Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
-
# ==========
|
2 |
import sys
|
3 |
import subprocess
|
4 |
import importlib
|
5 |
|
6 |
-
# List of required packages
|
7 |
required_packages = {
|
8 |
-
'gradio': 'gradio',
|
9 |
'pandas': 'pandas',
|
10 |
'PyPDF2': 'PyPDF2',
|
11 |
'transformers': 'transformers',
|
12 |
'pdfplumber': 'pdfplumber',
|
13 |
-
'typing_extensions': 'typing_extensions'
|
14 |
}
|
15 |
|
16 |
def check_and_install_packages():
|
@@ -24,20 +24,15 @@ def check_and_install_packages():
|
|
24 |
if missing_packages:
|
25 |
print(f"Missing packages: {', '.join(missing_packages)}")
|
26 |
print("Attempting to install...")
|
27 |
-
|
28 |
try:
|
29 |
subprocess.check_call([sys.executable, "-m", "pip", "install", *missing_packages])
|
30 |
-
print("Installation successful.
|
31 |
-
sys.exit(0)
|
32 |
except subprocess.CalledProcessError as e:
|
33 |
print(f"Failed to install packages. Error: {e}")
|
34 |
-
print("Please install them manually with:")
|
35 |
-
print(f"pip install {' '.join(missing_packages)}")
|
36 |
-
sys.exit(1)
|
37 |
|
38 |
check_and_install_packages()
|
39 |
|
40 |
-
# ========== MAIN IMPORTS
|
41 |
import gradio as gr
|
42 |
import pandas as pd
|
43 |
import json
|
@@ -49,14 +44,650 @@ from transformers import pipeline
|
|
49 |
from typing import List, Dict, Union
|
50 |
import pdfplumber
|
51 |
|
52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
|
|
54 |
if __name__ == "__main__":
|
55 |
-
|
56 |
-
try:
|
57 |
-
from IPython import get_ipython
|
58 |
-
if 'IPKernelApp' not in get_ipython().config:
|
59 |
-
app.launch()
|
60 |
-
except:
|
61 |
-
app.launch()
|
62 |
-
|
|
|
1 |
+
# ========== DEPENDENCY MANAGEMENT ==========
|
2 |
import sys
|
3 |
import subprocess
|
4 |
import importlib
|
5 |
|
6 |
+
# List of required packages
|
7 |
required_packages = {
|
8 |
+
'gradio': 'gradio>=3.0',
|
9 |
'pandas': 'pandas',
|
10 |
'PyPDF2': 'PyPDF2',
|
11 |
'transformers': 'transformers',
|
12 |
'pdfplumber': 'pdfplumber',
|
13 |
+
'typing_extensions': 'typing_extensions'
|
14 |
}
|
15 |
|
16 |
def check_and_install_packages():
|
|
|
24 |
if missing_packages:
|
25 |
print(f"Missing packages: {', '.join(missing_packages)}")
|
26 |
print("Attempting to install...")
|
|
|
27 |
try:
|
28 |
subprocess.check_call([sys.executable, "-m", "pip", "install", *missing_packages])
|
29 |
+
print("Installation successful.")
|
|
|
30 |
except subprocess.CalledProcessError as e:
|
31 |
print(f"Failed to install packages. Error: {e}")
|
|
|
|
|
|
|
32 |
|
33 |
check_and_install_packages()
|
34 |
|
35 |
+
# ========== MAIN IMPORTS ==========
|
36 |
import gradio as gr
|
37 |
import pandas as pd
|
38 |
import json
|
|
|
44 |
from typing import List, Dict, Union
|
45 |
import pdfplumber
|
46 |
|
47 |
+
# ========== TRANSCRIPT PARSING ==========
|
48 |
+
class UniversalTranscriptParser:
|
49 |
+
def __init__(self):
|
50 |
+
self.patterns = {
|
51 |
+
'miami_dade': self._compile_miami_dade_patterns(),
|
52 |
+
'homeschool': self._compile_homeschool_patterns(),
|
53 |
+
'doral_academy': self._compile_doral_academy_patterns()
|
54 |
+
}
|
55 |
+
|
56 |
+
self.grade_level_map = {
|
57 |
+
'09': '9th Grade', '10': '10th Grade', '11': '11th Grade', '12': '12th Grade',
|
58 |
+
'07': '7th Grade', '08': '8th Grade', 'MA': 'Middle School'
|
59 |
+
}
|
60 |
+
|
61 |
+
def parse_transcript(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
|
62 |
+
transcript_type = self._identify_transcript_type(text)
|
63 |
+
|
64 |
+
if transcript_type == 'homeschool':
|
65 |
+
return self._parse_homeschool(text)
|
66 |
+
elif transcript_type == 'doral_academy':
|
67 |
+
return self._parse_doral_academy(text)
|
68 |
+
else:
|
69 |
+
return self._parse_miami_dade(text)
|
70 |
+
|
71 |
+
def _identify_transcript_type(self, text: str) -> str:
|
72 |
+
if re.search(r'Sample OFFICIAL HIGH SCHOOL TRANSCRIPT', text):
|
73 |
+
return 'homeschool'
|
74 |
+
elif re.search(r'DORAL ACADEMY HIGH SCHOOL', text):
|
75 |
+
return 'doral_academy'
|
76 |
+
return 'miami_dade'
|
77 |
+
|
78 |
+
def _parse_homeschool(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
|
79 |
+
courses = []
|
80 |
+
current_grade = None
|
81 |
