File size: 21,532 Bytes
74ec333
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc8abe1
823b52c
 
 
 
 
907c533
 
c2354bc
907c533
78f318b
fc8abe1
 
 
823b52c
c60d2d1
823b52c
 
 
 
c60d2d1
907c533
fc8abe1
823b52c
 
 
 
14e49ed
 
 
 
 
 
823b52c
 
 
 
 
 
 
91d4500
 
 
 
823b52c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea7a2a8
 
 
 
 
 
823b52c
ea7a2a8
 
 
 
 
 
 
823b52c
ea7a2a8
823b52c
 
 
 
 
 
907c533
 
 
 
 
 
 
a280495
 
 
 
 
823b52c
4586bfa
823b52c
78f318b
823b52c
c60d2d1
a4da1a9
823b52c
c60d2d1
823b52c
c60d2d1
823b52c
fc8abe1
bab30c5
fc8abe1
 
 
 
 
 
 
 
a280495
bab30c5
a280495
7c26327
bab30c5
 
 
 
 
 
 
 
 
7c26327
 
 
 
 
 
 
bab30c5
 
78f318b
bab30c5
 
7c26327
bab30c5
 
 
7c26327
bab30c5
 
7c26327
 
 
 
 
bab30c5
7c26327
 
 
 
 
 
bab30c5
 
7c26327
 
 
 
bab30c5
 
7c26327
 
 
 
bab30c5
 
4586bfa
7c26327
 
 
 
4586bfa
 
7c26327
 
 
 
 
bab30c5
 
 
 
4586bfa
bab30c5
7c26327
bab30c5
 
 
 
74ec333
bab30c5
 
 
 
 
 
 
 
 
 
7c26327
20a37c7
 
4586bfa
74ec333
 
20a37c7
4586bfa
20a37c7
 
 
 
b7e5770
c60d2d1
 
 
 
 
4586bfa
 
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
# import re
# import pandas as pd
# import os
# from huggingface_hub import InferenceClient

# class DataProcessor:
#     INTERVENTION_COLUMN_OPTIONS = [
#         'Did the intervention happen today?',
#         'Did the intervention take place today?'
#     ]
#     YES_RESPONSES = ['yes', 'assessment day']  # Added this line
#     ENGAGED_STR = 'Engaged'
#     PARTIALLY_ENGAGED_STR = 'Partially Engaged'
#     NOT_ENGAGED_STR = 'Not Engaged'

#     def __init__(self, student_metrics_df=None):
#         self.hf_api_key = os.getenv('HF_API_KEY')
#         if not self.hf_api_key:
#             raise ValueError("HF_API_KEY not set in environment variables")
#         self.client = InferenceClient(api_key=self.hf_api_key)
#         self.student_metrics_df = student_metrics_df
#         self.intervention_column = None  # Will be set when processing data

#     def read_excel(self, uploaded_file):
#         return pd.read_excel(uploaded_file)

#     def format_session_data(self, df):
#         date_column = next((col for col in df.columns if col in ["Date of Session", "Date"]), None)
#         if date_column:
#             df[date_column] = pd.to_datetime(df[date_column], errors='coerce').dt.date
#         else:
#             print("Warning: Neither 'Date of Session' nor 'Date' column found in the dataframe.")
        
#         df['Timestamp'] = self.safe_convert_to_datetime(df['Timestamp'], '%I:%M %p')
#         df['Session Start Time'] = self.safe_convert_to_time(df['Session Start Time'], '%I:%M %p')
#         df['Session End Time'] = self.safe_convert_to_time(df['Session End Time'], '%I:%M %p')
#         return df

#     def safe_convert_to_time(self, series, format_str='%I:%M %p'):
#         try:
#             converted = pd.to_datetime(series, format='%H:%M:%S', errors='coerce')
#             if format_str:
#                 return converted.dt.strftime(format_str)
#             return converted
#         except Exception as e:
#             print(f"Error converting series to time: {e}")
#             return series

#     def safe_convert_to_datetime(self, series, format_str=None):
#         try:
#             converted = pd.to_datetime(series, errors='coerce')
#             if format_str:
#                 return converted.dt.strftime(format_str)
#             return converted
#         except Exception as e:
#             print(f"Error converting series to datetime: {e}")
#             return series

