Spaces:
Running
Running
File size: 54,966 Bytes
1b75011 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 |
import base64
import io
import random
import dash
import numpy as np
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from dash import Input, Output, State, callback, dcc, html
# Initialize the Dash app
app = dash.Dash(__name__, suppress_callback_exceptions=True)
server = app.server
# Define app layout
app.layout = html.Div(
[
# Header
html.Div(
[
html.H1(
"Sessions Observatory by helvia.ai 🔭📊",
className="app-header",
),
html.P(
"Upload a CSV/Excel file to visualize the chatbot's dialog topics.",
className="app-description",
),
],
className="header-container",
),
# File Upload Component
html.Div(
[
dcc.Upload(
id="upload-data",
children=html.Div(
[
html.Div("Drag and Drop", className="upload-text"),
html.Div("or", className="upload-divider"),
html.Div(
html.Button("Select a File", className="upload-button")
),
],
className="upload-content",
),
style={
"width": "100%",
"height": "120px",
"lineHeight": "60px",
"borderWidth": "1px",
"borderStyle": "dashed",
"borderRadius": "0.5rem",
"textAlign": "center",
"margin": "10px 0",
"backgroundColor": "hsl(210, 40%, 98%)",
"borderColor": "hsl(214.3, 31.8%, 91.4%)",
"cursor": "pointer",
},
multiple=False,
),
# Status message with more padding and emphasis
html.Div(
id="upload-status",
className="upload-status-message",
style={"display": "none"}, # Initially hidden
),
],
className="upload-container",
),
# Main Content Area (hidden until file is uploaded)
html.Div(
[
# Dashboard layout with flexible grid
html.Div(
[
# Left side: Bubble chart
html.Div(
[
html.H3(
id="topic-distribution-header",
children="Sessions Observatory",
className="section-header",
),
# dcc.Graph(id="bubble-chart", style={"height": "80vh"}),
dcc.Graph(
id="bubble-chart",
style={"height": "calc(100% - 154px)"},
), # this does not work for some reason
html.Div(
[
# Only keep Color by
html.Div(
[
html.Div(
html.Label(
"Color by:",
className="control-label",
),
className="control-label-container",
),
],
className="control-labels-row",
),
# Only keep Color by options
html.Div(
[
html.Div(
dcc.RadioItems(
id="color-metric",
options=[
{
"label": "Sentiment",
"value": "negative_rate",
},
{
"label": "Resolution",
"value": "unresolved_rate",
},
{
"label": "Urgency",
"value": "urgent_rate",
},
],
value="negative_rate",
inline=True,
className="radio-group",
inputClassName="radio-input",
labelClassName="radio-label",
),
className="radio-container",
),
],
className="control-options-row",
),
],
className="chart-controls",
),
],
className="chart-container",
),
# Right side: Interactive sidebar with topic details
html.Div(
[
html.Div(
[
html.H3(
"Topic Details", className="section-header"
),
html.Div(
id="topic-title", className="topic-title"
),
html.Div(
[
html.Div(
[
html.H4(
"Metadata",
className="subsection-header",
),
html.Div(
id="topic-metadata",
className="metadata-container",
),
],
className="metadata-section",
),
html.Div(
[
html.H4(
"Key Metrics",
className="subsection-header",
),
html.Div(
id="topic-metrics",
className="metrics-container",
),
],
className="metrics-section",
),
# Added Tags section
html.Div(
[
html.H4(
"Tags",
className="subsection-header",
),
html.Div(
id="important-tags",
className="tags-container",
),
]
),
],
className="details-section",
),
html.Div(
[
html.H4(
"Sample Dialogs (Summary)",
className="subsection-header",
),
html.Div(
id="sample-dialogs",
className="sample-dialogs-container",
),
],
className="samples-section",
),
],
className="topic-details-content",
),
html.Div(
id="no-topic-selected",
children=[
html.Div(
[
html.I(
className="fas fa-info-circle info-icon"
),
html.H3("No topic selected"),
html.P(
"Click or hover on a bubble to view topic details."
