colin/colibre
1
0
Fork 0
Code Issues 30 Pull Requests Actions Packages Projects Releases 33 Activity

filtres, tris fonctionnels (acheteur)

Browse Source
This commit is contained in:
Colin Maudry
2025-11-24 13:43:42 +01:00
parent 565a0cfd08
commit 8c98a60c75
4 changed files with 180 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/assets/style.css
+7 -1
View File
@@ -133,6 +133,12 @@ td[data-dash-column="objet"],td[data-dash-column="titulaire_nom"],td[data-dash-c
.marches_table {
font-family: "Open Sans", sans-serif;
}
.marches_table.stuck {
position: relative;
right: 200px;
}
.marches_table .cell-table tr:nth-child(even) td {
background-color: #feeeee;
font-family: "Open Sans", sans-serif;
@@ -212,7 +218,7 @@ summary > h3 {
}
#_pages_content {
padding-top: 28px;
padding: 28px 24px 0 24px;
}
/* Vue acheteur/titulaire/recherche */
src/pages/acheteur.py
+47 -42
View File
@@ -6,15 +6,13 @@ from dash import Input, Output, State, callback, dcc, html, register_page
from src.callbacks import get_top_org_table
from src.figures import DataTable, point_on_map
from src.utils import (
add_links_in_dict,
df,
filter_table_data,
format_number,
format_values,
get_annuaire_data,
get_default_hidden_columns,
get_departement_region,
meta_content,
setup_table_columns,
prepare_table_data,
)
register_page(
@@ -31,9 +29,11 @@ datatable = html.Div(
className="marches_table",
children=DataTable(
dtid="acheteur_datatable",
page_action="native",
page_action="custom",
filter_action="custom",
sort_action="custom",
page_size=10,
hidden_columns=get_default_hidden_columns(page="acheteur"),
),
)
@@ -41,7 +41,6 @@ layout = [
dcc.Store(id="acheteur_data", storage_type="memory"),
dcc.Location(id="url", refresh="callback-nav"),
html.Div(
className="container",
children=[
html.Div(
className="wrapper",
@@ -112,7 +111,29 @@ layout = [
),
# récupérer les données de l'acheteur sur l'api annuaire
html.H3("Derniers marchés publics attribués"),
html.Div(id="acheteur_last_marches", children=datatable),
dcc.Loading(
overlay_style={"visibility": "visible", "filter": "blur(2px)"},
id="loading-home",
type="default",
children=[
html.Div(
[
html.P("lignes", id="acheteur_nb_rows"),
html.Button(
"Téléchargement désactivé au-delà de 65 000 lignes",
id="btn-download-data-acheteur",
disabled=True,
),
dcc.Download(id="acheteur-download-data"),
dcc.Store(
id="acheteur_filtered_data", storage_type="memory"
),
],
className="table-menu",
),
datatable,
],
),
],
),
]
@@ -194,19 +215,6 @@ def get_acheteur_marches_data(url, acheteur_year: str) -> list[dict]:
acheteur_siret = url.split("/")[-1]
lff = df.lazy()
lff = lff.filter(pl.col("acheteur_id") == acheteur_siret)
lff = lff.select(
"id",
"uid",
"objet",
"dateNotification",
"titulaire_id",
"titulaire_typeIdentifiant",
"titulaire_nom",
"distance",
"montant",
"codeCPV",
"dureeMois",
)
if acheteur_year and acheteur_year != "Toutes":
acheteur_year = int(acheteur_year)
lff = lff.filter(pl.col("dateNotification").dt.year() == acheteur_year)
@@ -218,31 +226,28 @@ def get_acheteur_marches_data(url, acheteur_year: str) -> list[dict]:
@callback(
Output(component_id="acheteur_datatable", component_property="data"),
Output(component_id="acheteur_datatable", component_property="columns"),
Output(component_id="acheteur_datatable", component_property="tooltip_header"),
Input(component_id="acheteur_data", component_property="data"),
Input(component_id="acheteur_datatable", component_property="filter_query"),
Output("acheteur_datatable", "data"),
Output("acheteur_datatable", "columns"),
Output("acheteur_datatable", "tooltip_header"),
