File size: 9,049 Bytes
cfbfc47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from Models import Models 

class ResumeSegmenter:

    def __init__(self, zero_shot_classifier):
        self.zero_shot_classifier = zero_shot_classifier

    objective = (
        'career goal',
        'objective',
        'career objective',
        'employment objective',
        'professional objective',
        'summary',
        'summary of qualifications',
        'digital'
    )

    work_and_employment = (
        'employment history',
        'employment data',
        'career summary',
        'work history',
        'work experience',
        'experience',
        'professional experience',
        'professional background',
        'professional employment',
        'additional experience',
        'career related experience',
        "professional employment history",
        'related experience',
        'programming experience',
        'freelance',
        'freelance experience',
        'army experience',
        'military experience',
        'military background',
    )

    education_and_training = (
        'academic background',
        'academic experience',
        'programs',
        'courses',
        'related courses',
        'education',
        'educational background',
        'educational qualifications',
        'educational training',
        'education and training',
        'training',
        'academic training',
        'professional training',
        'course project experience',
        'related course projects',
        'internship experience',
        'internships',
        'apprenticeships',
        'college activities',
        'certifications',
        'special training',
    )

    skills_header = (
        'credentials',
        'qualifications',
        'areas of experience',
        'areas of expertise',
        'areas of knowledge',
        'skills',
        "other skills",
        "other abilities",
        'career related skills',
        'professional skills',
        'specialized skills',
        'technical skills',
        'computer skills',
        'personal skills',
        'computer knowledge',        
        'technologies',
        'technical experience',
        'proficiencies',
        'languages',
        'language competencies and skills',
        'programming languages',
        'competencies'
    )

    misc = (
        'activities and honors',
        'activities',
        'affiliations',
        'professional affiliations',
        'associations',
        'professional associations',
        'memberships',
        'professional memberships',
        'athletic involvement',
        'community involvement',
        'refere',
        'civic activities',
        'extra-Curricular activities',
        'professional activities',
        'volunteer work',
        'volunteer experience',
        'additional information',
        'interests'
    )

    accomplishments = (
        'achievement',
        'awards and achievements',
        'licenses',
        'presentations',
        'conference presentations',
        'conventions',
        'dissertations',
        'exhibits',
        'papers',
        'publications',
        'professional publications',
        'research experience',
        'research grants',
        'project',
        'research projects',
        'personal projects',
        'current research interests',
        'thesis',
        'theses',
    )


    def find_segment_indices(self, string_to_search, resume_segments, resume_indices):
        for i, line in enumerate(string_to_search):

            if line[0].islower():
                continue

            header = line.lower()

            if [o for o in self.objective if header.startswith(o)]:
                try:
                    resume_segments['objective'][header]
                except:
                    resume_indices.append(i)
                    header = [o for o in self.objective if header.startswith(o)][0]
                    resume_segments['objective'][header] = i
            elif [w for w in self.work_and_employment if header.startswith(w)]:
                try:
                    resume_segments['work_and_employment'][header]
                except:
                    resume_indices.append(i)
                    header = [w for w in self.work_and_employment if header.startswith(w)][0]
                    resume_segments['work_and_employment'][header] = i
            elif [e for e in self.education_and_training if header.startswith(e)]:
                try:
                    resume_segments['education_and_training'][header]
                except:
                    resume_indices.append(i)
                    header = [e for e in self.education_and_training if header.startswith(e)][0]
                    resume_segments['education_and_training'][header] = i
            elif [s for s in self.skills_header if header.startswith(s)]:
                try:
                    resume_segments['skills'][header]
                except:
                    resume_indices.append(i)
                    header = [s for s in self.skills_header if header.startswith(s)][0]
                    resume_segments['skills'][header] = i
            elif [m for m in self.misc if header.startswith(m)]:
                try:
                    resume_segments['misc'][header]
                except:
                    resume_indices.append(i)
                    header = [m for m in self.misc if header.startswith(m)][0]
                    resume_segments['misc'][header] = i
            elif [a for a in self.accomplishments if header.startswith(a)]:
                try:
                    resume_segments['accomplishments'][header]
                except:
                    resume_indices.append(i)
                    header = [a for a in self.accomplishments if header.startswith(a)][0]
                    resume_segments['accomplishments'][header] = i

    def slice_segments(self, string_to_search, resume_segments, resume_indices):
        resume_segments['contact_info'] = string_to_search[:resume_indices[0]]
        sec_idxs = {} 
        for section, value in resume_segments.items():
            if section == 'contact_info':
                continue
            
            for sub_section, start_idx in value.items():
                end_idx = len(string_to_search)
                if (resume_indices.index(start_idx) + 1) != len(resume_indices):
                    end_idx = resume_indices[resume_indices.index(start_idx) + 1]
                
                sec_idxs[section] = (start_idx, end_idx)
                # print(start_idx, end_idx)

                resume_segments[section][sub_section] = string_to_search[start_idx:end_idx]
        return sec_idxs

    def find_true_segment(self, dict_of_segments, segment_name):
        segment_classes = {
            'objective': ["objective", "other"],
            'work_and_employment':["employment history", "other"],
            'education_and_training': ["education", "other"],
            'skills': ["skills", "other"],
            'accomplishments': ["accomplishments", "other"],
            'misc': ["misc", "other"],
            'contact_info': ["contact information", "other"]
        }
        classes = segment_classes[segment_name]
        scores = []
        segs = dict_of_segments.keys()
        for seg in segs:
            sequence = dict_of_segments[seg]
            score = self.zero_shot_classifier(' '.join(sequence), classes)["scores"][0]
            scores.append(score)
        
        res = sorted(zip(dict_of_segments.keys(), scores), key=lambda x: x[1], reverse=True)
        if len(res):
            return res[0][0]
        else: return 0 

    def segment(self, string_to_search):
        print("Segmenting the Resume..")
        resume_segments = {
            'objective': {},
            'work_and_employment': {},
            'education_and_training': {},
            'skills': {},
            'accomplishments': {},
            'misc': {}
        }

        resume_indices = []

        self.find_segment_indices(string_to_search, resume_segments, resume_indices)
        if len(resume_indices) != 0:
            sec_idx = self.slice_segments(string_to_search, resume_segments, resume_indices)
        else:
            resume_segments['contact_info'] = []

        for segment in resume_segments:
            if segment == "contact_info": continue
            if not len(resume_segments[segment]) > 1:
                if len(resume_segments[segment]) == 1: 
                    only_key = list(resume_segments[segment].keys())[0]
                    resume_segments[segment] = resume_segments[segment][only_key][1:]
                    continue
            if segment != "work_and_employment": continue
            true_seg = self.find_true_segment(resume_segments[segment], segment)
            if not true_seg: 
                resume_segments[segment] = []
            else:     
                resume_segments[segment] = resume_segments[segment][true_seg][1:]
            
        return resume_segments