+
current_year = None
|
82 |
+
|
83 |
+
student_info = {}
|
84 |
+
name_match = re.search(r'Student Name:\s*(.+)\s*SSN:', text)
|
85 |
+
if name_match:
|
86 |
+
student_info['name'] = name_match.group(1).strip()
|
87 |
+
|
88 |
+
for line in text.split('\n'):
|
89 |
+
grade_match = re.match(r'^\|?\s*(\d+th Grade)\s*\|.*(\d{4}-\d{4})', line)
|
90 |
+
if grade_match:
|
91 |
+
current_grade = grade_match.group(1)
|
92 |
+
current_year = grade_match.group(2)
|
93 |
+
continue
|
94 |
+
|
95 |
+
course_match = re.match(
|
96 |
+
r'^\|?\s*([^\|]+?)\s*\|\s*([A-Z][+*]?)\s*\|\s*([^\|]+)\s*\|\s*(\d+\.?\d*)\s*\|\s*(\d+)',
|
97 |
+
line
|
98 |
+
)
|
99 |
+
|
100 |
+
if course_match and current_grade:
|
101 |
+
course_name = course_match.group(1).strip()
|
102 |
+
course_name = re.sub(r'^\|?\s*', '', course_name)
|
103 |
+
|
104 |
+
courses.append({
|
105 |
+
'name': course_name,
|
106 |
+
'grade_level': current_grade,
|
107 |
+
'school_year': current_year,
|
108 |
+
'grade': course_match.group(2),
|
109 |
+
'credit_type': course_match.group(3).strip(),
|
110 |
+
'credits': float(course_match.group(4)),
|
111 |
+
'quality_points': int(course_match.group(5)),
|
112 |
+
'transcript_type': 'homeschool'
|
113 |
+
})
|
114 |
+
|
115 |
+
gpa_data = {}
|
116 |
+
gpa_match = re.search(r'Cum\. GPA\s*\|\s*([\d\.]+)', text)
|
117 |
+
if gpa_match:
|
118 |
+
gpa_data['unweighted'] = gpa_match.group(1)
|
119 |
+
gpa_data['weighted'] = gpa_match.group(1)
|
120 |
+
|
121 |
+
return {
|
122 |
+
'student_info': student_info,
|
123 |
+
'courses': {'All': courses},
|
124 |
+
'gpa': gpa_data,
|
125 |
+
'grade_level': current_grade.replace('th Grade', '') if current_grade else "Unknown"
|
126 |
+
}
|
127 |
+
|
128 |
+
def _parse_doral_academy(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
|
129 |
+
courses = []
|
130 |
+
student_info = {}
|
131 |
+
name_match = re.search(r'LEGAL NAME:\s*([^\n]+)', text)
|
132 |
+
if name_match:
|
133 |
+
student_info['name'] = name_match.group(1).strip()
|
134 |
+
|
135 |
+
year_pattern = re.compile(r'YEAR:\s*(\d{4}-\d{4})\s*GRADE LEVEL:\s*(\d{2})', re.MULTILINE)
|
136 |
+
year_matches = year_pattern.finditer(text)
|
137 |
+
|
138 |
+
grade_year_map = {}
|
139 |
+
for match in year_matches:
|
140 |
+
grade_year_map[match.group(2)] = match.group(1)
|
141 |
+
|
142 |
+
course_pattern = re.compile(
|
143 |
+
r'(\d)\s+(\d{7})\s+([^\n]+?)\s+([A-Z]{2})\s+([A-Z])\s+([A-Z])\s+([A-Z])\s+(\d\.\d{2})\s+(\d\.\d{2})',
|
144 |
+
re.MULTILINE
|
145 |
+
)
|
146 |
+
|
147 |
+
courses_by_grade = defaultdict(list)
|
148 |
+
for match in course_pattern.finditer(text):
|
149 |
+
grade_level_num = match.group(1)
|
150 |
+
grade_level = self.grade_level_map.get(grade_level_num, f"Grade {grade_level_num}")
|
151 |
+
school_year = grade_year_map.get(grade_level_num, "Unknown")
|
152 |
+
|
153 |
+
course_info = {
|
154 |
+
'course_code': match.group(2),
|
155 |
+
'name': match.group(3).strip(),
|
156 |
+
'subject_area': match.group(4),
|
157 |
+
'grade': match.group(5),
|
158 |
+
'inclusion_status': match.group(6),
|
159 |
+
'credit_status': match.group(7),
|
160 |
+
'credits_attempted': float(match.group(8)),
|
161 |
+
'credits': float(match.group(9)),
|
162 |
+
'grade_level': grade_level,
|
163 |
+
'school_year': school_year,
|
164 |
+
'transcript_type': 'doral_academy'
|
165 |
+
}
|
166 |
+
|
167 |
+
courses_by_grade[grade_level_num].append(course_info)
|
168 |
+
|
169 |
+
gpa_data = {}
|
170 |
+
unweighted_match = re.search(r'Un-weighted GPA\s*([\d\.]+)', text)
|
171 |
+
weighted_match = re.search(r'Weighted GPA\s*([\d\.]+)', text)
|
172 |
+
|
173 |
+
if unweighted_match:
|
174 |
+
gpa_data['unweighted'] = unweighted_match.group(1)
|
175 |
+
if weighted_match:
|
176 |
+
gpa_data['weighted'] = weighted_match.group(1)
|
177 |
+
|
178 |
+
grade_level = "12" if re.search(r'GRADE LEVEL:\s*12', text) else "Unknown"
|
179 |
+
|
180 |
+
return {
|
181 |
+
'student_info': student_info,
|
182 |
+
'courses': dict(courses_by_grade),
|
183 |
+
'gpa': gpa_data,
|
184 |
+
'grade_level': grade_level
|
185 |
+
}
|
186 |
+
|
187 |
+
def _parse_miami_dade(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
|
188 |
+
courses = []
|
189 |
