Skip to content

Interpreting and Visualizing Models

Interpreting topic models can be challenging. Luckily Turftopic comes loaded with a bunch of utilities you can use for interpreting your topic models.

from turftopic import KeyNMF

model = KeyNMF(10)
topic_data = model.prepare_topic_data(corpus)

Topic Tables

The easiest way you can investigate topics in your fitted model is to use the built-in pretty printing utilities, that you can call on every fitted model or TopicData object.

Interpret your models with topic tables

model.print_topics()
# or
topic_data.print_topics()

Topic ID Top 10 Words
0 armenians, armenian, armenia, turks, turkish, genocide, azerbaijan, soviet, turkey, azerbaijani
1 sale, price, shipping, offer, sell, prices, interested, 00, games, selling
2 christians, christian, bible, christianity, church, god, scripture, faith, jesus, sin
3 encryption, chip, clipper, nsa, security, secure, privacy, encrypted, crypto, cryptography
....

# Print highest ranking documents for topic 0
model.print_representative_documents(0, corpus, document_topic_matrix)

# since topic_data already stores the corpus and the doc-topic-matrix, you only need to give a topic ID
topic_data.print_representative_documents(0)

Document Score
Poor 'Poly'. I see you're preparing the groundwork for yet another retreat from your... 0.40
Then you must be living in an alternate universe. Where were they? An Appeal to Mankind During the... 0.40
It is 'Serdar', 'kocaoglan'. Just love it. Well, it could be your head wasn't screwed on just right... 0.39

document = "I think guns should definitely banned from all public institutions, such as schools."

model.print_topic_distribution(document)
# or 
topic_data.print_topic_distribution(document)

Topic name Score
7_gun_guns_firearms_weapons 0.05
17_mail_address_email_send 0.00
3_encryption_chip_clipper_nsa 0.00
19_baseball_pitching_pitcher_hitter 0.00
11_graphics_software_program_3d 0.00

You can also export tables as pandas DataFrames by removing the print_ prefix, and postfixing the method with _df or export tables in a given format, by using the export_<something> method instead of print_<something>.

model.topics_df()
model.topic_distribution_df("something something")
topic_data.representative_documents_df(5)
model.export_topics(format="markdown")
model.export_topic_distribution("something something", format="markdown")
topic_data.export_representative_documents(5, format="markdown")
model.export_topics(format="latex")
model.export_topic_distribution("something something", format="latex")
topic_data.export_representative_documents(5, format="latex")
model.export_topics(format="csv")
model.export_topic_distribution("something something", format="csv")
topic_data.export_representative_documents(5, format="csv")

Visualization with topicwizard

Turftopic comes with a number of model-specific visualization utilities, which you can check out on the models page. We do provide a general overview here, as well as instructions on how to use topicwizard with Turftopic for interactive topic interpretation.

To use topicwizard you will first have to install it:

pip install topic-wizard

Web App

The easiest way to investigate any topic model interactively is to use the topicwizard web app. You can launch the app either using a TopicData or a model object and a representative sample of documents.

topic_data.visualize_topicwizard()
import topicwizard

topicwizard.visualize(corpus=documents, model=model)

Figures

You can also produce individual interactive figures using the Figures API in topicwizard. Almost all figures in the Figures API can be called on the figures submodule of any TopicData object.

Interpret your models using interactive figures

topic_data.figures.topic_map()

topic_data.figures.topic_barcharts()

topic_data.figures.word_map()

topic_data.figures.topic_wordclouds()

topic_data.figures.document_map()

Datamapplot (Clustering models)

You can interactively explore clusters using datamapplot directly in Turftopic! You will first have to install datamapplot for this to work:

pip install turftopic[datamapplot]
from turftopic import ClusteringTopicModel
from turftopic.namers import OpenAITopicNamer

model = ClusteringTopicModel(feature_importance="centroid").fit(corpus)

namer = OpenAITopicNamer("gpt-4o-mini")
model.rename_topics(namer)

fig = model.plot_clusters_datamapplot()
fig.save("clusters_visualization.html")
fig

Info

If you are not running Turftopic from a Jupyter notebook, make sure to call fig.show(). This will open up a new browser tab with the interactive figure.

Interactive figure to explore cluster structure in a clustering topic model.

Naming Topics

Topics in Turftopic by default are named based on the highest ranking keywords for a given topic. You might however want to get more fitting names for your topics either automatically or assigning them manually. See a our detailed guide about Namers to learn how you can use LLMs to assign names to topics.

Examples

from turftopic import KeyNMF
from turftopic.namers import OpenAITopicNamer

namer = OpenAITopicNamer("gpt-4o-mini")
model.rename_topics(namer)

model.print_topics()
Topic ID Topic Name Highest Ranking
0 Operating Systems and Software windows, dos, os, ms, microsoft, unix, nt, memory, program, apps
1 Atheism and Belief Systems atheism, atheist, atheists, belief, religion, religious, theists, beliefs, believe, faith
2 Computer Architecture and Performance motherboard, ram, memory, cpu, bios, isa, speed, 486, bus, performance
...
from turftopic import SemanticSignalSeparation

model = SemanticSignalSeparation(10).fit(corpus)
model.rename_topics({0: "New name for topic 0", 5: "New name for topic 5"})

API Reference

turftopic.container.TopicContainer

Bases: ABC

Base class for classes that contain topical information.

Source code in turftopic/container.py
  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
class TopicContainer(ABC):
    """Base class for classes that contain topical information."""

    @property
    def has_negative_side(self) -> bool:
        return np.any(self.components_ < 0)

    def get_topics(
        self, top_k: int = 10
    ) -> List[Tuple[Any, List[Tuple[str, float]]]]:
        """Returns high-level topic representations in form of the top K words
        in each topic.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.

        Returns
        -------
        list[tuple]
            List of topics. Each topic is a tuple of
            topic ID and the top k words.
            Top k words are a list of (word, word_importance) pairs.
        """
        n_topics = self.components_.shape[0]
        try:
            classes = self.classes_
        except AttributeError:
            classes = list(range(n_topics))
        highest = np.argpartition(-self.components_, top_k)[:, :top_k]
        vocab = self.get_vocab()
        top = []
        score = []
        for component, high in zip(self.components_, highest):
            importance = component[high]
            high = high[np.argsort(-importance)]
            score.append(component[high])
            top.append(vocab[high])
        topics = []
        for topic, words, scores in zip(classes, top, score):
            topic_data = (topic, list(zip(words, scores)))
            topics.append(topic_data)
        return topics

    def _top_terms(
        self, top_k: int = 10, positive: bool = True
    ) -> list[list[str]]:
        terms = []
        vocab = self.get_vocab()
        for component in self.components_:
            lowest = np.argpartition(component, top_k)[:top_k]
            lowest = lowest[np.argsort(component[lowest])]
            highest = np.argpartition(-component, top_k)[:top_k]
            highest = highest[np.argsort(-component[highest])]
            if not positive:
                terms.append(list(vocab[lowest]))
            else:
                terms.append(list(vocab[highest]))
        return terms

    def get_top_words(
        self, top_k: int = 10, positive: bool = True
    ) -> list[list[str]]:
        """Returns list of top words for each topic.

        Parameters
        ----------
        top_k: int, default 10
            Number of words to return.
        positive: bool, default True
            Indicates whether the highest
            or lowest scoring terms should be returned.
        """
        return self._top_terms(top_k, positive)

    def get_top_documents(
        self,
        raw_documents=None,
        document_topic_matrix=None,
        top_k: int = 10,
        positive: bool = True,
    ) -> list[list[str]]:
        """Returns list of top documents for each topic.

        Parameters
        ----------
        top_k: int, default 10
            Number of documents to return per topic.
        positive: bool, default True
            Indicates whether the highest
            or lowest scoring documents should be returned.
        """
        docs = []
        raw_documents = raw_documents or getattr(self, "corpus", None)
        if raw_documents is None:
            raise ValueError(
                "No corpus was passed, can't search for representative documents."
            )
        document_topic_matrix = document_topic_matrix or getattr(
            self, "document_topic_matrix", None
        )
        if document_topic_matrix is None:
            try:
                document_topic_matrix = self.transform(raw_documents)
            except AttributeError:
                raise ValueError(
                    "Transductive methods cannot "
                    "infer topical content in documents.\n"
                    "Please pass a document_topic_matrix."
                )
        for topic_doc_vec in document_topic_matrix.T:
            if positive:
                topic_doc_vec = -topic_doc_vec
            highest = np.argsort(topic_doc_vec)[:top_k]
            docs.append([raw_documents[i_doc] for i_doc in highest])
        return docs

    def get_top_images(self, top_k: int = True, positive: bool = True):
        """Returns list of top images for each topic.

        Parameters
        ----------
        top_k: int, default 10
            Number of images to return.
        positive: bool, default True
            Indicates whether the highest
            or lowest scoring images should be returned.
        """
        if not hasattr(self, "top_images"):
            raise ValueError(
                "Model either has not been fit or was fit without images. top_images property missing."
            )
        if (not positive) and not hasattr(self, "negative_images"):
            raise ValueError(
                "Model either has not been fit or was fit without images. top_images property missing."
            )
        top_images = self.top_images if positive else self.negative_images
        ims = []
        for topic_images in top_images:
            if len(topic_images) < top_k:
                warnings.warn(
                    "Number of images stored in the topic model is smaller than the specified top_k, returning all that the model has."
                )
            ims.append(topic_images[:top_k])
        return ims

    def _rename_automatic(self, namer: TopicNamer) -> list[str]:
        self.topic_names_ = namer.name_topics(self._top_terms())
        return self.topic_names_

    def _topics_table(
        self,
        top_k: int = 10,
        show_scores: bool = False,
        show_negative: Optional[bool] = None,
    ) -> list[list[str]]:
        if show_negative is None:
            show_negative = self.has_negative_side
        columns = ["Topic ID"]
        if getattr(self, "topic_names_", None):
            columns.append("Topic Name")
        columns.append("Highest Ranking")
        if show_negative:
            columns.append("Lowest Ranking")
        rows = []
        try:
            classes = self.classes_
        except AttributeError:
            classes = list(range(self.components_.shape[0]))
        vocab = self.get_vocab()
        for i_topic, (topic_id, component) in enumerate(
            zip(classes, self.components_)
        ):
            highest = np.argpartition(-component, top_k)[:top_k]
            highest = highest[np.argsort(-component[highest])]
            lowest = np.argpartition(component, top_k)[:top_k]
            lowest = lowest[np.argsort(component[lowest])]
            if show_scores:
                concat_positive = ", ".join(
                    [
                        f"{word}({importance:.2f})"
                        for word, importance in zip(
                            vocab[highest], component[highest]
                        )
                    ]
                )
                concat_negative = ", ".join(
                    [
                        f"{word}({importance:.2f})"
                        for word, importance in zip(
                            vocab[lowest], component[lowest]
                        )
                    ]
                )
            else:
                concat_positive = ", ".join([word for word in vocab[highest]])
                concat_negative = ", ".join([word for word in vocab[lowest]])
            row = [f"{topic_id}"]
            if getattr(self, "topic_names_", None):
                row.append(self.topic_names_[i_topic])
            row.append(f"{concat_positive}")
            if show_negative:
                row.append(concat_negative)
            rows.append(row)
        return [columns, *rows]

