undergrad-uh401/explore.ipynb

In [1]:

!pip install -r requirements.txt

Requirement already satisfied: awkward in /opt/conda/lib/python3.12/site-packages (from -r requirements.txt (line 1)) (2.8.10)
Requirement already satisfied: pandas in /opt/conda/lib/python3.12/site-packages (from -r requirements.txt (line 2)) (2.3.0)
Requirement already satisfied: numpy in /opt/conda/lib/python3.12/site-packages (from -r requirements.txt (line 3)) (2.2.6)
Requirement already satisfied: tqdm in /opt/conda/lib/python3.12/site-packages (from -r requirements.txt (line 5)) (4.67.1)
Requirement already satisfied: awkward-cpp==50 in /opt/conda/lib/python3.12/site-packages (from awkward->-r requirements.txt (line 1)) (50)
Requirement already satisfied: fsspec>=2022.11.0 in /opt/conda/lib/python3.12/site-packages (from awkward->-r requirements.txt (line 1)) (2025.5.1)
Requirement already satisfied: packaging in /opt/conda/lib/python3.12/site-packages (from awkward->-r requirements.txt (line 1)) (25.0)
Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.12/site-packages (from pandas->-r requirements.txt (line 2)) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.12/site-packages (from pandas->-r requirements.txt (line 2)) (2025.2)
Requirement already satisfied: tzdata>=2022.7 in /opt/conda/lib/python3.12/site-packages (from pandas->-r requirements.txt (line 2)) (2025.2)
Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas->-r requirements.txt (line 2)) (1.17.0)

In [30]:

import os

import numpy as np
import awkward as ak
import matplotlib.pyplot as plt
import pandas as pd

In [3]:

scorecard_dir = "data/scorecard"
scorecard_dir = os.path.join(scorecard_dir, os.listdir(scorecard_dir)[0])
data = ak.from_parquet(os.path.join(scorecard_dir, "merged.parquet"))

In [118]:

mask_nan = ~ak.any(np.isnan(data.academics.program_percentage.physical_science), axis=1)
mask_all_zero = ~ak.all(data.academics.program_percentage.physical_science == 0, axis=1)
mask = mask_nan & mask_all_zero
data_m = data[mask]

data_ua = data[data.school.name[:, -1] == "The University of Alabama"][0]

National Stats¶

In [119]:

for key in data_m.academics.program_percentage.fields:
    mean = ak.mean(data_m.academics.program_percentage[key], axis=0)
    if ak.all(mean < 0.03):
        continue
    plt.plot(mean * 100, label=key)
plt.xlabel("Year")
plt.ylabel("Percent Enrollment")
plt.title("Average Enrollment (National)")
plt.legend()
plt.show()

In [139]:

# Mean, nationwide, across all years
vals = {}
percents = data_m.academics.program_percentage
for key in percents.fields:
    vals[key] = ak.mean(percents[key]) * 100
df = pd.DataFrame({'Name': vals.keys(), 'Percent': vals.values() })
df.sort_values("Percent", ascending=False)

Out[139]:

<style scoped=""> .dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; } </style>

	Name	Percent
36	business_marketing	17.399856
35	health	12.027962
15	humanities	9.546438
8	education	6.705871
29	social_science	6.253486
26	psychology	5.195744
17	biological	4.908001
34	visual_performing	3.903754
4	communication	3.192944
27	security_law_enforcement	3.019295
6	computer	2.808726
9	engineering	2.803155
14	english	2.671756
20	multidiscipline	1.964365
21	parks_recreation_fitness	1.885363
37	history	1.670524
28	public_administration_social_service	1.601816
24	physical_science	1.598245
10	engineering_technology	1.377941
12	family_consumer_science	1.222658
18	mathematics	1.048517
11	language	0.951896
0	agriculture	0.819862
31	mechanic_repair_technology	0.811160
1	resources	0.700875
22	philosophy_religious	0.677424
7	personal_culinary	0.444786
23	theology_religious_vocation	0.432991
32	precision_production	0.379921
3	ethnic_cultural_gender	0.368425
13	legal	0.366860
33	transportation	0.331288
30	construction	0.317400
2	architecture	0.243856
5	communications_technology	0.215724
25	science_technology	0.080646
19	military	0.035292
16	library	0.012911

In [140]:

# Mean, nationwide, across latest year
vals = {}
percents = data_m.academics.program_percentage
for key in percents.fields:
    vals[key] = ak.mean(percents[key, -1]) * 100
df = pd.DataFrame({'Name': vals.keys(), 'Percent': vals.values() })
df.sort_values("Percent", ascending=False)

Out[140]:

<style scoped=""> .dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; } </style>