+
courses_by_grade = defaultdict(list)
|
190 |
+
|
191 |
+
student_info = {}
|
192 |
+
name_match = re.search(r'0783977 - ([^,]+),\s*([^\n]+)', text)
|
193 |
+
if name_match:
|
194 |
+
student_info['name'] = f"{name_match.group(2)} {name_match.group(1)}"
|
195 |
+
|
196 |
+
course_pattern = re.compile(
|
197 |
+
r'([A-Z]-[A-Za-z\s&]+)\s*\|\s*(\d{4}-\d{4})\s*\|\s*(\d{2})\s*\|\s*([A-Z0-9]+)\s*\|\s*([^\|]+)\s*\|\s*([^\|]+)\s*\|\s*([^\|]+)\s*\|\s*([A-Z]?)\s*\|\s*([A-Z]?)\s*\|\s*([^\|]+)',
|
198 |
+
re.MULTILINE
|
199 |
+
)
|
200 |
+
|
201 |
+
for match in course_pattern.finditer(text):
|
202 |
+
grade_level = self.grade_level_map.get(match.group(3), match.group(3))
|
203 |
+
credits = match.group(10).strip()
|
204 |
+
|
205 |
+
course_info = {
|
206 |
+
'requirement_category': match.group(1).strip(),
|
207 |
+
'school_year': match.group(2),
|
208 |
+
'grade_level': grade_level if isinstance(grade_level, str) else f"Grade {match.group(3)}",
|
209 |
+
'course_code': match.group(4).strip(),
|
210 |
+
'name': match.group(5).strip(),
|
211 |
+
'term': match.group(6).strip(),
|
212 |
+
'district_number': match.group(7).strip(),
|
213 |
+
'grade': match.group(8),
|
214 |
+
'inclusion_status': match.group(9),
|
215 |
+
'credits': 0.0 if 'inProgress' in credits else float(credits.replace(' ', '')),
|
216 |
+
'transcript_type': 'miami_dade'
|
217 |
+
}
|
218 |
+
|
219 |
+
courses_by_grade[match.group(3)].append(course_info)
|
220 |
+
|
221 |
+
gpa_data = {
|
222 |
+
'weighted': extract_gpa(text, 'Weighted GPA'),
|
223 |
+
'unweighted': extract_gpa(text, 'Un-weighted GPA')
|
224 |
+
}
|
225 |
+
|
226 |
+
grade_level = re.search(r'Current Grade:\s*(\d+)', text).group(1) if re.search(r'Current Grade:\s*(\d+)', text) else "Unknown"
|
227 |
+
|
228 |
+
return {
|
229 |
+
'student_info': student_info,
|
230 |
+
'courses': dict(courses_by_grade),
|
231 |
+
'gpa': gpa_data,
|
232 |
+
'grade_level': grade_level
|
233 |
+
}
|
234 |
+
|
235 |
+
def _compile_miami_dade_patterns(self):
|
236 |
+
return {
|
237 |
+
'student': re.compile(r'Current Grade:\s*(\d+).*YOG\s*(\d{4})'),
|
238 |
+
'course': re.compile(
|
239 |
+
r'([A-Z]-[A-Za-z\s&]+)\s*\|\s*(\d{4}-\d{4})\s*\|\s*(\d{2})\s*\|\s*([A-Z0-9]+)\s*\|\s*([^\|]+)\s*\|\s*([^\|]+)\s*\|\s*([^\|]+)\s*\|\s*([A-Z]?)\s*\|\s*([A-Z]?)\s*\|\s*([^\|]+)',
|
240 |
+
re.MULTILINE
|
241 |
+
)
|
242 |
+
}
|
243 |
+
|
244 |
+
def _compile_homeschool_patterns(self):
|
245 |
+
return {
|
246 |
+
'student': re.compile(r'Student Name:\s*(.+)\s*SSN:'),
|
247 |
+
'course': re.compile(
|
248 |
+
r'^\|?\s*([^\|]+?)\s*\|\s*([A-Z][+*]?)\s*\|\s*([^\|]+)\s*\|\s*(\d+\.?\d*)\s*\|\s*(\d+)'
|
249 |
+
)
|
250 |
+
}
|
251 |
+
|
252 |
+
def _compile_doral_academy_patterns(self):
|
253 |
+
return {
|
254 |
+
'student': re.compile(r'LEGAL NAME:\s*([^\n]+)'),
|
255 |
+
'course': re.compile(
|
256 |
+
r'(\d)\s+(\d{7})\s+([^\n]+?)\s+([A-Z]{2})\s+([A-Z])\s+([A-Z])\s+([A-Z])\s+(\d\.\d{2})\s+(\d\.\d{2})',
|
257 |
+
re.MULTILINE
|
258 |
+
)
|
259 |
+
}
|
260 |
+
|
261 |
+
def extract_gpa(text, gpa_type):
|
262 |
+
pattern = rf'{gpa_type}\s*([\d\.]+)'
|
263 |
+
match = re.search(pattern, text)
|
264 |
+
return match.group(1) if match else "N/A"
|
265 |
+
|
266 |
+
def parse_transcript(file):
|
267 |
+
parser = UniversalTranscriptParser()
|
268 |
+
|
269 |
+
if file.name.endswith('.pdf'):
|
270 |
+
text = ''
|
271 |
+
with pdfplumber.open(file.name) as pdf:
|
272 |
+
for page in pdf.pages:
|
273 |
+
text += page.extract_text() or '' + '\n'
|
274 |
+
|
275 |
+
parsed_data = parser.parse_transcript(text)
|
276 |
+
|
277 |
+
output_text = f"Student Transcript Summary\n{'='*40}\n"
|
278 |
+
|
279 |
+
if 'student_info' in parsed_data and 'name' in parsed_data['student_info']:
|
280 |
+
output_text += f"Student: {parsed_data['student_info']['name']}\n"
|
281 |
+
|
282 |
+
output_text += f"Current Grade Level: {parsed_data.get('grade_level', 'Unknown')}\n"
|
283 |
+
|
284 |
+
if 'gpa' in parsed_data:
|
285 |
+
gpa = parsed_data['gpa']
|
286 |
+
output_text += f"Weighted GPA: {gpa.get('weighted', 'N/A')}\n"
|
287 |
+
output_text += f"Unweighted GPA: {gpa.get('unweighted', 'N/A')}\n\n"
|
288 |
+
|
289 |
+
output_text += "Course History:\n{'='*40}\n"
