Merge remote-tracking branch 'origin/main'

visualize.ipynb

@@ -2738,7 +2738,7 @@
    ],
    "source": [
     "for plot in plots:\n",
-    "    plot.show()"
+    "    plot.show() "
    ]
   },
   {

visualize/visualize.py

@@ -0,0 +1,146 @@
+import pandas as pd  # stress hydrique and rendement, besoin en eau
+import plotly.graph_objects as go
+from typing import List
+import plotly.express as px
+from fuzzywuzzy import process
+from data_pipelines.historical_weather_data import (
+    download_historical_weather_data,
+    aggregate_hourly_weather_data,
+)
+
+def concatenate_historic_forecast(historic, forecast, cols_to_keep):
+    historic["period"] = "historique"
+    forecast["period"] = "futur"
+    historic = historic[cols_to_keep]
+    forecast = forecast[cols_to_keep]
+    full_data = pd.concat([historic, forecast])
+    return full_data
+
+
+def visualize_climate(
+    moderate: pd.DataFrame,
+    historic: pd.DataFrame,
+    x_axis="year",
+    column: str = "Precipitation (mm)",
+    cols_to_keep: List[str] = [
+        "Precipitation (mm)",
+        "Near Surface Air Temperature (°C)",
+        "Surface Downwelling Shortwave Radiation (W/m²)",
+        "year",
+        "period",
+    ],
+):
+    concatenated_df = concatenate_historic_forecast(historic, moderate, cols_to_keep)
+    concatenated_df = concatenated_df.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]
+        fig.add_trace(
+            go.Scatter(
+                x=segment[x_axis],
+                y=segment[column],
+                mode="lines",
+                name=f"{condition_value}",
+                line=dict(color="blue" if condition_value == "futur" else "purple"),
+            )
+        )
+
+    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")
+    return df
+
+
+def generate_plots(
+    moderate: pd.DataFrame,
+    historic: 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))
+    return plots
+
+if __name__ == "__main__":
+    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)
+
+    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)
+    historic = historic.reset_index()
+    historic = historic.rename(
+        columns={
+            "precipitation": "Precipitation (mm)",
+            "air_temperature_mean": "Near Surface Air Temperature (°C)",
+            "irradiance": "Surface Downwelling Shortwave Radiation (W/m²)",
+            "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)
+    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
+    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