fix: update document format

.gitattributes

@@ -6,4 +6,5 @@ data/raw/camb_wards.parquet filter=lfs diff=lfs merge=lfs -text
 data/raw/imd_camb.parquet filter=lfs diff=lfs merge=lfs -text
 data/raw/lsoa_camb.parquet filter=lfs diff=lfs merge=lfs -text
 data/raw/onspd_cambridge.parquet filter=lfs diff=lfs merge=lfs -text
+data/raw/camb_lads.parquet filter=lfs diff=lfs merge=lfs -text
 data/covers/*.docx filter=lfs diff=lfs merge=lfs -text

app.py

@@ -194,35 +194,71 @@ def display_download_buttons():
     # Create a container for the Executive Reports
     with st.expander("**Executive Reports**"):
         for i, rep in enumerate(representations_documents):
-            summaries_path = Paths.SUMMARY / f"Summary_of_Submitted_Responses-{rep}.pdf"
+            summaries_pdf_path = (
+                Paths.SUMMARY / f"Summary_of_Submitted_Representations-{rep}.pdf"
+            )
+            summaries_docx_path = (
+                Paths.SUMMARY / f"Summary_of_Submitted_Representations-{rep}.docx"
+            )
             with st.container():
                 st.subheader(f"Executive Report for {rep}")
-                with open(summaries_path, "rb") as pdf_file:
-                    st.download_button(
-                        label="Download Executive Report",
-                        data=pdf_file,
-                        file_name=f"Summary_of_Submitted_Responses-{rep}.pdf",
-                        mime="application/pdf",
-                        use_container_width=True,
-                        key=f"exec_{i}_{hash(rep)}",  # Ensure key uniqueness with index + hash
-                    )
+                col1, col2 = st.columns(2)
+                with col1:
+                    with open(summaries_pdf_path, "rb") as pdf_file:
+                        st.download_button(
+                            label="Download PDF Version",
+                            data=pdf_file,
+                            file_name=f"Summary_of_Submitted_Representations-{rep}.pdf",
+                            mime="application/pdf",
+                            use_container_width=True,
+                            key=f"exec_pdf_{i}_{hash(rep)}",
+                        )
+                with col2:
+                    if summaries_docx_path.exists():
+                        with open(summaries_docx_path, "rb") as docx_file:
+                            st.download_button(
+                                label="Download DOCX Version",
+                                data=docx_file,
+                                file_name=f"Summary_of_Submitted_Representations-{rep}.docx",
+                                mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+                                use_container_width=True,
+                                key=f"exec_docx_{i}_{hash(rep)}",
+                            )
+                    else:
+                        st.warning("DOCX version not available")
                 st.markdown("---")
 
     # Create a container for the Representation Summaries
     with st.expander("**Representation Summaries**"):
         for i, rep in enumerate(representations_documents):
-            report_path = Paths.SUMMARY / f"Summary_Documents-{rep}.pdf"
+            report_pdf_path = Paths.SUMMARY / f"Summary_Documents-{rep}.pdf"
+            report_docx_path = Paths.SUMMARY / f"Summary_Documents-{rep}.docx"
             with st.container():
                 st.subheader(f"Representation Summary for {rep}")
-                with open(report_path, "rb") as pdf_file:
-                    st.download_button(
-                        label="Download Representation Summary",
-                        data=pdf_file,
-                        file_name=f"Summary_Documents-{rep}.pdf",
-                        mime="application/pdf",
-                        use_container_width=True,
-                        key=f"rep_{i}_{hash(rep)}",  # Ensure key uniqueness with index + hash
-                    )
+                col1, col2 = st.columns(2)
+                with col1:
+                    with open(report_pdf_path, "rb") as pdf_file:
+                        st.download_button(
+                            label="Download PDF Version",
+                            data=pdf_file,
+                            file_name=f"Summary_Documents-{rep}.pdf",
+                            mime="application/pdf",
+                            use_container_width=True,
+                            key=f"rep_pdf_{i}_{hash(rep)}",
+                        )
+                with col2:
+                    if report_docx_path.exists():
+                        with open(report_docx_path, "rb") as docx_file:
+                            st.download_button(
+                                label="Download DOCX Version",
+                                data=docx_file,
+                                file_name=f"Summary_Documents-{rep}.docx",
+                                mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+                                use_container_width=True,
+                                key=f"rep_docx_{i}_{hash(rep)}",
+                            )
+                    else:
+                        st.warning("DOCX version not available")
                 st.markdown("---")
 