),
],
className="no-selection-message",
)
],
className="no-selection-container",
),
],
className="sidebar-container",
),
],
className="dashboard-container",
)
],
id="main-content",
style={"display": "none"},
),
# Store the processed data
dcc.Store(id="stored-data"),
],
className="app-container",
)
# Define CSS for the app
app.index_string = """
<!DOCTYPE html>
<html>
<head>
{%metas%}
<title>Sessions Observatory by helvia.ai 🔭📊</title>
{%favicon%}
{%css%}
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
<style>
@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap');
:root {
--background: hsl(210, 20%, 95%);
--foreground: hsl(222.2, 84%, 4.9%);
--card: hsl(0, 0%, 100%);
--card-foreground: hsl(222.2, 84%, 4.9%);
--popover: hsl(0, 0%, 100%);
--popover-foreground: hsl(222.2, 84%, 4.9%);
--primary: hsl(222.2, 47.4%, 11.2%);
--primary-foreground: hsl(210, 40%, 98%);
--secondary: hsl(210, 40%, 96.1%);
--secondary-foreground: hsl(222.2, 47.4%, 11.2%);
--muted: hsl(210, 40%, 96.1%);
--muted-foreground: hsl(215.4, 16.3%, 46.9%);
--accent: hsl(210, 40%, 96.1%);
--accent-foreground: hsl(222.2, 47.4%, 11.2%);
--destructive: hsl(0, 84.2%, 60.2%);
--destructive-foreground: hsl(210, 40%, 98%);
--border: hsl(214.3, 31.8%, 91.4%);
--input: hsl(214.3, 31.8%, 91.4%);
--ring: hsl(222.2, 84%, 4.9%);
--radius: 0.5rem;
}
* {
margin: 0;
padding: 0;
box-sizing: border-box;
font-family: 'Inter', sans-serif;
}
body {
background-color: var(--background);
color: var(--foreground);
font-feature-settings: "rlig" 1, "calt" 1;
}
.app-container {
max-width: 2500px;
margin: 0 auto;
padding: 1.5rem;
background-color: var(--background);
min-height: 100vh;
display: flex;
flex-direction: column;
}
.header-container {
margin-bottom: 2rem;
text-align: center;
}
.app-header {
color: var(--foreground);
margin-bottom: 0.75rem;
font-weight: 600;
font-size: 2rem;
line-height: 1.2;
}
.app-description {
color: var(--muted-foreground);
font-size: 1rem;
line-height: 1.5;
}
.upload-container {
margin-bottom: 2rem;
max-width: 800px;
margin-left: auto;
margin-right: auto;
}
.upload-content {
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
height: 80%;
padding: 1.5rem;
position: relative;
}
.upload-text {
font-size: 1rem;
color: var(--primary);
font-weight: 500;
}
.upload-divider {
color: var(--muted-foreground);
margin: 0.5rem 0;
font-size: 0.875rem;
}
.upload-button {
background-color: var(--primary);
color: var(--primary-foreground);
border: none;
padding: 0.5rem 1rem;
border-radius: var(--radius);
font-size: 0.875rem;
cursor: pointer;
transition: opacity 0.2s;
font-weight: 500;
box-shadow: 0 1px 2px rgba(0, 0, 0, 0.05);
height: 2.5rem;
}
.upload-button:hover {
opacity: 0.9;
}
/* Status message styling */
.upload-status-message {
margin-top: 1rem;
padding: 0.75rem;
font-weight: 500;
text-align: center;
border-radius: var(--radius);
font-size: 0.875rem;
transition: all 0.3s ease;
background-color: var(--secondary);
color: var(--secondary-foreground);
}
/* Chart controls styling */
.chart-controls {
margin-top: 1rem;
display: flex;
flex-direction: column;
gap: 0.75rem;
padding: 1rem;
background-color: var(--card);
border-radius: var(--radius);
border: 1px solid var(--border);
box-shadow: 0 1px 2px rgba(0, 0, 0, 0.05);
}
.control-labels-row {
display: flex;
width: 100%;
}
.control-options-row {
display: flex;
width: 100%;
}
.control-label-container {
padding: 0 0.5rem;
text-align: left;
}
.control-label {
font-weight: 500;
color: var(--foreground);
font-size: 0.875rem;
line-height: 1.25rem;
}
.radio-container {
padding: 0 0.5rem;
width: 100%;
}
.radio-group {
display: flex;
gap: 1rem;
}
.radio-input {
margin-right: 0.375rem;
cursor: pointer;
height: 1rem;
width: 1rem;
border-radius: 9999px;
border: 1px solid var(--border);
appearance: none;
-webkit-appearance: none;
background-color: var(--background);
transition: border-color 0.2s;
}
.radio-input:checked {
border-color: var(--primary);
background-color: var(--primary);
background-image: url("data:image/svg+xml,%3csvg viewBox='0 0 16 16' fill='white' xmlns='http://www.w3.org/2000/svg'%3e%3ccircle cx='8' cy='8' r='3'/%3e%3c/svg%3e");
background-size: 100% 100%;
background-position: center;
background-repeat: no-repeat;