Output("acheteur_datatable", "data_timestamp"),
Output("acheteur_nb_rows", "children"),
Output("btn-download-data-acheteur", "disabled"),
Output("btn-download-data-acheteur", "children"),
Output("btn-download-data-acheteur", "title"),
Input("acheteur_data", "data"),
Input("acheteur_datatable", "page_current"),
Input("acheteur_datatable", "page_size"),
Input("acheteur_datatable", "filter_query"),
Input("acheteur_datatable", "sort_by"),
State("acheteur_datatable", "data_timestamp"),
)
def get_last_marches_data(data, filter_query) -> tuple[list[dict], list, list]:
lff: pl.LazyFrame = pl.LazyFrame(data)
if filter_query:
lff = filter_table_data(lff, filter_query)
lff = lff.cast(pl.String)
dff: pl.DataFrame = format_values(lff.collect())
columns, tooltip_header = setup_table_columns(
dff,
hideable=False,
exclude=["titulaire_id", "titulaire_typeIdentifiant", "uid"],
def get_last_marches_data(
data, page_current, page_size, filter_query, sort_by, data_timestamp
) -> list[dict]:
return prepare_table_data(
data, data_timestamp, filter_query, page_current, page_size, sort_by
)
data = dff.to_dicts()
data = add_links_in_dict(data, "titulaire")
return data, columns, tooltip_header
@callback(
Output(component_id="top10_titulaires", component_property="children"),
src/pages/tableau.py
+4 -66
View File
@@ -6,22 +6,17 @@ from dash import Input, Output, State, callback, dcc, html, register_page
from src.figures import DataTable
from src.utils import (
add_links,
add_resource_link,
df,
filter_table_data,
format_number,
format_values,
get_default_hidden_columns,
meta_content,
setup_table_columns,
sort_table_data,
)
from utils import prepare_table_data
update_date = os.path.getmtime(os.getenv("DATA_FILE_PARQUET_PATH"))
update_date = datetime.fromtimestamp(update_date).strftime("%d/%m/%Y")
schema = df.collect_schema()
name = "Tableau"
register_page(
@@ -42,7 +37,7 @@ datatable = html.Div(
page_action="custom",
filter_action="custom",
sort_action="custom",
hidden_columns=get_default_hidden_columns(schema),
hidden_columns=get_default_hidden_columns(None),
),
)
@@ -138,65 +133,8 @@ layout = [
State("table", "data_timestamp"),
)
def update_table(page_current, page_size, filter_query, sort_by, data_timestamp):
if os.getenv("DEVELOPMENT").lower() == "true":
print(" + + + + + + + + + + + + + + + + + + ")
# Application des filtres
lff: pl.LazyFrame = df.lazy() # start from the original data
if filter_query:
lff = filter_table_data(lff, filter_query)
if len(sort_by) > 0:
lff = sort_table_data(lff, sort_by)
# Matérialisation des filtres
dff: pl.DataFrame = lff.collect()
height = dff.height
nb_rows = f"{format_number(height)} lignes ({format_number(dff.select('uid').unique().height)} marchés)"
# Pagination des données
start_row = page_current * page_size
# end_row = (page_current + 1) * page_size
dff = dff.slice(start_row, page_size)
# Tout devient string
dff = dff.cast(pl.String)
# Remplace les strings null par "", mais pas les numeric null
dff = dff.fill_null("")
# Ajout des liens vers l'annuaire des entreprises
dff = add_links(dff)
# Ajout des liens vers les fichiers Open Data
dff = add_resource_link(dff)
# Formatage des montants
dff = format_values(dff)
columns, tooltip = setup_table_columns(dff)
dicts = dff.to_dicts()
if height > 65000:
download_disabled = True
download_text = "Téléchargement désactivé au-delà de 65 000 lignes"
download_title = "Excel ne supporte pas d'avoir plus de 65 000 URLs dans une même feuille de calcul. Contactez-moi pour me présenter votre besoin en téléchargement afin que je puisse adapter la solution."