 

packages.txt

@@ -1,5 +1,5 @@
 texlive-latex-extra
-texlive-fonts-extra
+ttf-liberation
 cm-super
 dvipng
 pandoc

planning_ai/documents/document.py

@@ -3,7 +3,6 @@ import re
 from collections import Counter
 
 import geopandas as gpd
-import matplotlib as mpl
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
@@ -13,25 +12,9 @@ from polars.dependencies import subprocess
 
 from planning_ai.common.utils import Paths
 
-mpl.rcParams["text.usetex"] = True
-mpl.rcParams["text.latex.preamble"] = r"\usepackage{libertine}"
-
-WARDS = [
-    "E05013050",
-    "E05013051",
-    "E05013052",
-    "E05013053",
-    "E05013054",
-    "E05013055",
-    "E05013056",
-    "E05013057",
-    "E05013058",
-    "E05013059",
-    "E05013060",
-    "E05013061",
-    "E05013062",
-    "E05013063",
-]
+plt.rcParams.update(
+    {"font.family": "sans-serif", "font.sans-serif": ["Liberation Sans"]}
+)
 
 
 def _process_postcodes(final):
@@ -52,8 +35,8 @@ def _process_postcodes(final):
     )
     onspd = pl.read_parquet(
         Paths.RAW / "onspd_cambridge.parquet",
-        columns=["PCD", "OSWARD", "LSOA11", "OA21"],
-    ).with_columns(pl.col("PCD").str.replace_all(" ", "").alias("postcode"))
+        columns=["pcd", "osward", "lsoa11", "oa21"],
+    ).with_columns(pl.col("pcd").str.replace_all(" ", "").alias("postcode"))
     postcodes = postcodes.join(onspd, on="postcode")
     return postcodes
 
@@ -177,7 +160,7 @@ def fig_oa(postcodes, rep):
     )
     oac = oac.join(oa_pop, left_on="oa21cd", right_on="OA2021")
     oac = (
-        postcodes.join(oac, left_on="OA21", right_on="oa21cd", how="right")
+        postcodes.join(oac, left_on="oa21", right_on="oa21cd", how="right")
         .group_by(["supergroup", "supergroup_name"])
         .sum()
         .select(["supergroup", "supergroup_name", "population", "count"])
@@ -210,20 +193,21 @@ def fig_oa(postcodes, rep):
     bars1 = ax1.bar(
         oa_pd["supergroup"],
         oa_pd["perc_diff"],
-        label="Percentage of Representations (\%)",
+        label="Percentage of Representations (%)",
         color=colors[: len(oa_pd)],
-        edgecolor="black",
+        edgecolor="none",
+        width=0.9,
     )
 
     # Add centerline at y=0
-    ax1.axhline(0, color="black", linewidth=1.5)
+    ax1.axhline(0, color="black", linewidth=1)
 
     # Annotate bars with percentage values
     for bar in bars1:
         height = bar.get_height()
         if height > 0:
             ax1.annotate(
-                f"{height:.0f}\%",
+                f"{height:.0f}%",
                 xy=(bar.get_x() + bar.get_width() / 2, height),
                 xytext=(0, 3),  # 3 points vertical offset
                 textcoords="offset points",
@@ -232,16 +216,16 @@ def fig_oa(postcodes, rep):
             )
         else:
             ax1.annotate(
-                f"{height:.0f}\%",
+                f"{height:.0f}%",
                 xy=(bar.get_x() + bar.get_width() / 2, height),
-                xytext=(0, -6),  # 10 points vertical offset
+                xytext=(0, -6),
                 textcoords="offset points",
                 ha="center",
                 va="top",
             )
 
     ax1.set_xlabel("Output Area Classification (OAC) Supergroup")
-    ax1.set_ylabel("Difference from national average (\%)")
+    ax1.set_ylabel("Difference from national average (%)")
 
     supergroup_names = [
         f"{i}: {name}"
@@ -259,10 +243,14 @@ def fig_oa(postcodes, rep):
 
 
 def fig_wards(postcodes, rep):
+    camb_lads = gpd.read_parquet(Paths.RAW / "camb_lads.parquet")
     ward_boundaries = gpd.read_parquet(Paths.RAW / "camb_wards.parquet")
-    camb_ward_boundaries = ward_boundaries[ward_boundaries["WD21CD"].isin(WARDS)]
+    ward_pcs = postcodes.group_by("osward").sum()
+    camb_ward_boundaries = ward_boundaries[
+        ward_boundaries["WD21CD"].isin(postcodes["osward"].unique())
+    ]
     ward_boundaries_prop = ward_boundaries.merge(
-        postcodes.to_pandas(), left_on="WD21CD", right_on="OSWARD"
+        ward_pcs.to_pandas(), left_on="WD21CD", right_on="osward"
     )
 