    def print_topics(
        self,
        top_k: int = 10,
        show_scores: bool = False,
        show_negative: Optional[bool] = None,
    ):
        """Pretty prints topics in the model in a table.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.
        show_scores: bool, default False
            Indicates whether to show importance scores for each word.
        show_negative: bool, default False
            Indicates whether the most negative terms should also be displayed.
        """
        columns, *rows = self._topics_table(top_k, show_scores, show_negative)
        table = Table(show_lines=True)
        for column in columns:
            if column == "Highest Ranking":
                table.add_column(
                    column, justify="left", style="magenta", max_width=100
                )
            elif column == "Lowest Ranking":
                table.add_column(
                    column, justify="left", style="red", max_width=100
                )
            elif column == "Topic ID":
                table.add_column(column, style="blue", justify="right")
            else:
                table.add_column(column)
        for row in rows:
            table.add_row(*row)
        console = Console()
        console.print(table)

    def export_topics(
        self,
        top_k: int = 10,
        show_scores: bool = False,
        show_negative: Optional[bool] = None,
        format: str = "csv",
    ) -> str:
        """Exports top K words from topics in a table in a given format.
        Returns table as a pure string.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.
        show_scores: bool, default False
            Indicates whether to show importance scores for each word.
        show_negative: bool, default False
            Indicates whether the most negative terms should also be displayed.
        format: 'csv', 'latex' or 'markdown'
            Specifies which format should be used.
            'csv', 'latex' and 'markdown' are supported.
        """
        table = self._topics_table(
            top_k, show_scores, show_negative=show_negative
        )
        return export_table(table, format=format)

    def _representative_docs(
        self,
        topic_id,
        raw_documents=None,
        document_topic_matrix=None,
        top_k=5,
        show_negative: Optional[bool] = None,
    ) -> list[list[str]]:
        if show_negative is None:
            show_negative = self.has_negative_side
        raw_documents = (
            raw_documents
            if raw_documents is not None
            else getattr(self, "corpus", None)
        )
        if raw_documents is None:
            raise ValueError(
                "No corpus was passed, can't search for representative documents."
            )
        document_topic_matrix = (
            document_topic_matrix
            if document_topic_matrix is not None
            else getattr(self, "document_topic_matrix", None)
        )
        if document_topic_matrix is None:
            try:
                document_topic_matrix = self.transform(raw_documents)
            except AttributeError:
                raise ValueError(
                    "Transductive methods cannot "
                    "infer topical content in documents.\n"
                    "Please pass a document_topic_matrix."
                )
        try:
            topic_id = list(self.classes_).index(topic_id)
        except AttributeError:
            pass
        kth = min(top_k, document_topic_matrix.shape[0] - 1)
        highest = np.argpartition(-document_topic_matrix[:, topic_id], kth)[
            :kth
        ]
        highest = highest[
            np.argsort(-document_topic_matrix[highest, topic_id])
        ]
        scores = document_topic_matrix[highest, topic_id]
        columns = []
        columns.append("Document")
        columns.append("Score")
        rows = []
        for document_id, score in zip(highest, scores):
            doc = raw_documents[document_id]
            doc = remove_whitespace(doc)
            if len(doc) > 300:
                doc = doc[:300] + "..."
            rows.append([doc, f"{score:.2f}"])
        if show_negative:
            rows.append(["...", ""])
            lowest = np.argpartition(document_topic_matrix[:, topic_id], kth)[
                :kth
            ]
            lowest = lowest[
                np.argsort(document_topic_matrix[lowest, topic_id])
            ]
            lowest = lowest[::-1]
            scores = document_topic_matrix[lowest, topic_id]
            for document_id, score in zip(lowest, scores):
                doc = raw_documents[document_id]
                doc = remove_whitespace(doc)
                if len(doc) > 300:
                    doc = doc[:300] + "..."
                rows.append([doc, f"{score:.2f}"])
        return [columns, *rows]

    def print_representative_documents(
        self,
        topic_id,
        raw_documents=None,
        document_topic_matrix=None,
        top_k=5,
        show_negative: Optional[bool] = None,
    ):
        """Pretty prints the highest ranking documents in a topic.

        Parameters
        ----------
        topic_id: int
            ID of the topic to display.
        raw_documents: list of str
            List of documents to consider.
        document_topic_matrix: ndarray of shape (n_documents, n_topics), optional
            Document topic matrix to use. This is useful for transductive methods,
            as they cannot infer topics from text.
        top_k: int, default 5
            Top K documents to show.
        show_negative: bool, default False
            Indicates whether lowest ranking documents should also be shown.
        """
        columns, *rows = self._representative_docs(
            topic_id,
            raw_documents,
            document_topic_matrix,
            top_k,
            show_negative,
        )
        table = Table(show_lines=True)
        table.add_column(
            "Document", justify="left", style="magenta", max_width=100
        )
        table.add_column("Score", style="blue", justify="right")
        for row in rows:
            table.add_row(*row)
        console = Console()
        console.print(table)

    def export_representative_documents(
        self,
        topic_id,
        raw_documents=None,
        document_topic_matrix=None,
        top_k=5,
        show_negative: Optional[bool] = None,
        format: str = "csv",
    ):
        """Exports the highest ranking documents in a topic as a text table.

        Parameters
        ----------
        topic_id: int
            ID of the topic to display.
        raw_documents: list of str
            List of documents to consider.
        document_topic_matrix: ndarray of shape (n_topics, n_topics), optional
            Document topic matrix to use. This is useful for transductive methods,
            as they cannot infer topics from text.
        top_k: int, default 5
            Top K documents to show.
        show_negative: bool, default False
            Indicates whether lowest ranking documents should also be shown.
        format: 'csv', 'latex' or 'markdown'
            Specifies which format should be used.
            'csv', 'latex' and 'markdown' are supported.
        """
        table = self._representative_docs(
            topic_id,
            raw_documents,
            document_topic_matrix,
            top_k,
            show_negative,
        )
        return export_table(table, format=format)

    @property
    def topic_names(self) -> list[str]:
        """Names of the topics based on the highest scoring 4 terms."""
        topic_names = getattr(self, "topic_names_", None)
        if topic_names is not None:
            return list(topic_names)
        topic_desc = self.get_topics(top_k=4)
        names = []
        for topic_id, terms in topic_desc:
            concat_words = "_".join([word for word, importance in terms])
            names.append(f"{topic_id}_{concat_words}")
        return names

    def rename_topics(
        self, names: Union[list[str], dict[int, str], TopicNamer]
    ) -> None:
        """Rename topics in a model manually or automatically, using a namer.

        Examples:
        ```python
        model.rename_topics(["Automobiles", "Telephones"])
        # Or:
        model.rename_topics({-1: "Outliers", 2: "Christianity"})
        # Or:
        namer = OpenAITopicNamer()
        model.rename_topics(namer)
        ```

        Parameters
        ----------
        names: list[str] or dict[int,str]
            Should be a list of topic names, or a mapping of topic IDs to names.
        """
        if isinstance(names, TopicNamer):
            self._rename_automatic(names)
        elif isinstance(names, dict):
            topic_names = self.topic_names
            for topic_id, topic_name in names.items():
                try:
                    topic_id = list(self.classes_).index(topic_id)
                except AttributeError:
                    pass
                topic_names[topic_id] = topic_name
            self.topic_names_ = topic_names
        else:
            names = list(names)
            n_given = len(names)
            n_topics = self.components_.shape[0]
            if n_topics != n_given:
                raise ValueError(
                    f"Number of topics ({n_topics}) doesn't match the length of the given topic name list ({n_given})."
                )
            self.topic_names_ = names

    def _topic_distribution(
        self, text=None, topic_dist=None, top_k: int = 10
    ) -> list[list[str]]:
        if topic_dist is None:
            if text is None:
                raise ValueError(
                    "You should either pass a text or a distribution."
                )
            try:
                topic_dist = self.transform([text])
            except AttributeError:
                raise ValueError(
                    "Transductive methods cannot "
                    "infer topical content in documents.\n"
                    "Please pass a topic distribution."
                )
        topic_dist = np.squeeze(np.asarray(topic_dist))
        highest = np.argsort(-topic_dist)[:top_k]
        columns = []
        columns.append("Topic name")
        columns.append("Score")
        rows = []
        for ind in highest:
            score = topic_dist[ind]
            rows.append([self.topic_names[ind], f"{score:.2f}"])
        return [columns, *rows]

    def print_topic_distribution(
        self, text=None, topic_dist=None, top_k: int = 10
    ):
        """Pretty prints topic distribution in a document.

        Parameters
        ----------
        text: str, optional
            Text to infer topic distribution for.
        topic_dist: ndarray of shape (n_topics), optional
            Already inferred topic distribution for the text.
            This is useful for transductive methods,
            as they cannot infer topics from text.
        top_k: int, default 10
            Top K topics to show.
        """
        columns, *rows = self._topic_distribution(text, topic_dist, top_k)
        table = Table()
        table.add_column("Topic name", justify="left", style="magenta")
        table.add_column("Score", justify="right", style="blue")
        for row in rows:
            table.add_row(*row)
        console = Console()
        console.print(table)

    def export_topic_distribution(
        self, text=None, topic_dist=None, top_k: int = 10, format="csv"
    ) -> str:
        """Exports topic distribution as a text table.

        Parameters
        ----------
        text: str, optional
            Text to infer topic distribution for.
        topic_dist: ndarray of shape (n_topics), optional
            Already inferred topic distribution for the text.
            This is useful for transductive methods,
            as they cannot infer topics from text.
        top_k: int, default 10
            Top K topics to show.
        format: 'csv', 'latex' or 'markdown'
            Specifies which format should be used.
            'csv', 'latex' and 'markdown' are supported.
        """
        table = self._topic_distribution(text, topic_dist, top_k)
        return export_table(table, format=format)

    def topics_df(
        self,
        top_k: int = 10,
        show_scores: bool = False,
        show_negative: Optional[bool] = None,
    ):
        """Extracts topics into a pandas dataframe.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.
        show_scores: bool, default False
            Indicates whether to show importance scores for each word.
        show_negative: bool, default False
            Indicates whether the most negative terms should also be displayed.
        """
        try:
            import pandas as pd
        except ModuleNotFoundError:
            raise ModuleNotFoundError(
                "You need to pip install pandas to be able to use dataframes."
            )
        columns, *rows = self._topics_table(top_k, show_scores, show_negative)
        return pd.DataFrame(rows, columns=columns)

    def representative_documents_df(
        self,
        topic_id,
        raw_documents=None,
        document_topic_matrix=None,
        top_k=5,
        show_negative: Optional[bool] = None,
    ):
        """Collects highest ranking documents in a topic to a dataframe.

