, while actual data is shown in a gradient from red (high prices) to green (low prices)."
-)
-st.write(
-    "Note: The color scale is customized to highlight missing values in light grey, while the actual data is represented using a reversed RdYlGn color scale, where red indicates higher prices and green indicates lower prices."
-)
+with left_co:
+    fig = px.bar(
+        bottom_departements,
+        x="Department Name",
+        y="Average Price per m²",
+        title="Bottom 5 Departments by Average Price per Square Meter",
+    )
+    st.plotly_chart(fig)
+    st.dataframe(
+        bottom_departements.assign(
+            **{
+                "Average Price per m²": lambda x: x["Average Price per m²"].apply(
+                    lambda y: f"{y:,.2f} €"
+                )
+            }
+        ),
+        hide_index=True,
+        column_order=("Department Code", "Department Name", "Average Price per m²"),
+        column_config={
+            "Average Price per m²": {"formatter": "currency", "currency": "EUR"}
+        },
+    )
 
-st.subheader("Select a Department to View Commune Prices")
+with right_co:
+    # display a bar chart of the top_departements
+    fig = px.bar(
+        top_departements.sort_values(by="Average Price per m²", ascending=True),
+        x="Department Name",
+        y="Average Price per m²",
+        title="Top 5 Departments by Average Price per Square Meter",
+    )
+    st.plotly_chart(fig)
+    st.dataframe(
+        top_departements.assign(
+            **{
+                "Average Price per m²": lambda x: x["Average Price per m²"].apply(
+                    lambda y: f"{y:,.2f} €"
+                )
+            }
+        ),
+        hide_index=True,
+        column_order=("Department Code", "Department Name", "Average Price per m²"),
+        column_config={
+            "Average Price per m²": {"formatter": "currency", "currency": "EUR"}
+        },
+    )
+
+###############################################################################
+
+st.subheader("Select Department(s) to View Historical Prices", divider=True)
 
 with st.spinner("Loading data and preparing maps..."):
     (dataset_housing_prices, communes_geojson, insee_df) = (
@@ -145,36 +353,403 @@ with st.spinner("Loading data and preparing maps..."):
     ]["prixm2moyen"].min()
     max_global_commune_prixm2moyen = dataset_housing_prices["prixm2moyen"].max()
 
-selected_departement = st.selectbox(
-    "Select a Department",
-    options=_format_department_code(insee_df)["code_departement"].unique(),
-    format_func=lambda x: f"{x} - {insee_df[insee_df['code_departement'] == x]['nom_departement'].values[0]}"
-    if x in insee_df["code_departement"].values
-    else x,
+# Get all unique department codes for selectbox options
+all_departement_codes = _format_department_code(insee_df)["code_departement"].unique()
+
+# --- Department Selection 1 & 2 ---
+col_dept1, col_dept2 = st.columns(2)
+
+# Set default department values
+default_dept_1 = all_departement_codes[0] if len(all_departement_codes) > 0 else None
+default_dept_2 = all_departement_codes[1] if len(all_departement_codes) > 1 else None
+
+with col_dept1:
+    selected_departement = st.selectbox(
+        "Select the first Department",
+        options=all_departement_codes,
+        format_func=lambda x: f"{x} - {insee_df[insee_df['code_departement'] == x]['nom_departement'].values[0]}"
+        if x in insee_df["code_departement"].values
+        else x,
+        key="departement_select_1",
+        index=list(all_departement_codes).index(default_dept_1)
+        if default_dept_1
+        else 0,
+    )
+
+with col_dept2:
+    selected_departement_2 = st.selectbox(
+        "Select the second Department (Optional for comparison)",
+        options=[None] + list(all_departement_codes),  # Add None option
+        format_func=lambda x: f"{x} - {insee_df[insee_df['code_departement'] == x]['nom_departement'].values[0]}"
+        if x is not None and x in insee_df["code_departement"].values
+        else "None (Only show Department 1)",
+        key="departement_select_2",
+        index=list([None] + list(all_departement_codes)).index(default_dept_2)
+        if default_dept_2
+        else 0,
+    )
+
+st.write(
+    "This chart shows the average price per square meter in the selected department(s) over the years, with a focus on climatic events."