     _, ax = plt.subplots(figsize=(8, 8))
@@ -270,15 +258,10 @@ def fig_wards(postcodes, rep):
         ax=ax,
         column="count",
         legend=True,
-        legend_kwds={"label": "Number of Representations"},
+        legend_kwds={"label": "Number of Representations", "fmt": "{:.0f}"},
     )
-    ward_boundaries.plot(ax=ax, color="none", edgecolor="gray")
-    camb_ward_boundaries.plot(ax=ax, color="none", edgecolor="black")
-
-    bounds = np.array([541419.8982, 253158.2036, 549420.4025, 262079.7998])
-    buffer = 20_000
-    ax.set_xlim([bounds[0] - buffer, bounds[2] + buffer])
-    ax.set_ylim([bounds[1] - buffer, bounds[3] + buffer])
+    camb_lads.plot(ax=ax, color="none", edgecolor="gray", linewidth=0.5)
+    camb_ward_boundaries.plot(ax=ax, color="none", edgecolor="black", linewidth=0.5)
 
     plt.axis("off")
     plt.tight_layout()
@@ -290,7 +273,7 @@ def fig_imd(postcodes, rep):
     imd = pl.read_parquet(Paths.RAW / "imd_camb.parquet")
     pops = pl.read_parquet(Paths.RAW / "pops_camb.parquet")
     imd = (
-        postcodes.join(imd, left_on="LSOA11", right_on="LSOA", how="right")
+        postcodes.join(imd, left_on="lsoa11", right_on="LSOA", how="right")
         .join(pops, left_on="LSOA", right_on="LSOA 2021 Code")
         .group_by("SOA_decile")
         .agg(pl.col("count").sum(), pl.col("LSOA").count(), pl.col("Total").sum())
@@ -317,15 +300,16 @@ def fig_imd(postcodes, rep):
     ax1.bar(
         x,  # Shift to the left
         postcodes_pd["perc_diff"],
-        edgecolor="black",
+        edgecolor="none",
         color=colors,
+        width=0.9,
     )
 
     # Set labels and ticks
     ax1.set_xlabel("Deprivation Quintile")
-    ax1.set_ylabel("Difference from national average (\%)")
+    ax1.set_ylabel("Difference from national average (%)")
     ax1.set_xticks(x)
-    ax1.axhline(0, color="black", linewidth=1.5)
+    ax1.axhline(0, color="black", linewidth=1)
 
     # ax1.legend(loc="upper center", bbox_to_anchor=(0.5, 1.1), ncol=5, frameon=False)
     plt.tight_layout()
@@ -361,16 +345,40 @@ def build_final_report(out, rep):
     fig_imd(postcodes, rep)
 
