adding pessimistic scenario

visualize/visualize.py

@@ -6,11 +6,13 @@ from data_pipelines.historical_weather_data import (
     download_historical_weather_data,
     aggregate_hourly_weather_data,
 )
+import os
+from forecast import get_forecast_datasets, get_forecast_data
 
 
-def concatenate_historic_forecast(historic, forecast, cols_to_keep):
+def concatenate_historic_forecast(historic, forecast, cols_to_keep, value_period_col = "forecast scénario modéré"):
     historic["period"] = "historique"
-    forecast["period"] = "futur"
+    forecast["period"] = value_period_col
     historic = historic[cols_to_keep]
     forecast = forecast[cols_to_keep]
     full_data = pd.concat([historic, forecast])
@@ -20,6 +22,7 @@ def concatenate_historic_forecast(historic, forecast, cols_to_keep):
 def visualize_climate(
     moderate: pd.DataFrame,
     historic: pd.DataFrame,
+    pessimist: pd.DataFrame,
     x_axis="year",
     column: str = "Precipitation (mm)",
     cols_to_keep: List[str] = [
@@ -30,62 +33,146 @@ def visualize_climate(
         "period",
     ],
 ):
-    concatenated_df = concatenate_historic_forecast(historic, moderate, cols_to_keep)
-    concatenated_df = concatenated_df.sort_values(by=x_axis)  # Ensure order
+    concatenated_moderate = concatenate_historic_forecast(historic, moderate, cols_to_keep)
+    concatenated_moderate = concatenated_moderate.sort_values(by=x_axis)  # Ensure order
 