	Name	Percent
35	health	22.149643
36	business_marketing	14.511786
15	humanities	10.181786
8	education	7.426786
6	computer	7.148571
31	mechanic_repair_technology	6.220357
27	security_law_enforcement	4.961071
10	engineering_technology	3.409286
20	multidiscipline	2.957857
12	family_consumer_science	2.880357
32	precision_production	2.701429
17	biological	2.671786
29	social_science	2.312143
28	public_administration_social_service	1.677500
26	psychology	1.285714
4	communication	1.136786
9	engineering	0.972143
34	visual_performing	0.807500
7	personal_culinary	0.698571
11	language	0.633929
18	mathematics	0.611071
21	parks_recreation_fitness	0.593214
30	construction	0.573571
13	legal	0.529286
24	physical_science	0.421429
14	english	0.237500
37	history	0.208929
22	philosophy_religious	0.072500
3	ethnic_cultural_gender	0.007500
1	resources	0.000000
5	communications_technology	0.000000
2	architecture	0.000000
0	agriculture	0.000000
16	library	0.000000
19	military	0.000000
25	science_technology	0.000000
23	theology_religious_vocation	0.000000
33	transportation	0.000000

Enrollment, UA¶

In [141]:

plt.clf()
for key in data_ua.academics.program_percentage.fields:
    vals = data_ua.academics.program_percentage[key]
    if ak.sum(vals) == 0:
        continue
    if ak.all(vals < 0.05):
        continue

    plt.plot(vals * 100, label=key)
plt.xlabel("Year")
plt.ylabel("Percent Enrollment")
plt.title("Average Enrollment (UA)")
plt.legend()
plt.show()


vals = {}
data_m = data_ua.academics.program_percentage
for key in data_m.fields:
    vals[key] = data_m[key][-1] * 100
    
df = pd.DataFrame({'Name': vals.keys(), 'Percent': vals.values() })
display(df.sort_values("Percent", ascending=False))
display(sum(df['Percent']))

<style scoped=""> .dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; } </style>

	Name	Percent
36	business_marketing	30.11
9	engineering	9.66
35	health	9.66
4	communication	9.42
29	social_science	7.99
12	family_consumer_science	6.96
26	psychology	5.13
17	biological	3.89
21	parks_recreation_fitness	2.86
8	education	2.72
34	visual_performing	2.17
20	multidiscipline	1.72
6	computer	1.44
37	history	1.17
28	public_administration_social_service	1.09
24	physical_science	1.06
14	english	0.97
18	mathematics	0.89
11	language	0.45
1	resources	0.38
22	philosophy_religious	0.18
3	ethnic_cultural_gender	0.09
5	communications_technology	0.00
2	architecture	0.00
0	agriculture	0.00
16	library	0.00
10	engineering_technology	0.00
7	personal_culinary	0.00
15	humanities	0.00
13	legal	0.00
19	military	0.00
27	security_law_enforcement	0.00
23	theology_religious_vocation	0.00
25	science_technology	0.00
33	transportation	0.00
32	precision_production	0.00
31	mechanic_repair_technology	0.00
30	construction	0.00

100.00999999999999

Misc. Stats (Fun)¶

In [142]:

avg_students = ak.mean(data.student.enrollment.undergrad_12_month, axis=1)
plt.hist(avg_students, bins=np.arange(0, 100_000, 1_000))
plt.xlabel("Students Enrolled")
plt.ylabel("Univeristy Count")
plt.title("Enrollemnt Distribution (Average)")
plt.yscale("log")

In [143]:

plt.hist(data.student.enrollment.undergrad_12_month[:, -1], bins=np.arange(0, 100_000, 1_000))
plt.xlabel("Students Enrolled")
plt.ylabel("Univeristy Count")
plt.title("Enrollemnt Distribution (Last Year)")
plt.yscale("log")

In [144]:

plt.hist(data.admissions.admission_rate.overall[:, -1])

Out[144]:

(array([ 35.,  48.,  40.,  75., 118., 158., 227., 334., 389., 522.]),
 array([0. , 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1. ]),
 <BarContainer object of 10 artists>)

In [145]:

data.school.fields

Out[145]:

['name',
 'city',
 'state',
 'zip',
 'accreditor',
 'school_url',
 'price_calculator_url',
 'degrees_awarded',
 'under_investigation',
 'main_campus',
 'branches',
 'ownership',
 'state_fips',
 'region_id',
 'locale',
 'degree_urbanization',
 'carnegie_basic',
 'carnegie_undergrad',
 'carnegie_size_setting',
 'minority_serving',
 'men_only',
 'women_only',
 'religious_affiliation',
 'online_only',
 'operating',
 'tuition_revenue_per_fte',
 'instructional_expenditure_per_fte',
 'faculty_salary',
 'ft_faculty_rate',
 'alias',
 'institutional_characteristics',
 'open_admissions_policy',
 'accreditor_code',
 'title_iv',
 'ownership_peps',
 'endowment',
 'dolflag',
 'peps_ownership',
 'address',
 'sector']