first commit

section_1_graph_export_module/counselling_interval_script.py

@@ -0,0 +1,189 @@
+# FILE: counselling_interval_script.py
+# CREATED: 1/12/25
+# AUTHOR: Vincent Allen
+# CONTACT: vincent@vtallen.com valle276@live.kutztown.edu
+# PURPOSE:
+
+# This library file implements control code needed to take the input yearly satisfaction survey data obtained through
+# the satisfaction survey scorecard in Neoserra and pass it to the library functions that generate the graph images.
+
+# No data cleaning is required for the files in this dataset as the scorecard does that for us. We are just taking the data and showing it per
+# center instead of network wide. The network wide stat is retained through a horizontal line.
+
+# Third party libraries
+import pandas as pd
+
+# Python modules
+import sys
+import os.path
+import argparse
+import json
+
+# Custom modules
+from section_1_graph_library_module import ( #pyright:ignore
+    make_interval_snapshot_chart
+)
+
+from pasbdc_data_cleaning import clean_center_name #pyright:ignore
+from constants_module import NEOSERRA_COLUMNS, OUT_COLUMNS
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("--signuptostartcsv",
+                        type=str,
+                        required=True,
+                        help='The path to the dataset containing the "Average # of Days between Client Sign-up and Client Start Date" from the Neoserra scorecard. If provided the graph will be generated')
+    parser.add_argument("--signuptostartfigure",
+                        type=str,
+                        required=False,
+                        default="signuptostart",
+                        help='The filename to give the sign up to client start date graph.')
+
+    parser.add_argument("--signuptocounsellingcsv",
+                        type=str,
+                        required=True,
+                        help='The path to the dataset containing the "Average # of Days between Client Sign-up and 1st Counseling Session" from the Neoserra scorecard. If provided the graph will be generated')
+
+    parser.add_argument("--signuptocounsellingfigure",
+                        type=str,
+                        required=False,
+                        default="signuptocounselling",
+                        help='The filename to give the sign up to first counselling graph.')
+
+    parser.add_argument("--starttocounsellingcsv",
+                        type=str,
+                        required=True,
+                        help='The path to the dataset containing the "Average # of Days between Client Start Date to 1st Counseling Session" from the Neoserra scorecard. If provided the graph will be generated')
+
+    parser.add_argument("--starttocounsellingfigure",
+                        type=str,
+                        required=False,
+                        default="starttocounselling",
+                        help='The filename to give the sign up to first counselling graph.')
+
+    parser.add_argument("--initialtofollowupcsv",
+                        type=str,
+                        required=True,
+                        help='The path to the dataset containing the "Average # of Days between Initial Counseling in the period to 1st Followup Counseling" from the Neoserra scorecard. If provided the graph will be generated')
+
+    parser.add_argument("--initialtofollowupfigure",
+                        type=str,
+                        required=False,
+                        default="initialtofollowup",
+                        help='The filename to give the inital session to follow up graph.')
+
+    parser.add_argument("--trainingtocounsellingcsv",
+                        type=str,
+                        required=True,
+                        help='The path to the dataset containing the "Avg. # of Days between Training in the period to 1st Counseling Session" from the Neoserra scorecard. If provided the graph will be generated')
+
+    parser.add_argument("--trainingtocounsellingfigure",
+                        type=str,
+                        required=False,
+                        default="trainingtocounselling",
+                        help='The filename to give the inital session to follow up graph.')
+
+    parser.add_argument("--fiscalyear",
+                        type=str,
+                        required=True,
+                        help="The fiscal year tag to place at the end of graph titles to indicate which year the data came from.")
+
+    parser.add_argument("--outpath",
+                        type=str,
+                        required=True,
+                        help="The base directory path to place generated files into.")
+
+    parser.add_argument("--report",
+                        type=str,
+                        required=False,
+                        default="counselling-interval",
+                        help="The name to give the graphs of this report. Will be used by the word code to determine what report the grpahs belong to."
+                        )
+
+    parser.add_argument("--mapping",
+                        type=str,
+                        required=False,
+                        help="Path to a JSON file to override default column names mappings.")
+
+    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.signuptostartcsv:
+        signup_to_start_df = pd.read_csv(args.signuptostartcsv)
+        # Filter out a testing record that can appear in this data set
+        signup_to_start_df = signup_to_start_df[signup_to_start_df[NEOSERRA_COLUMNS.center] != 'API Testing Sandbox']
+        clean_center_name(signup_to_start_df )
+        fig = make_interval_snapshot_chart(
+            signup_to_start_df,
+            title=f"Average Days between Client Sign-up and Client Start Date",
+            fiscal_year_tag=args.fiscalyear,
+            col_interval_data_value=NEOSERRA_COLUMNS.interval_data_value,
+            col_neo_center=NEOSERRA_COLUMNS.center
+        )
+        fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.signuptostartfigure}_.png"))
+
+
+    if args.signuptocounsellingcsv:
+        signup_to_counselling_df = pd.read_csv(args.signuptocounsellingcsv)
+        clean_center_name(signup_to_counselling_df )
+        fig = make_interval_snapshot_chart(
+            signup_to_counselling_df ,
+            title=f"Average Days between Client Sign-up and 1st Counseling Session",
+            fiscal_year_tag=args.fiscalyear,
+            col_interval_data_value=NEOSERRA_COLUMNS.interval_data_value,
+            col_neo_center=NEOSERRA_COLUMNS.center
+        )
+        fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.signuptocounsellingfigure}_.png"))
+
+    if args.starttocounsellingcsv:
+        start_to_counselling_df = pd.read_csv(args.starttocounsellingcsv)
+        clean_center_name(start_to_counselling_df )
+        fig = make_interval_snapshot_chart(
+            start_to_counselling_df,
+            title=f"Average Days between Client Start Date and 1st Counseling Session",
+            fiscal_year_tag=args.fiscalyear,
+            col_interval_data_value=NEOSERRA_COLUMNS.interval_data_value,
+            col_neo_center=NEOSERRA_COLUMNS.center
+        )
+        fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.starttocounsellingfigure}_.png"))
+
+    if args.initialtofollowupcsv:
+        inital_to_followup_df = pd.read_csv(args.initialtofollowupcsv)
+        clean_center_name(inital_to_followup_df )
+        fig = make_interval_snapshot_chart(
+            inital_to_followup_df ,
+            title=f"Average Days between Initial Counseling and 1st Followup Counseling",
+            fiscal_year_tag=args.fiscalyear,
+            col_interval_data_value=NEOSERRA_COLUMNS.interval_data_value,
+            col_neo_center=NEOSERRA_COLUMNS.center
+        )
+        fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.initialtofollowupfigure}_.png"))
+
+    if args.trainingtocounsellingcsv:
+        training_to_counselling_df = pd.read_csv(args.trainingtocounsellingcsv)
+        clean_center_name(training_to_counselling_df )
+        fig = make_interval_snapshot_chart(
+            training_to_counselling_df,
+            title=f"Average Days between Training and 1st Counseling Session",
+            fiscal_year_tag=args.fiscalyear,
+            col_interval_data_value=NEOSERRA_COLUMNS.interval_data_value,
+            col_neo_center=NEOSERRA_COLUMNS.center
+        )
+        fig.write_image(os.path.join(args.outpath, f"{args.report}_{args.trainingtocounsellingfigure}_.png"))