File size: 28,718 Bytes
9ac410d 88d066d b65c592 2955054 b1ed479 2955054 b1ed479 2955054 b1ed479 2955054 b1ed479 2955054 b1ed479 eb38733 2955054 b65c592 5929cca 2955054 5196b87 caf704e ebf4966 2955054 ebf4966 caf704e 2955054 caf704e 674df9a b65c592 2955054 b65c592 eea9f45 b65c592 2955054 39de0ed b65c592 39de0ed bc4e2d4 2955054 b65c592 2955054 b65c592 2955054 bc4e2d4 b65c592 7746185 2955054 674df9a caf704e b65c592 98209de 2955054 eb38733 e1fae35 eb38733 e1fae35 eb38733 e1fae35 b65c592 ebf4966 5196b87 eb38733 e1fae35 34d0e07 eb38733 e1fae35 34d0e07 eb38733 e1fae35 34d0e07 eb38733 e1fae35 34d0e07 eb38733 e1fae35 34d0e07 eb38733 e1fae35 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 |
import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from gliner import GLiNER
import plotly.express as px
with st.sidebar:
st.button("DEMO APP", type="primary")
expander = st.expander("**Important notes on the AI Resume Analysis based on Keywords App**")
expander.write('''
**Supported File Formats**
This app accepts files in .pdf formats.
**How to Use**
Paste the job description first. Then, upload your resume to retrieve the results. You can upload up to 10 resumes in total.
**Usage Limits**
You can request results up to 10 times in total.
**Subscription Management**
This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own AI Resume Analysis based on Keywords Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app within five business days. If you wish to delete your Account with us, please contact us at [email protected]
**Customization**
To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
**File Handling and Errors**
The app may display an error message if your file is corrupt, or has other errors.
For any errors or inquiries, please contact us at [email protected]
''')
st.subheader("Candidate Profile 1", divider = "green")
txt = st.text_area("Job description", key = "text 1")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 1"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 1")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 2")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 2", divider = "green")
txt = st.text_area("Job description", key = "text 2")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 2"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 3")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 4")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 3", divider = "green")
txt = st.text_area("Job description", key = "text 3")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 3"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 5")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 6")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 4", divider = "green")
txt = st.text_area("Job description", key = "text 4")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 4"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 7")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 8")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 5", divider = "green")
txt = st.text_area("Job description", key = "text 5")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 5"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 9")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 10")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 6", divider = "green")
txt = st.text_area("Job description", key = "text 6")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 6"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 11")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 12")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 7", divider = "green")
txt = st.text_area("Job description", key = "text 7")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 7"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 13")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 14")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 8", divider = "green")
txt = st.text_area("Job description", key = "text 8")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 8"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 16")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 18")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 9", divider = "green")
txt = st.text_area("Job description", key = "text 9")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 9"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 17")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 18")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
st.subheader("Candidate Profile 10", divider = "green")
txt = st.text_area("Job description", key = "text 10")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 2
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume in .pdf format", type="pdf", key="candidate 10"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name = 'Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "figure 19")
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Jon Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "figure 20")
st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
else:
st.warning(f"You have reached the maximum upload attempts ({max_attempts})")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
|