else:
download_disabled = False
download_text = "Télécharger au format Excel"
download_title = ""
return (
dicts,
columns,
tooltip,
data_timestamp + 1,
nb_rows,
download_disabled,
download_text,
download_title,
return prepare_table_data(
None, data_timestamp, filter_query, page_current, page_size, sort_by
)
src/utils.py
+115 -5
View File
@@ -7,7 +7,6 @@ from time import localtime, sleep
import polars as pl
import polars.selectors as cs
from httpx import get, post
from polars import Schema
from polars.exceptions import ComputeError
from unidecode import unidecode
@@ -356,18 +355,47 @@ def setup_table_columns(dff, hideable: bool = True, exclude: list = None) -> tup
return columns, tooltip
def get_default_hidden_columns(schema: Schema):
def get_default_hidden_columns(page):
if page == "acheteur":
displayed_columns = [
"uid",
"objet",
"dateNotification",
"titulaire_id",
"titulaire_typeIdentifiant",
"titulaire_nom",
"distance",
"montant",
"codeCPV",
"dureeRestanteMois",
]
elif page == "titulaire":
displayed_columns = [
"uid",
"objet",
"dateNotification",
"acheteur_id",
"acheteur_nom",
"distance",
"montant",
"codeCPV",
"dureeRestanteMois",
]
else:
displayed_columns = os.getenv("DISPLAYED_COLUMNS")
hidden_columns = []
if displayed_columns:
if displayed_columns is None:
raise ValueError("DISPLAYED_COLUMNS n'est pas configuré")
else:
displayed_columns = displayed_columns.replace(" ", "").split(",")
hidden_columns = []
for col in schema.names():
if col in displayed_columns:
continue
else:
hidden_columns.append(col)
return hidden_columns
raise ValueError("DISPLAYED_COLUMNS n'est pas configuré")
def get_data_schema() -> dict:
@@ -503,9 +531,91 @@ def search_org(dff: pl.DataFrame, query: str, org_type: str) -> pl.DataFrame:
return dff
def prepare_table_data(
data, data_timestamp, filter_query, page_current, page_size, sort_by
):
"""
Fonction de préparation des données pour les datatables, afin de permettre une gestion fine des logiques,
notamment pour les filtres et les tris.
:param data
:param data_timestamp:
:param filter_query:
:param page_current:
:param page_size:
:param sort_by:
:return:
"""
if os.getenv("DEVELOPMENT").lower() == "true":
print(" + + + + + + + + + + + + + + + + + + ")
# Récupération des données
if data:
lff: pl.LazyFrame = pl.LazyFrame(data)
else:
lff: pl.LazyFrame = df.lazy() # start from the original data
# Application des filtres
if filter_query:
lff = filter_table_data(lff, filter_query)
# Application des tris
if len(sort_by) > 0:
lff = sort_table_data(lff, sort_by)
# Matérialisation des filtres
dff: pl.DataFrame = lff.collect()
height = dff.height
nb_rows = f"{format_number(height)} lignes ({format_number(dff.select('uid').unique().height)} marchés)"
# Pagination des données
start_row = page_current * page_size
# end_row = (page_current + 1) * page_size
dff = dff.slice(start_row, page_size)
# Tout devient string
dff = dff.cast(pl.String)
# Remplace les strings null par "", mais pas les numeric null
dff = dff.fill_null("")
# Ajout des liens vers l'annuaire des entreprises
dff = add_links(dff)
# Ajout des liens vers les fichiers Open Data
if "sourceFile" in dff.columns:
dff = add_resource_link(dff)
# Formatage des montants
dff = format_values(dff)
columns, tooltip = setup_table_columns(dff)
dicts = dff.to_dicts()
if height > 65000:
download_disabled = True
download_text = "Téléchargement désactivé au-delà de 65 000 lignes"
download_title = "Excel ne supporte pas d'avoir plus de 65 000 URLs dans une même feuille de calcul. Contactez-moi pour me présenter votre besoin en téléchargement afin que je puisse adapter la solution."
else:
download_disabled = False
download_text = "Télécharger au format Excel"
download_title = ""
return (
dicts,
columns,
tooltip,
data_timestamp + 1,
nb_rows,
download_disabled,
download_text,
download_title,
)
df: pl.DataFrame = get_decp_data()
schema = df.collect_schema()
df_acheteurs = get_org_data(df, "acheteur")
df_titulaires = get_org_data(df, "titulaire")
departements = get_departements()
domain_name = (
"test.decp.info" if os.getenv("DEVELOPMENT").lower() == "true" else "decp.info"