initial commit

discount-rate.py

@@ -0,0 +1,65 @@
+import random
+import pandas as pd
+from faker import Faker
+
+fake = Faker()
+
+def generate_student_data(num_students):
+    data = []
+
+    for _ in range(num_students):
+        # Generate basic student data
+        student_id = fake.unique.uuid4()
+        student_type = random.choice(['First-time Freshmen', 'Transfer Student', 'Graduate Student', 'Audit Student'])
+        major = fake.word().capitalize()
+        gpa = round(random.uniform(2.0, 4.0), 2)
+        sat_score = random.randint(800, 1600)
+        act_score = random.randint(1, 36)
+        state = fake.state()
+        zip_code = fake.zipcode()
+        country = fake.country()
+        first_generation = random.choice([True, False])
+        need_rank = random.randint(1, 6)
+        efc = random.randint(0, 100000)  # Expected Family Contribution
+        financial_aid_package = random.randint(1000, 50000)  # Financial aid package amount
+
+        # Published tuition price for calculation of discount rate
+        published_tuition_price = random.randint(30000, 70000)
+        discount_rate = round((financial_aid_package / published_tuition_price) * 100, 2)
+
+        # Enrollment funnel stages
+        funnel_stage = random.choice(['Lead', 'Prospect', 'Applied', 'Admitted', 'Waitlisted', 'Denied', 'Deposited', 'Enrolled'])
+
+        # Generate synthetic data point
+        student_data = {
+            'Student ID': student_id,
+            'Student Type': student_type,
+            'Major': major,
+            'GPA': gpa,
+            'SAT Score': sat_score,
+            'ACT Score': act_score,
+            'State': state,
+            'Zip Code': zip_code,
+            'Country': country,
+            'First Generation': first_generation,
+            'Need Rank': need_rank,
+            'EFC': efc,
+            'Financial Aid Package': financial_aid_package,
+            'Published Tuition Price': published_tuition_price,
+            'Discount Rate': discount_rate,
+            'Funnel Stage': funnel_stage
+        }
+
+        data.append(student_data)
+
+    return pd.DataFrame(data)
+
+# Generate synthetic data for 1000 students
+num_students = 1000
+student_df = generate_student_data(num_students)
+
+# Save the data to a CSV file
+student_df.to_csv('synthetic_student_data.csv', index=False)
+
+# Display the first few rows of the generated data
+print(student_df.head())

enrollment_funnel.csv

@@ -0,0 +1,7 @@
+Stage,Number of Students,Major,Average GPA,Average SAT Score,Average ACT Score,FAFSA Submitted (%)
+Lead,623,Health Sciences,3.5316770756441245,907,31,74.35827527016656
+Prospect,2493,Engineering,3.267485520320892,1524,31,82.22203363168144
+Applied,3217,Science,2.7354665240742904,1152,19,77.48081160042938
+Admitted,2693,Arts,3.065928947863109,1591,30,41.523607636679706
+Deposited,2068,Science,2.50389253657547,1202,31,83.36074905373616
+Enrolled,1853,Science,3.8024516605533805,1538,24,57.707333539656275