#     def replace_student_names_with_initials(self, df):
#         updated_columns = []
#         for col in df.columns:
#             if 'Student Attendance' in col:
#                 # Search for the last occurrence of text within square brackets at the end of the string
#                 match = re.search(r'\[(.+?)\]$', col)
#                 if not match:
#                     # Handle cases where the closing bracket might be missing
#                     match = re.search(r'\[(.+)$', col)
#                 if match:
#                     name = match.group(1).strip()
#                     # Remove any trailing closing bracket if it wasn't matched earlier
#                     name = name.rstrip(']')
#                     # Get initials
#                     initials = ''.join([part[0] for part in name.strip().split()])
#                     updated_col = f'Student Attendance [{initials}]'
#                     updated_columns.append(updated_col)
#                 else:
#                     # If no match is found, keep the column name as is
#                     updated_columns.append(col)
#             else:
#                 updated_columns.append(col)
#         df.columns = updated_columns
#         return df


#     def find_intervention_column(self, df):
#         for column in self.INTERVENTION_COLUMN_OPTIONS:
#             if column in df.columns:
#                 self.intervention_column = column
#                 return column
#         raise ValueError("No intervention column found in the dataframe.")

#     def get_intervention_column(self, df):
#         if self.intervention_column is None:
#             self.intervention_column = self.find_intervention_column(df)
#         return self.intervention_column

#     def compute_intervention_statistics(self, df):
#         intervention_column = self.get_intervention_column(df)
#         total_days = len(df)
#         sessions_held = df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES).sum()  # Modified line
#         intervention_frequency = (sessions_held / total_days) * 100 if total_days > 0 else 0
#         return pd.DataFrame({
#             'Intervention Dosage (%)': [round(intervention_frequency, 0)],
#             'Intervention Sessions Held': [sessions_held],
#             'Intervention Sessions Not Held': [total_days - sessions_held],
#             'Total Number of Days Available': [total_days]
#         })

#     def classify_engagement(self, engagement_str):
#         engagement_str = str(engagement_str).lower()
#         if engagement_str.startswith(self.ENGAGED_STR.lower()):
#             return self.ENGAGED_STR
#         elif engagement_str.startswith(self.PARTIALLY_ENGAGED_STR.lower()):
#             return self.PARTIALLY_ENGAGED_STR
#         elif engagement_str.startswith(self.NOT_ENGAGED_STR.lower()):
#             return self.NOT_ENGAGED_STR
#         else:
#             return 'Unknown'
    
#     def compute_student_metrics(self, df):
#         intervention_column = self.get_intervention_column(df)
#         intervention_df = df[df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES)]
#         intervention_sessions_held = len(intervention_df)
#         student_columns = [col for col in df.columns if col.startswith('Student Attendance')]
    
#         student_metrics = {}
#         for col in student_columns:
#             student_name = col.replace('Student Attendance [', '').replace(']', '').strip()
#             student_data = intervention_df[[col]].copy()
#             student_data[col] = student_data[col].fillna('Absent')
    
#             # Classify each entry
#             student_data['Engagement'] = student_data[col].apply(self.classify_engagement)
    
#             # Calculate attendance
#             attendance_values = student_data['Engagement'].apply(
#                 lambda x: 1 if x in [self.ENGAGED_STR, self.PARTIALLY_ENGAGED_STR, self.NOT_ENGAGED_STR] else 0
#             )
    
#             sessions_attended = attendance_values.sum()
#             attendance_pct = (sessions_attended / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
#             attendance_pct = round(attendance_pct)
    
#             # Engagement counts (excluding 'Absent')
#             engagement_counts = {
#                 self.ENGAGED_STR: 0,
#                 self.PARTIALLY_ENGAGED_STR: 0,
#                 self.NOT_ENGAGED_STR: 0
#             }
    
#             # Count the engagement types, excluding 'Absent'
#             for x in student_data['Engagement']:
#                 if x in engagement_counts:
#                     engagement_counts[x] += 1
#                 # 'Absent' is not counted in engagement_counts
    
#             total_present_sessions = sum(engagement_counts.values())
    
#             engaged_pct = (
#                 (engagement_counts[self.ENGAGED_STR] / total_present_sessions * 100)
#                 if total_present_sessions > 0 else 0
#             )
#             engaged_pct = round(engaged_pct)
    
