import os
import sys
from datetime import datetime
from bokeh.models import ColumnDataSource, HoverTool
from bokeh.plotting import figure, show
sys.path.append(os.path.abspath('../../../scripts/'))
import mdapi_functions as md
from bokeh.io import output_notebook
import bokeh.io as io
from IPython.display import display, Markdown

Temporal coverage of NHS England datasets

display(Markdown('Last modified: ' + datetime.now().strftime("%d %b %Y")))

Last modified: 13 Mar 2026

The availability of NHS England datasets differs according to when each dataset was established, if the dataset has since been retired and the time periods permitted to flow to UK LLC.

Hover over the bar representing each dataset to see its full name and time range.

output_notebook(hide_banner=True)
dss1 = md.get_md_api_dss()
dss1 = dss1[dss1["source"] == "NHSE"][["table", "collection_start", "collection_end", "table_name"]]
dss1 = dss1[~dss1["collection_start"].isnull()]
dss1 = dss1.set_index(keys="table", drop=False).reindex(
    [
        "GDPPR",
        "PCM",
        "HESOP",
        "HESAPC",
        "HESAPC_ACP",
        "HESAPC_MAT",
        "HESCC",
        "ECDS",
        "HESAE",
        "COVIDSGSS",
        "IELISA",
        "NPEX",
        "CHESS",
        "CVS",
        "CVAR",
        "CANCER",
        "DEMOGRAPHICS",
        "MORTALITY",
        "MHSDS",
        "IAPT",
        "CSDS"
]).reset_index(drop=True).iloc[::-1]


def ins_ongoing_date(x):
    if x == "ongoing":
        return datetime.now().date()
    else:
        return datetime.strptime(x, '%m/%Y').date()
dss1["collection_end"] = dss1["collection_end"].apply(lambda x: ins_ongoing_date(x))
dss1["collection_start"] = dss1["collection_start"].apply(lambda x: ins_ongoing_date(x))
dss1.loc[0, "collection_start"] = datetime.strptime("01/1940", '%m/%Y').date()

p = figure(x_axis_type="datetime", y_range=dss1["table"].to_list(), width=600, height=400, toolbar_location=None,
           title="Temporal coverage of NHS England datasets in the UK LLC TRE")
p.hbar(y="table", left='collection_start', right='collection_end', height=0.4, source=ColumnDataSource(dss1), fill_color="#00b289")

hover = HoverTool(tooltips = [("Name","@table_name"), ("Start","@collection_start{%b-%Y}"),("End", "@collection_end{%b-%Y}")], formatters={"@collection_start":"datetime", "@collection_end":"datetime"})
p.add_tools(hover)

p.ygrid.grid_line_color = None
p.xaxis.axis_label = "Dataset Collection Period"

p.outline_line_color = None
show(p)