|
290 |
+
|
291 |
+
if 'courses' in parsed_data:
|
292 |
+
courses_by_grade = parsed_data['courses']
|
293 |
+
|
294 |
+
def grade_sort_key(grade):
|
295 |
+
try:
|
296 |
+
num = int(re.search(r'\d+', grade).group())
|
297 |
+
return num
|
298 |
+
except (AttributeError, ValueError):
|
299 |
+
return float('inf')
|
300 |
+
|
301 |
+
grades_sorted = sorted(courses_by_grade.keys(), key=grade_sort_key)
|
302 |
+
|
303 |
+
for grade in grades_sorted:
|
304 |
+
output_text += f"\nGrade {grade}:\n{'-'*30}\n"
|
305 |
+
for course in courses_by_grade[grade]:
|
306 |
+
output_text += f"- {course.get('name', 'Unnamed Course')}"
|
307 |
+
if 'grade' in course and course['grade']:
|
308 |
+
output_text += f" (Grade: {course['grade']})"
|
309 |
+
if 'credits' in course:
|
310 |
+
output_text += f" | Credits: {course['credits']}"
|
311 |
+
if 'school_year' in course:
|
312 |
+
output_text += f" | Year: {course['school_year']}"
|
313 |
+
output_text += "\n"
|
314 |
+
|
315 |
+
return output_text, parsed_data
|
316 |
+
else:
|
317 |
+
return "Unsupported file format (PDF only for transcript parsing)", None
|
318 |
+
|
319 |
+
def transcript_display(transcript_dict):
|
320 |
+
if not transcript_dict or "courses" not in transcript_dict:
|
321 |
+
return "No course information available"
|
322 |
+
|
323 |
+
display = "### Detailed Course History\n"
|
324 |
+
courses_by_grade = transcript_dict["courses"]
|
325 |
+
|
326 |
+
if isinstance(courses_by_grade, dict):
|
327 |
+
def grade_sort_key(grade):
|
328 |
+
try:
|
329 |
+
num = int(re.search(r'\d+', grade).group())
|
330 |
+
return num
|
331 |
+
except (AttributeError, ValueError):
|
332 |
+
return float('inf')
|
333 |
+
|
334 |
+
grades_sorted = sorted(courses_by_grade.keys(), key=grade_sort_key)
|
335 |
+
|
336 |
+
for grade in grades_sorted:
|
337 |
+
display += f"\n**Grade {grade}**\n"
|
338 |
+
for course in courses_by_grade[grade]:
|
339 |
+
display += f"- {course.get('name', 'Unnamed Course')}"
|
340 |
+
if 'grade' in course and course['grade']:
|
341 |
+
display += f" (Grade: {course['grade']})"
|
342 |
+
if 'credits' in course:
|
343 |
+
display += f" | Credits: {course['credits']}"
|
344 |
+
if 'school_year' in course:
|
345 |
+
display += f" | Year: {course['school_year']}"
|
346 |
+
display += "\n"
|
347 |
+
|
348 |
+
if 'gpa' in transcript_dict:
|
349 |
+
gpa = transcript_dict['gpa']
|
350 |
+
display += "\n**GPA Information**\n"
|
351 |
+
display += f"- Unweighted: {gpa.get('unweighted', 'N/A')}\n"
|
352 |
+
display += f"- Weighted: {gpa.get('weighted', 'N/A')}\n"
|
353 |
+
|
354 |
+
return display
|
355 |
+
|
356 |
+
# ========== LEARNING STYLE QUIZ ==========
|
357 |
+
learning_style_questions = [
|
358 |
+
"When you study for a test, you prefer to:",
|
359 |
+
"When you need directions to a new place, you prefer:",
|
360 |
+
"When you learn a new skill, you prefer to:",
|
361 |
+
"When you're trying to concentrate, you:",
|
362 |
+
"When you meet new people, you remember them by:",
|
363 |
+
"When you're assembling furniture or a gadget, you:",
|
364 |
+
"When choosing a restaurant, you rely most on:",
|
365 |
+
"When you're in a waiting room, you typically:",
|
366 |
+
"When giving someone instructions, you tend to:",
|
367 |
+
"When you're trying to recall information, you:",
|
368 |
+
"When you're at a museum or exhibit, you:",
|
369 |
+
"When you're learning a new language, you prefer:",
|
370 |
+
"When you're taking notes in class, you:",
|
371 |
+
"When you're explaining something complex, you:",
|
372 |
+
"When you're at a party, you enjoy:",
|
373 |
+
"When you're trying to remember a phone number, you:",
|
374 |
+
"When you're relaxing, you prefer to:",
|
375 |
+
"When you're learning to use new software, you:",
|
376 |
+
"When you're giving a presentation, you rely on:",
|
377 |
+
"When you're solving a difficult problem, you:"
|
378 |
+
]
|
379 |
+
|
380 |
+
learning_style_options = [
|
381 |
+
["Read the textbook (Reading/Writing)", "Listen to lectures (Auditory)", "Use diagrams/charts (Visual)", "Practice problems (Kinesthetic)"],
|
382 |
+
["Look at a map (Visual)", "Have someone tell you (Auditory)", "Write down directions (Reading/Writing)", "Try walking/driving there (Kinesthetic)"],