enrollment_management.csv

@@ -0,0 +1,61 @@
+Term,Cohort Size,Financial Aid Packages,Discount Rate (%),First-time Freshmen (%),Transfer Students (%),Graduate Students (%),Audit Students (%)
+Fall,441,6816,33.982362667289095,58.77819010304718,29.918624840606583,10.7630274706883,1.1875858711648797
+Spring,184,5569,59.08610601342477,64.61280531313804,11.117423093547,16.05651058764529,2.0746899281012294
+Summer,244,10442,51.43785312539856,59.544543155733635,24.740711135820177,18.728815125036597,1.0887389681212065
+Fall,450,6895,31.232025503036272,46.20053079630236,20.91831540329978,19.380536111117692,2.9926607465835717
+Spring,177,24117,41.96462704334384,48.218833819634014,24.11662967757389,5.867958466365611,2.9048427871560567
+Summer,82,8863,43.005622127422264,46.437673591251226,29.3730388794827,10.917826979121948,4.325485960250004
+Fall,225,17913,52.32127928997346,51.317772496839275,23.76060020350078,6.601340989038266,2.2311089590841977
+Spring,492,12455,37.525815820399835,41.16889396930701,26.739277484747475,10.034900971954448,4.265542940852249
+Summer,420,9014,35.5300102299411,58.547616530136786,27.337374106216828,7.5451985584334835,4.871895061759292
+Fall,424,16093,32.42618899851593,50.096626446661794,26.7696152752797,14.702725425030858,1.3536328934625863
+Spring,71,23070,42.84943424820323,59.67167906142227,18.52182950093882,10.824025759848084,4.167271357878532
+Summer,287,8009,50.65499702296099,51.56189862896695,14.45152835142061,8.440921185574245,3.3598235885505443
+Fall,207,21538,31.745807865253308,60.448410069183694,17.933032039085038,8.989068874463584,2.9201838680739005
+Spring,87,15729,57.456411828794415,50.2187370839272,27.837938175535534,10.405176428079024,2.6821431146603003
+Summer,279,6409,43.27056689193313,47.82083584707709,12.93209643384051,8.89924794281394,4.138673055777238
+Fall,414,17249,37.1936207747221,54.881123628802186,20.266523373847857,11.798612702432465,3.5574454278969694
+Spring,100,5784,32.816198702438754,60.78671076075818,14.664561448490556,5.484739266644757,4.2201786700774475
+Summer,487,13096,35.48597991321922,50.45009813359592,21.626108344535645,9.196452607534185,4.612604234706505
+Fall,313,12560,58.03841992019129,68.09944455567123,27.262770439780077,11.168100813082795,3.469054848389168
+Spring,332,17533,49.14811781530051,41.175589800269385,27.607199372768335,14.041728230349477,4.9218509003695115
+Summer,76,12343,45.500887722797,52.53838095146736,14.733703873641575,9.064364637726948,3.432351398167541
+Fall,275,12206,49.713339855005,69.02741654560742,28.153874126970926,6.9977768783562455,3.5465772864891303
+Spring,326,10801,43.07018696033673,56.439156497442625,21.837774776425686,6.143005693987448,3.2192624341689027
+Summer,335,24190,51.90117949685455,52.704128269243554,17.00436493400627,19.107977407030752,1.3640083642053211
+Fall,146,21921,31.431483830749464,57.05560851249875,24.163623911663997,11.249585866077188,3.905588130600913
+Spring,333,10986,46.98111631482229,57.27773725774254,19.633339759282308,13.717439317712394,3.1897852275964462
+Summer,416,23225,34.75939342927473,61.94943265898921,17.55975180244509,18.787648277533393,2.8036417896644177
+Fall,497,15647,33.60493943416927,43.83069188267397,24.101687285933195,6.241226300529592,4.6418851136130925
+Spring,366,13716,40.25639000149205,47.50049347648314,14.974483088605758,18.14992228888689,2.191837806167802
+Summer,353,24334,32.75397197440326,57.416320370317294,16.60505058038197,13.27381808816105,3.0944091040600448
+Fall,196,17323,32.8247096480568,66.01349821629167,18.689036889765426,7.472513917055014,3.7905674859738534
+Spring,53,9780,39.34239928173883,56.85600076431321,15.073643477462774,11.168826748780535,4.185887102695509
+Summer,84,7368,59.38531585864526,47.157905793710206,18.104041735628343,16.664034256028383,2.8373872317846898
+Fall,241,17039,35.25990809668016,60.39534339700737,21.429460504100213,12.20555122799532,4.368365660074838
+Spring,98,11655,30.514833054952508,62.19726281342123,24.819477218213365,19.779290759982565,4.07567096526159
+Summer,66,13173,52.90093269011733,47.14708457211938,25.343897062171436,10.651084549069111,1.2649439114074634
+Fall,221,9495,54.207389311523386,51.33186658528885,26.455807037533862,16.24367449964108,1.1834450656185318
+Spring,269,15893,40.38912963268203,56.0298242059169,24.88423313886596,10.894841734682887,3.483222737688365
+Summer,207,18403,43.940214388188345,54.896835720492334,23.620788541938182,17.437463310597714,2.389653632901657
+Fall,95,18121,49.4932104792829,51.688542586576105,14.750129425849398,13.536222037486215,1.8365231643140567
+Spring,422,15966,31.441767725911014,48.92905523527933,18.004457857440496,5.95267744385002,3.3185997378869536
+Summer,55,5853,58.474371947741574,42.9995466148559,19.554297817604553,5.552328014539871,2.36625284182618
+Fall,148,21958,56.60041161894142,41.60455890242107,11.657826433867085,7.007781782009498,3.1490536668562803
+Spring,429,22532,37.82680870025142,68.75624490649595,20.567402425944184,5.205079472404959,2.840476635934288
+Summer,282,14907,30.45913620871154,65.41429432286769,18.72671663213112,6.130385905286935,3.3390644237966147
+Fall,86,9777,58.00308924238449,50.64715571388162,26.04218498053468,15.37571595753368,2.6012019556411254
+Spring,329,20338,45.03119651745777,68.70402655379368,29.558013375085416,13.015194125441946,3.790670294787727
+Summer,398,7491,46.18132345200188,60.3030971327291,21.120100772851693,16.24866124204958,1.7202690893971941
+Fall,351,20328,50.518913081944234,54.47562848927927,16.453727765551672,18.69748628386464,3.786005864908316
+Spring,230,19599,48.47553493169741,54.79076973315415,10.868015665963455,13.77724298488208,2.6466448574301125
+Summer,144,24508,58.31674813682271,42.49853233585779,28.49286660447192,15.89181266107772,4.497270419417669
+Fall,148,8051,58.327547913755026,42.75112441775443,28.38231430557319,16.35621803063684,3.0609442194568435
+Spring,237,20979,56.01596800665011,58.073227777033566,15.059803359784823,10.667758239136797,4.892441397080417
+Summer,165,21388,49.09210792338034,56.61109157037402,23.90822246213295,8.616272484944478,3.407741582163841
+Fall,240,5876,54.02847884047199,46.38183685072687,11.508690941795386,8.075679927597873,1.8953962636252824
+Spring,302,9142,50.315050271489454,68.38583628645071,13.324308638185059,8.771636592676977,4.287162547377797
+Summer,465,20202,47.201011250158004,63.43888151413608,14.336182131729824,9.120976955388631,2.380330511289547
+Fall,210,11966,33.855010597017305,43.403938060523444,15.889878936788598,8.108414735120846,2.390476857930734
+Spring,305,12079,54.33612530208009,67.92787317061878,29.916627500587413,18.173310012187883,1.1272187259406605
+Summer,372,12987,54.61918427231866,69.22744625603231,23.938501117276296,16.35498698258343,3.1948612368296345