}
.radio-label {
font-weight: 400;
color: var(--foreground);
display: flex;
align-items: center;
cursor: pointer;
font-size: 0.875rem;
line-height: 1.25rem;
}
/* Dashboard container */
.dashboard-container {
display: flex;
flex-wrap: wrap;
gap: 1.5rem;
flex: 1;
height: 100%;
}
.chart-container {
flex: 2.75;
min-width: 400px;
background: var(--card);
border-radius: var(--radius);
box-shadow: 0 1px 3px rgba(0, 0, 0, 0.1);
padding: 1rem;
border: 0.75px solid var(--border);
height: 100%;
}
.sidebar-container {
flex: 1;
min-width: 300px;
background: var(--card);
border-radius: var(--radius);
box-shadow: 0 1px 3px rgba(0, 0, 0, 0.1);
padding: 1rem;
position: relative;
height: 100vh;
overflow-y: auto;
border: 1px solid var(--border);
height: 100%;
}
.section-header {
margin-bottom: 1rem;
color: var(--foreground);
border-bottom: 1px solid var(--border);
padding-bottom: 0.75rem;
font-weight: 600;
font-size: 1.25rem;
}
.subsection-header {
margin: 1rem 0 0.75rem;
color: var(--foreground);
font-size: 1rem;
font-weight: 600;
}
.topic-title {
font-size: 1.25rem;
font-weight: 600;
color: var(--foreground);
margin-bottom: 1rem;
padding: 0.5rem 0.75rem;
background-color: var(--secondary);
border-radius: var(--radius);
}
.metadata-container {
display: flex;
flex-wrap: wrap;
gap: 0.75rem;
margin-bottom: 1rem;
}
.metadata-item {
background-color: var(--secondary);
padding: 0.5rem 0.75rem;
border-radius: var(--radius);
font-size: 0.875rem;
display: flex;
align-items: center;
color: var(--secondary-foreground);
}
.metadata-icon {
margin-right: 0.5rem;
color: var(--primary);
}
.metrics-container {
display: flex;
justify-content: space-between;
gap: 0.75rem;
margin-bottom: 0.75rem;
}
.metric-box {
background-color: var(--card);
border-radius: var(--radius);
padding: 0.75rem;
text-align: center;
flex: 1;
border: 1px solid var(--border);
}
.metric-box.negative {
border-left: 3px solid var(--destructive);
}
.metric-box.unresolved {
border-left: 3px solid hsl(47.9, 95.8%, 53.1%);
}
.metric-box.urgent {
border-left: 3px solid hsl(217.2, 91.2%, 59.8%);
}
.metric-value {
font-size: 1.5rem;
font-weight: 600;
margin-bottom: 0.25rem;
color: var(--foreground);
line-height: 1;
}
.metric-label {
font-size: 0.75rem;
color: var(--muted-foreground);
}
.sample-dialogs-container {
margin-top: 0.75rem;
}
.dialog-item {
background-color: var(--secondary);
border-radius: var(--radius);
padding: 1rem;
margin-bottom: 0.75rem;
border-left: 3px solid var(--primary);
}
.dialog-summary {
font-size: 0.875rem;
line-height: 1.5;
margin-bottom: 0.5rem;
color: var(--foreground);
}
.dialog-metadata {
display: flex;
flex-wrap: wrap;
gap: 0.5rem;
margin-top: 0.5rem;
font-size: 0.75rem;
}
.dialog-tag {
padding: 0.25rem 0.5rem;
border-radius: var(--radius);
font-size: 0.7rem;
font-weight: 500;
}
.tag-sentiment {
background-color: var(--destructive);
color: var(--destructive-foreground);
}
.tag-resolution {
background-color: hsl(47.9, 95.8%, 53.1%);
color: hsl(222.2, 84%, 4.9%);
}
.tag-urgency {
background-color: hsl(217.2, 91.2%, 59.8%);
color: hsl(210, 40%, 98%);
}
.tag-chat-id {
background-color: hsl(215.4, 16.3%, 46.9%);
color: hsl(210, 40%, 98%);
font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
font-weight: 500;
}
.no-selection-container {
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
display: flex;
align-items: center;
justify-content: center;
background-color: hsla(0, 0%, 100%, 0.95);
z-index: 10;
border-radius: var(--radius);
}
.no-selection-message {
text-align: center;
color: var(--muted-foreground);
padding: 1.5rem;
}
.info-icon {
font-size: 2rem;
margin-bottom: 0.75rem;
color: var(--muted);
}
/* Tags container */
.tags-container {
display: flex;
flex-wrap: wrap;
gap: 8px;
margin-top: 5px;
margin-bottom: 15px;
padding: 6px;
border-radius: 8px;
background-color: #f8f9fa;
}
.topic-tag {
padding: 0.375rem 0.75rem;
border-radius: var(--radius);
font-size: 0.75rem;
display: inline-flex;
align-items: center;
transition: all 0.2s ease;
font-weight: 500;
margin-bottom: 0.25rem;
cursor: default;
background-color: var(--muted);
color: var(--muted-foreground);
border: 1px solid var(--border);
}
.topic-tag {
padding: 6px 12px;
border-radius: 15px;