        Parameters
        ----------
        topic_id: int
            ID of the topic to display.
        raw_documents: list of str
            List of documents to consider.
        document_topic_matrix: ndarray of shape (n_documents, n_topics), optional
            Document topic matrix to use. This is useful for transductive methods,
            as they cannot infer topics from text.
        top_k: int, default 5
            Top K documents to show.
        show_negative: bool, default False
            Indicates whether lowest ranking documents should also be shown.
        """
        try:
            import pandas as pd
        except ModuleNotFoundError:
            raise ModuleNotFoundError(
                "You need to pip install pandas to be able to use dataframes."
            )
        if show_negative is None:
            show_negative = self.has_negative_side
        raw_documents = raw_documents or getattr(self, "corpus", None)
        if raw_documents is None:
            raise ValueError(
                "No corpus was passed, can't search for representative documents."
            )
        document_topic_matrix = document_topic_matrix or getattr(
            self, "document_topic_matrix", None
        )
        if document_topic_matrix is None:
            try:
                document_topic_matrix = self.transform(raw_documents)
            except AttributeError:
                raise ValueError(
                    "Transductive methods cannot "
                    "infer topical content in documents.\n"
                    "Please pass a document_topic_matrix."
                )
        try:
            topic_id = list(self.classes_).index(topic_id)
        except AttributeError:
            pass
        kth = min(top_k, document_topic_matrix.shape[0] - 1)
        highest = np.argpartition(-document_topic_matrix[:, topic_id], kth)[
            :kth
        ]
        highest = highest[
            np.argsort(-document_topic_matrix[highest, topic_id])
        ]
        scores = document_topic_matrix[highest, topic_id]
        columns = [["Document", "Score"]]
        rows = []
        for document_id, score in zip(highest, scores):
            doc = raw_documents[document_id]
            rows.append([doc, score])
        if show_negative:
            lowest = np.argpartition(document_topic_matrix[:, topic_id], kth)[
                :kth
            ]
            lowest = lowest[
                np.argsort(document_topic_matrix[lowest, topic_id])
            ]
            lowest = lowest[::-1]
            scores = document_topic_matrix[lowest, topic_id]
            for document_id, score in zip(lowest, scores):
                doc = raw_documents[document_id]
                rows.append([doc, score])
        return pd.DataFrame(rows, columns=columns)

    def topic_distribution_df(
        self, text=None, topic_dist=None, top_k: int = 10
    ):
        """Extracts topic distribution into a dataframe.

        Parameters
        ----------
        text: str, optional
            Text to infer topic distribution for.
        topic_dist: ndarray of shape (n_topics), optional
            Already inferred topic distribution for the text.
            This is useful for transductive methods,
            as they cannot infer topics from text.
        top_k: int, default 10
            Top K topics to show.
        """
        try:
            import pandas as pd
        except ModuleNotFoundError:
            raise ModuleNotFoundError(
                "You need to pip install pandas to be able to use dataframes."
            )
        if topic_dist is None:
            if text is None:
                raise ValueError(
                    "You should either pass a text or a distribution."
                )
            try:
                topic_dist = self.transform([text])
            except AttributeError:
                raise ValueError(
                    "Transductive methods cannot "
                    "infer topical content in documents.\n"
                    "Please pass a topic distribution."
                )
        topic_dist = np.squeeze(np.asarray(topic_dist))
        highest = np.argsort(-topic_dist)[:top_k]
        columns = []
        columns.append("Topic name")
        columns.append("Score")
        rows = []
        for ind in highest:
            score = topic_dist[ind]
            rows.append([self.topic_names[ind], score])
        return pd.DataFrame(rows, columns=columns)

    def get_time_slices(self) -> list[tuple[datetime, datetime]]:
        """Returns starting and ending datetime of
        each timeslice in the model."""
        bins = getattr(self, "time_bin_edges", None)
        if bins is None:
            raise AttributeError(
                "Topic model is not dynamic, time_bin_edges attribute is missing."
            )
        res = []
        for i_bin, slice_end in enumerate(bins[1:]):
            res.append((bins[i_bin], slice_end))
        return res

    def get_topics_over_time(
        self, top_k: int = 10
    ) -> list[list[tuple[Any, list[tuple[str, float]]]]]:
        """Returns high-level topic representations in form of the top K words
        in each topic.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.

        Returns
        -------
        list[list[tuple]]
            List of topics over each time slice in the dynamic model.
            Each time slice is a list of topics.
            Each topic is a tuple of topic ID and the top k words.
            Top k words are a list of (word, word_importance) pairs.
        """
        temporal_components = getattr(self, "temporal_components_", None)
        if temporal_components is None:
            raise AttributeError(
                "Topic model is not dynamic, temporal_components_ attribute is missing."
            )
        n_topics = temporal_components.shape[1]
        try:
            classes = self.classes_
        except AttributeError:
            classes = list(range(n_topics))
        res = []
        for components in temporal_components:
            highest = np.argpartition(-components, top_k)[:, :top_k]
            vocab = self.get_vocab()
            top = []
            score = []
            for component, high in zip(components, highest):
                importance = component[high]
                high = high[np.argsort(-importance)]
                score.append(component[high])
                top.append(vocab[high])
            topics = []
            for topic, words, scores in zip(classes, top, score):
                topic_data = (topic, list(zip(words, scores)))
                topics.append(topic_data)
            res.append(topics)
        return res

    def _topics_over_time(
        self,
        top_k: int = 5,
        show_scores: bool = False,
        date_format: str = "%Y %m %d",
    ) -> list[list[str]]:
        temporal_components = getattr(self, "temporal_components_", None)
        if temporal_components is None:
            raise AttributeError(
                "Topic model is not dynamic, temporal_components_ attribute is missing."
            )
        temporal_importance = getattr(self, "temporal_importance_", None)
        if temporal_components is None:
            raise AttributeError(
                "Topic model is not dynamic, temporal_importance_ attribute is missing."
            )
        slices = self.get_time_slices()
        slice_names = []
        for start_dt, end_dt in slices:
            start_str = start_dt.strftime(date_format)
            end_str = end_dt.strftime(date_format)
            slice_names.append(f"{start_str} - {end_str}")
        n_topics = temporal_components.shape[1]
        try:
            topic_names = self.topic_names
        except AttributeError:
            topic_names = [f"Topic {i}" for i in range(n_topics)]
        columns = []
        rows = []
        columns.append("Time Slice")
        for topic in topic_names:
            columns.append(topic)
        for slice_name, components, weights in zip(
            slice_names, temporal_components, temporal_importance
        ):
            fields = []
            fields.append(slice_name)
            vocab = self.get_vocab()
            for component, weight in zip(components, weights):
                if np.all(component == 0) or np.all(np.isnan(component)):
                    fields.append("Topic not present.")
                    continue
                if weight < 0:
                    component = -component
                top = np.argpartition(-component, top_k)[:top_k]
                importance = component[top]
                top = top[np.argsort(-importance)]
                top = top[importance != 0]
                scores = component[top]
                words = vocab[top]
                if show_scores:
                    concat_words = ", ".join(
                        [
                            f"{word}({importance:.2f})"
                            for word, importance in zip(words, scores)
                        ]
                    )
                else:
                    concat_words = ", ".join([word for word in words])
                fields.append(concat_words)
            rows.append(fields)
        return [columns, *rows]

    def print_topics_over_time(
        self,
        top_k: int = 5,
        show_scores: bool = False,
        date_format: str = "%Y %m %d",
    ):
        """Pretty prints topics in the model in a table.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.
        show_scores: bool, default False
            Indicates whether to show importance scores for each word.
        """
        columns, *rows = self._topics_over_time(
            top_k, show_scores, date_format
        )
        table = Table(show_lines=True)
        for column in columns:
            table.add_column(column)
        for row in rows:
            table.add_row(*row)
        console = Console()
        console.print(table)

    def export_topics_over_time(
        self,
        top_k: int = 5,
        show_scores: bool = False,
        date_format: str = "%Y %m %d",
        format="csv",
    ) -> str:
        """Pretty prints topics in the model in a table.

        Parameters
        ----------
        top_k: int, default 10
            Number of top words to return for each topic.
        show_scores: bool, default False
            Indicates whether to show importance scores for each word.
        format: 'csv', 'latex' or 'markdown'
            Specifies which format should be used.
            'csv', 'latex' and 'markdown' are supported.
        """
        table = self._topics_over_time(top_k, show_scores, date_format)
        return export_table(table, format=format)

    def topics_over_time_df(
        self,
        top_k: int = 5,
        show_scores: bool = False,
        format="csv",
    ):
        try:
            import pandas as pd
        except ModuleNotFoundError:
            raise ModuleNotFoundError(
                "You need to pip install pandas to be able to use dataframes."
            )

        def parse_time_slice(slice: str) -> tuple[datetime, datetime]:
            date_format = "%Y %m %d"
            start_date, end_date = slice.split(" - ")
            return datetime.strptime(
                start_date, date_format
            ), datetime.strptime(end_date, date_format)

        columns, *rows = self._topics_over_time(top_k, show_scores)
        df = pd.DataFrame(rows, columns=columns)
        df["Time Slice"] = df["Time Slice"].map(parse_time_slice)
        return df

    def plot_topics_over_time(
        self,
        top_k: int = 6,
        color_discrete_sequence: Optional[Iterable[str]] = None,
        color_discrete_map: Optional[dict[str, str]] = None,
    ):
        """Displays topics over time in the fitted dynamic model on a dynamic HTML figure.

        > You will need to `pip install plotly` to use this method.

        Parameters
        ----------
        top_k: int, default 6
            Number of top words per topic to display on the figure.
        color_discrete_sequence: Iterable[str], default None
            Color palette to use in the plot.
            Example:

            ```python
            import plotly.express as px
            model.plot_topics_over_time(color_discrete_sequence=px.colors.qualitative.Light24)
            ```

        color_discrete_map: dict[str, str], default None
            Topic names mapped to the colors that should
            be associated with them.