melt-rate.py

@@ -0,0 +1,72 @@
+import pandas as pd
+import numpy as np
+
+# Set random seed for reproducibility
+np.random.seed(42)
+
+# Define probabilities for each stage transition
+stage_probabilities = {
+    'Lead': 0.25,
+    'Prospect': 0.20,
+    'Applied': 0.25,
+    'Admitted': 0.24,
+    'Deposited': 0.05,
+    'Enrolled': 0.01
+}
+
+# Ensure the probabilities sum to 1 for initial stage assignment
+total_probability = sum(stage_probabilities.values())
+stage_probabilities_normalized = {k: v / total_probability for k, v in stage_probabilities.items()}
+
+# Generate synthetic data for enrollment funnel with student IDs
+num_students = 30000
+stages = ['Lead', 'Prospect', 'Applied', 'Admitted', 'Deposited', 'Enrolled']
+majors = ['Science', 'Arts', 'Engineering', 'Business', 'Health Sciences']
+enrollment_funnel = {
+    'Student_ID': [f'S{1000+i}' for i in range(num_students)],
+    'Stage': np.random.choice(list(stage_probabilities_normalized.keys()), size=num_students,
+                              p=list(stage_probabilities_normalized.values())),
+    'Major': np.random.choice(majors, size=num_students),
+    'Average GPA': np.random.uniform(2.5, 4.0, size=num_students),
+    'Average SAT Score': np.random.randint(900, 1600, size=num_students),
+    'Average ACT Score': np.random.randint(18, 36, size=num_students),
+    'FAFSA Submitted (%)': np.random.uniform(40, 90, size=num_students)
+}
+
+# Create DataFrame
+df_enrollment_funnel = pd.DataFrame(enrollment_funnel)
+
+# Function to simulate student progression through stages
+def simulate_progression(df):
+    progression = df.copy()
+    for stage in stages[1:]:
+        previous_stage = stages[stages.index(stage) - 1]
+        transition_prob = stage_probabilities.get(stage, 0.5)
+        in_previous_stage = progression['Stage'] == previous_stage
+        progressed = in_previous_stage & (np.random.rand(len(progression)) < transition_prob)
+        progression.loc[progressed, 'Stage'] = stage
+    return progression
+
+# Simulate student progression through stages
+df_enrollment_funnel = simulate_progression(df_enrollment_funnel)
+
+# Filter students who reached the 'Deposited' stage but did not enroll
+deposited_students = df_enrollment_funnel[df_enrollment_funnel['Stage'] == 'Deposited']
+enrolled_students = df_enrollment_funnel[df_enrollment_funnel['Stage'] == 'Enrolled']
+
+# Identify melted students (Deposited but not Enrolled)
+melted_students = deposited_students[~deposited_students['Student_ID'].isin(enrolled_students['Student_ID'])]
+
+# Calculate melt rate
+total_deposited = len(deposited_students)
+total_melted = len(melted_students)
+melt_rate = (total_melted / total_deposited) * 100 if total_deposited > 0 else 0
+
+print(f"Total Deposited Students: {total_deposited}")
+print(f"Total Melted Students: {total_melted}")
+print(f"Melt Rate: {melt_rate:.2f}%")
+
+# Save melted students to CSV for further analysis
+melted_students.to_csv('melted_students.csv', index=False)
+
+print("Melt rate calculated and melted students identified.")