+)
+
+# --- Data Preparation for Department Chart ---
+all_departments_to_plot = []
+
+# Process Department 1 data
+if selected_departement:  # Ensure a department is selected
+    department_data_1 = dataset_housing_prices[
+        dataset_housing_prices["code_departement"] == selected_departement
+    ].copy()
+    if not department_data_1.empty:
+        department_data_1["annee"] = department_data_1["annee"].astype(str)
+        # Group by year and calculate mean for the department
+        department_data_1 = (
+            department_data_1.groupby("annee")["prixm2moyen"].mean().reset_index()
+        )
+        # Get the department name for the legend
+        departement_name_1 = (
+            insee_df[insee_df["code_departement"] == selected_departement][
+                "nom_departement"
+            ].values[0]
+            if selected_departement in insee_df["code_departement"].values
+            else selected_departement
+        )
+        department_data_1.rename(
+            columns={"prixm2moyen": departement_name_1}, inplace=True
+        )
+        all_departments_to_plot.append(department_data_1)
+    else:
+        st.warning(f"No data available for Department 1: {selected_departement}")
+
+# Process Department 2 data if selected
+if (
+    selected_departement_2 and selected_departement_2 != selected_departement
+):  # Ensure a valid second department is chosen and it's not the same as the first
+    department_data_2 = dataset_housing_prices[
+        dataset_housing_prices["code_departement"] == selected_departement_2
+    ].copy()
+    if not department_data_2.empty:
+        department_data_2["annee"] = department_data_2["annee"].astype(str)
+        # Group by year and calculate mean for the department
+        department_data_2 = (
+            department_data_2.groupby("annee")["prixm2moyen"].mean().reset_index()
+        )
+        # Get the department name for the legend
+        departement_name_2 = (
+            insee_df[insee_df["code_departement"] == selected_departement_2][
+                "nom_departement"
+            ].values[0]
+            if selected_departement_2 in insee_df["code_departement"].values
+            else selected_departement_2
+        )
+        department_data_2.rename(
+            columns={"prixm2moyen": departement_name_2}, inplace=True
+        )
+        all_departments_to_plot.append(department_data_2)
+    else:
+        st.warning(f"No data available for Department 2: {selected_departement_2}")
+elif (
+    selected_departement_2 == selected_departement
+    and selected_departement_2 is not None
+):
+    st.info("You've selected the same department for both. Showing only one line.")
+
+
+# Combine dataframes for plotting the department comparison chart
+if all_departments_to_plot:
+    combined_dept_df = reduce(
+        lambda left, right: pd.merge(left, right, on="annee", how="outer"),
+        all_departments_to_plot,
+    )
+    combined_dept_df.set_index("annee", inplace=True)
+
+    fig_dept = px.line(
+        combined_dept_df.reset_index(),
+        x="annee",
+        y=combined_dept_df.columns,
+        title="Average Price per m² in Selected Department(s) Over the Years",
+        labels={"annee": "Year", "value": "Average Price per m² (€)"},
+    )
+    fig_dept.update_layout(
+        xaxis_title="Year",
+        yaxis_title="Average Price per m² (€)",
+        legend_title_text="Department",
+    )
+    st.plotly_chart(fig_dept, use_container_width=True)
+else:
+    st.info("Please select at least one department to display data.")
+
+selected_departement_label = (
+    f"{insee_df[insee_df['code_departement'] == selected_departement]['nom_departement'].values[0]}"
+    if selected_departement in insee_df["code_departement"].values
+    else selected_departement
+)
+
+# Prepare data for box plot
+box_plot_data = dataset_housing_prices[
+    (dataset_housing_prices["code_departement"] == selected_departement)
+    | (dataset_housing_prices["code_departement"] == selected_departement_2)
+].copy()
+box_plot_data["annee"] = box_plot_data["annee"].astype(
+    str
+)  # Ensure 'annee' is string for categorical x-axis
+# Create the box plot
+fig_box = px.box(
+    box_plot_data,
+    x="annee",
+    y="prixm2moyen",
+    color="code_departement",
+    title=f"Distribution of Prices in Department {selected_departement_label} by Year",
+)
+fig_box.update_layout(
+    xaxis_title="Year",
+    yaxis_title="Average Price per m² (€)",
+)
+st.plotly_chart(fig_box, use_container_width=True)
+
+###############################################################################
+
+# display the top 5 communes in the selected department by average price per square meter
+st.subheader(
+    f"Top and Bottom 5 Communes in Department {selected_departement_label}",
+    divider=True,
+)
+
+# selected year
+selected_year_communes = st.selectbox(
+    "Select a Year",