#             partially_engaged_pct = (
#                 (engagement_counts[self.PARTIALLY_ENGAGED_STR] / total_present_sessions * 100)
#                 if total_present_sessions > 0 else 0
#             )
#             partially_engaged_pct = round(partially_engaged_pct)
    
#             not_engaged_pct = (
#                 (engagement_counts[self.NOT_ENGAGED_STR] / total_present_sessions * 100)
#                 if total_present_sessions > 0 else 0
#             )
#             not_engaged_pct = round(not_engaged_pct)
    
#             # Engagement percentage is based on Engaged and Partially Engaged sessions
#             engagement_pct = (
#                 ((engagement_counts[self.ENGAGED_STR] + engagement_counts[self.PARTIALLY_ENGAGED_STR]) / total_present_sessions * 100)
#                 if total_present_sessions > 0 else 0
#             )
#             engagement_pct = round(engagement_pct)
    
#             # Absent percentage (for reference, not used in engagement calculation)
#             absent_sessions = student_data['Engagement'].value_counts().get('Absent', 0)
#             absent_pct = (absent_sessions / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
#             absent_pct = round(absent_pct)
    
#             # Determine if the student attended ≥ 90% of sessions
#             attended_90 = "Yes" if attendance_pct >= 90 else "No"
    
#             # Determine if the student was engaged ≥ 80% of the time
#             engaged_80 = "Yes" if engagement_pct >= 80 else "No"
    
#             # Store metrics
#             student_metrics[student_name] = {
#                 'Attended ≥ 90%': attended_90,
#                 'Engagement ≥ 80%': engaged_80,
#                 'Attendance (%)': attendance_pct,
#                 'Engagement (%)': engagement_pct,
#                 f'{self.ENGAGED_STR} (%)': engaged_pct,
#                 f'{self.PARTIALLY_ENGAGED_STR} (%)': partially_engaged_pct,
#                 f'{self.NOT_ENGAGED_STR} (%)': not_engaged_pct,
#                 'Absent (%)': absent_pct
#             }
    
#         # Create a DataFrame from student_metrics
#         student_metrics_df = pd.DataFrame.from_dict(student_metrics, orient='index').reset_index()
#         student_metrics_df.rename(columns={'index': 'Student'}, inplace=True)
#         return student_metrics_df
    
#     def compute_average_metrics(self, student_metrics_df):
#         # Calculate the attendance and engagement average percentages across students
#         attendance_avg_stats = student_metrics_df['Attendance (%)'].mean()  # Average attendance percentage
#         engagement_avg_stats = student_metrics_df['Engagement (%)'].mean()  # Average engagement percentage
        
#         # Round the averages to whole numbers
#         attendance_avg_stats = round(attendance_avg_stats)
#         engagement_avg_stats = round(engagement_avg_stats)
        
#         return attendance_avg_stats, engagement_avg_stats
    
#     def evaluate_student(self, row, attendance_threshold=90, engagement_threshold=80):
#         if row["Attended ≥ 90%"] == "No":
#             return "Address Attendance"
#         elif row["Engagement ≥ 80%"] == "No":
#             return "Address Engagement"
#         else:
#             return "Consider barriers, fidelity, and progress monitoring"



import re
import pandas as pd
import os
from huggingface_hub import InferenceClient

class DataProcessor:
    INTERVENTION_COLUMN_OPTIONS = [
        'Did the intervention happen today?',
        'Did the intervention take place today?'
    ]
    YES_RESPONSES = ['yes', 'assessment day']  # Added this line
    ENGAGED_STR = 'Engaged'
    PARTIALLY_ENGAGED_STR = 'Partially Engaged'
    NOT_ENGAGED_STR = 'Not Engaged'

    def __init__(self, student_metrics_df=None):
        self.hf_api_key = os.getenv('HF_API_KEY')
        if not self.hf_api_key:
            raise ValueError("HF_API_KEY not set in environment variables")
        self.client = InferenceClient(api_key=self.hf_api_key)
        self.student_metrics_df = student_metrics_df
        self.intervention_column = None  # Will be set when processing data

    def read_excel(self, uploaded_file):
        return pd.read_excel(uploaded_file)

    def format_session_data(self, df):
        date_column = next((col for col in df.columns if col in ["Date of Session", "Date"]), None)
        if date_column:
            df[date_column] = pd.to_datetime(df[date_column], errors='coerce').dt.date
        else:
            print("Warning: Neither 'Date of Session' nor 'Date' column found in the dataframe.")
        