private_universities.csv

@@ -0,0 +1,21 @@
+University,Funding from Tuition and Donations (%),Board Size,President Reports To,Enrollment,Average Class Size,Student-Faculty Ratio,Endowment per Student ($),Retention Rate (%)
+Private University 1,100,48,Board of Trustees,3433,27,11.0,48044,86.3
+Private University 2,100,38,Board of Trustees,6311,13,9.5,61214,92.9
+Private University 3,100,24,Board of Trustees,6051,23,12.0,71228,91.3
+Private University 4,100,17,Board of Trustees,7420,27,8.2,58984,81.2
+Private University 5,100,30,Board of Trustees,18568,18,13.9,50774,72.4
+Private University 6,100,48,Board of Trustees,7396,11,11.1,12568,79.3
+Private University 7,100,28,Board of Trustees,9666,29,10.8,72592,86.7
+Private University 8,100,32,Board of Trustees,19942,24,14.5,77563,86.6
+Private University 9,100,20,Board of Trustees,19431,16,13.1,12695,84.8
+Private University 10,100,20,Board of Trustees,3747,21,10.3,58190,76.9
+Private University 11,100,33,Board of Trustees,1189,17,12.0,15258,84.0
+Private University 12,100,45,Board of Trustees,4005,24,11.6,97538,79.6
+Private University 13,100,49,Board of Trustees,2899,12,14.7,49504,94.3
+Private University 14,100,33,Board of Trustees,2267,23,13.9,43159,91.2
+Private University 15,100,12,Board of Trustees,18912,26,13.2,23986,88.0
+Private University 16,100,31,Board of Trustees,12394,13,11.8,71858,75.9
+Private University 17,100,11,Board of Trustees,4556,27,12.1,22666,76.4
+Private University 18,100,33,Board of Trustees,4890,17,14.8,48660,71.0
+Private University 19,100,39,Board of Trustees,9838,13,12.2,13561,87.8
+Private University 20,100,47,Board of Trustees,15502,11,9.9,36854,72.8

public_universities.csv

@@ -0,0 +1,21 @@
+University,Funding from State (%),Board Size,President Reports To,Enrollment,State Funding Stability,Average Class Size,Student-Faculty Ratio,Endowment per Student ($),Retention Rate (%)
+Public University 1,47,11,State’s Regents,30230,Stable,46,23.2,35306,70.1
+Public University 2,32,11,State’s Regents,35707,Variable,46,23.0,21646,82.2
+Public University 3,38,14,State’s Regents,41976,Variable,31,16.5,36065,81.3
+Public University 4,50,12,State’s Regents,64262,Variable,31,20.1,30199,83.4
+Public University 5,26,10,State’s Regents,43776,Variable,34,22.0,46976,79.6
+Public University 6,36,10,State’s Regents,50080,Stable,30,23.6,21371,76.7
+Public University 7,39,13,State’s Regents,21306,Variable,30,18.3,16835,74.5
+Public University 8,48,14,State’s Regents,26776,Stable,48,17.2,7049,69.3
+Public University 9,23,9,State’s Regents,47251,Variable,31,22.1,36616,83.5
+Public University 10,49,13,State’s Regents,29474,Stable,41,23.1,43191,84.3
+Public University 11,24,14,State’s Regents,60294,Variable,35,18.5,25932,67.1
+Public University 12,42,12,State’s Regents,41959,Variable,33,16.0,34855,67.6
+Public University 13,26,12,State’s Regents,25530,Variable,40,24.4,12158,72.1
+Public University 14,32,12,State’s Regents,49320,Variable,46,19.0,48016,71.2
+Public University 15,34,12,State’s Regents,23748,Stable,35,20.2,12400,84.9
+Public University 16,30,12,State’s Regents,51968,Variable,34,23.4,47642,64.4
+Public University 17,48,14,State’s Regents,52562,Stable,49,21.8,20151,60.5
+Public University 18,23,14,State’s Regents,33545,Stable,31,22.4,6154,72.3
+Public University 19,32,11,State’s Regents,20663,Stable,35,17.1,9499,64.5
+Public University 20,26,10,State’s Regents,54766,Stable,40,20.4,11295,69.2

