feat: final push for submission

scorecard_tools.py

@@ -0,0 +1,162 @@
+import os
+import logging
+
+import awkward as ak
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+
+logger = logging.getLogger("Scorecard Data")
+
+
+def mask_valid(data):
+    # Strip out NaN and zero placeholders
+    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 = data[mask]
+
+    return data
+
+def mask_school(data, name):
+    return data[data.school.name[:, -1] == name][0]
+
+
+# Percentage enrollment per field over time averaged across the nation
+def save_scorecard_stats_national(output_dir, data, ext="png"):
+    prog_percentage = data.academics.program_percentage
+    students = data.student.enrollment.undergrad_12_month
+
+    # Percent enrollment
+    for key in prog_percentage.fields:
+        # Find the mean across the nation
+        mean = ak.mean(prog_percentage[key], axis=0)
+        if ak.all(mean < 0.05):
+            continue
+        plt.plot(mean * 100, label=key)
+    plt.xlabel("Year")
+    plt.ylabel("Percent Enrollment")
+    plt.title("Average Enrollment (National)")
+    plt.legend()
+    plt.savefig(os.path.join(output_dir, f"national-enrollment-percent.{ext}"))
+    plt.clf()
+
+    # Students enrolled
+    for key in prog_percentage.fields:
+        # Find the mean across the nation
+        mean_perc = ak.mean(prog_percentage[key], axis=0)
+        if ak.all(mean_perc < 0.05):
+            continue
+            
+        mean = ak.mean(prog_percentage[key] * students, axis=0)
+        plt.plot(mean, label=key)
+    plt.xlabel("Year")
+    plt.ylabel("Percent Enrollment")
+    plt.title("Average Enrollment (National)")
+    plt.legend()
+    plt.savefig(os.path.join(output_dir, f"national-enrollment-students.{ext}"))
+    plt.clf()
+
+    
+# Percentage enrollment per field over time averaged across one school
+def save_scorecard_stats_school(output_dir, data, school: str, ext="png"):
+    data = mask_school(data, school)
+    prog_percentage = data.academics.program_percentage
+    students = data.student.enrollment.undergrad_12_month
+
+    # Plot percent enrollment
+    for key in prog_percentage.fields:
+        # Find the mean across the nation
+        mean = ak.mean(prog_percentage[key], axis=0)
+        if mean < 0.05:
+            continue
+        plt.plot(prog_percentage[key] * 100, label=key)
+    plt.xlabel("Year")
+    plt.ylabel("Percent Enrollment")
+    plt.title(f"Average Enrollment ({school})")
+    plt.legend()
+    plt.savefig(os.path.join(output_dir, f"{school}-enrollment-percent.{ext}"))
+    plt.clf()
+
+    # Plot student enrollment
+    for key in prog_percentage.fields:
+        # Find the mean across the nation
+        mean = ak.mean(prog_percentage[key], axis=0)
+        if mean < 0.05:
+            continue
+        plt.plot(prog_percentage[key] * students, label=key)
+    plt.xlabel("Year")
+    plt.ylabel("Percent Enrollment")
+    plt.title(f"Average Enrollment ({school})")
+    plt.legend()
+    plt.savefig(os.path.join(output_dir, f"{school}-enrollment-students.{ext}"))
+    plt.clf()
+
+def save_scorecard_stats(output_dir, data, ext="png"):
+    # Students Enrolled Distribution (Average)
+    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")
+    plt.savefig(os.path.join(output_dir, f"dist-students-enrolled-avg.{ext}"))
+    plt.clf()
+
+    # Students Enrolled Distribution (Last Year)
+    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")
+    plt.savefig(os.path.join(output_dir, f"dist-students-enrolled-last-year.{ext}"))
+    plt.clf()
+
+
+
+# Print national enrollment stats
+def print_enrollment_national(data):
+    prog_percentage = data.academics.program_percentage
+    students = data.student.enrollment.undergrad_12_month
+    
+    # Create dataframe of enrollment across the nation (latest academic year and average)
+    df = {'Name': list(prog_percentage.fields), 'Percent (Last)': [], 'Percent (Avg)': [], "Students (Last)": [], "Students (Avg)": [] }
+    for key in df['Name']:
+        vals = prog_percentage[key]
+        df['Percent (Last)'].append(ak.mean(vals[-1]) * 100)
+        df['Percent (Avg)'].append(ak.mean(vals) * 100)
+        df['Students (Last)'].append(ak.mean(vals[-1] * students[-1]))
+        df['Students (Avg)'].append(ak.mean(vals * students))
+        
+    df = pd.DataFrame(df)
+
+    # Print Dataframe
+    logger.info("\n\nNational Percentage (Last Academic Year): ")
+    print(df.sort_values("Percent (Last)", ascending=False))
+    
+    logger.info("\n\nNational Percentage (Avg): ")
+    print(df.sort_values("Percent (Avg)", ascending=False))
+
+def print_enrollment(data, name: str):
+    data = mask_school(data, name)
+    prog_percentage = data.academics.program_percentage
+    students = data.student.enrollment.undergrad_12_month
+    
+    # Create dataframe of enrollment across the nation (latest academic year and average)
+    df = {'Name': list(prog_percentage.fields), 'Percent (Last)': [], 'Percent (Avg)': [], "Students (Last)": [], "Students (Avg)": [] }
+    for key in df['Name']:
+        vals = prog_percentage[key]
+        df['Percent (Last)'].append(vals[-1] * 100)
+        df['Percent (Avg)'].append(ak.mean(vals) * 100)
+        df['Students (Last)'].append(vals[-1] * students[-1])
+        df['Students (Avg)'].append(ak.mean(vals * students))
+        
+    df = pd.DataFrame(df)
+
+    # Print Dataframe
+    logger.info(f"\n\nProgram Percentage ({name}, Last Academic Year): ")
+    print(df.sort_values("Percent (Last)", ascending=False))
+    
+    logger.info(f"\n\nProgram Percentage ({name}, Avg): ")
+    print(df.sort_values("Percent (Avg)", ascending=False))