|
383 |
+
["Read instructions (Reading/Writing)", "Have someone show you (Visual)", "Listen to explanations (Auditory)", "Try it yourself (Kinesthetic)"],
|
384 |
+
["Need quiet (Reading/Writing)", "Need background noise (Auditory)", "Need to move around (Kinesthetic)", "Need visual stimulation (Visual)"],
|
385 |
+
["Their face (Visual)", "Their name (Auditory)", "What you talked about (Reading/Writing)", "What you did together (Kinesthetic)"],
|
386 |
+
["Read the instructions carefully (Reading/Writing)", "Look at the diagrams (Visual)", "Ask someone to explain (Auditory)", "Start putting pieces together (Kinesthetic)"],
|
387 |
+
["Online photos of the food (Visual)", "Recommendations from friends (Auditory)", "Reading the menu online (Reading/Writing)", "Remembering how it felt to eat there (Kinesthetic)"],
|
388 |
+
["Read magazines (Reading/Writing)", "Listen to music (Auditory)", "Watch TV (Visual)", "Fidget or move around (Kinesthetic)"],
|
389 |
+
["Write them down (Reading/Writing)", "Explain verbally (Auditory)", "Demonstrate (Visual)", "Guide them physically (Kinesthetic)"],
|
390 |
+
["See written words in your mind (Visual)", "Hear the information in your head (Auditory)", "Write it down to remember (Reading/Writing)", "Associate it with physical actions (Kinesthetic)"],
|
391 |
+
["Read all the descriptions (Reading/Writing)", "Listen to audio guides (Auditory)", "Look at the displays (Visual)", "Touch interactive exhibits (Kinesthetic)"],
|
392 |
+
["Study grammar rules (Reading/Writing)", "Listen to native speakers (Auditory)", "Use flashcards with images (Visual)", "Practice conversations (Kinesthetic)"],
|
393 |
+
["Write detailed paragraphs (Reading/Writing)", "Record the lecture (Auditory)", "Draw diagrams and charts (Visual)", "Doodle while listening (Kinesthetic)"],
|
394 |
+
["Write detailed steps (Reading/Writing)", "Explain verbally with examples (Auditory)", "Draw diagrams (Visual)", "Use physical objects to demonstrate (Kinesthetic)"],
|
395 |
+
["Conversations with people (Auditory)", "Watching others or the environment (Visual)", "Writing notes or texting (Reading/Writing)", "Dancing or physical activities (Kinesthetic)"],
|
396 |
+
["See the numbers in your mind (Visual)", "Say them aloud (Auditory)", "Write them down (Reading/Writing)", "Dial them on a keypad (Kinesthetic)"],
|
397 |
+
["Read a book (Reading/Writing)", "Listen to music (Auditory)", "Watch TV/movies (Visual)", "Do something physical (Kinesthetic)"],
|
398 |
+
["Read the manual (Reading/Writing)", "Ask someone to show you (Visual)", "Call tech support (Auditory)", "Experiment with the software (Kinesthetic)"],
|
399 |
+
["Detailed notes (Reading/Writing)", "Verbal explanations (Auditory)", "Visual slides (Visual)", "Physical demonstrations (Kinesthetic)"],
|
400 |
+
["Write out possible solutions (Reading/Writing)", "Talk through it with someone (Auditory)", "Draw diagrams (Visual)", "Build a model or prototype (Kinesthetic)"]
|
401 |
+
]
|
402 |
+
|
403 |
+
def learning_style_quiz(*answers):
|
404 |
+
scores = {
|
405 |
+
"Visual": 0,
|
406 |
+
"Auditory": 0,
|
407 |
+
"Reading/Writing": 0,
|
408 |
+
"Kinesthetic": 0
|
409 |
+
}
|
410 |
+
|
411 |
+
for i, answer in enumerate(answers):
|
412 |
+
if answer == learning_style_options[i][0]:
|
413 |
+
scores["Reading/Writing"] += 1
|
414 |
+
elif answer == learning_style_options[i][1]:
|
415 |
+
scores["Auditory"] += 1
|
416 |
+
elif answer == learning_style_options[i][2]:
|
417 |
+
scores["Visual"] += 1
|
418 |
+
elif answer == learning_style_options[i][3]:
|
419 |
+
scores["Kinesthetic"] += 1
|
420 |
+
|
421 |
+
max_score = max(scores.values())
|
422 |
+
total_questions = len(learning_style_questions)
|
423 |
+
|
424 |
+
percentages = {style: (score/total_questions)*100 for style, score in scores.items()}
|
425 |
+
|
426 |
+
sorted_styles = sorted(scores.items(), key=lambda x: x[1], reverse=True)
|
427 |
+
|
428 |
+
result = "Your Learning Style Results:\n\n"
|
429 |
+
for style, score in sorted_styles:
|
430 |
+
result += f"{style}: {score}/{total_questions} ({percentages[style]:.1f}%)\n"
|
431 |
+
|
432 |