small-university.py

@@ -0,0 +1,73 @@
+import pandas as pd
+import numpy as np
+from faker import Faker
+
+# Initialize Faker for generating fake data
+fake = Faker()
+
+# Set random seed for reproducibility
+np.random.seed(42)
+
+# Generate synthetic data for small private universities
+private_universities = {
+    'University': [f'Private University {i}' for i in range(1, 21)],
+    'Funding from Tuition and Donations (%)': [100] * 20,
+    'Board Size': np.random.randint(10, 51, size=20),
+    'President Reports To': ['Board of Trustees'] * 20,
+    'Enrollment': np.random.randint(1000, 20001, size=20),
+    'Average Class Size': np.random.randint(10, 30, size=20),
+    'Student-Faculty Ratio': np.round(np.random.uniform(8, 15, size=20), 1),
+    'Endowment per Student ($)': np.random.randint(10000, 100000, size=20),
+    'Retention Rate (%)': np.round(np.random.uniform(70, 95, size=20), 1)
+}
+
+# Generate synthetic data for public universities
+public_universities = {
+    'University': [f'Public University {i}' for i in range(1, 21)],
+    'Funding from State (%)': np.random.randint(20, 51, size=20),
+    'Board Size': np.random.randint(9, 16, size=20),
+    'President Reports To': ['State’s Regents'] * 20,
+    'Enrollment': np.random.randint(20000, 70001, size=20),
+    'State Funding Stability': np.random.choice(['Stable', 'Variable'], size=20),
+    'Average Class Size': np.random.randint(30, 50, size=20),
+    'Student-Faculty Ratio': np.round(np.random.uniform(15, 25, size=20), 1),
+    'Endowment per Student ($)': np.random.randint(5000, 50000, size=20),
+    'Retention Rate (%)': np.round(np.random.uniform(60, 85, size=20), 1)
+}
+
+# Generate synthetic data for enrollment management
+enrollment_management = {
+    'Term': ['Fall', 'Spring', 'Summer'] * 20,
+    'Cohort Size': np.random.randint(50, 500, size=60),
+    'Financial Aid Packages': np.random.randint(5000, 25000, size=60),
+    'Discount Rate (%)': np.random.uniform(30, 60, size=60),
+    'First-time Freshmen (%)': np.random.uniform(40, 70, size=60),
+    'Transfer Students (%)': np.random.uniform(10, 30, size=60),
+    'Graduate Students (%)': np.random.uniform(5, 20, size=60),
+    'Audit Students (%)': np.random.uniform(1, 5, size=60)
+}
+
+# Generate synthetic data for enrollment funnel
+enrollment_funnel = {
+    'Stage': ['Lead', 'Prospect', 'Applied', 'Admitted', 'Deposited', 'Enrolled'],
+    'Number of Students': np.random.randint(100, 5000, size=6),
+    'Major': np.random.choice(['Science', 'Arts', 'Engineering', 'Business', 'Health Sciences'], size=6),
+    'Average GPA': np.random.uniform(2.5, 4.0, size=6),
+    'Average SAT Score': np.random.randint(900, 1600, size=6),
+    'Average ACT Score': np.random.randint(18, 36, size=6),
+    'FAFSA Submitted (%)': np.random.uniform(40, 90, size=6)
+}
+
+# Create DataFrames
+df_private = pd.DataFrame(private_universities)
+df_public = pd.DataFrame(public_universities)
+df_enrollment_management = pd.DataFrame(enrollment_management)
+df_enrollment_funnel = pd.DataFrame(enrollment_funnel)
+
+# Save to CSV files
+df_private.to_csv('private_universities.csv', index=False)
+df_public.to_csv('public_universities.csv', index=False)
+df_enrollment_management.to_csv('enrollment_management.csv', index=False)
+df_enrollment_funnel.to_csv('enrollment_funnel.csv', index=False)
+
+print("Synthetic data generated and saved to CSV files.")