208 lines
8.9 KiB
Python
208 lines
8.9 KiB
Python
# FILE: pasbdc_funding_analysis_script.py
|
|
# CREATED: 12/26/25
|
|
# AUTHOR: Vincent Allen
|
|
# PURPOSE: Script to generate capital funding analysis graphs and datasets from prepared Neoserra data.
|
|
|
|
# Third party libraries
|
|
import pandas as pd
|
|
import sys
|
|
import os.path
|
|
import argparse
|
|
import json
|
|
|
|
# Custom modules
|
|
from section_1_graph_library_module import ( #pyright:ignore
|
|
make_funding_attribution_network_wide,
|
|
make_funding_attribution_rate_chart,
|
|
make_theoretical_funding_attribution_rate_chart,
|
|
make_funding_director_confirmed_graph,
|
|
)
|
|
|
|
from milestone_attribution_dataset_module import sanitize_funding_data
|
|
from constants_module import NEOSERRA_COLUMNS, OUT_COLUMNS
|
|
from shared_tools_module import csv_url_to_dataframe
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser(description="Generate Capital Funding Analysis Graphs")
|
|
|
|
input_data_group = parser.add_mutually_exclusive_group(required=True)
|
|
|
|
input_data_group.add_argument("--inputcsv",
|
|
type=str,
|
|
help="The path to the raw capital funding CSV dataset. Either a path to a CSV file is required OR a value must be provided for --exportmoduleurl")
|
|
|
|
input_data_group.add_argument("--exportmoduleurl",
|
|
type=str,
|
|
help="The URL pointing to the configured Neoserra export module for the funding analysis data. Either the export module url is required, or a value must be provided for --inputcsv.")
|
|
|
|
parser.add_argument("--outpath",
|
|
type=str,
|
|
required=True,
|
|
help="The base directory path to place generated files into.")
|
|
|
|
parser.add_argument("--fiscalyear",
|
|
type=str,
|
|
required=True,
|
|
help="The fiscal year the input data comes from")
|
|
|
|
parser.add_argument("--mapping",
|
|
type=str,
|
|
required=False,
|
|
help="Path to a JSON file to override default column names mappings.")
|
|
|
|
# --- GRAPH 1: Network Wide Stacked Bar ---
|
|
parser.add_argument("--netwidefilename",
|
|
type=str,
|
|
default="fundingattributionnetworkwide",
|
|
help="Filename for the network-wide attribution stacked bar chart.")
|
|
|
|
parser.add_argument("--netwidetitle",
|
|
type=str,
|
|
default="Capital Funding Attributions Per Center",
|
|
help="Title for the network-wide attribution graph.")
|
|
|
|
# --- GRAPH 2: Attribution Rate Chart ---
|
|
parser.add_argument("--ratefilename",
|
|
type=str,
|
|
default="fundingattributionrate",
|
|
help="Filename for the attribution rate bar chart.")
|
|
|
|
parser.add_argument("--ratedatafilename",
|
|
type=str,
|
|
default="funding_attribution_rate_data.csv",
|
|
help="Filename for the intermediate dataset used for the attribution rate chart.")
|
|
|
|
# --- GRAPH 3: Theoretical Rate Chart ---
|
|
parser.add_argument("--theoreticalfilename",
|
|
type=str,
|
|
default="theoreticalfundingattributionrate",
|
|
help="Filename for the theoretical attribution rate bar chart.")
|
|
|
|
parser.add_argument("--theoreticaltitle",
|
|
type=str,
|
|
default="Documented Percentage if All Funding Milestones With an Attribution Source had an Affirmation",
|
|
help="Title for the theoretical attribution rate graph.")
|
|
|
|
parser.add_argument("--theoreticaldatafilename",
|
|
type=str,
|
|
default="theoretical_funding_rate_data.csv",
|
|
help="Filename for the intermediate dataset used for the theoretical rate chart.")
|
|
|
|
# --- GRAPH 4: Director Confirmed Chart ---
|
|
parser.add_argument("--directorfilename",
|
|
type=str,
|
|
default="directorconfirmedfunding",
|
|
help="Filename for the director confirmed funding bar chart.")
|
|
|
|
parser.add_argument("--directortitle",
|
|
type=str,
|
|
default="Percentage of Director Confirmed Capital Funding Attributions Per Center",
|
|
help="Title for the director confirmed graph.")
|
|
|
|
parser.add_argument("--directordatafilename",
|
|
type=str,
|
|
default="director_confirmed_data.csv",
|
|
help="Filename for the intermediate dataset used for the director confirmed chart.")
|
|
|
|
parser.add_argument("--report",
|
|
type=str,
|
|
default="fundinganalysis",
|
|
help="The report name to use in filenames so that the word generation script can use the image registry to find this report's images.")