+
result += "\n"
|
433 |
+
|
434 |
+
primary_styles = [style for style, score in scores.items() if score == max_score]
|
435 |
+
|
436 |
+
if len(primary_styles) == 1:
|
437 |
+
result += f"Your primary learning style is: {primary_styles[0]}\n\n"
|
438 |
+
if primary_styles[0] == "Visual":
|
439 |
+
result += "Tips for Visual Learners:\n"
|
440 |
+
result += "- Use color coding in your notes\n"
|
441 |
+
result += "- Create mind maps and diagrams\n"
|
442 |
+
result += "- Watch educational videos\n"
|
443 |
+
result += "- Use flashcards with images\n"
|
444 |
+
elif primary_styles[0] == "Auditory":
|
445 |
+
result += "Tips for Auditory Learners:\n"
|
446 |
+
result += "- Record lectures and listen to them\n"
|
447 |
+
result += "- Participate in study groups\n"
|
448 |
+
result += "- Explain concepts out loud to yourself\n"
|
449 |
+
result += "- Use rhymes or songs to remember information\n"
|
450 |
+
elif primary_styles[0] == "Reading/Writing":
|
451 |
+
result += "Tips for Reading/Writing Learners:\n"
|
452 |
+
result += "- Write detailed notes\n"
|
453 |
+
result += "- Create summaries in your own words\n"
|
454 |
+
result += "- Read textbooks and articles\n"
|
455 |
+
result += "- Make lists to organize information\n"
|
456 |
+
else:
|
457 |
+
result += "Tips for Kinesthetic Learners:\n"
|
458 |
+
result += "- Use hands-on activities\n"
|
459 |
+
result += "- Take frequent movement breaks\n"
|
460 |
+
result += "- Create physical models\n"
|
461 |
+
result += "- Associate information with physical actions\n"
|
462 |
+
else:
|
463 |
+
result += f"You have multiple strong learning styles: {', '.join(primary_styles)}\n\n"
|
464 |
+
result += "You may benefit from combining different learning approaches.\n"
|
465 |
+
|
466 |
+
return result
|
467 |
+
|
468 |
+
# ========== SAVE STUDENT PROFILE ==========
|
469 |
+
def save_profile(name, age, interests, transcript, learning_style,
|
470 |
+
movie, movie_reason, show, show_reason,
|
471 |
+
book, book_reason, character, character_reason, blog):
|
472 |
+
age = int(age) if age else 0
|
473 |
+
|
474 |
+
favorites = {
|
475 |
+
"movie": movie,
|
476 |
+
"movie_reason": movie_reason,
|
477 |
+
"show": show,
|
478 |
+
"show_reason": show_reason,
|
479 |
+
"book": book,
|
480 |
+
"book_reason": book_reason,
|
481 |
+
"character": character,
|
482 |
+
"character_reason": character_reason
|
483 |
+
}
|
484 |
+
|
485 |
+
data = {
|
486 |
+
"name": name,
|
487 |
+
"age": age,
|
488 |
+
"interests": interests,
|
489 |
+
"transcript": transcript,
|
490 |
+
"learning_style": learning_style,
|
491 |
+
"favorites": favorites,
|
492 |
+
"blog": blog
|
493 |
+
}
|
494 |
+
|
495 |
+
os.makedirs("student_profiles", exist_ok=True)
|
496 |
+
json_path = os.path.join("student_profiles", f"{name.replace(' ', '_')}_profile.json")
|
497 |
+
with open(json_path, "w") as f:
|
498 |
+
json.dump(data, f, indent=2)
|
499 |
+
|
500 |
+
markdown_summary = f"""### Student Profile: {name}
|
501 |
+
**Age:** {age}
|
502 |
+
**Interests:** {interests}
|
503 |
+
**Learning Style:** {learning_style}
|
504 |
+
#### Transcript:
|
505 |
+
{transcript_display(transcript)}
|
506 |
+
#### Favorites:
|
507 |
+
- Movie: {favorites['movie']} ({favorites['movie_reason']})
|
508 |
+
- Show: {favorites['show']} ({favorites['show_reason']})
|
509 |
+
- Book: {favorites['book']} ({favorites['book_reason']})
|
510 |
+
- Character: {favorites['character']} ({favorites['character_reason']})
|
511 |
+
#### Blog:
|
512 |
+
{blog if blog else "_No blog provided_"}
|
513 |
+
"""
|
514 |
+
return markdown_summary
|
515 |
+
|
516 |
+
# ========== AI TEACHING ASSISTANT ==========
|
517 |
+
def load_profile():
|
518 |
+
if not os.path.exists("student_profiles"):
|
519 |
+
return {}
|
520 |
+
files = [f for f in os.listdir("student_profiles") if f.endswith('.json')]
|
521 |
+
if files:
|
522 |
+
with open(os.path.join("student_profiles", files[0]), "r") as f:
|
523 |
+
return json.load(f)
|
524 |
+
return {}
|
525 |
+
|
526 |
+
def generate_response(message, history):
|
527 |
+
profile = load_profile()
|
528 |
+
if not profile:
|
529 |
+
return "Please complete and save your profile first using the previous tabs."