     quarto_doc = (
-        "---\n"
-        f"title: 'Summary of Submitted Representations: {rep}'\n"
-        "geometry: a4paper\n"
-        "margin: 2cm\n"
-        "fontfamily: libertinus\n"
-        "monofont: 'JetBrains Mono'\n"
-        "monofontoptions:\n"
-        "  - Scale=0.55\n"
-        "---\n\n"
-        "# Executive Summary\n\n"
+        f"---\ntitle: '**Summary of Submitted Representations: {rep}**'\n"
+        r"""
+mainfont: Liberation Sans
+fontsize: 11pt
+margin: 2cm
+geometry: a4paper
+header-includes: |
+    \usepackage{graphicx}
+    \usepackage{fancyhdr}
+    \usepackage{geometry}
+    \usepackage{sectsty}
+    \geometry{top=1in, bottom=1in, left=1in, right=1in}
+    \pagestyle{fancy}
+    \fancyhead[L]{}
+    \fancyhead[C]{}
+    \fancyhead[R]{\includegraphics[width=3cm]{logo.png}}
+    \fancyfoot[L]{}
+    \fancyfoot[C]{}
+    \fancyfoot[R]{\thepage}
+    \renewcommand{\headrulewidth}{0pt}
+    \renewcommand{\footrulewidth}{0pt}
+    \linespread{1.2}
+    \usepackage{titlesec}
+    \usepackage{xcolor}
+    \definecolor{uolblue}{HTML}{1F2B7D}
+    \titleformat{\section}[block]{\normalfont\Large\bfseries\color{uolblue}}{}{0em}{}
+    \titleformat{\subsection}[block]{\normalfont\large\bfseries\color{uolblue}}{}{0em}{}
+    \fancypagestyle{plain}{\fancyhf{}\fancyfoot[R]{\thepage}\fancyhead[R]{\includegraphics[width=3cm]{logo.png}}}
+    \usepackage{titling}
+    \pretitle{\begin{flushleft}\Huge\color{uolblue}}
+    \posttitle{\end{flushleft}\vspace{-2em}}
+---
+"""
+        "\n# Executive Summary\n\n"
         f"{final['executive']}\n\n"
         f"There were a total of {len(responses):,} responses. Of these, submissions indicated "
         "the following support and objection of the plan:\n\n"
@@ -380,8 +388,8 @@ def build_final_report(out, rep):
         "\n# Profile of Submissions\n\n"
         f"{figures_paragraph}\n\n"
         f"![Total number of representations submitted by Ward\\label{{fig-wards}}](./data/out/summary/figs/wards-{rep}.pdf)\n\n"
-        f"![Total number of representations submitted by Output Area (OA 2021)\\label{{fig-oas}}](./data/out/summary/figs/oas-{rep}.pdf)\n\n"
-        f"![Percentage of representations submitted by quintile of index of multiple deprivation (2019)\\label{{fig-imd}}](./data/out/summary/figs/imd_decile-{rep}.pdf)\n\n"
+        f"![Proportional frequency of representations submitted by 2021 Output Area\\label{{fig-oas}}](./data/out/summary/figs/oas-{rep}.pdf)\n\n"
+        f"![Distribution of representations submitted by quintile of index of multiple deprivation (2019)\\label{{fig-imd}}](./data/out/summary/figs/imd_decile-{rep}.pdf)\n\n"
         r"\newpage"
         "\n\n# Themes and Policies\n\n"
         f"{themes_paragraph}\n\n"
@@ -408,15 +416,25 @@ def build_final_report(out, rep):
         "to page 12 of the document attached to representation 175933."
     )
 
-    out_path = Paths.SUMMARY / f"Summary_of_Submitted_Responses-{rep}.md"
-    out_file = Paths.SUMMARY / f"Summary_of_Submitted_Responses-{rep}.pdf"
+    out_path = Paths.SUMMARY / f"Summary_of_Submitted_Representations-{rep}.md"
+    out_file = Paths.SUMMARY / f"Summary_of_Submitted_Representations-{rep}"
     with open(out_path, "w") as f:
         f.write(quarto_doc)
-    command = ["pandoc", f"{out_path}", "-o", f"{out_file}"]
     try:
+        command = [
+            "pandoc",
+            f"{out_path}",
+            "-o",
+            f"{out_file}.pdf",
+            "--pdf-engine=xelatex",
+        ]
+        subprocess.run(command, check=True, capture_output=True)
+        command = ["pandoc", f"{out_path}", "-o", f"{out_file}.docx"]
         subprocess.run(command, check=True, capture_output=True)
     except subprocess.CalledProcessError as e:
-        logging.error(f"Error during Summary_of_Submitted_Responses.md render: {e}")
+        logging.error(
+            f"Error during Summary_of_Submitted_Representations.md render: {e}"
+        )
 