     fig = go.Figure()
-    # colors = {"historique": "blue", "forecast": "purple"}
 
-    for condition_value in concatenated_df["period"].unique():
-        segment = concatenated_df[concatenated_df["period"] == condition_value]
+    if column == "Precipitation (mm)":
+        for condition_value in concatenated_moderate["period"].unique():
+            segment = concatenated_moderate[concatenated_moderate["period"] == condition_value]
+            avg_precipitation = segment.groupby(x_axis)[column].mean().reset_index()  
+            
+            fig.add_trace(
+                go.Bar(
+                    x=avg_precipitation[x_axis],  
+                    y=avg_precipitation[column],  
+                    name=f"{condition_value}",
+                    marker=dict(color="blue" if condition_value == "historique" else "purple"),
+                )
+            )
+        
+        concatenated_pessimist = concatenate_historic_forecast(historic, pessimist, cols_to_keep, "forecast scénario pessimiste")
+        concatenated_pessimist = concatenated_pessimist.sort_values(by=x_axis)
+        concatenated_pessimist = concatenated_pessimist[concatenated_pessimist["period"]!="historique"]
+        for condition_value in concatenated_pessimist["period"].unique():
+            segment = concatenated_pessimist[concatenated_pessimist["period"] == condition_value]
+            avg_precipitation = segment.groupby(x_axis)[column].mean().reset_index()  
+            
+            fig.add_trace(
+                go.Bar(
+                    x=avg_precipitation[x_axis],  
+                    y=avg_precipitation[column],  
+                    name=f"{condition_value}",
+                    marker=dict(color="orange" if condition_value != "historique" else "blue"),
+                )
+            )
+        
+        # Update layout for bar chart
+        fig.update_layout(
+            title=f"Moyenne de {column} par année",
+            xaxis_title="Année",  # Set the x-axis title to Year
+            yaxis_title="Précipitation (mm)",  # Set the y-axis title to Precipitation
+            barmode='group'  # Group bars for different conditions
+        )
+    
+    else:
+        # For other columns, continue with the line plot as before
+        for condition_value in concatenated_moderate["period"].unique():
+            segment = concatenated_moderate[concatenated_moderate["period"] == condition_value]
+            if condition_value == "historique":
+                fig.add_trace(
+                    go.Scatter(
+                        x=segment[x_axis],  # Years on x-axis
+                        y=segment[column],  # Precipitation values on y-axis
+                        mode="lines",
+                        name=f"{condition_value}",
+                        line=dict(color="blue" if condition_value == "historique" else "purple"),
+                        showlegend=False
+                    )
+                )
+            else:
+                fig.add_trace(
+                    go.Scatter(
+                        x=segment[x_axis],  # Years on x-axis
+                        y=segment[column],  # Precipitation values on y-axis
+                        mode="lines",
+                        name=f"{condition_value}",
+                        line=dict(color="blue" if condition_value == "historique" else "purple"),
+                    )
+                )
+            
+        # Continue with pessimistic data as in the original function...
+        concatenated_pessimist = concatenate_historic_forecast(historic, pessimist, cols_to_keep, "forecast scénario pessimiste")
+        concatenated_pessimist = concatenated_pessimist.sort_values(by=x_axis)
+        for condition_value in concatenated_pessimist["period"].unique():
+            segment = concatenated_pessimist[concatenated_pessimist["period"] == condition_value]
+            fig.add_trace(
+                go.Scatter(
+                    x=segment[x_axis],  # Years on x-axis
+                    y=segment[column],  # Precipitation values on y-axis
+                    mode="lines",
+                    name=f"{condition_value}",
+                    line=dict(color="blue" if condition_value == "historique" else "orange"),
+                )
+            )
+        
+        # Interpolation for the pessimistic scenario...
+        interpolation_pessimist = concatenated_pessimist[concatenated_pessimist[x_axis] > 2023]
         fig.add_trace(
             go.Scatter(
-                x=segment[x_axis],
-                y=segment[column],
+                x=interpolation_pessimist[x_axis],
+                y=interpolation_pessimist[column].interpolate(),
                 mode="lines",
-                name=f"{condition_value}",
-                line=dict(color="blue" if condition_value == "futur" else "purple"),
-            )
+                name = "forecast scénario pessimiste",
+                line=dict(color="orange"),
+                showlegend=False
+                
+            ),
+        )
+        interpolation_moderate = concatenated_moderate[concatenated_moderate[x_axis] > 2023]
+        fig.add_trace(
+            go.Scatter(
+                x=interpolation_moderate[x_axis],
+                y=interpolation_moderate[column].interpolate(),
+                mode="lines",
+                name = "forecast scénario modéré",
+                line=dict(color="purple"),
+                showlegend=False
+                
+            ),
+        )
+        fig.update_layout(
+            title=f"Historique et Forecast pour {column}",
+            xaxis_title="Year",  # Set the x-axis title to Year
+            yaxis_title=column,  # Set the y-axis title to Precipitation
         )
-
-    interpolation_df = concatenated_df[concatenated_df[x_axis] > 2023]
-    fig.add_trace(
-        go.Scatter(
-            x=interpolation_df[x_axis],
-            y=interpolation_df[column].interpolate(),
-            mode="lines",
-            line=dict(color="blue"),
-            showlegend=False,
-        ),
-    )
-
-    fig.update_layout(
-        title=f"Historique et Forecast pour {column}",
-        xaxis_title="Date",
-        yaxis_title=column,
-    )
 
     return fig
 
-
-def aggregate_yearly(df, col_to_agg):
-    df[col_to_agg] = df.groupby("year")[col_to_agg].transform("mean")
+def aggregate_yearly(df, col_to_agg, operation = "mean"):
+    df[col_to_agg] = df.groupby("year")[col_to_agg].transform(operation)
     return df
 
 
 def generate_plots(
     moderate: pd.DataFrame,
     historic: pd.DataFrame,
+    pessimist: pd.DataFrame,
     x_axes: List[str],
     cols_to_plot: List[str],
 ):
     plots = []
     for i, col in enumerate(cols_to_plot):
-        plots.append(visualize_climate(moderate, historic, x_axes[i], col))
+        plots.append(visualize_climate(moderate, historic, pessimist, x_axes[i], col))
     return plots
 
-
 def get_plots():
+    cols_to_plot = [
+    "Precipitation (mm)",
+    "Near Surface Air Temperature (°C)",
+    "Surface Downwelling Shortwave Radiation (W/m²)",
+]
     cols_to_keep = [
         "Precipitation (mm)",
         "Near Surface Air Temperature (°C)",
@@ -93,30 +180,11 @@ def get_plots():
         "year",
         "period",
     ]
-    cols_to_plot = [
-        "Precipitation (mm)",
-        "Near Surface Air Temperature (°C)",
-        "Surface Downwelling Shortwave Radiation (W/m²)",
-    ]
     x_axes = ["year"] * len(cols_to_plot)
-
     latitude = 47
     longitude = 5
     start_year = 2000
     end_year = 2025
-    cols_to_keep = [
-        "Precipitation (mm)",
-        "Near Surface Air Temperature (°C)",
-        "Surface Downwelling Shortwave Radiation (W/m²)",
-        "year",
-        "period",
-    ]
-    cols_to_plot = [
-        "Precipitation (mm)",
-        "Near Surface Air Temperature (°C)",
-        "Surface Downwelling Shortwave Radiation (W/m²)",
-    ]
-    x_axes = ["year"] * len(cols_to_plot)
 
