Skip to content

Commit 8bd4c1e

Browse files
cclebergccleberg
committed
add terminations notebook
1 parent 8e4ddbe commit 8bd4c1e

9 files changed

Lines changed: 524 additions & 1 deletion

File tree

‎.gitignore‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
notebooks/.ipynb_checkpoints
1+
.ipynb_checkpoints/

‎notebooks/Untitled.ipynb‎

Lines changed: 137 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,137 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"id": "84b491a8-4ce7-44f3-aed9-feba2ddd1b3b",
7+
"metadata": {},
8+
"outputs": [
9+
{
10+
"ename": "FileNotFoundError",
11+
"evalue": "[Errno 2] No such file or directory: 'hr_terminations.csv'",
12+
"output_type": "error",
13+
"traceback": [
14+
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
15+
"\u001b[31mFileNotFoundError\u001b[39m Traceback (most recent call last)",
16+
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 4\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpandas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpd\u001b[39;00m\n\u001b[32m 3\u001b[39m \u001b[38;5;66;03m# Load the datasets\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m df_hr = \u001b[43mpd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mhr_terminations.csv\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[32m 5\u001b[39m df_app = pd.read_csv(\u001b[33m'\u001b[39m\u001b[33mapp_abc_users.csv\u001b[39m\u001b[33m'\u001b[39m)\n\u001b[32m 7\u001b[39m \u001b[38;5;66;03m# Convert date columns to actual datetime objects immediately\u001b[39;00m\n",
17+
"\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.1/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:1026\u001b[39m, in \u001b[36mread_csv\u001b[39m\u001b[34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[39m\n\u001b[32m 1013\u001b[39m kwds_defaults = _refine_defaults_read(\n\u001b[32m 1014\u001b[39m dialect,\n\u001b[32m 1015\u001b[39m delimiter,\n\u001b[32m (...)\u001b[39m\u001b[32m 1022\u001b[39m dtype_backend=dtype_backend,\n\u001b[32m 1023\u001b[39m )\n\u001b[32m 1024\u001b[39m kwds.update(kwds_defaults)\n\u001b[32m-> \u001b[39m\u001b[32m1026\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
18+
"\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.1/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:620\u001b[39m, in \u001b[36m_read\u001b[39m\u001b[34m(filepath_or_buffer, kwds)\u001b[39m\n\u001b[32m 617\u001b[39m _validate_names(kwds.get(\u001b[33m\"\u001b[39m\u001b[33mnames\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[32m 619\u001b[39m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m620\u001b[39m parser = \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 622\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[32m 623\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
19+
"\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.1/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:1620\u001b[39m, in \u001b[36mTextFileReader.__init__\u001b[39m\u001b[34m(self, f, engine, **kwds)\u001b[39m\n\u001b[32m 1617\u001b[39m \u001b[38;5;28mself\u001b[39m.options[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m] = kwds[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m]\n\u001b[32m 1619\u001b[39m \u001b[38;5;28mself\u001b[39m.handles: IOHandles | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1620\u001b[39m \u001b[38;5;28mself\u001b[39m._engine = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
20+
"\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.1/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:1880\u001b[39m, in \u001b[36mTextFileReader._make_engine\u001b[39m\u001b[34m(self, f, engine)\u001b[39m\n\u001b[32m 1878\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[32m 1879\u001b[39m mode += \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m-> \u001b[39m\u001b[32m1880\u001b[39m \u001b[38;5;28mself\u001b[39m.handles = \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1881\u001b[39m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1882\u001b[39m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1883\u001b[39m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1884\u001b[39m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mcompression\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1885\u001b[39m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmemory_map\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1886\u001b[39m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m=\u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1887\u001b[39m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding_errors\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstrict\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1888\u001b[39m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstorage_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1889\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1890\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m.handles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 1891\u001b[39m f = \u001b[38;5;28mself\u001b[39m.handles.handle\n",
21+