 
 def build_summaries_document(out, rep):
@@ -430,24 +448,56 @@ def build_summaries_document(out, rep):
         for document in out["generate_final_report"]["documents"]
     )
     header = (
-        "---\n"
-        f"title: 'Summary Documents: {rep}'\n"
-        "fontfamily: libertinus\n"
-        "geometry: a4paper\n"
-        "margin: 2cm\n"
-        "monofont: 'JetBrains Mono'\n"
-        "monofontoptions:\n"
-        "  - Scale=0.55\n"
-        "---\n\n"
-        f"{summary_intro}\n\n"
+        f"---\ntitle: '**Summary Documents: {rep}**'\n"
+        r"""
+mainfont: Liberation Sans
+fontsize: 11pt
+margin: 2cm
+geometry: a4paper
+header-includes: |
+    \usepackage{graphicx}
+    \usepackage{fancyhdr}
+    \usepackage{geometry}
+    \usepackage{sectsty}
+    \geometry{top=1in, bottom=1in, left=1in, right=1in}
+    \pagestyle{fancy}
+    \fancyhead[L]{}
+    \fancyhead[C]{}
+    \fancyhead[R]{\includegraphics[width=3cm]{logo.png}}
+    \fancyfoot[L]{}
+    \fancyfoot[C]{}
+    \fancyfoot[R]{\thepage}
+    \renewcommand{\headrulewidth}{0pt}
+    \renewcommand{\footrulewidth}{0pt}
+    \linespread{1.2}
+    \usepackage{titlesec}
+    \usepackage{xcolor}
+    \definecolor{uolblue}{HTML}{1F2B7D}
+    \titleformat{\section}[block]{\normalfont\Large\bfseries\color{uolblue}}{}{0em}{}
+    \titleformat{\subsection}[block]{\normalfont\large\bfseries\color{uolblue}}{}{0em}{}
+    \fancypagestyle{plain}{\fancyhf{}\fancyfoot[R]{\thepage}\fancyhead[R]{\includegraphics[width=3cm]{logo.png}}}
+    \usepackage{titling}
+    \pretitle{\begin{flushleft}\Huge\color{uolblue}}
+    \posttitle{\end{flushleft}\vspace{-2em}}
+---
+"""
+        f"\n{summary_intro}\n\n"
     )
     out_path = Paths.SUMMARY / f"Summary_Documents-{rep}.md"
-    out_file = Paths.SUMMARY / f"Summary_Documents-{rep}.pdf"
+    out_file = Paths.SUMMARY / f"Summary_Documents-{rep}"
     with open(out_path, "w") as f:
         f.write(f"{header}{full_text}")
 
-    command = ["pandoc", f"{out_path}", "-o", f"{out_file}"]
     try:
+        command = [
+            "pandoc",
+            f"{out_path}",
+            "-o",
+            f"{out_file}.pdf",
+            "--pdf-engine=xelatex",
+        ]
+        subprocess.run(command, check=True, capture_output=True)
+        command = ["pandoc", f"{out_path}", "-o", f"{out_file}.docx"]
         subprocess.run(command, check=True, capture_output=True)
     except subprocess.CalledProcessError as e:
         logging.error(f"Error during render: {e}")

planning_ai/documents/figures.txt

@@ -1,5 +1,5 @@
 This section describes the characteristics of where submissions were received from. This can help to identify how representative submissions were and whether there were any communities whose views were not being considered. Figure \ref{fig-wards} shows the number (frequency) of submitted representations by Ward based on the address attached to the submission. To interpret the figure, areas which are coloured white had no submissions from residents, and then areas are coloured in based on the total number of submissions with yellows and greens representing the largest numbers. This figure helps to identify which Wards are more active in terms of participation and representation in this report.
 
-Figure \ref{fig-oas} displays the percentage of representations submitted by the Output Area Classification (2021). The Output Area Classification is the Office for National Statistics preferred classification of neighbourhoods.  This measure groups neighbourhoods (here defined as Output Areas, typically containing 100 people) into categories that capture similar types of people based on population, demographic and socioeconomic characteristics. It therefore provides an insightful view of the types of communities who submitted representations. To interpret the figure, where bars extend higher/upwards, this represents a larger population share within a specific area type. The blue bars represent the characteristics of who submitted representations, and the orange bars represent the underlying population – allowing one to compare whether the profile of submissions matched the characteristics of the local population. This figure uses OAC 'Supergroups', which are the highest level of the hierarchy, and provide information relative to the average values for the UK population at large.
+Figure \ref{fig-oas} displays the percentage of representations submitted by the Output Area Classification (2021). The Output Area Classification is the Office for National Statistics preferred classification of neighbourhoods.  This measure groups neighbourhoods (here defined as Output Areas, typically containing 100 people) into categories that capture similar types of people based on population, demographic and socio-economic characteristics. It therefore provides an insightful view of the types of communities who submitted representations. To interpret the figure, where bars extend higher/upwards, this represents a larger population share within a specific area type. The blue bars represent the characteristics of who submitted representations, and the orange bars represent the underlying population – allowing one to compare whether the profile of submissions matched the characteristics of the local population. This figure uses OAC 'Supergroups', which are the highest level of the hierarchy, and provide information relative to the average values for the UK population at large.
 