font-size: 0.8rem;
display: inline-flex;
align-items: center;
box-shadow: 0 1px 3px rgba(0,0,0,0.12);
transition: all 0.2s ease;
font-weight: 500;
margin-bottom: 5px;
cursor: default;
border: 1px solid rgba(0,0,0,0.08);
background-color: #6c757d; /* Consistent medium gray color */
color: white;
}
.topic-tag:hover {
transform: translateY(-1px);
box-shadow: 0 3px 5px rgba(0,0,0,0.15);
background-color: #5a6268; /* Slightly darker on hover */
}
.topic-tag-icon {
margin-right: 5px;
font-size: 0.7rem;
opacity: 0.8;
color: rgba(255, 255, 255, 0.9);
}
.no-tags-message {
color: var(--muted-foreground);
font-style: italic;
padding: 0.75rem;
text-align: center;
width: 100%;
}
/* Responsive adjustments */
@media (max-width: 768px) {
.dashboard-container {
flex-direction: column;
}
.chart-container, .sidebar-container {
width: 100%;
}
.app-header {
font-size: 1.5rem;
}
}
</style>
</head>
<body>
{%app_entry%}
<footer>
{%config%}
{%scripts%}
{%renderer%}
</footer>
</body>
</html>
"""
@callback(
Output("topic-distribution-header", "children"),
Input("stored-data", "data"),
)
def update_topic_distribution_header(data):
if not data:
return "Sessions Observatory" # Default when no data is available
df = pd.DataFrame(data)
total_dialogs = df["count"].sum() # Sum up the 'count' column
return f"Sessions Observatory ({total_dialogs} dialogs)"
# Define callback to process uploaded file
@callback(
[
Output("stored-data", "data"),
Output("upload-status", "children"),
Output("upload-status", "style"), # Add style output for visibility
Output("main-content", "style"),
],
[Input("upload-data", "contents")],
[State("upload-data", "filename")],
)
def process_upload(contents, filename):
if contents is None:
return None, "", {"display": "none"}, {"display": "none"} # Keep hidden
try:
# Parse uploaded file
content_type, content_string = contents.split(",")
decoded = base64.b64decode(content_string)
if "csv" in filename.lower():
df = pd.read_csv(io.StringIO(decoded.decode("utf-8")))
elif "xls" in filename.lower():
df = pd.read_excel(io.BytesIO(decoded))
else:
return (
None,
html.Div(
[
html.I(
className="fas fa-exclamation-circle",
style={"color": "var(--destructive)", "marginRight": "8px"},
),
"Please upload a CSV or Excel file.",
],
style={"color": "var(--destructive)"},
),
{"display": "block"}, # Make visible after error
{"display": "none"},
)
# Process the dataframe to get topic statistics
topic_stats = analyze_topics(df)
return (
topic_stats.to_dict("records"),
html.Div(
[
html.I(
className="fas fa-check-circle",
style={
"color": "hsl(142.1, 76.2%, 36.3%)",
"marginRight": "8px",
},
),
f'Successfully uploaded "{filename}"',
],
style={"color": "hsl(142.1, 76.2%, 36.3%)"},
),
{"display": "block"}, # maybe add the above line here too #TODO
{
"display": "block",
"height": "calc(100vh - 40px)",
}, # Make visible after successful upload
)
except Exception as e:
return (
None,
html.Div(
[
html.I(
className="fas fa-exclamation-triangle",
style={"color": "var(--destructive)", "marginRight": "8px"},
),
f"Error processing file: {str(e)}",
],
style={"color": "var(--destructive)"},
),
{"display": "block"}, # Make visible after error
{"display": "none"},
)
# Function to analyze the topics and create statistics
def analyze_topics(df):
# Group by topic name and calculate metrics
topic_stats = (
df.groupby("deduplicated_topic_name")
.agg(
count=("id", "count"),
negative_count=("Sentiment", lambda x: (x == "negative").sum()),
unresolved_count=("Resolution", lambda x: (x == "unresolved").sum()),
urgent_count=("Urgency", lambda x: (x == "urgent").sum()),
)
.reset_index()
)
# Calculate rates
topic_stats["negative_rate"] = (
topic_stats["negative_count"] / topic_stats["count"] * 100
).round(1)
topic_stats["unresolved_rate"] = (
topic_stats["unresolved_count"] / topic_stats["count"] * 100
).round(1)
topic_stats["urgent_rate"] = (
topic_stats["urgent_count"] / topic_stats["count"] * 100
).round(1)
# Apply binned layout
topic_stats = apply_binned_layout(topic_stats)
return topic_stats
# New binned layout function
def apply_binned_layout(df, padding=0, bin_config=None, max_items_per_row=6):
"""
Apply a binned layout where bubbles are grouped into rows based on dialog count.