     df = download_historical_weather_data(latitude, longitude, start_year, end_year)
     historic = aggregate_hourly_weather_data(df)
@@ -129,22 +197,51 @@ def get_plots():
             "index": "time",
         }
     )
-    historic["time"] = pd.to_datetime(historic["time"])
-    historic = historic.sort_values("time")
-    historic = historic[historic["time"] < "2025-01-01"]
-    climate_data_path = "data/data_climate_test/final_climate_data.csv"  # will use a similar func to download_historical_weather_data
-    moderate = pd.read_csv(climate_data_path)
+    folder_to_parse_moderate = "climate_data_moderate/"
+    climate_sub_folder_moderate = [
+        os.path.join(folder_to_parse_moderate, e)
+        for e in os.listdir(folder_to_parse_moderate)
+        if os.path.isdir(os.path.join(folder_to_parse_moderate, e))
+    ]
+    climate_sub_files_moderate = [
+        os.path.join(e, i)
+        for e in climate_sub_folder_moderate
+        for i in os.listdir(e)
+        if i.endswith(".nc")
+    ]
+    datasets_moderate = get_forecast_datasets(climate_sub_files_moderate)
+    moderate = get_forecast_data(datasets_moderate, latitude, longitude)
+
+    folder_to_parse_pessimist = "climate_data_pessimist/"
+    climate_sub_folder_pessimist = [
+        os.path.join(folder_to_parse_pessimist, e)
+        for e in os.listdir(folder_to_parse_pessimist)
+        if os.path.isdir(os.path.join(folder_to_parse_pessimist, e))
+    ]
+    climate_sub_files_pessimist = [
+        os.path.join(e, i)
+        for e in climate_sub_folder_pessimist
+        for i in os.listdir(e)
+        if i.endswith(".nc")
+    ]
+    datasets_pessimist = get_forecast_datasets(climate_sub_files_pessimist)
+    pessimist = get_forecast_data(datasets_pessimist, latitude, longitude)
+    moderate = moderate.rename(columns={"Precipitation (kg m-2 s-1)": "Precipitation (mm)"})#TODO : do yearly precipitations
     moderate["time"] = pd.to_datetime(moderate["time"])
-    moderate = moderate.sort_values("time")
-    moderate["year"] = moderate["time"].dt.year
-    historic["year"] = historic["time"].dt.year
-    moderate["Precipitation (mm)"] = moderate["Precipitation (mm)"] * 3600
+    moderate = moderate.sort_values('time')
+    moderate['year'] = moderate["time"].dt.year
+    moderate["Precipitation (mm)"] = moderate["Precipitation (mm)"]*31536000
+    pessimist = pessimist.rename(columns={"Precipitation (kg m-2 s-1)": "Precipitation (mm)"})
+    pessimist["time"] = pd.to_datetime(pessimist["time"])
+    pessimist = pessimist.sort_values('time')
+    pessimist['year'] = pessimist["time"].dt.year
+    pessimist["Precipitation (mm)"] = pessimist["Precipitation (mm)"]*31536000
+    pessimist["period"] = "forecast scénario pessimiste"
+    historic['year'] = historic["time"].dt.year
+    historic["Precipitation (mm)"] = historic["Precipitation (mm)"]*8760.0
     for col in cols_to_plot:
         moderate = aggregate_yearly(moderate, col)
         historic = aggregate_yearly(historic, col)
-
-    plots = generate_plots(
-        moderate, historic, x_axes, cols_to_plot
-    )  # List of 3 plots to show
-
+        pessimist = aggregate_yearly(pessimist, col)
+    plots = generate_plots(moderate, historic, pessimist, x_axes, cols_to_plot)
     return plots