        Returns
        -------
        go.Figure
            Plotly graph objects Figure, that can be displayed or exported as
            HTML or static image.
        """
        try:
            import plotly.express as px
            import plotly.graph_objects as go
        except (ImportError, ModuleNotFoundError) as e:
            raise ModuleNotFoundError(
                "Please install plotly if you intend to use plots in Turftopic."
            ) from e
        temporal_components = getattr(self, "temporal_components_", None)
        if temporal_components is None:
            raise AttributeError(
                "Topic model is not dynamic, temporal_components_ attribute is missing."
            )
        temporal_importance = getattr(self, "temporal_importance_", None)
        if temporal_components is None:
            raise AttributeError(
                "Topic model is not dynamic, temporal_importance_ attribute is missing."
            )
        if color_discrete_sequence is not None:
            topic_colors = itertools.cycle(color_discrete_sequence)
        elif color_discrete_map is not None:
            topic_colors = [
                color_discrete_map[topic_name]
                for topic_name in self.topic_names
            ]
        else:
            topic_colors = px.colors.qualitative.Dark24
        fig = go.Figure()
        vocab = self.get_vocab()
        n_topics = temporal_components.shape[1]
        try:
            topic_names = self.topic_names
        except AttributeError:
            topic_names = [f"Topic {i}" for i in range(n_topics)]
        for trace_color, (i_topic, topic_imp_t) in zip(
            itertools.cycle(topic_colors), enumerate(temporal_importance.T)
        ):
            component_over_time = temporal_components[:, i_topic, :]
            name_over_time = []
            for component, importance in zip(component_over_time, topic_imp_t):
                if importance < 0:
                    component = -component
                top = np.argpartition(-component, top_k)[:top_k]
                values = component[top]
                if np.all(values == 0) or np.all(np.isnan(values)):
                    name_over_time.append("<not present>")
                    continue
                top = top[np.argsort(-values)]
                name_over_time.append(", ".join(vocab[top]))
            times = self.time_bin_edges[:-1]
            fig.add_trace(
                go.Scatter(
                    x=times,
                    y=topic_imp_t,
                    mode="markers+lines",
                    text=name_over_time,
                    name=topic_names[i_topic],
                    hovertemplate="<b>%{text}</b>",
                    marker=dict(
                        line=dict(width=2, color="black"),
                        size=14,
                        color=trace_color,
                    ),
                    line=dict(width=3),
                )
            )
        fig.update_layout(
            template="plotly_white",
            hoverlabel=dict(font_size=16, bgcolor="white"),
            hovermode="x",
            font=dict(family="Roboto Mono"),
        )
        fig.add_hline(y=0, line_dash="dash", opacity=0.5)
        fig.update_xaxes(title="Time Slice Start")
        fig.update_yaxes(title="Topic Importance")
        return fig

    @staticmethod
    def _image_grid(
        images: list[Image.Image],
        final_size=(1200, 1200),
        grid_size: tuple[int, int] = (4, 4),
    ):
        grid_img = Image.new("RGB", final_size, (255, 255, 255))
        cell_width = final_size[0] // grid_size[0]
        cell_height = final_size[1] // grid_size[1]
        n_rows, n_cols = grid_size
        for idx, img in enumerate(images[: n_rows * n_cols]):
            img = img.resize(
                (cell_width, cell_height), resample=Image.Resampling.LANCZOS
            )
            x_offset = (idx % grid_size[0]) * cell_width
            y_offset = (idx // grid_size[1]) * cell_height
            grid_img.paste(img, (x_offset, y_offset))
        return grid_img

    def plot_topics_with_images(self, n_cols: int = 3, grid_size: int = 4):
        """Plots the most important images for each topic, along with keywords.

        Note that you will need to `pip install plotly` to use plots in Turftopic.

        Parameters
        ----------
        n_cols: int, default 3
            Number of columns you want to have in the grid of topics.
        grid_size: int, default 4
            The square root of the number of images you want to display for a given topic.
            For instance if grid_size==4, all topics will have 16 images displayed,
            since the joint image will have 4 columns and 4 rows.

        Returns
        -------
        go.Figure
            Plotly figure containing top images and keywords for topics.
        """
        if not hasattr(self, "top_images"):
            raise ValueError(
                "Model either has not been fit or was fit without images. top_images property missing."
            )
        try:
            import plotly.graph_objects as go
        except (ImportError, ModuleNotFoundError) as e:
            raise ModuleNotFoundError(
                "Please install plotly if you intend to use plots in Turftopic."
            ) from e
        negative_images = getattr(self, "negative_images", None)
        if negative_images is not None:
            # If the model has negative images, it should display them side by side with the positive ones.
            n_components = self.components_.shape[0]
            fig = go.Figure()
            width, height = 1200, 1200
            scale_factor = 0.25
            w, h = width * scale_factor, height * scale_factor
            padding = 10
            figure_height = (h + padding) * n_components
            figure_width = (w + padding) * 2
            fig = fig.add_trace(
                go.Scatter(
                    x=[0, figure_width],
                    y=[0, figure_height],
                    mode="markers",
                    marker_opacity=0,
                )
            )
            vocab = self.get_vocab()
            for i, component in enumerate(self.components_):
                positive = vocab[np.argsort(-component)[:7]]
                negative = vocab[np.argsort(component)[:7]]
                pos_image = self._image_grid(
                    self.top_images[i],
                    (width, height),
                    grid_size=(grid_size, grid_size),
                )
                neg_image = self._image_grid(
                    self.negative_images[i],
                    (width, height),
                    grid_size=(grid_size, grid_size),
                )
                x0 = 0
                y0 = (h + padding) * (n_components - i)
                fig = fig.add_layout_image(
                    dict(
                        x=x0,
                        sizex=w,
                        y=y0,
                        sizey=h,
                        xref="x",
                        yref="y",
                        opacity=1.0,
                        layer="below",
                        sizing="stretch",
                        source=pos_image,
                    ),
                )
                fig.add_annotation(
                    x=(w / 2),
                    y=(h + padding) * (n_components - i) - (h / 2),
                    text="<b> " + "<br> ".join(positive),
                    font=dict(
                        size=16,
                        family="Roboto Mono",
                        color="white",
                    ),
                    bgcolor="rgba(0,0,255, 0.5)",
                )
                x0 = (w + padding) * 1
                fig = fig.add_layout_image(
                    dict(
                        x=x0,
                        sizex=w,
                        y=y0,
                        sizey=h,
                        xref="x",
                        yref="y",
                        opacity=1.0,
                        layer="below",
                        sizing="stretch",
                        source=neg_image,
                    ),
                )
                fig.add_annotation(
                    x=(w + padding) + (w / 2),
                    y=(h + padding) * (n_components - i) - (h / 2),
                    text="<b> " + "<br> ".join(negative),
                    font=dict(
                        size=16,
                        family="Times New Roman",
                        color="white",
                    ),
                    bgcolor="rgba(255,0,0, 0.5)",
                )
            fig = fig.update_xaxes(visible=False, range=[0, figure_width])
            fig = fig.update_yaxes(
                visible=False,
                range=[0, figure_height],
                # the scaleanchor attribute ensures that the aspect ratio stays constant
                scaleanchor="x",
            )
            fig = fig.update_layout(
                width=figure_width,
                height=figure_height,
                margin={"l": 0, "r": 0, "t": 0, "b": 0},
            )
            return fig
        else:
            fig = go.Figure()
            width, height = 1200, 1200
            scale_factor = 0.25
            w, h = width * scale_factor, height * scale_factor
            padding = 10
            n_components = self.components_.shape[0]
            n_rows = n_components // n_cols + int(bool(n_components % n_cols))
            figure_height = (h + padding) * n_rows
            figure_width = (w + padding) * n_cols
            fig = fig.add_trace(
                go.Scatter(
                    x=[0, figure_width],
                    y=[0, figure_height],
                    mode="markers",
                    marker_opacity=0,
                )
            )
            vocab = self.get_vocab()
            for i, component in enumerate(self.components_):
                col = i % n_cols
                row = i // n_cols
                top_7 = vocab[np.argsort(-component)[:7]]
                images = self.top_images[i]
                image = self._image_grid(
                    images, (width, height), grid_size=(grid_size, grid_size)
                )
                x0 = (w + padding) * col
                y0 = (h + padding) * (n_rows - row)
                fig = fig.add_layout_image(
                    dict(
                        x=x0,
                        sizex=w,
                        y=y0,
                        sizey=h,
                        xref="x",
                        yref="y",
                        opacity=1.0,
                        layer="below",
                        sizing="stretch",
                        source=image,
                    ),
                )
                fig.add_annotation(
                    x=(w + padding) * col + (w / 2),
                    y=(h + padding) * (n_rows - row) - (h / 2),
                    text="<b> " + "<br> ".join(top_7),
                    font=dict(
                        size=16,
                        family="Times New Roman",
                        color="white",
                    ),
                    bgcolor="rgba(0,0,0, 0.5)",
                )
            fig = fig.update_xaxes(visible=False, range=[0, figure_width])
            fig = fig.update_yaxes(
                visible=False,
                range=[0, figure_height],
                # the scaleanchor attribute ensures that the aspect ratio stays constant
                scaleanchor="x",
            )
            fig = fig.update_layout(
                width=figure_width,
                height=figure_height,
                margin={"l": 0, "r": 0, "t": 0, "b": 0},
            )
            return fig

    def plot_multimodal_topics(
        self,
        top_k: int = 10,
        grid_size: int = 4,
        raw_documents=None,
        document_topic_matrix=None,
    ):
        """Plots all multimodal topics in a model along with top documents individually,
        and provides a slider to switch between them.

        Parameters
        ----------
        top_k: int = 10
            Number of top words and documents to display.
        grid_size: int, default 4
            The square root of the number of images you want to display for a given topic.
            For instance if grid_size==4, all topics will have 16 images displayed,
            since the joint image will have 4 columns and 4 rows.
        raw_documents: list of str, optional
            List of documents to consider.
        document_topic_matrix: ndarray of shape (n_documents, n_topics), optional
            Document topic matrix to use. This is useful for transductive methods,
            as they cannot infer topics from text.

