{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "4201132e-811d-4c88-86cb-d24bb9e55549",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "67e3b5f9-b662-4ba4-85fc-debc0ad33d12",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b8d125cf-c22a-4a1b-8c8a-6eb5e9939969",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Clients: 11049\n",
"Sessions: 828614\n"
]
}
],
"source": [
"clients_df = pd.read_csv('naics_tagged_client_list.csv')\n",
"counseling_df = pd.read_csv('client_counsoling_sessions.csv')\n",
"\n",
"print(f\"Clients: {clients_df.shape[0]}\")\n",
"print(f\"Sessions: {counseling_df.shape[0]}\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f8bb3f3e-7d23-45b7-b6d0-6193631590ab",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Session Date | \n",
" Client | \n",
" Client ID | \n",
" Counselor | \n",
" Session Type | \n",
" Contact Type | \n",
" Center | \n",
" Prep+Contact | \n",
" Total Hours | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 9/30/2022 12:00 AM | \n",
" Butler Technologies (PI704874) | \n",
" PI704874 | \n",
" Towers, Kate | \n",
" Follow-up | \n",
" Online (email or chat) | \n",
" University of Pittsburgh SBDC | \n",
" 4.5 | \n",
" 4.5 | \n",
"
\n",
" \n",
" | 1 | \n",
" 9/30/2022 12:00 AM | \n",
" Louri Bean Creative (PI706063) | \n",
" PI706063 | \n",
" Wholihan, Michael | \n",
" Initial/New | \n",
" Outreach (face-to-face) | \n",
" University of Pittsburgh SBDC | \n",
" 3.0 | \n",
" 3.0 | \n",
"
\n",
" \n",
" | 2 | \n",
" 9/30/2022 12:00 AM | \n",
" Leverage Cleaning (PI705380) | \n",
" PI705380 | \n",
" Wholihan, Michael | \n",
" Follow-up | \n",
" Phone | \n",
" University of Pittsburgh SBDC | \n",
" 2.0 | \n",
" 2.0 | \n",
"
\n",
" \n",
" | 3 | \n",
" 9/30/2022 12:00 AM | \n",
" Scratch & co (PI704915) | \n",
" PI704915 | \n",
" Wholihan, Michael | \n",
" Follow-up | \n",
" Outreach (face-to-face) | \n",
" University of Pittsburgh SBDC | \n",
" 3.0 | \n",
" 3.0 | \n",
"
\n",
" \n",
" | 4 | \n",
" 9/30/2022 12:00 AM | \n",
" Diverse Industrial Solutions, LLC (IN001291) | \n",
" IN001291 | \n",
" Wholihan, Michael | \n",
" Initial/New | \n",
" Phone | \n",
" University of Pittsburgh SBDC | \n",
" 2.0 | \n",
" 2.0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Session Date Client Client ID \\\n",
"0 9/30/2022 12:00 AM Butler Technologies (PI704874) PI704874 \n",
"1 9/30/2022 12:00 AM Louri Bean Creative (PI706063) PI706063 \n",
"2 9/30/2022 12:00 AM Leverage Cleaning (PI705380) PI705380 \n",
"3 9/30/2022 12:00 AM Scratch & co (PI704915) PI704915 \n",
"4 9/30/2022 12:00 AM Diverse Industrial Solutions, LLC (IN001291) IN001291 \n",
"\n",
" Counselor Session Type Contact Type \\\n",
"0 Towers, Kate Follow-up Online (email or chat) \n",
"1 Wholihan, Michael Initial/New Outreach (face-to-face) \n",
"2 Wholihan, Michael Follow-up Phone \n",
"3 Wholihan, Michael Follow-up Outreach (face-to-face) \n",
"4 Wholihan, Michael Initial/New Phone \n",
"\n",
" Center Prep+Contact Total Hours \n",
"0 University of Pittsburgh SBDC 4.5 4.5 \n",
"1 University of Pittsburgh SBDC 3.0 3.0 \n",
"2 University of Pittsburgh SBDC 2.0 2.0 \n",
"3 University of Pittsburgh SBDC 3.0 3.0 \n",
"4 University of Pittsburgh SBDC 2.0 2.0 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"counseling_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "6cd5bca1-8895-4133-a71e-1a9e9cdd9f71",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Unnamed: 0 | \n",
" Client | \n",
" Client ID | \n",
" County Out of State | \n",
" Email | \n",
" Last Counseling | \n",
" NAICs | \n",
" Phone | \n",
" Physical Address | \n",
" Physical Address County | \n",
" Physical Address State | \n",
" Primary Contact | \n",
" Primary NAICS | \n",
" NAICS_2 | \n",
" PA NAICs Code Percentage | \n",
" PASBDC NAICs Code Percentage | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0 | \n",
" \\tProinnov@ LLC (WD04170) | \n",
" WD04170 | \n",
" False | \n",
" JardensonC@ICLOUD.com | \n",
" 9/9/2025 12:00 AM | \n",
" NaN | \n",
" (267) 748-4465 | \n",