Bubbles in each row will be centered horizontally.
Args:
df: DataFrame containing the topic data
padding: Padding from edges as percentage
bin_config: List of tuples defining bin ranges and descriptions.
Example: [(300, None, "300+ dialogs"), (250, 299, "250-299 dialogs"), ...]
max_items_per_row: Maximum number of items to display in a single row
Returns:
DataFrame with updated x, y positions
"""
# Create a copy of the dataframe to avoid modifying the original
df_sorted = df.copy()
# Default bin configuration if none is provided
# 8 rows x 6 bubbles is usually good
if bin_config is None:
bin_config = [
(100, None, "100+ dialogs"),
(50, 99, "50-99 dialogs"),
(25, 49, "25-49 dialogs"),
(9, 24, "9-24 dialogs"),
(7, 8, "7-8 dialogs"),
(5, 7, "5-6 dialogs"),
(4, 4, "4 dialogs"),
(0, 3, "0-3 dialogs"),
]
# Generate bin descriptions and conditions dynamically
bin_descriptions = {}
conditions = []
bin_values = []
for i, (lower, upper, description) in enumerate(bin_config):
bin_name = f"Bin {i + 1}"
bin_descriptions[bin_name] = description
bin_values.append(bin_name)
if upper is None: # No upper limit
conditions.append(df_sorted["count"] >= lower)
else:
conditions.append(
(df_sorted["count"] >= lower) & (df_sorted["count"] <= upper)
)
# Apply the conditions to create the bin column
df_sorted["bin"] = np.select(conditions, bin_values, default="Bin 8")
df_sorted["bin_description"] = df_sorted["bin"].map(bin_descriptions)
# Sort by bin (ascending to get Bin 1 first) and by count (descending) within each bin
df_sorted = df_sorted.sort_values(by=["bin", "count"], ascending=[True, False])
# Now split bins that have more than max_items_per_row items
original_bins = df_sorted["bin"].unique()
new_rows = []
new_bin_descriptions = bin_descriptions.copy()
for bin_name in original_bins:
bin_mask = df_sorted["bin"] == bin_name
bin_group = df_sorted[bin_mask]
bin_size = len(bin_group)
# If bin has more items than max_items_per_row, split it
if bin_size > max_items_per_row:
# Calculate how many sub-bins we need
num_sub_bins = (bin_size + max_items_per_row - 1) // max_items_per_row
# Calculate items per sub-bin (distribute evenly)
items_per_sub_bin = [bin_size // num_sub_bins] * num_sub_bins
# Distribute the remainder one by one to achieve balance
remainder = bin_size % num_sub_bins
for i in range(remainder):
items_per_sub_bin[i] += 1
# Original bin description
original_description = bin_descriptions[bin_name]
# Create new row entries and update bin assignments
start_idx = 0
for i in range(num_sub_bins):
# Create new bin name with sub-bin index
new_bin_name = f"{bin_name}_{i + 1}"
# Create new bin description with sub-bin index
new_description = f"{original_description} ({i + 1}/{num_sub_bins})"
new_bin_descriptions[new_bin_name] = new_description
# Get slice of dataframe for this sub-bin
end_idx = start_idx + items_per_sub_bin[i]
sub_bin_rows = bin_group.iloc[start_idx:end_idx].copy()
# Update bin name and description
sub_bin_rows["bin"] = new_bin_name
sub_bin_rows["bin_description"] = new_description
# Add to new rows
new_rows.append(sub_bin_rows)
# Update start index for next iteration
start_idx = end_idx
# Remove the original bin from df_sorted
df_sorted = df_sorted[~bin_mask]
# Combine the original dataframe (with small bins) and the new split bins
if new_rows:
df_sorted = pd.concat([df_sorted] + new_rows)
# Re-sort with the new bin names
df_sorted = df_sorted.sort_values(by=["bin", "count"], ascending=[True, False])
# Calculate the vertical positions for each row (bin)
bins_with_topics = sorted(df_sorted["bin"].unique())
num_rows = len(bins_with_topics)
available_height = 100 - (2 * padding)
row_height = available_height / num_rows
# Calculate and assign y-positions (vertical positions)
row_positions = {}
for i, bin_name in enumerate(bins_with_topics):
# Calculate row position (centered within its allocated space)
row_pos = padding + i * row_height + (row_height / 2)
row_positions[bin_name] = row_pos
df_sorted["y"] = df_sorted["bin"].map(row_positions)
# Center the bubbles in each row horizontally
center_point = 50 # Middle of the chart (0-100 scale)
for bin_name in bins_with_topics:
# Get topics in this bin
bin_mask = df_sorted["bin"] == bin_name
num_topics_in_bin = bin_mask.sum()