        """
        if not hasattr(self, "top_images"):
            raise ValueError(
                "Model either has not been fit or was fit without images. top_images property missing."
            )
        try:
            import plotly.express as px
            import plotly.graph_objects as go
            from plotly.subplots import make_subplots
        except (ImportError, ModuleNotFoundError) as e:
            raise ModuleNotFoundError(
                "Please install plotly if you intend to use plots in Turftopic."
            ) from e
        negative_images = getattr(self, "negative_images", None)
        negative_topics = (
            self.get_top_words(top_k=top_k, positive=False)
            if negative_images is not None
            else None
        )
        specs = [{"type": "image"}, {"type": "table"}]
        if negative_images is not None:
            specs.append({"type": "image"})
        fig = make_subplots(
            rows=1,
            cols=2 if negative_images is None else 3,
            specs=[specs],
            shared_yaxes=True,
            shared_xaxes=True,
        )
        width, height = 1200, 1200
        topics = self.get_top_words(top_k=top_k)
        n_topics = len(topics)
        annotations = []
        for i, topic in enumerate(topics):
            images = self.top_images[i]
            image = TopicContainer._image_grid(
                images, (width, height), grid_size=(grid_size, grid_size)
            )
            trace = px.imshow(image).data[0]
            trace.visible = False
            fig.add_trace(trace, col=1, row=1)
            annt = dict(
                x=width / 2,
                y=height / 2,
                text="<b> " + "<br> ".join(topic),
                font=dict(
                    size=16,
                    family="Roboto Mono",
                    color="white",
                ),
                bgcolor="rgba(0,0,255, 0.5)",
                xref="x",
                yref="y",
            )
            annotations.append(annt)
        if negative_topics is not None:
            for i, negative_topic in enumerate(negative_topics):
                images = negative_images[i]
                image = TopicContainer._image_grid(
                    images, (width, height), grid_size=(grid_size, grid_size)
                )
                trace = px.imshow(image).data[0]
                trace.visible = False
                fig.add_trace(trace, col=3, row=1)
                annotations.append(
                    dict(
                        x=width / 2,
                        y=height / 2,
                        text="<b> " + "<br> ".join(negative_topic),
                        font=dict(
                            size=16,
                            family="Roboto Mono",
                            color="white",
                        ),
                        bgcolor="rgba(255,0,0, 0.5)",
                        xref="x2",
                        yref="y2",
                    )
                )
        fig = fig.add_annotation(**annotations[0])
        if negative_images is not None:
            fig.add_annotation(**annotations[n_topics])
        classes = getattr(self, "classes_", np.arange(n_topics))
        for i, topic_id in enumerate(classes):
            header, *cells = self._representative_docs(
                topic_id,
                raw_documents=raw_documents,
                document_topic_matrix=document_topic_matrix,
                top_k=top_k,
                show_negative=negative_images is not None,
            )
            # Transposing cells
            cells = [list(column) for column in zip(*cells)]
            fig.add_trace(
                go.Table(
                    columnorder=[1, 2],
                    columnwidth=[400, 80],
                    header=dict(
                        values=header,
                        fill_color="white",
                        line=dict(color="black", width=4),
                        font=dict(
                            family="Roboto Mono", color="black", size=20
                        ),
                    ),
                    cells=dict(
                        values=cells,
                        fill_color="white",
                        align="left",
                        line=dict(color="black", width=2),
                        font=dict(
                            family="Roboto Mono", color="black", size=16
                        ),
                        height=40,
                    ),
                    visible=False,
                ),
                col=2,
                row=1,
            )
        fig.data[0].visible = True
        fig.data[n_topics].visible = True
        if negative_images is not None:
            fig.data[n_topics * 2].visible = True
        fig = fig.update_layout(
            margin={"l": 0, "r": 0, "t": 40, "b": 20},
            template="plotly_white",
            font=dict(family="Roboto Mono"),
        )
        fig = fig.update_xaxes(visible=False)
        fig = fig.update_yaxes(visible=False)
        steps = []
        n_traces = n_topics * 2 if negative_images is None else n_topics * 3
        for i, name in enumerate(self.topic_names):
            _annt = [annotations[i]]
            if negative_topics is not None:
                _annt.append(annotations[n_topics + i])
            step = dict(
                method="update",
                label=name,
                args=[
                    {"visible": [False] * n_traces},
                    {
                        "title": "Topic: " + name,
                        "annotations": _annt,
                    },
                ],
            )
            step["args"][0]["visible"][i] = True
            step["args"][0]["visible"][n_topics + i] = True
            if negative_images is not None:
                step["args"][0]["visible"][n_topics * 2 + i] = True
            steps.append(step)
        sliders = [
            dict(
                active=0,
                currentvalue={"prefix": "Topic: "},
                pad={"t": 50, "b": 20, "r": 40, "l": 40},
                steps=steps,
            )
        ]
        fig = fig.update_layout(sliders=sliders)
        return fig

topic_names: list[str] property

Names of the topics based on the highest scoring 4 terms.

export_representative_documents(topic_id, raw_documents=None, document_topic_matrix=None, top_k=5, show_negative=None, format='csv')

Exports the highest ranking documents in a topic as a text table.

Parameters:

Name Type Description Default
topic_id

ID of the topic to display.

required
raw_documents

List of documents to consider.

None
document_topic_matrix

Document topic matrix to use. This is useful for transductive methods, as they cannot infer topics from text.

None
top_k

Top K documents to show.

5
show_negative Optional[bool]

Indicates whether lowest ranking documents should also be shown.

None
format str

Specifies which format should be used. 'csv', 'latex' and 'markdown' are supported.

'csv'
Source code in turftopic/container.py
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
def export_representative_documents(
    self,
    topic_id,
    raw_documents=None,
    document_topic_matrix=None,
    top_k=5,
    show_negative: Optional[bool] = None,
    format: str = "csv",
):
    """Exports the highest ranking documents in a topic as a text table.

    Parameters
    ----------
    topic_id: int
        ID of the topic to display.
    raw_documents: list of str
        List of documents to consider.
    document_topic_matrix: ndarray of shape (n_topics, n_topics), optional
        Document topic matrix to use. This is useful for transductive methods,
        as they cannot infer topics from text.
    top_k: int, default 5
        Top K documents to show.
    show_negative: bool, default False
        Indicates whether lowest ranking documents should also be shown.
    format: 'csv', 'latex' or 'markdown'
        Specifies which format should be used.
        'csv', 'latex' and 'markdown' are supported.
    """
    table = self._representative_docs(
        topic_id,
        raw_documents,
        document_topic_matrix,
        top_k,
        show_negative,
    )
    return export_table(table, format=format)

export_topic_distribution(text=None, topic_dist=None, top_k=10, format='csv')

Exports topic distribution as a text table.

Parameters:

Name Type Description Default
text

Text to infer topic distribution for.

None
topic_dist

Already inferred topic distribution for the text. This is useful for transductive methods, as they cannot infer topics from text.

None
top_k int

Top K topics to show.

10
format

Specifies which format should be used. 'csv', 'latex' and 'markdown' are supported.

'csv'
Source code in turftopic/container.py
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
def export_topic_distribution(
    self, text=None, topic_dist=None, top_k: int = 10, format="csv"
) -> str:
    """Exports topic distribution as a text table.

    Parameters
    ----------
    text: str, optional
        Text to infer topic distribution for.
    topic_dist: ndarray of shape (n_topics), optional
        Already inferred topic distribution for the text.
        This is useful for transductive methods,
        as they cannot infer topics from text.
    top_k: int, default 10
        Top K topics to show.
    format: 'csv', 'latex' or 'markdown'
        Specifies which format should be used.
        'csv', 'latex' and 'markdown' are supported.
    """
    table = self._topic_distribution(text, topic_dist, top_k)
    return export_table(table, format=format)

export_topics(top_k=10, show_scores=False, show_negative=None, format='csv')

Exports top K words from topics in a table in a given format. Returns table as a pure string.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

10
show_scores bool

Indicates whether to show importance scores for each word.

False
show_negative Optional[bool]

Indicates whether the most negative terms should also be displayed.

None
format str

Specifies which format should be used. 'csv', 'latex' and 'markdown' are supported.

'csv'
Source code in turftopic/container.py
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
def export_topics(
    self,
    top_k: int = 10,
    show_scores: bool = False,
    show_negative: Optional[bool] = None,
    format: str = "csv",
) -> str:
    """Exports top K words from topics in a table in a given format.
    Returns table as a pure string.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.
    show_scores: bool, default False
        Indicates whether to show importance scores for each word.
    show_negative: bool, default False
        Indicates whether the most negative terms should also be displayed.
    format: 'csv', 'latex' or 'markdown'
        Specifies which format should be used.
        'csv', 'latex' and 'markdown' are supported.
    """
    table = self._topics_table(
        top_k, show_scores, show_negative=show_negative
    )
    return export_table(table, format=format)

export_topics_over_time(top_k=5, show_scores=False, date_format='%Y %m %d', format='csv')

Pretty prints topics in the model in a table.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

5
show_scores bool

Indicates whether to show importance scores for each word.

False
format

Specifies which format should be used. 'csv', 'latex' and 'markdown' are supported.

'csv'
Source code in turftopic/container.py
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
def export_topics_over_time(
    self,
    top_k: int = 5,
    show_scores: bool = False,
    date_format: str = "%Y %m %d",
    format="csv",
) -> str:
    """Pretty prints topics in the model in a table.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.
    show_scores: bool, default False
        Indicates whether to show importance scores for each word.
    format: 'csv', 'latex' or 'markdown'
        Specifies which format should be used.
        'csv', 'latex' and 'markdown' are supported.
    """
    table = self._topics_over_time(top_k, show_scores, date_format)
    return export_table(table, format=format)

get_time_slices()

Returns starting and ending datetime of each timeslice in the model.

Source code in turftopic/container.py
722
723
724
725
726
727
728
729
730
731
732
733
def get_time_slices(self) -> list[tuple[datetime, datetime]]:
    """Returns starting and ending datetime of
    each timeslice in the model."""
    bins = getattr(self, "time_bin_edges", None)
    if bins is None:
        raise AttributeError(
            "Topic model is not dynamic, time_bin_edges attribute is missing."
        )
    res = []
    for i_bin, slice_end in enumerate(bins[1:]):
        res.append((bins[i_bin], slice_end))
    return res

get_top_documents(raw_documents=None, document_topic_matrix=None, top_k=10, positive=True)

Returns list of top documents for each topic.

Parameters:

Name Type Description Default
top_k int

Number of documents to return per topic.

10
positive bool

Indicates whether the highest or lowest scoring documents should be returned.

True
Source code in turftopic/container.py
 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
def get_top_documents(
    self,
    raw_documents=None,
    document_topic_matrix=None,
    top_k: int = 10,
    positive: bool = True,
) -> list[list[str]]:
    """Returns list of top documents for each topic.

    Parameters
    ----------
    top_k: int, default 10
        Number of documents to return per topic.
    positive: bool, default True
        Indicates whether the highest
        or lowest scoring documents should be returned.
    """
    docs = []
    raw_documents = raw_documents or getattr(self, "corpus", None)
    if raw_documents is None:
        raise ValueError(
            "No corpus was passed, can't search for representative documents."
        )
    document_topic_matrix = document_topic_matrix or getattr(
        self, "document_topic_matrix", None
    )
    if document_topic_matrix is None:
        try:
            document_topic_matrix = self.transform(raw_documents)
        except AttributeError:
            raise ValueError(
                "Transductive methods cannot "
                "infer topical content in documents.\n"
                "Please pass a document_topic_matrix."
            )
    for topic_doc_vec in document_topic_matrix.T:
        if positive:
            topic_doc_vec = -topic_doc_vec
        highest = np.argsort(topic_doc_vec)[:top_k]
        docs.append([raw_documents[i_doc] for i_doc in highest])
    return docs

get_top_images(top_k=True, positive=True)

Returns list of top images for each topic.

Parameters:

Name Type Description Default
top_k int

Number of images to return.

True
positive bool

Indicates whether the highest or lowest scoring images should be returned.

True
Source code in turftopic/container.py
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
def get_top_images(self, top_k: int = True, positive: bool = True):
    """Returns list of top images for each topic.

    Parameters
    ----------
    top_k: int, default 10
        Number of images to return.
    positive: bool, default True
        Indicates whether the highest
        or lowest scoring images should be returned.
    """
    if not hasattr(self, "top_images"):
        raise ValueError(
            "Model either has not been fit or was fit without images. top_images property missing."
        )
    if (not positive) and not hasattr(self, "negative_images"):
        raise ValueError(
            "Model either has not been fit or was fit without images. top_images property missing."
        )
    top_images = self.top_images if positive else self.negative_images
    ims = []
    for topic_images in top_images:
        if len(topic_images) < top_k:
            warnings.warn(
                "Number of images stored in the topic model is smaller than the specified top_k, returning all that the model has."
            )
        ims.append(topic_images[:top_k])
    return ims

get_top_words(top_k=10, positive=True)

Returns list of top words for each topic.