+    options=dataset_housing_prices["annee"].unique(),
+    format_func=lambda x: str(x),
+    key="year_communes_selectbox",
+    index=list(dataset_housing_prices["annee"].unique()).index(2029) if 2029 in dataset_housing_prices["annee"].unique()
+    else 0,
+)
+
+top_communes = (
+    dataset_housing_prices[
+        (dataset_housing_prices["code_departement"] == selected_departement)
+        & (dataset_housing_prices["annee"] == selected_year_communes)
+    ]
+    .groupby("code_commune_insee")["prixm2moyen"]
+    .mean()
+    .reset_index()
+    .sort_values(by="prixm2moyen", ascending=False)
+    .rename(
+        columns={
+            "code_commune_insee": "Commune Code",
+            "prixm2moyen": "Average Price per m²",
+        }
+    )
+    .assign(
+        **{
+            "Commune Name": lambda x: x["Commune Code"].apply(
+                lambda code: insee_df[
+                    _format_department_code(insee_df)["code_commune_INSEE"] == code
+                ]["nom_commune_complet"].values[0]
+                if code
+                in _format_department_code(insee_df)["code_commune_INSEE"].values
+                else "Unknown"
+            )
+        }
+    )
+    .head(5)
 )
+bottom_communes = (
+    dataset_housing_prices[
+        (dataset_housing_prices["code_departement"] == selected_departement)
+        & (dataset_housing_prices["annee"] == selected_year_communes)
+        & (dataset_housing_prices["prixm2moyen"] > 0)
+    ]
+    .groupby("code_commune_insee")["prixm2moyen"]
+    .mean()
+    .reset_index()
+    .sort_values(by="prixm2moyen", ascending=True)
+    .rename(
+        columns={
+            "code_commune_insee": "Commune Code",
+            "prixm2moyen": "Average Price per m²",
+        }
+    )
+    .assign(
+        **{
+            "Commune Name": lambda x: x["Commune Code"].apply(
+                lambda code: insee_df[
+                    _format_department_code(insee_df)["code_commune_INSEE"] == code
+                ]["nom_commune_complet"].values[0]
+                if code
+                in _format_department_code(insee_df)["code_commune_INSEE"].values
+                else "Unknown"
+            )
+        }
+    )
+    .head(5)
+)
+left_co, right_co = st.columns(2)
+with left_co:
+    fig = px.bar(
+        bottom_communes.sort_values(by="Average Price per m²", ascending=True),
+        x="Commune Name",
+        y="Average Price per m²",
+        title="Bottom 5 Communes by Average Price per Square Meter",
+    )
+    st.plotly_chart(fig)
+    st.dataframe(
+        bottom_communes.assign(
+            **{
+                "Average Price per m²": lambda x: x["Average Price per m²"].apply(
+                    lambda y: f"{y:,.2f} €"
+                )
+            }
+        ),
+        hide_index=True,
+        column_order=("Commune Code", "Commune Name", "Average Price per m²"),
+    )
+
+with right_co:
+    fig = px.bar(
+        top_communes.sort_values(by="Average Price per m²", ascending=True),
+        x="Commune Name",
+        y="Average Price per m²",
+        title="Top 5 Communes by Average Price per Square Meter",
+    )
+    st.plotly_chart(fig)
+    st.dataframe(
+        top_communes.assign(
+            **{
+                "Average Price per m²": lambda x: x["Average Price per m²"].apply(
+                    lambda y: f"{y:,.2f} €"
+                )
+            }
+        ),
+        hide_index=True,
+        column_order=("Commune Code", "Commune Name", "Average Price per m²"),
+    )
 
+###############################################################################
+
+st.subheader("Average Price per Square Meter in French Communes", divider=True)
 fig_department = display_choropleth_map_for_department(
     dataset_housing_prices,
     selected_departement,
     communes_geojson,
     min_global_commune_prixm2moyen,
     max_global_commune_prixm2moyen,
-    metric_name="prixm2moyen",
-    metric_description="Average Price per Square Meter",
-    title=f"Average Predicted Price per Square Meter in Department {selected_departement} (Animated by Year)",
-    height_graph=1400,
+    title=f"Average Price per Square Meter in Department {selected_departement_label} (Animated by Year)",
+    height_graph=1000,
     width_graph=1400,
 )
-
-st.subheader("Average Price per Square Meter in French Communes (2015-2024)")
 st.plotly_chart(fig_department, use_container_width=False)
-st.write("Hover over the map to see detailed information for each commune and year.")
 st.write(
     "Missing values are represented in light grey, while actual data is shown in a gradient from red (high prices) to green (low prices)."
 )
-st.write(
-    "Note: The color scale is customized to highlight missing values in light grey, while the actual data is represented using a reversed RdYlGn color scale, where red indicates higher prices and green indicates lower prices."