        df['Timestamp'] = self.safe_convert_to_datetime(df['Timestamp'], '%I:%M %p')
        df['Session Start Time'] = self.safe_convert_to_time(df['Session Start Time'], '%I:%M %p')
        df['Session End Time'] = self.safe_convert_to_time(df['Session End Time'], '%I:%M %p')
        return df

    def safe_convert_to_time(self, series, format_str='%I:%M %p'):
        try:
            converted = pd.to_datetime(series, format='%H:%M:%S', errors='coerce')
            if format_str:
                return converted.dt.strftime(format_str)
            return converted
        except Exception as e:
            print(f"Error converting series to time: {e}")
            return series

    def safe_convert_to_datetime(self, series, format_str=None):
        try:
            converted = pd.to_datetime(series, errors='coerce')
            if format_str:
                return converted.dt.strftime(format_str)
            return converted
        except Exception as e:
            print(f"Error converting series to datetime: {e}")
            return series

    def replace_student_names_with_initials(self, df):
        updated_columns = []
        for col in df.columns:
            if 'Student Attendance' in col:
                # Search for the last occurrence of text within square brackets at the end of the string
                match = re.search(r'\[(.+?)\]$', col)
                if not match:
                    # Handle cases where the closing bracket might be missing
                    match = re.search(r'\[(.+)$', col)
                if match:
                    name = match.group(1).strip()
                    # Remove any trailing closing bracket if it wasn't matched earlier
                    name = name.rstrip(']')
                    # Get initials
                    initials = ''.join([part[0] for part in name.strip().split()])
                    updated_col = f'Student Attendance [{initials}]'
                    updated_columns.append(updated_col)
                else:
                    # If no match is found, keep the column name as is
                    updated_columns.append(col)
            else:
                updated_columns.append(col)
        df.columns = updated_columns
        return df

    def find_intervention_column(self, df):
        for column in self.INTERVENTION_COLUMN_OPTIONS:
            if column in df.columns:
                self.intervention_column = column
                return column
        raise ValueError("No intervention column found in the dataframe.")

    def get_intervention_column(self, df):
        if self.intervention_column is None:
            self.intervention_column = self.find_intervention_column(df)
        return self.intervention_column

    def compute_intervention_statistics(self, df):
        intervention_column = self.get_intervention_column(df)
        total_days = len(df)
        sessions_held = df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES).sum()  # Modified line
        intervention_frequency = (sessions_held / total_days) * 100 if total_days > 0 else 0
        return pd.DataFrame({
            'Intervention Dosage (%)': [round(intervention_frequency, 0)],
            'Intervention Sessions Held': [sessions_held],
            'Intervention Sessions Not Held': [total_days - sessions_held],
            'Total Number of Days Available': [total_days]
        })

    def classify_engagement(self, engagement_str):
        engagement_str = str(engagement_str).lower()
        if engagement_str.startswith(self.ENGAGED_STR.lower()):
            return self.ENGAGED_STR
        elif engagement_str.startswith(self.PARTIALLY_ENGAGED_STR.lower()):
            return self.PARTIALLY_ENGAGED_STR
        elif engagement_str.startswith(self.NOT_ENGAGED_STR.lower()):
            return self.NOT_ENGAGED_STR
        else:
            return 'Unknown'
    
    def compute_student_metrics(self, df):
        intervention_column = self.get_intervention_column(df)
        intervention_df = df[df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES)]
        intervention_sessions_held = len(intervention_df)
        student_columns = [col for col in df.columns if col.startswith('Student Attendance')]
    
        student_metrics = {}
        for col in student_columns:
            student_name = col.replace('Student Attendance [', '').replace(']', '').strip()
            student_data = intervention_df[[col]].copy()
            student_data[col] = student_data[col].fillna('Absent')
    