if num_topics_in_bin == 1:
# If there's only one bubble, place it in the center
df_sorted.loc[bin_mask, "x"] = center_point
else:
if num_topics_in_bin < max_items_per_row:
# For fewer bubbles, add a little bit of spacing between them
# Calculate the total width needed
total_width = (num_topics_in_bin - 1) * 17.5 # 10 units between bubbles
# Calculate starting position (to center the group)
start_pos = center_point - (total_width / 2)
# Assign positions
positions = [start_pos + (i * 17.5) for i in range(num_topics_in_bin)]
df_sorted.loc[bin_mask, "x"] = positions
else:
# For multiple bubbles, distribute them evenly around the center
# Calculate the total width needed
total_width = (num_topics_in_bin - 1) * 15 # 15 units between bubbles
# Calculate starting position (to center the group)
start_pos = center_point - (total_width / 2)
# Assign positions
positions = [start_pos + (i * 15) for i in range(num_topics_in_bin)]
df_sorted.loc[bin_mask, "x"] = positions
# Add original rank for reference
df_sorted["size_rank"] = range(1, len(df_sorted) + 1)
return df_sorted
# New function to update positions based on selected size metric
def update_bubble_positions(df: pd.DataFrame) -> pd.DataFrame:
# For the main chart, we always use the binned layout
return apply_binned_layout(df)
# Callback to update the bubble chart
@callback(
Output("bubble-chart", "figure"),
[
Input("stored-data", "data"),
Input("color-metric", "value"),
],
)
def update_bubble_chart(data, color_metric):
if not data:
return go.Figure()
df = pd.DataFrame(data)
# Update positions using binned layout
df = update_bubble_positions(df)
# Always use count for sizing
size_values = df["count"]
raw_sizes = df["count"]
size_title = "Dialog Count"
# Apply log scaling to the size values for better visualization
# To make the smallest bubble bigger, increase the min_size value (currently 2.5).
min_size = 1 # Minimum bubble size
if size_values.max() > size_values.min():
# Log-scale the sizes
log_sizes = np.log1p(size_values)
# Scale to a reasonable range for visualization
# To make the biggest bubble smaller, reduce the multiplier (currently 50).
size_values = (
min_size
+ (log_sizes - log_sizes.min()) / (log_sizes.max() - log_sizes.min()) * 50
)
else:
# If all values are the same, use a default size
size_values = np.ones(len(df)) * 12.5
# DEBUG: Print sizes of bubbles in the first and second bins
bins = sorted(df["bin"].unique())
if len(bins) >= 1:
first_bin = bins[0]
print(f"DEBUG - First bin '{first_bin}' bubble sizes:")
first_bin_df = df[df["bin"] == first_bin]
for idx, row in first_bin_df.iterrows():
print(
f" Topic: {row['deduplicated_topic_name']}, Raw size: {row['count']}, Displayed size: {size_values[idx]}"
)
if len(bins) >= 2:
second_bin = bins[1]
print(f"DEBUG - Second bin '{second_bin}' bubble sizes:")
second_bin_df = df[df["bin"] == second_bin]
for idx, row in second_bin_df.iterrows():
print(
f" Topic: {row['deduplicated_topic_name']}, Raw size: {row['count']}, Displayed size: {size_values[idx]}"
)
# Determine color based on selected metric
if color_metric == "negative_rate":
color_values = df["negative_rate"]
# color_title = "Negative Sentiment (%)"
color_title = "Negativity (%)"
# color_scale = "RdBu" # no ice, RdBu - og is Reds - matter is good too
# color_scale = "Portland"
# color_scale = "RdYlGn_r"
# color_scale = "Teal"
color_scale = "Teal"
elif color_metric == "unresolved_rate":
color_values = df["unresolved_rate"]
color_title = "Unresolved (%)"
# color_scale = "Burg" # og is YlOrRd
# color_scale = "Temps"
# color_scale = "Armyrose"
# color_scale = "YlOrRd"
color_scale = "Teal"
else:
color_values = df["urgent_rate"]
color_title = "Urgency (%)"
# color_scale = "Magenta" # og is Blues
# color_scale = "Tealrose"
# color_scale = "Portland"
color_scale = "Teal"
# Set all text positions to bottom for consistent layout
text_positions = ["bottom center"] * len(df)
# Create enhanced hover text that includes bin information
hover_text = [
f"Topic: {topic}<br>{size_title}: {raw:.1f}<br>{color_title}: {color:.1f}<br>Group: {bin_desc}"
for topic, raw, color, bin_desc in zip(
df["deduplicated_topic_name"],
raw_sizes,
color_values,
df["bin_description"],
)
]
# Create bubble chart
fig = px.scatter(
df,