Parameters:

Name Type Description Default
top_k int

Number of words to return.

10
positive bool

Indicates whether the highest or lowest scoring terms should be returned.

True
Source code in turftopic/container.py
81
82
83
84
85
86
87
88
89
90
91
92
93
94
def get_top_words(
    self, top_k: int = 10, positive: bool = True
) -> list[list[str]]:
    """Returns list of top words for each topic.

    Parameters
    ----------
    top_k: int, default 10
        Number of words to return.
    positive: bool, default True
        Indicates whether the highest
        or lowest scoring terms should be returned.
    """
    return self._top_terms(top_k, positive)

get_topics(top_k=10)

Returns high-level topic representations in form of the top K words in each topic.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

10

Returns:

Type Description
list[tuple]

List of topics. Each topic is a tuple of topic ID and the top k words. Top k words are a list of (word, word_importance) pairs.

Source code in turftopic/container.py
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
def get_topics(
    self, top_k: int = 10
) -> List[Tuple[Any, List[Tuple[str, float]]]]:
    """Returns high-level topic representations in form of the top K words
    in each topic.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.

    Returns
    -------
    list[tuple]
        List of topics. Each topic is a tuple of
        topic ID and the top k words.
        Top k words are a list of (word, word_importance) pairs.
    """
    n_topics = self.components_.shape[0]
    try:
        classes = self.classes_
    except AttributeError:
        classes = list(range(n_topics))
    highest = np.argpartition(-self.components_, top_k)[:, :top_k]
    vocab = self.get_vocab()
    top = []
    score = []
    for component, high in zip(self.components_, highest):
        importance = component[high]
        high = high[np.argsort(-importance)]
        score.append(component[high])
        top.append(vocab[high])
    topics = []
    for topic, words, scores in zip(classes, top, score):
        topic_data = (topic, list(zip(words, scores)))
        topics.append(topic_data)
    return topics

get_topics_over_time(top_k=10)

Returns high-level topic representations in form of the top K words in each topic.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

10

Returns:

Type Description
list[list[tuple]]

List of topics over each time slice in the dynamic model. Each time slice is a list of topics. Each topic is a tuple of topic ID and the top k words. Top k words are a list of (word, word_importance) pairs.

Source code in turftopic/container.py
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
def get_topics_over_time(
    self, top_k: int = 10
) -> list[list[tuple[Any, list[tuple[str, float]]]]]:
    """Returns high-level topic representations in form of the top K words
    in each topic.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.

    Returns
    -------
    list[list[tuple]]
        List of topics over each time slice in the dynamic model.
        Each time slice is a list of topics.
        Each topic is a tuple of topic ID and the top k words.
        Top k words are a list of (word, word_importance) pairs.
    """
    temporal_components = getattr(self, "temporal_components_", None)
    if temporal_components is None:
        raise AttributeError(
            "Topic model is not dynamic, temporal_components_ attribute is missing."
        )
    n_topics = temporal_components.shape[1]
    try:
        classes = self.classes_
    except AttributeError:
        classes = list(range(n_topics))
    res = []
    for components in temporal_components:
        highest = np.argpartition(-components, top_k)[:, :top_k]
        vocab = self.get_vocab()
        top = []
        score = []
        for component, high in zip(components, highest):
            importance = component[high]
            high = high[np.argsort(-importance)]
            score.append(component[high])
            top.append(vocab[high])
        topics = []
        for topic, words, scores in zip(classes, top, score):
            topic_data = (topic, list(zip(words, scores)))
            topics.append(topic_data)
        res.append(topics)
    return res

plot_multimodal_topics(top_k=10, grid_size=4, raw_documents=None, document_topic_matrix=None)

Plots all multimodal topics in a model along with top documents individually, and provides a slider to switch between them.

Parameters:

Name Type Description Default
top_k int

Number of top words and documents to display.

10
grid_size int

The square root of the number of images you want to display for a given topic. For instance if grid_size==4, all topics will have 16 images displayed, since the joint image will have 4 columns and 4 rows.

4
raw_documents

List of documents to consider.

None
document_topic_matrix

Document topic matrix to use. This is useful for transductive methods, as they cannot infer topics from text.

None
Source code in turftopic/container.py
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
def plot_multimodal_topics(
    self,
    top_k: int = 10,
    grid_size: int = 4,
    raw_documents=None,
    document_topic_matrix=None,
):
    """Plots all multimodal topics in a model along with top documents individually,
    and provides a slider to switch between them.

    Parameters
    ----------
    top_k: int = 10
        Number of top words and documents to display.
    grid_size: int, default 4
        The square root of the number of images you want to display for a given topic.
        For instance if grid_size==4, all topics will have 16 images displayed,
        since the joint image will have 4 columns and 4 rows.
    raw_documents: list of str, optional
        List of documents to consider.
    document_topic_matrix: ndarray of shape (n_documents, n_topics), optional
        Document topic matrix to use. This is useful for transductive methods,
        as they cannot infer topics from text.

    """
    if not hasattr(self, "top_images"):
        raise ValueError(
            "Model either has not been fit or was fit without images. top_images property missing."
        )
    try:
        import plotly.express as px
        import plotly.graph_objects as go
        from plotly.subplots import make_subplots
    except (ImportError, ModuleNotFoundError) as e:
        raise ModuleNotFoundError(
            "Please install plotly if you intend to use plots in Turftopic."
        ) from e
    negative_images = getattr(self, "negative_images", None)
    negative_topics = (
        self.get_top_words(top_k=top_k, positive=False)
        if negative_images is not None
        else None
    )
    specs = [{"type": "image"}, {"type": "table"}]
    if negative_images is not None:
        specs.append({"type": "image"})
    fig = make_subplots(
        rows=1,
        cols=2 if negative_images is None else 3,
        specs=[specs],
        shared_yaxes=True,
        shared_xaxes=True,
    )
    width, height = 1200, 1200
    topics = self.get_top_words(top_k=top_k)
    n_topics = len(topics)
    annotations = []
    for i, topic in enumerate(topics):
        images = self.top_images[i]
        image = TopicContainer._image_grid(
            images, (width, height), grid_size=(grid_size, grid_size)
        )
        trace = px.imshow(image).data[0]
        trace.visible = False
        fig.add_trace(trace, col=1, row=1)
        annt = dict(
            x=width / 2,
            y=height / 2,
            text="<b> " + "<br> ".join(topic),
            font=dict(
                size=16,
                family="Roboto Mono",
                color="white",
            ),
            bgcolor="rgba(0,0,255, 0.5)",
            xref="x",
            yref="y",
        )
        annotations.append(annt)
    if negative_topics is not None:
        for i, negative_topic in enumerate(negative_topics):
            images = negative_images[i]
            image = TopicContainer._image_grid(
                images, (width, height), grid_size=(grid_size, grid_size)
            )
            trace = px.imshow(image).data[0]
            trace.visible = False
            fig.add_trace(trace, col=3, row=1)
            annotations.append(
                dict(
                    x=width / 2,
                    y=height / 2,
                    text="<b> " + "<br> ".join(negative_topic),
                    font=dict(
                        size=16,
                        family="Roboto Mono",
                        color="white",
                    ),
                    bgcolor="rgba(255,0,0, 0.5)",
                    xref="x2",
                    yref="y2",
                )
            )
    fig = fig.add_annotation(**annotations[0])
    if negative_images is not None:
        fig.add_annotation(**annotations[n_topics])
    classes = getattr(self, "classes_", np.arange(n_topics))
    for i, topic_id in enumerate(classes):
        header, *cells = self._representative_docs(
            topic_id,
            raw_documents=raw_documents,
            document_topic_matrix=document_topic_matrix,
            top_k=top_k,
            show_negative=negative_images is not None,
        )
        # Transposing cells
        cells = [list(column) for column in zip(*cells)]
        fig.add_trace(
            go.Table(
                columnorder=[1, 2],
                columnwidth=[400, 80],
                header=dict(
                    values=header,
                    fill_color="white",
                    line=dict(color="black", width=4),
                    font=dict(
                        family="Roboto Mono", color="black", size=20
                    ),
                ),
                cells=dict(
                    values=cells,
                    fill_color="white",
                    align="left",
                    line=dict(color="black", width=2),
                    font=dict(
                        family="Roboto Mono", color="black", size=16
                    ),
                    height=40,
                ),
                visible=False,
            ),
            col=2,
            row=1,
        )
    fig.data[0].visible = True
    fig.data[n_topics].visible = True
    if negative_images is not None:
        fig.data[n_topics * 2].visible = True
    fig = fig.update_layout(
        margin={"l": 0, "r": 0, "t": 40, "b": 20},
        template="plotly_white",
        font=dict(family="Roboto Mono"),
    )
    fig = fig.update_xaxes(visible=False)
    fig = fig.update_yaxes(visible=False)
    steps = []
    n_traces = n_topics * 2 if negative_images is None else n_topics * 3
    for i, name in enumerate(self.topic_names):
        _annt = [annotations[i]]
        if negative_topics is not None:
            _annt.append(annotations[n_topics + i])
        step = dict(
            method="update",
            label=name,
            args=[
                {"visible": [False] * n_traces},
                {
                    "title": "Topic: " + name,
                    "annotations": _annt,
                },
            ],
        )
        step["args"][0]["visible"][i] = True
        step["args"][0]["visible"][n_topics + i] = True
        if negative_images is not None:
            step["args"][0]["visible"][n_topics * 2 + i] = True
        steps.append(step)
    sliders = [
        dict(
            active=0,
            currentvalue={"prefix": "Topic: "},
            pad={"t": 50, "b": 20, "r": 40, "l": 40},
            steps=steps,
        )
    ]
    fig = fig.update_layout(sliders=sliders)
    return fig

plot_topics_over_time(top_k=6, color_discrete_sequence=None, color_discrete_map=None)

Displays topics over time in the fitted dynamic model on a dynamic HTML figure.

You will need to pip install plotly to use this method.

Parameters:

Name Type Description Default
top_k int

Number of top words per topic to display on the figure.

6
color_discrete_sequence Optional[Iterable[str]]

Color palette to use in the plot. Example:

import plotly.express as px
model.plot_topics_over_time(color_discrete_sequence=px.colors.qualitative.Light24)
None
color_discrete_map Optional[dict[str, str]]

Topic names mapped to the colors that should be associated with them.

None

Returns:

Type Description
Figure

Plotly graph objects Figure, that can be displayed or exported as HTML or static image.