            # Classify each entry
            student_data['Engagement'] = student_data[col].apply(self.classify_engagement)
    
            # Calculate attendance
            attendance_values = student_data['Engagement'].apply(
                lambda x: 1 if x in [self.ENGAGED_STR, self.PARTIALLY_ENGAGED_STR, self.NOT_ENGAGED_STR] else 0
            )
    
            sessions_attended = attendance_values.sum()
            attendance_pct = (sessions_attended / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
            attendance_pct = round(attendance_pct)
    
            # Engagement counts (excluding 'Absent')
            engagement_counts = {
                self.ENGAGED_STR: 0,
                self.PARTIALLY_ENGAGED_STR: 0,
                self.NOT_ENGAGED_STR: 0
            }
    
            # Count the engagement types, excluding 'Absent'
            for x in student_data['Engagement']:
                if x in engagement_counts:
                    engagement_counts[x] += 1
                # 'Absent' is not counted in engagement_counts
    
            total_present_sessions = sum(engagement_counts.values())
    
            engaged_pct = (
                (engagement_counts[self.ENGAGED_STR] / total_present_sessions * 100)
                if total_present_sessions > 0 else 0
            )
            engaged_pct = round(engaged_pct)
    
            partially_engaged_pct = (
                (engagement_counts[self.PARTIALLY_ENGAGED_STR] / total_present_sessions * 100)
                if total_present_sessions > 0 else 0
            )
            partially_engaged_pct = round(partially_engaged_pct)
    
            not_engaged_pct = (
                (engagement_counts[self.NOT_ENGAGED_STR] / total_present_sessions * 100)
                if total_present_sessions > 0 else 0
            )
            not_engaged_pct = round(not_engaged_pct)
    
            # Engagement percentage is based on Engaged and Partially Engaged sessions
            engagement_pct = (
                ((engagement_counts[self.ENGAGED_STR] + engagement_counts[self.PARTIALLY_ENGAGED_STR]) / total_present_sessions * 100)
                if total_present_sessions > 0 else 0
            )
            engagement_pct = round(engagement_pct)
    
            # Absent percentage (for reference, not used in engagement calculation)
            absent_sessions = student_data['Engagement'].value_counts().get('Absent', 0)
            absent_pct = (absent_sessions / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
            absent_pct = round(absent_pct)
    
            # Determine if the student attended ≥ 90% of sessions
            attended_90 = "Yes" if attendance_pct >= 90 else "No"
    
            # Determine if the student was engaged ≥ 80% of the time
            engaged_80 = "Yes" if engagement_pct >= 80 else "No"
    
            # Store metrics
            student_metrics[student_name] = {
                'Attended ≥ 90%': attended_90,
                'Engagement ≥ 80%': engaged_80,
                'Attendance (%)': attendance_pct,
                # 'Engagement (%)': engagement_pct, REMOVED REMOVED
                f'{self.ENGAGED_STR} (%)': engaged_pct,
                f'{self.PARTIALLY_ENGAGED_STR} (%)': partially_engaged_pct,
                f'{self.NOT_ENGAGED_STR} (%)': not_engaged_pct,
                'Absent (%)': absent_pct
            }
    
        # Create a DataFrame from student_metrics
        student_metrics_df = pd.DataFrame.from_dict(student_metrics, orient='index').reset_index()
        student_metrics_df.rename(columns={'index': 'Student'}, inplace=True)
        return student_metrics_df
    
    def compute_average_metrics(self, student_metrics_df):
        # Calculate the attendance and engagement average percentages across students
        attendance_avg_stats = student_metrics_df['Attendance (%)'].mean()  # Average attendance percentage
        # engagement_avg_stats = student_metrics_df['Engagement (%)'].mean()  # Average engagement percentage REMOVED REMOVED
        engagement_avg_stats = student_metrics_df[f'{self.ENGAGED_STR} (%)'].mean()  # Average engagement percentage
        
        # Round the averages to whole numbers
        attendance_avg_stats = round(attendance_avg_stats)
        engagement_avg_stats = round(engagement_avg_stats)
        
        return attendance_avg_stats, engagement_avg_stats
    
    def evaluate_student(self, row, attendance_threshold=90, engagement_threshold=80):
        if row["Attended ≥ 90%"] == "No":
            return "Address Attendance"
        elif row["Engagement ≥ 80%"] == "No":
            return "Address Engagement"
        else:
            return "Consider barriers, fidelity, and progress monitoring"