-)
-st.write(
-    "The map is animated by year, allowing you to see how the average price per square meter changes over time."
+
+###############################################################################
+
+st.subheader(
+    f"Historical Price comparaison in Selected Commune in Departement {selected_departement_label}",
+    divider=True,
 )
+
+available_communes = dataset_housing_prices[
+    dataset_housing_prices["code_departement"] == selected_departement
+]["code_commune_insee"].unique()
+
+let_col1, right_col2 = st.columns(2)
+with let_col1:
+    # --- Commune Selection 1 ---
+    selected_commune_1 = st.selectbox(
+        "Select the first Commune",
+        options=available_communes,
+        format_func=lambda x: f"{x} - {insee_df[insee_df['code_commune_INSEE'] == x]['nom_commune_complet'].values[0]}"
+        if x in insee_df["code_commune_INSEE"].values
+        else x,
+        key="commune_select_1",
+        index=0 if len(available_communes) > 1 else 0,
+    )
+with right_col2:
+    # --- Commune Selection 2 ---
+    selected_commune_2 = st.selectbox(
+        "Select the second Commune (Optional for comparison)",
+        options=[None]
+        + list(
+            available_communes
+        ),  # Add None as an option to not select a second commune
+        format_func=lambda x: f"{x} - {insee_df[insee_df['code_commune_INSEE'] == x]['nom_commune_complet'].values[0]}"
+        if x is not None and x in insee_df["code_commune_INSEE"].values
+        else "None (Only show Commune 1)",
+        key="commune_select_2",
+        index=2 if len(available_communes) > 2 else 0,
+    )
+
+# --- Data Preparation for Chart ---
+all_communes_to_plot = []
+
+# Process Commune 1 data
+commune_data_1 = dataset_housing_prices[
+    dataset_housing_prices["code_commune_insee"] == selected_commune_1
+].copy()
+if not commune_data_1.empty:
+    commune_data_1["annee"] = commune_data_1["annee"].astype(str)
+    commune_data_1 = commune_data_1.groupby("annee")["prixm2moyen"].mean().reset_index()
+    # Rename the price column to reflect the commune for the legend
+    commune_name_1 = (
+        insee_df[insee_df["code_commune_INSEE"] == selected_commune_1][
+            "nom_commune_complet"
+        ].values[0]
+        if selected_commune_1 in insee_df["code_commune_INSEE"].values
+        else selected_commune_1
+    )
+    commune_data_1.rename(columns={"prixm2moyen": commune_name_1}, inplace=True)
+    all_communes_to_plot.append(commune_data_1)
+else:
+    st.warning(f"No data available for Commune 1: {selected_commune_1}")
+
+
+# Process Commune 2 data if selected
+if (
+    selected_commune_2 and selected_commune_2 != selected_commune_1
+):  # Ensure a valid second commune is chosen and it's not the same as the first
+    commune_data_2 = dataset_housing_prices[
+        dataset_housing_prices["code_commune_insee"] == selected_commune_2
+    ].copy()
+    if not commune_data_2.empty:
+        commune_data_2["annee"] = commune_data_2["annee"].astype(str)
+        commune_data_2 = (
+            commune_data_2.groupby("annee")["prixm2moyen"].mean().reset_index()
+        )
+        # Rename the price column for the second commune
+        commune_name_2 = (
+            insee_df[insee_df["code_commune_INSEE"] == selected_commune_2][
+                "nom_commune_complet"
+            ].values[0]
+            if selected_commune_2 in insee_df["code_commune_INSEE"].values
+            else selected_commune_2
+        )
+        commune_data_2.rename(columns={"prixm2moyen": commune_name_2}, inplace=True)
+        all_communes_to_plot.append(commune_data_2)
+    else:
+        st.warning(f"No data available for Commune 2: {selected_commune_2}")
+elif selected_commune_2 == selected_commune_1 and selected_commune_2 is not None:
+    st.info("You've selected the same commune for both. Showing only one line.")
+
+# Combine dataframes for plotting
+if all_communes_to_plot:
+    # Use reduce or pd.merge to combine, ensuring 'annee' is the common key
+
+    # Start with the first dataframe, then merge others
+    combined_df = reduce(
+        lambda left, right: pd.merge(left, right, on="annee", how="outer"),
+        all_communes_to_plot,
+    )
+    combined_df.set_index("annee", inplace=True)
+
+    st.line_chart(
+        combined_df,
+        use_container_width=True,
+        height=400,
+        x_label="Year",
+        y_label="Average Price per m² (€)",
+    )
+else:
+    st.info("Please select at least one commune to display data.")