x="x",
y="y",
size=size_values,
color=color_values,
# text="deduplicated_topic_name", # Remove text here
hover_name="deduplicated_topic_name",
hover_data={
"x": False,
"y": False,
"bin_description": True,
},
size_max=42.5, # Maximum size of the bubbles, change this to adjust the size
color_continuous_scale=color_scale,
custom_data=[
"deduplicated_topic_name",
"count",
"negative_rate",
"unresolved_rate",
"urgent_rate",
"bin_description",
],
)
# Update traces: Remove text related properties
fig.update_traces(
mode="markers", # Remove '+text'
marker=dict(sizemode="area", opacity=0.8, line=dict(width=1, color="white")),
hovertemplate="%{hovertext}<extra></extra>",
hovertext=hover_text,
)
# Create annotations for the bubbles
annotations = []
for i, row in df.iterrows():
# Wrap text every 2 words
words = row["deduplicated_topic_name"].split()
wrapped_text = "<br>".join(
[" ".join(words[i : i + 4]) for i in range(0, len(words), 4)]
)
# Calculate size for vertical offset (approximately based on the bubble size)
# Add vertical offset based on bubble size to place text below the bubble
marker_size = (
size_values[i] / 20 # type: ignore # FIXME: size_values[df.index.get_loc(i)] / 20
) # Adjust this divisor as needed to get proper spacing
annotations.append(
dict(
x=row["x"],
y=row["y"]
+ 0.125 # Adding this so in a row with maximum bubbles, the left one does not overlap with the bin label
+ marker_size, # Add vertical offset to position text below the bubble
text=wrapped_text,
showarrow=False,
textangle=0,
font=dict(
size=10,
# size=8,
color="var(--foreground)",
family="Arial, sans-serif",
weight="bold",
),
xanchor="center",
yanchor="top", # Anchor to top of text box so it hangs below the bubble
bgcolor="rgba(255,255,255,0.7)", # Add semi-transparent background for better readability
bordercolor="rgba(0,0,0,0.1)", # Add a subtle border color
borderwidth=1,
borderpad=1,
# TODO: Radius for rounded corners
)
)
# Add bin labels and separator lines
unique_bins = sorted(df["bin"].unique())
bin_y_positions = [
df[df["bin"] == bin_name]["y"].mean() for bin_name in unique_bins
]
# Dynamically extract bin descriptions
bin_descriptions = df.set_index("bin")["bin_description"].to_dict()
for bin_name, bin_y in zip(unique_bins, bin_y_positions):
# Add horizontal line
fig.add_shape(
type="line",
x0=0,
y0=bin_y,
x1=100,
y1=bin_y,
line=dict(color="rgba(0,0,0,0.1)", width=1, dash="dot"),
layer="below",
)
# Add subtle lines for each bin and bin labels
for bin_name, bin_y in zip(unique_bins, bin_y_positions):
# Add horizontal line
fig.add_shape(
type="line",
x0=0,
y0=bin_y,
x1=100,
y1=bin_y,
line=dict(color="rgba(0,0,0,0.1)", width=1, dash="dot"),
layer="below",
)
# Add bin label annotation
annotations.append(
dict(
x=0, # Position the label on the left side
y=bin_y,
xref="x",
yref="y",
text=bin_descriptions[bin_name],
showarrow=False,
font=dict(size=8.25, color="var(--muted-foreground)"),
align="left",
xanchor="left",
yanchor="middle",
bgcolor="rgba(255,255,255,0.7)",
borderpad=1,
)
)
fig.update_layout(
title=None,
xaxis=dict(
showgrid=False,
zeroline=False,
showticklabels=False,
title=None,
range=[0, 100],
),
yaxis=dict(
showgrid=False,
zeroline=False,
showticklabels=False,
title=None,
range=[0, 100],
autorange="reversed", # Keep largest at top
),
hovermode="closest",
margin=dict(l=0, r=0, t=10, b=10),
coloraxis_colorbar=dict(
title=color_title,
title_font=dict(size=9),
tickfont=dict(size=8),
thickness=10,
len=0.6,
yanchor="middle",
y=0.5,
xpad=0,
),
legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1),
paper_bgcolor="rgba(0,0,0,0)",
plot_bgcolor="rgba(0,0,0,0)",
hoverlabel=dict(bgcolor="white", font_size=12, font_family="Inter"),
annotations=annotations, # Add bin labels as annotations
)
return fig
# Update the update_topic_details callback to use grayscale colors for tags based on frequency
@callback(
[
Output("topic-title", "children"),
Output("topic-metadata", "children"),
Output("topic-metrics", "children"),
Output("important-tags", "children"),
Output("sample-dialogs", "children"),
Output("no-topic-selected", "style"),
],
[Input("bubble-chart", "hoverData"), Input("bubble-chart", "clickData")],
[State("stored-data", "data"), State("upload-data", "contents")],
)