-Figure \ref{fig-imd} shows the percentage of responses by level of neighbourhood socioeconomic deprivation. The information is presented using the 2019 Index of Multiple Deprivation, divided into quintiles (i.e., dividing the English population into equal fifths). This measure is the UK Government’s preferred measure of socioeconomic deprivation and is based on information about income, employment, education, health, crime, housing and the local environment for small areas (Lower Super Output Areas, typically containing 1600 people). To interpret the graph, bars represent the share of population from each quintile. Quintile 1 represents the most deprived 20% of areas, and quintile 5 the least deprived 20% of areas. The orange bars represent the distribution of people who submitted representations (i.e., larger bars mean that more people from these areas submitted representations). The blue bars show the distribution of the local population, allowing one to evaluate whether the evidence submitted was from the same communities in the area.
+Figure \ref{fig-imd} shows the percentage of responses by level of neighbourhood socio-economic deprivation. The information is presented using the 2019 Index of Multiple Deprivation, divided into quintiles (i.e., dividing the English population into equal fifths). This measure is the UK Government’s preferred measure of socioeconomic deprivation and is based on information about income, employment, education, health, crime, housing and the local environment for small areas (Lower Super Output Areas, typically containing 1600 people). To interpret the graph, bars represent the share of population from each quintile. Quintile 1 represents the most deprived 20% of areas, and quintile 5 the least deprived 20% of areas. The orange bars represent the distribution of people who submitted representations (i.e., larger bars mean that more people from these areas submitted representations). The blue bars show the distribution of the local population, allowing one to evaluate whether the evidence submitted was from the same communities in the area.

planning_ai/documents/introduction.txt

@@ -1 +1 @@
-This report was produced using a generative pre-trained transformer (GPT) large-language model (LLM) to produce an abstractive summary of all responses to the related planning application. This model automatically reviews every response in detail, and extracts key information to inform decision making. This document first consolidates this information into a single-page executive summary, highlighting areas of particular interest to consider, and the broad consensus of responses. Figures generated from responses then give both a geographic and statistical overview, highlighting any demographic imbalances in responses. The document then extracts detailed information from responses, grouped by theme and policy. In this section we incorporate citations which relate with the 'Summary Responses' document, to increase transparency.
+This report was produced using a generative pre-trained transformer (GPT) large-language model (LLM) to produce a summary of all responses to the related planning application. This model automatically reviews every response in detail, and extracts key information to inform decision making. This document first consolidates this information into a single-page executive summary, highlighting areas of particular interest to consider, and the broad consensus of responses. Figures generated from responses then give both a geographic and statistical overview, highlighting any demographic imbalances in responses. The document then extracts detailed information from responses, grouped by theme and policy. In this section we incorporate citations which relate with the 'Summary Responses' document, to increase transparency.

planning_ai/documents/summary_intro.txt

@@ -1,3 +1,7 @@
-This document provides a summary of each representation, along with the **Document ID** which corresponds with the citations in the coresponding **Summary of Submitted Representations** document. Each summary also provides the **Representations ID** which correponds with the `id` column in the `.json` JDL files. This allows the user to link the produced summaries back to the original documents.
+This document provides a summary of each representation, along with the **Document ID** which corresponds with the citations in the corresponding **Summary of Submitted Representations** document. Each summary also provides the **Representations ID** which corresponds with the `id` column in the `.json` JDI files. This allows the user to link the produced summaries back to the original documents.
+
+Note that PDF documents have been split by pages into multiple **Document ID**, but will share the same **Representations ID**.
+
+---
+
 
-Note that PDF documents have been split by pages into multiple **Document ID**, but will share the same **Representations ID**+

planning_ai/documents/themes.txt

@@ -1 +1 @@
-The following section provides a detailed breakdown of notable details from responses, grouped by themes and policies. Both themes and associated policies are automatically determined through an analysis of the summary content by an LLM agent. Each theme is grouped by whether a responses is supporting, opposed, or a general comment. This section aims to give a comprehensive view of the key issues raised by the respondents with respect to the themes and policies outlined. We have incorporated citations into eac hpoint (see numbers in square brackets) which relate to the specific document they were made in, to promote the transparency of where information was sourced from. @tbl-themes gives a breakdown of the number of submissions that relate with each theme, submissions may relate to more than one theme.
+The following section provides a detailed breakdown of notable details from responses, grouped by themes and policies. Both themes and associated policies are automatically determined through an analysis of the summary content by an LLM agent. Each theme is grouped by whether responses are supporting, opposed, or a general comment. This section aims to give a comprehensive view of the key issues raised by the respondents with respect to the themes and policies outlined. We have incorporated citations into each point (see numbers in square brackets) which relate to the specific document they were made in, to promote the transparency of where information was sourced from. @tbl-themes gives a breakdown of the number of submissions that relate with each theme, submissions may relate to more than one theme.