"\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.1/libexec/lib/python3.14/site-packages/pandas/io/common.py:873\u001b[39m, in \u001b[36mget_handle\u001b[39m\u001b[34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[39m\n\u001b[32m 868\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[32m 869\u001b[39m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[32m 870\u001b[39m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[32m 871\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m ioargs.encoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs.mode:\n\u001b[32m 872\u001b[39m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m873\u001b[39m handle = \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[32m 874\u001b[39m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 875\u001b[39m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 876\u001b[39m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 877\u001b[39m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 878\u001b[39m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 879\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 880\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 881\u001b[39m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[32m 882\u001b[39m handle = \u001b[38;5;28mopen\u001b[39m(handle, ioargs.mode)\n",
22+
"\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: 'hr_terminations.csv'"
23+
]
24+
}
25+
],
26+
"source": [
27+
"import pandas as pd\n",
28+
"\n",
29+
"# Load the datasets\n",
30+
"df_hr = pd.read_csv('hr_terminations.csv')\n",
31+
"df_app = pd.read_csv('app_abc_users.csv')\n",
32+
"\n",
33+
"# Convert date columns to actual datetime objects immediately\n",
34+
"df_hr['Term_Date'] = pd.to_datetime(df_hr['Term_Date'])\n",
35+
"df_app['Last_Login'] = pd.to_datetime(df_app['Last_Login'])\n",
36+
"\n",
37+
"print(f\"HR Records: {len(df_hr)}\")\n",
38+
"print(f\"App Records: {len(df_app)}\")\n",
39+
"df_hr.head()"
40+
]
41+
},
42+
{
43+
"cell_type": "code",
44+
"execution_count": null,
45+
"id": "f67f851a-ee33-405a-abf4-9393f1837047",
46+
"metadata": {},
47+
"outputs": [],
48+
"source": [
49+
"# Strip whitespace from IDs and Names to prevent 'false negatives'\n",
50+
"df_hr['Employee_ID'] = df_hr['Employee_ID'].str.strip()\n",
51+
"df_app['User_ID'] = df_app['User_ID'].str.strip()\n",
52+
"\n",
53+
"# Standardizing names for easier visual review later\n",
54+
"df_hr['Name'] = df_hr['Name'].str.strip().str.title()\n",
55+
"df_app['Full_Name'] = df_app['Full_Name'].str.strip().str.title()\n",
56+
"\n",
57+
"print(\"Data cleaning complete.\")"
58+
]
59+
},
60+
{
61+
"cell_type": "code",
62+
"execution_count": null,
63+
"id": "6a32518c-fe0a-4fb9-89fe-7796d5267957",
64+
"metadata": {},
65+
"outputs": [],
66+
"source": [
67+
"# We join on the ID. \n",
68+
"# We use 'left' because we only care about people on the termination list.\n",
69+
"audit_merge = pd.merge(\n",
70+
" df_hr, \n",
71+
" df_app, \n",
72+
" left_on='Employee_ID', \n",
73+
" right_on='User_ID', \n",
74+
" how='left'\n",
75+
")\n",
76+
"\n",
77+
"# Display the merged table\n",
78+
"audit_merge"
79+
]
80+
},
81+
{
82+
"cell_type": "code",
83+
"execution_count": null,
84+
"id": "b46cc115-8fee-476c-9f8c-6980d49a000f",
85+
"metadata": {},
86+
"outputs": [],
87+
"source": [
88+
"# 1. Identify Terminated but still 'Active' in Application\n",
89+
"active_leavers = audit_merge[audit_merge['Account_Status'] == 'Active'].copy()\n",
90+
"\n",
91+
"# 2. Identify Logins occurring AFTER termination date\n",
92+
"# This is a critical security finding indicating potential account misuse\n",
93+
"post_term_logins = audit_merge[audit_merge['Last_Login'] > audit_merge['Term_Date']].copy()\n",
94+
"\n",
95+
"print(f\"Finding 1: {len(active_leavers)} users still marked as 'Active'\")\n",
96+
"print(f\"Finding 2: {len(post_term_logins)} users logged in after termination\")"
97+
]
98+
},
99+
{
100+
"cell_type": "code",
101+
"execution_count": null,
102+
"id": "9644d4b3-9682-4ebe-acfc-1474218c58b0",
103+
"metadata": {},
104+
"outputs": [],
105+
"source": [
106+
"# Create a summary report\n",
107+
"with pd.ExcelWriter('Termination_Audit_Report.xlsx') as writer:\n",
108+
" active_leavers.to_excel(writer, sheet_name='Active_Leavers', index=False)\n",
109+
" post_term_logins.to_excel(writer, sheet_name='Post_Term_Logins', index=False)\n",
110+
" audit_merge.to_excel(writer, sheet_name='Full_Traceability_Matrix', index=False)\n",
111+
"\n",
112+
"print(\"Audit Report Exported: Termination_Audit_Report.xlsx\")"
113+
]
114+
}
115+
],
116+
"metadata": {
117+
"kernelspec": {
118+
"display_name": "Python 3 (ipykernel)",
119+
"language": "python",
120+
"name": "python3"
121+
},
122+
"language_info": {
123+
"codemirror_mode": {
124+
"name": "ipython",
125+
"version": 3
126+
},
127+
"file_extension": ".py",
128+
"mimetype": "text/x-python",
129+
"name": "python",
130+
"nbconvert_exporter": "python",
131+
"pygments_lexer": "ipython3",
132+
"version": "3.14.2"
133+
}
134+
},
135+
"nbformat": 4,
136+
"nbformat_minor": 5
137+
}

notebooks/basic_data_analysis.ipynb renamed to notebooks/basic_data_analysis/basic_data_analysis.ipynb

File renamed without changes.

notebooks/racf_access_analysis.ipynb renamed to notebooks/racf_access_analysis/racf_access_analysis.ipynb

File renamed without changes.

notebooks/sample_racf_data.txt renamed to notebooks/racf_access_analysis/sample_racf_data.txt

File renamed without changes.

‎notebooks/terminations/Termination_Audit_Report.xlsx‎

6.65 KB
Binary file not shown.

0 commit comments

Comments
 (0)