Source code in turftopic/container.py
 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
def plot_topics_over_time(
    self,
    top_k: int = 6,
    color_discrete_sequence: Optional[Iterable[str]] = None,
    color_discrete_map: Optional[dict[str, str]] = None,
):
    """Displays topics over time in the fitted dynamic model on a dynamic HTML figure.

    > You will need to `pip install plotly` to use this method.

    Parameters
    ----------
    top_k: int, default 6
        Number of top words per topic to display on the figure.
    color_discrete_sequence: Iterable[str], default None
        Color palette to use in the plot.
        Example:

        ```python
        import plotly.express as px
        model.plot_topics_over_time(color_discrete_sequence=px.colors.qualitative.Light24)
        ```

    color_discrete_map: dict[str, str], default None
        Topic names mapped to the colors that should
        be associated with them.

    Returns
    -------
    go.Figure
        Plotly graph objects Figure, that can be displayed or exported as
        HTML or static image.
    """
    try:
        import plotly.express as px
        import plotly.graph_objects as go
    except (ImportError, ModuleNotFoundError) as e:
        raise ModuleNotFoundError(
            "Please install plotly if you intend to use plots in Turftopic."
        ) from e
    temporal_components = getattr(self, "temporal_components_", None)
    if temporal_components is None:
        raise AttributeError(
            "Topic model is not dynamic, temporal_components_ attribute is missing."
        )
    temporal_importance = getattr(self, "temporal_importance_", None)
    if temporal_components is None:
        raise AttributeError(
            "Topic model is not dynamic, temporal_importance_ attribute is missing."
        )
    if color_discrete_sequence is not None:
        topic_colors = itertools.cycle(color_discrete_sequence)
    elif color_discrete_map is not None:
        topic_colors = [
            color_discrete_map[topic_name]
            for topic_name in self.topic_names
        ]
    else:
        topic_colors = px.colors.qualitative.Dark24
    fig = go.Figure()
    vocab = self.get_vocab()
    n_topics = temporal_components.shape[1]
    try:
        topic_names = self.topic_names
    except AttributeError:
        topic_names = [f"Topic {i}" for i in range(n_topics)]
    for trace_color, (i_topic, topic_imp_t) in zip(
        itertools.cycle(topic_colors), enumerate(temporal_importance.T)
    ):
        component_over_time = temporal_components[:, i_topic, :]
        name_over_time = []
        for component, importance in zip(component_over_time, topic_imp_t):
            if importance < 0:
                component = -component
            top = np.argpartition(-component, top_k)[:top_k]
            values = component[top]
            if np.all(values == 0) or np.all(np.isnan(values)):
                name_over_time.append("<not present>")
                continue
            top = top[np.argsort(-values)]
            name_over_time.append(", ".join(vocab[top]))
        times = self.time_bin_edges[:-1]
        fig.add_trace(
            go.Scatter(
                x=times,
                y=topic_imp_t,
                mode="markers+lines",
                text=name_over_time,
                name=topic_names[i_topic],
                hovertemplate="<b>%{text}</b>",
                marker=dict(
                    line=dict(width=2, color="black"),
                    size=14,
                    color=trace_color,
                ),
                line=dict(width=3),
            )
        )
    fig.update_layout(
        template="plotly_white",
        hoverlabel=dict(font_size=16, bgcolor="white"),
        hovermode="x",
        font=dict(family="Roboto Mono"),
    )
    fig.add_hline(y=0, line_dash="dash", opacity=0.5)
    fig.update_xaxes(title="Time Slice Start")
    fig.update_yaxes(title="Topic Importance")
    return fig

plot_topics_with_images(n_cols=3, grid_size=4)

Plots the most important images for each topic, along with keywords.

Note that you will need to pip install plotly to use plots in Turftopic.

Parameters:

Name Type Description Default
n_cols int

Number of columns you want to have in the grid of topics.

3
grid_size int

The square root of the number of images you want to display for a given topic. For instance if grid_size==4, all topics will have 16 images displayed, since the joint image will have 4 columns and 4 rows.

4

Returns:

Type Description
Figure

Plotly figure containing top images and keywords for topics.

Source code in turftopic/container.py
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
def plot_topics_with_images(self, n_cols: int = 3, grid_size: int = 4):
    """Plots the most important images for each topic, along with keywords.

    Note that you will need to `pip install plotly` to use plots in Turftopic.

    Parameters
    ----------
    n_cols: int, default 3
        Number of columns you want to have in the grid of topics.
    grid_size: int, default 4
        The square root of the number of images you want to display for a given topic.
        For instance if grid_size==4, all topics will have 16 images displayed,
        since the joint image will have 4 columns and 4 rows.

    Returns
    -------
    go.Figure
        Plotly figure containing top images and keywords for topics.
    """
    if not hasattr(self, "top_images"):
        raise ValueError(
            "Model either has not been fit or was fit without images. top_images property missing."
        )
    try:
        import plotly.graph_objects as go
    except (ImportError, ModuleNotFoundError) as e:
        raise ModuleNotFoundError(
            "Please install plotly if you intend to use plots in Turftopic."
        ) from e
    negative_images = getattr(self, "negative_images", None)
    if negative_images is not None:
        # If the model has negative images, it should display them side by side with the positive ones.
        n_components = self.components_.shape[0]
        fig = go.Figure()
        width, height = 1200, 1200
        scale_factor = 0.25
        w, h = width * scale_factor, height * scale_factor
        padding = 10
        figure_height = (h + padding) * n_components
        figure_width = (w + padding) * 2
        fig = fig.add_trace(
            go.Scatter(
                x=[0, figure_width],
                y=[0, figure_height],
                mode="markers",
                marker_opacity=0,
            )
        )
        vocab = self.get_vocab()
        for i, component in enumerate(self.components_):
            positive = vocab[np.argsort(-component)[:7]]
            negative = vocab[np.argsort(component)[:7]]
            pos_image = self._image_grid(
                self.top_images[i],
                (width, height),
                grid_size=(grid_size, grid_size),
            )
            neg_image = self._image_grid(
                self.negative_images[i],
                (width, height),
                grid_size=(grid_size, grid_size),
            )
            x0 = 0
            y0 = (h + padding) * (n_components - i)
            fig = fig.add_layout_image(
                dict(
                    x=x0,
                    sizex=w,
                    y=y0,
                    sizey=h,
                    xref="x",
                    yref="y",
                    opacity=1.0,
                    layer="below",
                    sizing="stretch",
                    source=pos_image,
                ),
            )
            fig.add_annotation(
                x=(w / 2),
                y=(h + padding) * (n_components - i) - (h / 2),
                text="<b> " + "<br> ".join(positive),
                font=dict(
                    size=16,
                    family="Roboto Mono",
                    color="white",
                ),
                bgcolor="rgba(0,0,255, 0.5)",
            )
            x0 = (w + padding) * 1
            fig = fig.add_layout_image(
                dict(
                    x=x0,
                    sizex=w,
                    y=y0,
                    sizey=h,
                    xref="x",
                    yref="y",
                    opacity=1.0,
                    layer="below",
                    sizing="stretch",
                    source=neg_image,
                ),
            )
            fig.add_annotation(
                x=(w + padding) + (w / 2),
                y=(h + padding) * (n_components - i) - (h / 2),
                text="<b> " + "<br> ".join(negative),
                font=dict(
                    size=16,
                    family="Times New Roman",
                    color="white",
                ),
                bgcolor="rgba(255,0,0, 0.5)",
            )
        fig = fig.update_xaxes(visible=False, range=[0, figure_width])
        fig = fig.update_yaxes(
            visible=False,
            range=[0, figure_height],
            # the scaleanchor attribute ensures that the aspect ratio stays constant
            scaleanchor="x",
        )
        fig = fig.update_layout(
            width=figure_width,
            height=figure_height,
            margin={"l": 0, "r": 0, "t": 0, "b": 0},
        )
        return fig
    else:
        fig = go.Figure()
        width, height = 1200, 1200
        scale_factor = 0.25
        w, h = width * scale_factor, height * scale_factor
        padding = 10
        n_components = self.components_.shape[0]
        n_rows = n_components // n_cols + int(bool(n_components % n_cols))
        figure_height = (h + padding) * n_rows
        figure_width = (w + padding) * n_cols
        fig = fig.add_trace(
            go.Scatter(
                x=[0, figure_width],
                y=[0, figure_height],
                mode="markers",
                marker_opacity=0,
            )
        )
        vocab = self.get_vocab()
        for i, component in enumerate(self.components_):
            col = i % n_cols
            row = i // n_cols
            top_7 = vocab[np.argsort(-component)[:7]]
            images = self.top_images[i]
            image = self._image_grid(
                images, (width, height), grid_size=(grid_size, grid_size)
            )
            x0 = (w + padding) * col
            y0 = (h + padding) * (n_rows - row)
            fig = fig.add_layout_image(
                dict(
                    x=x0,
                    sizex=w,
                    y=y0,
                    sizey=h,
                    xref="x",
                    yref="y",
                    opacity=1.0,
                    layer="below",
                    sizing="stretch",
                    source=image,
                ),
            )
            fig.add_annotation(
                x=(w + padding) * col + (w / 2),
                y=(h + padding) * (n_rows - row) - (h / 2),
                text="<b> " + "<br> ".join(top_7),
                font=dict(
                    size=16,
                    family="Times New Roman",
                    color="white",
                ),
                bgcolor="rgba(0,0,0, 0.5)",
            )
        fig = fig.update_xaxes(visible=False, range=[0, figure_width])
        fig = fig.update_yaxes(
            visible=False,
            range=[0, figure_height],
            # the scaleanchor attribute ensures that the aspect ratio stays constant
            scaleanchor="x",
        )
        fig = fig.update_layout(
            width=figure_width,
            height=figure_height,
            margin={"l": 0, "r": 0, "t": 0, "b": 0},
        )
        return fig

print_representative_documents(topic_id, raw_documents=None, document_topic_matrix=None, top_k=5, show_negative=None)

Pretty prints the highest ranking documents in a topic.

Parameters:

Name Type Description Default
topic_id

ID of the topic to display.

required
raw_documents

List of documents to consider.

None
document_topic_matrix

Document topic matrix to use. This is useful for transductive methods, as they cannot infer topics from text.

None
top_k

Top K documents to show.

5
show_negative Optional[bool]

Indicates whether lowest ranking documents should also be shown.

None
Source code in turftopic/container.py
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
def print_representative_documents(
    self,
    topic_id,
    raw_documents=None,
    document_topic_matrix=None,
    top_k=5,
    show_negative: Optional[bool] = None,
):
    """Pretty prints the highest ranking documents in a topic.