|
|
|
|
return parser.parse_args()
|
|
|
|
if __name__ == "__main__":
|
|
args = parse_args()
|
|
|
|
# Handle optional JSON mapping override
|
|
if args.mapping:
|
|
NEOSERRA_COLUMNS.apply_json_mapping(args.mapping)
|
|
OUT_COLUMNS.apply_json_mapping(args.mapping)
|
|
|
|
# Ensure output directory exists
|
|
if not os.path.exists(args.outpath):
|
|
try:
|
|
os.makedirs(args.outpath)
|
|
except OSError as e:
|
|
print(f"Error creating output directory: {e}")
|
|
sys.exit(1)
|
|
|
|
if args.inputcsv:
|
|
print(f"Loading input data from {args.inputcsv}...\n")
|
|
try:
|
|
funding_df = pd.read_csv(args.inputcsv)
|
|
except Exception as e:
|
|
print(f"Failed to read input CSV: {e}")
|
|
sys.exit(1)
|
|
elif args.exportmoduleurl:
|
|
try:
|
|
funding_df = csv_url_to_dataframe(args.exportmoduleurl)
|
|
except Exception as e:
|
|
print("Failed to fetch data from the export module.")
|
|
print(f"got={e}")
|
|
exit(1)
|
|
|
|
# Filter for reportable records only.
|
|
# This will fail with a KeyError if the column is missing, as required.
|
|
funding_df = funding_df[funding_df[NEOSERRA_COLUMNS.reportable] == 1]
|
|
|
|
funding_df = sanitize_funding_data(
|
|
df=funding_df,
|
|
col_neo_center=NEOSERRA_COLUMNS.center,
|
|
col_neo_attribution_source=NEOSERRA_COLUMNS.milestone_attribution_source,
|
|
col_neo_affirmation=NEOSERRA_COLUMNS.milestone_affirmation,
|
|
col_out_documentation_level=OUT_COLUMNS.milestone_documentation_level
|
|
)
|
|
|
|
funding_df.to_csv(os.path.join(args.outpath, f"cleaned_funding_{args.fiscalyear}.csv"), index=False)
|
|
|
|
# 1. Network Wide Attribution
|
|
print("Generating Network Wide Attribution Graph...\n")
|
|
network_fig = make_funding_attribution_network_wide(
|
|
funding_df,
|
|
fiscal_year=args.fiscalyear,
|
|
title=args.netwidetitle,
|
|
col_neo_center=NEOSERRA_COLUMNS.center,
|
|
col_documentation_level=OUT_COLUMNS.milestone_documentation_level
|
|
)
|
|
network_fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.netwidefilename}_.png"))
|
|
|
|
# 2. Attribution Rate Chart
|
|
print("Generating Attribution Rate Chart and Dataset...\n")
|
|
rate_fig = make_funding_attribution_rate_chart(
|
|
funding_df,
|
|
fiscal_year=args.fiscalyear,
|
|
source_data_export_path=str(os.path.join(args.outpath, args.ratedatafilename)),
|
|
documented_tag=OUT_COLUMNS.val_documented,
|
|
col_neo_center=NEOSERRA_COLUMNS.center,
|
|
col_documentation_level=OUT_COLUMNS.milestone_documentation_level
|
|
)
|
|
rate_fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.ratefilename}_.png"))
|
|
|
|
# 3. Theoretical Attribution Rate Chart
|
|
print("Generating Theoretical Attribution Rate Chart and Dataset...\n")
|
|
theoretical_fig = make_theoretical_funding_attribution_rate_chart(
|
|
funding_df,
|
|
title=args.theoreticaltitle,
|
|
fiscal_year=args.fiscalyear,
|
|
source_data_export_path=str(os.path.join(args.outpath, args.theoreticaldatafilename)),
|
|
documented_tag=OUT_COLUMNS.val_documented,
|
|
affirmation_missing_tag=OUT_COLUMNS.val_affirmation_missing,
|
|
col_neo_center=NEOSERRA_COLUMNS.center,
|
|
col_documentation_level=OUT_COLUMNS.milestone_documentation_level
|
|
)
|
|
theoretical_fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.theoreticalfilename}_.png"))
|
|
|
|
# 4. Director Confirmed Graph
|
|
print("Generating Director Confirmed Graph and Dataset...\n")
|
|
director_fig = make_funding_director_confirmed_graph(
|
|
funding_df,
|
|
fiscal_year=args.fiscalyear,
|
|
title=args.directortitle,
|
|
source_data_export_path=str(os.path.join(args.outpath, args.directordatafilename)),
|
|
col_neo_center=NEOSERRA_COLUMNS.center,
|
|
col_neo_attribution_source=NEOSERRA_COLUMNS.milestone_attribution_source
|
|
)
|
|
director_fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.directorfilename}_.png"))
|
|
|
|
print("DONE!") |