def update_topic_details(hover_data, click_data, stored_data, file_contents):
# Determine which data to use (prioritize click over hover)
hover_info = hover_data or click_data
if not hover_info or not stored_data or not file_contents:
return "", [], [], "", [], {"display": "flex"}
# Extract topic name from the hover data
topic_name = hover_info["points"][0]["customdata"][0]
# Get stored data for this topic
df_stored = pd.DataFrame(stored_data)
topic_data = df_stored[df_stored["deduplicated_topic_name"] == topic_name].iloc[0]
# Get original data to sample conversations
content_type, content_string = file_contents.split(",")
decoded = base64.b64decode(content_string)
if (
content_type
== "data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64"
):
df_full = pd.read_excel(io.BytesIO(decoded))
else: # Assume CSV
df_full = pd.read_csv(io.StringIO(decoded.decode("utf-8")))
# Filter to this topic
topic_conversations = df_full[df_full["deduplicated_topic_name"] == topic_name]
# Create the title
title = html.Div([html.Span(topic_name)])
# Create metadata items
metadata_items = [
html.Div(
[
html.I(className="fas fa-comments metadata-icon"),
html.Span(f"{int(topic_data['count'])} dialogs"),
],
className="metadata-item",
),
]
# Create metrics boxes
metrics_boxes = [
html.Div(
[
html.Div(f"{topic_data['negative_rate']}%", className="metric-value"),
html.Div("Negative Sentiment", className="metric-label"),
],
className="metric-box negative",
),
html.Div(
[
html.Div(f"{topic_data['unresolved_rate']}%", className="metric-value"),
html.Div("Unresolved", className="metric-label"),
],
className="metric-box unresolved",
),
html.Div(
[
html.Div(f"{topic_data['urgent_rate']}%", className="metric-value"),
html.Div("Urgent", className="metric-label"),
],
className="metric-box urgent",
),
]
# New: Extract and process consolidated_tags with improved styling
tags_list = []
for _, row in topic_conversations.iterrows():
tags_str = row.get("consolidated_tags", "")
if pd.notna(tags_str):
tags = [tag.strip() for tag in tags_str.split(",") if tag.strip()]
tags_list.extend(tags)
# Count tag frequencies for better insight
tag_counts = {}
for tag in tags_list:
tag_counts[tag] = tag_counts.get(tag, 0) + 1
# Sort by frequency (most common first) and then alphabetically for ties
sorted_tags = sorted(tag_counts.items(), key=lambda x: (-x[1], x[0]))
# Keep only the top K tags
TOP_K = 15
sorted_tags = sorted_tags[:TOP_K]
if sorted_tags:
# Create beautifully styled tags with count indicators and consistent color
tags_output = html.Div(
[
html.Div(
[
html.I(className="fas fa-tag topic-tag-icon"),
html.Span(f"{tag} ({count})"),
],
className="topic-tag",
)
for tag, count in sorted_tags
],
className="tags-container",
)
else:
tags_output = html.Div(
[
html.I(className="fas fa-info-circle", style={"marginRight": "5px"}),
"No tags found for this topic",
],
className="no-tags-message",
)
# Sample up to 5 random dialogs
sample_size = min(5, len(topic_conversations))
if sample_size > 0:
sample_indices = random.sample(range(len(topic_conversations)), sample_size)
samples = topic_conversations.iloc[sample_indices]
dialog_items = []
for _, row in samples.iterrows():
# Create dialog item with tags
sentiment_tag = html.Span(
row["Sentiment"], className="dialog-tag tag-sentiment"
)
resolution_tag = html.Span(
row["Resolution"], className="dialog-tag tag-resolution"
)
urgency_tag = html.Span(row["Urgency"], className="dialog-tag tag-urgency")
# Add Chat ID tag if 'id' column exists
chat_id_tag = None
if "id" in row:
chat_id_tag = html.Span(
f"Chat ID: {row['id']}", className="dialog-tag tag-chat-id"
)
# Compile all tags, including the new Chat ID tag if available
tags = [sentiment_tag, resolution_tag, urgency_tag]
if chat_id_tag:
tags.append(chat_id_tag)
dialog_items.append(
html.Div(
[
html.Div(row["Summary"], className="dialog-summary"),
html.Div(
tags,
className="dialog-metadata",
),
],
className="dialog-item",
)
)
sample_dialogs = dialog_items
else:
sample_dialogs = [
html.Div(
"No sample dialogs available for this topic.",
style={"color": "var(--muted-foreground)"},
)
]
return (
title,
metadata_items,
metrics_boxes,
tags_output,
sample_dialogs,
{"display": "none"},
)
if __name__ == "__main__":
app.run_server(debug=False)
|