    Parameters
    ----------
    topic_id: int
        ID of the topic to display.
    raw_documents: list of str
        List of documents to consider.
    document_topic_matrix: ndarray of shape (n_documents, n_topics), optional
        Document topic matrix to use. This is useful for transductive methods,
        as they cannot infer topics from text.
    top_k: int, default 5
        Top K documents to show.
    show_negative: bool, default False
        Indicates whether lowest ranking documents should also be shown.
    """
    columns, *rows = self._representative_docs(
        topic_id,
        raw_documents,
        document_topic_matrix,
        top_k,
        show_negative,
    )
    table = Table(show_lines=True)
    table.add_column(
        "Document", justify="left", style="magenta", max_width=100
    )
    table.add_column("Score", style="blue", justify="right")
    for row in rows:
        table.add_row(*row)
    console = Console()
    console.print(table)

print_topic_distribution(text=None, topic_dist=None, top_k=10)

Pretty prints topic distribution in a document.

Parameters:

Name Type Description Default
text

Text to infer topic distribution for.

None
topic_dist

Already inferred topic distribution for the text. This is useful for transductive methods, as they cannot infer topics from text.

None
top_k int

Top K topics to show.

10
Source code in turftopic/container.py
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
def print_topic_distribution(
    self, text=None, topic_dist=None, top_k: int = 10
):
    """Pretty prints topic distribution in a document.

    Parameters
    ----------
    text: str, optional
        Text to infer topic distribution for.
    topic_dist: ndarray of shape (n_topics), optional
        Already inferred topic distribution for the text.
        This is useful for transductive methods,
        as they cannot infer topics from text.
    top_k: int, default 10
        Top K topics to show.
    """
    columns, *rows = self._topic_distribution(text, topic_dist, top_k)
    table = Table()
    table.add_column("Topic name", justify="left", style="magenta")
    table.add_column("Score", justify="right", style="blue")
    for row in rows:
        table.add_row(*row)
    console = Console()
    console.print(table)

print_topics(top_k=10, show_scores=False, show_negative=None)

Pretty prints topics in the model in a table.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

10
show_scores bool

Indicates whether to show importance scores for each word.

False
show_negative Optional[bool]

Indicates whether the most negative terms should also be displayed.

None
Source code in turftopic/container.py
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
def print_topics(
    self,
    top_k: int = 10,
    show_scores: bool = False,
    show_negative: Optional[bool] = None,
):
    """Pretty prints topics in the model in a table.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.
    show_scores: bool, default False
        Indicates whether to show importance scores for each word.
    show_negative: bool, default False
        Indicates whether the most negative terms should also be displayed.
    """
    columns, *rows = self._topics_table(top_k, show_scores, show_negative)
    table = Table(show_lines=True)
    for column in columns:
        if column == "Highest Ranking":
            table.add_column(
                column, justify="left", style="magenta", max_width=100
            )
        elif column == "Lowest Ranking":
            table.add_column(
                column, justify="left", style="red", max_width=100
            )
        elif column == "Topic ID":
            table.add_column(column, style="blue", justify="right")
        else:
            table.add_column(column)
    for row in rows:
        table.add_row(*row)
    console = Console()
    console.print(table)

print_topics_over_time(top_k=5, show_scores=False, date_format='%Y %m %d')

Pretty prints topics in the model in a table.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

5
show_scores bool

Indicates whether to show importance scores for each word.

False
Source code in turftopic/container.py
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
def print_topics_over_time(
    self,
    top_k: int = 5,
    show_scores: bool = False,
    date_format: str = "%Y %m %d",
):
    """Pretty prints topics in the model in a table.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.
    show_scores: bool, default False
        Indicates whether to show importance scores for each word.
    """
    columns, *rows = self._topics_over_time(
        top_k, show_scores, date_format
    )
    table = Table(show_lines=True)
    for column in columns:
        table.add_column(column)
    for row in rows:
        table.add_row(*row)
    console = Console()
    console.print(table)

rename_topics(names)

Rename topics in a model manually or automatically, using a namer.

Examples:

model.rename_topics(["Automobiles", "Telephones"])
# Or:
model.rename_topics({-1: "Outliers", 2: "Christianity"})
# Or:
namer = OpenAITopicNamer()
model.rename_topics(namer)

Parameters:

Name Type Description Default
names Union[list[str], dict[int, str], TopicNamer]

Should be a list of topic names, or a mapping of topic IDs to names.

required
Source code in turftopic/container.py
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
def rename_topics(
    self, names: Union[list[str], dict[int, str], TopicNamer]
) -> None:
    """Rename topics in a model manually or automatically, using a namer.

    Examples:
    ```python
    model.rename_topics(["Automobiles", "Telephones"])
    # Or:
    model.rename_topics({-1: "Outliers", 2: "Christianity"})
    # Or:
    namer = OpenAITopicNamer()
    model.rename_topics(namer)
    ```

    Parameters
    ----------
    names: list[str] or dict[int,str]
        Should be a list of topic names, or a mapping of topic IDs to names.
    """
    if isinstance(names, TopicNamer):
        self._rename_automatic(names)
    elif isinstance(names, dict):
        topic_names = self.topic_names
        for topic_id, topic_name in names.items():
            try:
                topic_id = list(self.classes_).index(topic_id)
            except AttributeError:
                pass
            topic_names[topic_id] = topic_name
        self.topic_names_ = topic_names
    else:
        names = list(names)
        n_given = len(names)
        n_topics = self.components_.shape[0]
        if n_topics != n_given:
            raise ValueError(
                f"Number of topics ({n_topics}) doesn't match the length of the given topic name list ({n_given})."
            )
        self.topic_names_ = names

representative_documents_df(topic_id, raw_documents=None, document_topic_matrix=None, top_k=5, show_negative=None)

Collects highest ranking documents in a topic to a dataframe.

Parameters:

Name Type Description Default
topic_id

ID of the topic to display.

required
raw_documents

List of documents to consider.

None
document_topic_matrix

Document topic matrix to use. This is useful for transductive methods, as they cannot infer topics from text.

None
top_k

Top K documents to show.

5
show_negative Optional[bool]

Indicates whether lowest ranking documents should also be shown.

None
Source code in turftopic/container.py
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
def representative_documents_df(
    self,
    topic_id,
    raw_documents=None,
    document_topic_matrix=None,
    top_k=5,
    show_negative: Optional[bool] = None,
):
    """Collects highest ranking documents in a topic to a dataframe.

    Parameters
    ----------
    topic_id: int
        ID of the topic to display.
    raw_documents: list of str
        List of documents to consider.
    document_topic_matrix: ndarray of shape (n_documents, n_topics), optional
        Document topic matrix to use. This is useful for transductive methods,
        as they cannot infer topics from text.
    top_k: int, default 5
        Top K documents to show.
    show_negative: bool, default False
        Indicates whether lowest ranking documents should also be shown.
    """
    try:
        import pandas as pd
    except ModuleNotFoundError:
        raise ModuleNotFoundError(
            "You need to pip install pandas to be able to use dataframes."
        )
    if show_negative is None:
        show_negative = self.has_negative_side
    raw_documents = raw_documents or getattr(self, "corpus", None)
    if raw_documents is None:
        raise ValueError(
            "No corpus was passed, can't search for representative documents."
        )
    document_topic_matrix = document_topic_matrix or getattr(
        self, "document_topic_matrix", None
    )
    if document_topic_matrix is None:
        try:
            document_topic_matrix = self.transform(raw_documents)
        except AttributeError:
            raise ValueError(
                "Transductive methods cannot "
                "infer topical content in documents.\n"
                "Please pass a document_topic_matrix."
            )
    try:
        topic_id = list(self.classes_).index(topic_id)
    except AttributeError:
        pass
    kth = min(top_k, document_topic_matrix.shape[0] - 1)
    highest = np.argpartition(-document_topic_matrix[:, topic_id], kth)[
        :kth
    ]
    highest = highest[
        np.argsort(-document_topic_matrix[highest, topic_id])
    ]
    scores = document_topic_matrix[highest, topic_id]
    columns = [["Document", "Score"]]
    rows = []
    for document_id, score in zip(highest, scores):
        doc = raw_documents[document_id]
        rows.append([doc, score])
    if show_negative:
        lowest = np.argpartition(document_topic_matrix[:, topic_id], kth)[
            :kth
        ]
        lowest = lowest[
            np.argsort(document_topic_matrix[lowest, topic_id])
        ]
        lowest = lowest[::-1]
        scores = document_topic_matrix[lowest, topic_id]
        for document_id, score in zip(lowest, scores):
            doc = raw_documents[document_id]
            rows.append([doc, score])
    return pd.DataFrame(rows, columns=columns)

topic_distribution_df(text=None, topic_dist=None, top_k=10)

Extracts topic distribution into a dataframe.

Parameters:

Name Type Description Default
text

Text to infer topic distribution for.

None
topic_dist

Already inferred topic distribution for the text. This is useful for transductive methods, as they cannot infer topics from text.

None
top_k int

Top K topics to show.

10
Source code in turftopic/container.py
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
def topic_distribution_df(
    self, text=None, topic_dist=None, top_k: int = 10
):
    """Extracts topic distribution into a dataframe.

    Parameters
    ----------
    text: str, optional
        Text to infer topic distribution for.
    topic_dist: ndarray of shape (n_topics), optional
        Already inferred topic distribution for the text.
        This is useful for transductive methods,
        as they cannot infer topics from text.
    top_k: int, default 10
        Top K topics to show.
    """
    try:
        import pandas as pd
    except ModuleNotFoundError:
        raise ModuleNotFoundError(
            "You need to pip install pandas to be able to use dataframes."
        )
    if topic_dist is None:
        if text is None:
            raise ValueError(
                "You should either pass a text or a distribution."
            )
        try:
            topic_dist = self.transform([text])
        except AttributeError:
            raise ValueError(
                "Transductive methods cannot "
                "infer topical content in documents.\n"
                "Please pass a topic distribution."
            )
    topic_dist = np.squeeze(np.asarray(topic_dist))
    highest = np.argsort(-topic_dist)[:top_k]
    columns = []
    columns.append("Topic name")
    columns.append("Score")
    rows = []
    for ind in highest:
        score = topic_dist[ind]
        rows.append([self.topic_names[ind], score])
    return pd.DataFrame(rows, columns=columns)

topics_df(top_k=10, show_scores=False, show_negative=None)

Extracts topics into a pandas dataframe.

Parameters:

Name Type Description Default
top_k int

Number of top words to return for each topic.

10
show_scores bool

Indicates whether to show importance scores for each word.

False
show_negative Optional[bool]

Indicates whether the most negative terms should also be displayed.

None
Source code in turftopic/container.py
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
def topics_df(
    self,
    top_k: int = 10,
    show_scores: bool = False,
    show_negative: Optional[bool] = None,
):
    """Extracts topics into a pandas dataframe.

    Parameters
    ----------
    top_k: int, default 10
        Number of top words to return for each topic.
    show_scores: bool, default False
        Indicates whether to show importance scores for each word.
    show_negative: bool, default False
        Indicates whether the most negative terms should also be displayed.
    """
    try:
        import pandas as pd
    except ModuleNotFoundError:
        raise ModuleNotFoundError(
            "You need to pip install pandas to be able to use dataframes."
        )
    columns, *rows = self._topics_table(top_k, show_scores, show_negative)
    return pd.DataFrame(rows, columns=columns)