" 6752 Oakland St. | \n",
" Philadelphia | \n",
" Pennsylvania | \n",
" Jardenson Castro | \n",
" NaN | \n",
" 0.0 | \n",
" 0.000000 | \n",
" 14.915377 | \n",
"
\n",
" \n",
" | 1 | \n",
" 1 | \n",
" \"C.J.A.\"/ Crawley Jones and Allen real estate... | \n",
" WD02759 | \n",
" False | \n",
" mrkcrawley@gmail.com | \n",
" 10/20/2025 12:00 AM | \n",
" 531390-OtherActivitiesRelatedtoRealEstate\\r\\r\\... | \n",
" (215) 290-9828 | \n",
" 673 Rively ave | \n",
" Delaware | \n",
" Pennsylvania | \n",
" mark crawley | \n",
" 531390 - Other Activities Related to Real Esta... | \n",
" 53.0 | \n",
" 2.510127 | \n",
" 2.688026 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" Anjie's Cleaning Bees (PS018402) | \n",
" PS018402 | \n",
" False | \n",
" anjelicagonzalez2001@gmail.com | \n",
" 10/14/2024 12:00 AM | \n",
" 561720-JanitorialServices\\r\\r\\n\\r\\r\\n | \n",
" (717) 521-3625 | \n",
" 1129 High St | \n",
" Lycoming | \n",
" Pennsylvania | \n",
" Anjelica Gonzez | \n",
" 561720 - Janitorial Services \\r\\r\\n | \n",
" 56.0 | \n",
" 3.605647 | \n",
" 4.344285 | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" BRENIMAN PROPERTIES, LLC (C8538) | \n",
" C8538 | \n",
" False | \n",
" r_breniman@yahoo.com | \n",
" 10/17/2025 12:00 AM | \n",
" 531120-LessorsofNonresidentialBuildings(except... | \n",
" NaN | \n",
" 147 Heeter Rd | \n",
" Clarion | \n",
" Pennsylvania | \n",
" RYAN BRENIMAN | \n",
" 531120 - Lessors of Nonresidential Buildings (... | \n",
" 53.0 | \n",
" 2.510127 | \n",
" 2.688026 | \n",
"
\n",
" \n",
" | 4 | \n",
" 4 | \n",
" Civil War Cider Co., Inc. (BU016079) | \n",
" BU016079 | \n",
" False | \n",
" rob@civilwarcider.com | \n",
" 10/21/2024 12:00 AM | \n",
" 312130-Wineries\\r\\r\\n\\r\\r\\n | \n",
" (570) 523-3414 | \n",
" 606 Market St. | \n",
" Union | \n",
" Pennsylvania | \n",
" Robert Antanitis, II | \n",
" 312130 - Wineries \\r\\r\\n | \n",
" 31.0 | \n",
" 2.876304 | \n",
" 4.923522 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Unnamed: 0 Client Client ID \\\n",
"0 0 \\tProinnov@ LLC (WD04170) WD04170 \n",
"1 1 \"C.J.A.\"/ Crawley Jones and Allen real estate... WD02759 \n",
"2 2 Anjie's Cleaning Bees (PS018402) PS018402 \n",
"3 3 BRENIMAN PROPERTIES, LLC (C8538) C8538 \n",
"4 4 Civil War Cider Co., Inc. (BU016079) BU016079 \n",
"\n",
" County Out of State Email Last Counseling \\\n",
"0 False JardensonC@ICLOUD.com 9/9/2025 12:00 AM \n",
"1 False mrkcrawley@gmail.com 10/20/2025 12:00 AM \n",
"2 False anjelicagonzalez2001@gmail.com 10/14/2024 12:00 AM \n",
"3 False r_breniman@yahoo.com 10/17/2025 12:00 AM \n",
"4 False rob@civilwarcider.com 10/21/2024 12:00 AM \n",
"\n",
" NAICs Phone \\\n",
"0 NaN (267) 748-4465 \n",
"1 531390-OtherActivitiesRelatedtoRealEstate\\r\\r\\... (215) 290-9828 \n",
"2 561720-JanitorialServices\\r\\r\\n\\r\\r\\n (717) 521-3625 \n",
"3 531120-LessorsofNonresidentialBuildings(except... NaN \n",
"4 312130-Wineries\\r\\r\\n\\r\\r\\n (570) 523-3414 \n",
"\n",
" Physical Address Physical Address County Physical Address State \\\n",
"0 6752 Oakland St. Philadelphia Pennsylvania \n",
"1 673 Rively ave Delaware Pennsylvania \n",
"2 1129 High St Lycoming Pennsylvania \n",
"3 147 Heeter Rd Clarion Pennsylvania \n",
"4 606 Market St. Union Pennsylvania \n",
"\n",
" Primary Contact Primary NAICS \\\n",
"0 Jardenson Castro NaN \n",
"1 mark crawley 531390 - Other Activities Related to Real Esta... \n",
"2 Anjelica Gonzez 561720 - Janitorial Services \\r\\r\\n \n",
"3 RYAN BRENIMAN 531120 - Lessors of Nonresidential Buildings (... \n",
"4 Robert Antanitis, II 312130 - Wineries \\r\\r\\n \n",
"\n",
" NAICS_2 PA NAICs Code Percentage PASBDC NAICs Code Percentage \n",
"0 0.0 0.000000 14.915377 \n",
"1 53.0 2.510127 2.688026 \n",
"2 56.0 3.605647 4.344285 \n",
"3 53.0 2.510127 2.688026 \n",
"4 31.0 2.876304 4.923522 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"clients_df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "694bb828-bbdc-4f6d-a002-ec9d8f603ed5",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}