transcript_eval/main.py at main · CAHLR/transcript_eval · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
import os
from dotenv import load_dotenv
from csvConcatenation import concatenate_csv_files
from matchPercentage import match_percentage
from postProcessRegex import regex_post_process
from postProcessOSL import post_process_OSL
from methodClaude import method_claude_sdk_pipeline
from methodO1 import methodO1
from methodAWSpdf import process_pdfs_in_folder
from missingCourses import find_missing_courses

# Load .env file
load_dotenv()

def method_awsBoto(transcript_name, output_folder, orig):
    orig = output_folder
    output_folder = output_folder + "awsBoto"
    os.makedirs(output_folder, exist_ok=True)

    process_pdfs_in_folder(transcript_name, output_folder)
    concatenate_csv_files(output_folder)

    file_a = output_folder + "/" + output_folder + "_combined.csv"
    file_b = "validation/" + orig + ".csv"
    output = output_folder + "/MISSING_courses.csv"
    output2 = output_folder + "/MATCHED_courses.csv"

    find_missing_courses(
        file_a, file_b, output, output2, course_threshold=80, grade_threshold=70
    )
    post_process_method(output_folder, orig)


def method_claude(transcript_name, output_folder, orig):
    output_folder = output_folder + "claude"
    os.makedirs(output_folder, exist_ok=True)

    pdf_path = transcript_name + ".pdf"
    method_claude_sdk_pipeline(pdf_path=pdf_path, output_folder=output_folder)

    concatenate_csv_files(output_folder)

    file_a = output_folder + "/" + output_folder + "_combined.csv"
    file_b = "testing_validation/" + orig + ".csv"
    output = output_folder + "/MISSING_courses.csv"
    output2 = output_folder + "/MATCHED_courses.csv"

    find_missing_courses(
        file_a, file_b, output, output2, course_threshold=80, grade_threshold=70
    )
    post_process_method(output_folder, orig)


def method_o1(transcript_name, output_folder, orig):
    output_folder = output_folder + "o1"
    os.makedirs(output_folder, exist_ok=True)

    # Safely retrieve API key from environment
    api_key = os.getenv("GPT4O_API_KEY")
    if not api_key:
        raise ValueError("Missing GPT4O_API_KEY in environment.")


    pdf_path = transcript_name + ".pdf"
    methodO1(pdf_path, api_key, output_folder)

    concatenate_csv_files(output_folder)

    file_a = output_folder + "/" + output_folder + "_combined.csv"
    file_b = "testing_validation/" + orig + ".csv"
    output = output_folder + "/MISSING_courses.csv"
    output2 = output_folder + "/MATCHED_courses.csv"

    find_missing_courses(
        file_a, file_b, output, output2, course_threshold=80, grade_threshold=70
    )
    post_process_method(output_folder, orig)


def post_process_method(output_folder, orig):

    # REGEX
    regex_post_process(output_folder)
    print(
        output_folder,
        "regex ---------------------------------------------------------------------------",
    )
    # match_percentage(output_folder + '/' +'FINAL_post_process_REGEX.csv', 'testing_validation/'+ orig + '.csv')
    match_percentage(
        output_folder + "/" + "FINAL_post_process_REGEX.csv",
        "testing_validation/" + orig + ".csv",
    )
    print(
        "---------------------------------------------------------------------------------------------"
    )

    # OSL
    print(
        output_folder,
        "open 4o OSL ---------------------------------------------------------------------------",
    )
    post_process_OSL("input_example.csv", "output_example.csv", output_folder)
    # match_percentage(output_folder + '/' +'Final_post_processed_gpt4o.csv', 'testing_validation/'+ orig + '.csv')
    match_percentage(
        output_folder + "/" + "Final_post_processed_gpt4o.csv",
        "testing_validation/" + orig + ".csv",
    )
    print(
        output_folder,
        "---------------------------------------------------------------------------",
    )


# output_folder = [
#     "asu",
#     "dickonson_uni",
#     "edmonds",
#     "g_r",
#     "taylor",
#     "trans",
#     "uva",
#     "va",
#     "west_mich",
# ]
# transcript_name = [
#     "transcripts/asu",
#     "transcripts/dickonson_uni",
#     "transcripts/edmonds",
#     "transcripts/g_r",
#     "transcripts/taylor",
#     "transcripts/trans",
#     "transcripts/uva",
#     "transcripts/va",
#     "transcripts/west_mich",
# ]


output_folder = ['depaul', 'mich_state_uni', 'suny', 'kutztown_upenn', 'wayne','western_mich_uni']
transcript_name = ['testing_transcripts/depaul', 'testing_transcripts/mich_state_uni', 'testing_transcripts/suny', 'testing_transcripts/kutztown_upenn', 'testing_transcripts/wayne','testing_transcripts/western_mich_uni']

# output_folder = ['wayne']
# transcript_name = ['testing_transcripts/wayne']

# output_folder = ['herkimer_SUNY']
# transcript_name = ['testing_transcripts/herkimer_SUNY']


# testing


for i in range(len(output_folder)):

    #method_awsBoto(transcript_name[i], output_folder[i], output_folder[i])
    method_o1(transcript_name[i], output_folder[i], output_folder[i])
    #method_claude(transcript_name[i], output_folder[i], output_folder[i])