climateqa/engine/talk_to_data/drias/plot_informations.py

from climateqa.engine.talk_to_data.drias.config import DRIAS_INDICATOR_TO_UNIT

def indicator_evolution_informations(
        indicator: str,
        params: dict[str, str]
) -> str:
    unit = DRIAS_INDICATOR_TO_UNIT[indicator]
    if "location" not in params:
        raise ValueError('"location" must be provided in params')
    location = params["location"]
    return f"""
This plot shows how the climate indicator **{indicator}** evolves over time in **{location}**.

It combines both historical observations and future projections according to the climate scenario RCP8.5.

The x-axis represents the years, and the y-axis shows the value of the indicator ({unit}).

A 10-year rolling average curve is displayed to give a better idea of the overall trend.

**Data source:**
- The data come from the DRIAS TRACC data. The data were initially extracted from [the DRIAS website](https://www.drias-climat.fr/drias_prod/accueil/okapiWebDrias/index.jsp?iddrias=climat) and then preprocessed to a tabular format and uploaded as parquet in this [Hugging Face dataset](https://huggingface.co/datasets/timeki/drias_db).
- For each year and climate model, the value of {indicator} in {location} is collected, to build the time series.
- The coordinates used for {location} correspond to the closest available point in the DRIAS database, which uses a regular grid with a spatial resolution of 8 km.
- The indicator values shown are those for the selected climate model.
- If ALL climate model is selected, the average value of the indicator between all the climate models is used. 
"""

def indicator_number_of_days_per_year_informations(
        indicator: str,
        params: dict[str, str]
) -> str:
    unit = DRIAS_INDICATOR_TO_UNIT[indicator]
    if "location" not in params:
        raise ValueError('"location" must be provided in params')
    location = params["location"]
    return f"""
This plot displays a bar chart showing the yearly frequency of the climate indicator **{indicator}** in **{location}**.

The x-axis represents the years, and the y-axis shows the frequency of {indicator} ({unit}) per year.

**Data source:**  
- The data come from the DRIAS TRACC data. The data were initially extracted from [the DRIAS website](https://www.drias-climat.fr/drias_prod/accueil/okapiWebDrias/index.jsp?iddrias=climat) and then preprocessed to a tabular format and uploaded as parquet in this [Hugging Face dataset](https://huggingface.co/datasets/timeki/drias_db).
- For each year and climate model, the value of {indicator} in {location} is collected, to build the time series.
- The coordinates used for {location} correspond to the closest available point in the DRIAS database, which uses a regular grid with a spatial resolution of 8 km.
- The indicator values shown are those for the selected climate model.
- If ALL climate model is selected, the average value of the indicator between all the climate models is used. 
"""

def distribution_of_indicator_for_given_year_informations(
        indicator: str,
        params: dict[str, str]
) -> str:
    unit = DRIAS_INDICATOR_TO_UNIT[indicator]
    year = params["year"]
    if year is None:
        year = 2030
    return f"""
This plot shows a histogram of the distribution of the climate indicator **{indicator}** across all locations for the year **{year}**.

It allows you to visualize how the values of {indicator} ({unit}) are spread for a given year.

**Data source:**  
- The data come from the DRIAS TRACC data. The data were initially extracted from [the DRIAS website](https://www.drias-climat.fr/drias_prod/accueil/okapiWebDrias/index.jsp?iddrias=climat) and then preprocessed to a tabular format and uploaded as parquet in this [Hugging Face dataset](https://huggingface.co/datasets/timeki/drias_db).
- For each grid point in the dataset and climate model, the value of {indicator} for the year {year} is extracted.
- The indicator values shown are those for the selected climate model.
- If ALL climate model is selected, the average value of the indicator between all the climate models is used. 
"""

def map_of_france_of_indicator_for_given_year_informations(
        indicator: str,
        params: dict[str, str]
) -> str:
    unit = DRIAS_INDICATOR_TO_UNIT[indicator]
    year = params["year"]
    if year is None:
        year = 2030
    return f"""
This plot displays a choropleth map showing the spatial distribution of **{indicator}** across all regions of France for the year **{year}**.

Each region is colored according to the value of the indicator ({unit}), allowing you to visually compare how {indicator} varies geographically within France for the selected year and climate model.

**Data source:**  
- The data come from the DRIAS TRACC data. The data were initially extracted from [the DRIAS website](https://www.drias-climat.fr/drias_prod/accueil/okapiWebDrias/index.jsp?iddrias=climat) and then preprocessed to a tabular format and uploaded as parquet in this [Hugging Face dataset](https://huggingface.co/datasets/timeki/drias_db).
- For each region of France, the value of {indicator} in {year} and for the selected climate model is extracted and mapped to its geographic coordinates.
- The regions correspond to 8 km squares centered on the grid points of the DRIAS dataset.
- The indicator values shown are those for the selected climate model.
- If ALL climate model is selected, the average value of the indicator between all the climate models is used.
"""