|
530 |
+
|
531 |
+
learning_style = profile.get("learning_style", "")
|
532 |
+
grade_level = profile.get("transcript", {}).get("grade_level", "unknown")
|
533 |
+
gpa = profile.get("transcript", {}).get("gpa", {})
|
534 |
+
interests = profile.get("interests", "")
|
535 |
+
courses = profile.get("transcript", {}).get("courses", {})
|
536 |
+
|
537 |
+
greetings = ["hi", "hello", "hey"]
|
538 |
+
study_help = ["study", "learn", "prepare", "exam"]
|
539 |
+
grade_help = ["grade", "gpa", "score"]
|
540 |
+
interest_help = ["interest", "hobby", "passion"]
|
541 |
+
course_help = ["courses", "classes", "transcript", "schedule"]
|
542 |
+
|
543 |
+
if any(greet in message.lower() for greet in greetings):
|
544 |
+
return f"Hello {profile.get('name', 'there')}! How can I help you today?"
|
545 |
+
|
546 |
+
elif any(word in message.lower() for word in study_help):
|
547 |
+
if "Visual" in learning_style:
|
548 |
+
response = ("Based on your visual learning style, I recommend:\n"
|
549 |
+
"- Creating mind maps or diagrams\n"
|
550 |
+
"- Using color-coded notes\n"
|
551 |
+
"- Watching educational videos")
|
552 |
+
elif "Auditory" in learning_style:
|
553 |
+
response = ("Based on your auditory learning style, I recommend:\n"
|
554 |
+
"- Recording lectures and listening to them\n"
|
555 |
+
"- Participating in study groups\n"
|
556 |
+
"- Explaining concepts out loud")
|
557 |
+
elif "Reading/Writing" in learning_style:
|
558 |
+
response = ("Based on your reading/writing learning style, I recommend:\n"
|
559 |
+
"- Writing detailed notes\n"
|
560 |
+
"- Creating summaries in your own words\n"
|
561 |
+
"- Reading textbooks and articles")
|
562 |
+
elif "Kinesthetic" in learning_style:
|
563 |
+
response = ("Based on your kinesthetic learning style, I recommend:\n"
|
564 |
+
"- Hands-on practice\n"
|
565 |
+
"- Creating physical models\n"
|
566 |
+
"- Taking frequent movement breaks")
|
567 |
+
else:
|
568 |
+
response = ("Here are some general study tips:\n"
|
569 |
+
"- Break study sessions into 25-minute chunks\n"
|
570 |
+
"- Review material regularly\n"
|
571 |
+
"- Teach concepts to someone else")
|
572 |
+
|
573 |
+
return response
|
574 |
+
|
575 |
+
elif any(word in message.lower() for word in grade_help):
|
576 |
+
return (f"Your GPA information:\n"
|
577 |
+
f"- Unweighted: {gpa.get('unweighted', 'N/A')}\n"
|
578 |
+
f"- Weighted: {gpa.get('weighted', 'N/A')}\n\n"
|
579 |
+
"To improve your grades, try:\n"
|
580 |
+
"- Setting specific goals\n"
|
581 |
+
"- Meeting with teachers\n"
|
582 |
+
"- Developing a study schedule")
|
583 |
+
|
584 |
+
elif any(word in message.lower() for word in interest_help):
|
585 |
+
return (f"I see you're interested in: {interests}\n\n"
|
586 |
+
"You might want to:\n"
|
587 |
+
"- Find clubs or activities related to these interests\n"
|
588 |
+
"- Explore career paths that align with them")
|
589 |
+
|
590 |
+
elif any(word in message.lower() for word in course_help):
|
591 |
+
response = "Here's a summary of your courses:\n"
|
592 |
+
if isinstance(courses, dict):
|
593 |
+
def grade_sort_key(grade):
|
594 |
+
try:
|
595 |
+
num = int(re.search(r'\d+', grade).group())
|
596 |
+
return num
|
597 |
+
except (AttributeError, ValueError):
|
598 |
+
return float('inf')
|
599 |
+
|
600 |
+
grades_sorted = sorted(courses.keys(), key=grade_sort_key)
|
601 |
+
|
602 |
+
for grade in grades_sorted:
|
603 |
+
response += f"\nGrade {grade}:\n"
|
604 |
+
for course in courses[grade]:
|
605 |
+
response += f"- {course.get('name', 'Unnamed Course')}"
|
606 |
+
if 'grade' in course:
|
607 |
+
response += f" (Grade: {course['grade']})"
|
608 |
+
response += "\n"
|
609 |
+
else:
|
610 |
+
response += "No detailed course information available."
|
611 |
+
return response
|
612 |
+
|
613 |
+
elif "help" in message.lower():
|
614 |
+
return ("I can help with:\n"
|
615 |
+
"- Study tips based on your learning style\n"
|
616 |
+
"- GPA and grade information\n"
|
617 |
+
"- Course history and schedules\n"
|
618 |
+
"- General academic advice\n\n"
|
619 |
+
"Try asking about study strategies or your grades!")
|
620 |
+
|
621 |
+
else:
|
622 |
+
return ("I'm your personalized teaching assistant. "
|
623 |
+
"I can help with study tips, grade information, and academic advice. "
|
624 |
+
"Try asking about how to study for your classes!")
|
625 |
+
|
626 |
+
# ========== GRADIO INTERFACE ==========
|
627 |
+
with gr.Blocks() as app:
|
628 |
+
with gr.Tab("Step 1: Upload Transcript"):
|
629 |
+
gr.Markdown("### Upload your transcript (PDF recommended)")
|
630 |
+
transcript_file = gr.File(label="Transcript file", file_types=[".pdf"])
|
631 |
+
transcript_output = gr.Textbox(label="Transcript Results", lines=20)
|
632 |
+
transcript_data = gr.State()
|
633 |
+
transcript_file.change(
|
634 |
+
fn=parse_transcript,
|
635 |
+
inputs=transcript_file,
|
636 |
+
outputs=[transcript_output, transcript_data]
|
637 |
+
)
|
638 |
+
|
639 |
+
with gr.Tab("Step 2: Learning Style Quiz"):
|
640 |
+
gr.Markdown("### Learning Style Quiz (20 Questions)")
|
641 |
+
quiz_components = []
|
642 |
+
for i, (question, options) in enumerate(zip(learning_style_questions, learning_style_options)):
|
643 |
+
quiz_components.append(gr.Radio(options, label=f"{i+1}. {question}"))
|
644 |
+
|
645 |
+
learning_output = gr.Textbox(label="Your Learning Style", lines=15)
|
646 |
+
gr.Button("Submit Quiz").click(
|
647 |
+
fn=learning_style_quiz,
|
648 |
+
inputs=quiz_components,
|
649 |
+
outputs=learning_output
|
650 |
+
)
|
651 |
+
|
652 |
+
with gr.Tab("Step 3: Personal Questions"):
|
653 |
+
name = gr.Textbox(label="What's your name?")
|
654 |
+
age = gr.Number(label="How old are you?", precision=0)
|
655 |
+
interests = gr.Textbox(label="What are your interests?")
|
656 |
+
movie = gr.Textbox(label="Favorite movie?")
|
657 |
+
movie_reason = gr.Textbox(label="Why do you like that movie?")
|
658 |
+
show = gr.Textbox(label="Favorite TV show?")
|
659 |
+
show_reason = gr.Textbox(label="Why do you like that show?")
|
660 |
+
book = gr.Textbox(label="Favorite book?")
|
661 |
+
book_reason = gr.Textbox(label="Why do you like that book?")
|
662 |
+
character = gr.Textbox(label="Favorite character?")
|
663 |
+
character_reason = gr.Textbox(label="Why do you like that character?")
|
664 |
+
blog_checkbox = gr.Checkbox(label="Do you want to write a blog?", value=False)
|
665 |
+
blog_text = gr.Textbox(label="Write your blog here", visible=False, lines=5)
|
666 |
+
blog_checkbox.change(lambda x: gr.update(visible=x), inputs=blog_checkbox, outputs=blog_text)
|
667 |
+
|
668 |
+
with gr.Tab("Step 4: Save & Review"):
|
669 |
+
output_summary = gr.Markdown()
|
670 |
+
save_btn = gr.Button("Save Profile")
|
671 |
+
save_btn.click(
|
672 |
+
fn=save_profile,
|
673 |
+
inputs=[name, age, interests, transcript_data, learning_output,
|
674 |
+
movie, movie_reason, show, show_reason,
|
675 |
+
book, book_reason, character, character_reason, blog_text],
|
676 |
+
outputs=output_summary
|
677 |
+
)
|
678 |
+
|
679 |
+
with gr.Tab("🤖 AI Teaching Assistant"):
|
680 |
+
gr.Markdown("## Your Personalized Learning Assistant")
|
681 |
+
chatbot = gr.ChatInterface(
|
682 |
+
fn=generate_response,
|
683 |
+
examples=[
|
684 |
+
"How should I study for my next test?",
|
685 |
+
"What's my GPA information?",
|
686 |
+
"Show me my course history",
|
687 |
+
"How can I improve my grades?"
|
688 |
+
]
|
689 |
+
)
|
690 |
|
691 |
+
# ========== RUN APPLICATION ==========
|
692 |
if __name__ == "__main__":
|
693 |
+
app.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|