mirror of https://github.com/explosion/spaCy.git
63 lines
2.6 KiB
Plaintext
63 lines
2.6 KiB
Plaintext
//- 💫 DOCS > USAGE > TRAINING > TEXT CLASSIFICATION
|
||
|
||
+h(3, "example-textcat") Adding a text classifier to a spaCy model
|
||
+tag-new(2)
|
||
|
||
p
|
||
| This example shows how to train a multi-label convolutional neural
|
||
| network text classifier on IMDB movie reviews, using spaCy's new
|
||
| #[+api("textcategorizer") #[code TextCategorizer]] component. The
|
||
| dataset will be loaded automatically via Thinc's built-in dataset
|
||
| loader. Predictions are available via
|
||
| #[+api("doc#attributes") #[code Doc.cats]].
|
||
|
||
+github("spacy", "examples/training/train_textcat.py", 500)
|
||
|
||
+h(4) Step by step guide
|
||
|
||
+list("numbers")
|
||
+item
|
||
| #[strong Load the model] you want to start with, or create an
|
||
| #[strong empty model] using
|
||
| #[+api("spacy#blank") #[code spacy.blank]] with the ID of your
|
||
| language. If you're using an existing model, make sure to disable all
|
||
| other pipeline components during training using
|
||
| #[+api("language#disable_pipes") #[code nlp.disable_pipes]]. This
|
||
| way, you'll only be training the text classifier.
|
||
|
||
+item
|
||
| #[strong Add the text classifier] to the pipeline, and add the labels
|
||
| you want to train – for example, #[code POSITIVE].
|
||
|
||
+item
|
||
| #[strong Load and pre-process the dataset], shuffle the data and
|
||
| split off a part of it to hold back for evaluation. This way, you'll
|
||
| be able to see results on each training iteration.
|
||
|
||
+item
|
||
| #[strong Loop over] the training examples, partition them into
|
||
| batches and create #[code Doc] and #[code GoldParse] objects for each
|
||
| example in the batch.
|
||
|
||
+item
|
||
| #[strong Update the model] by calling
|
||
| #[+api("language#update") #[code nlp.update]], which steps
|
||
| through the examples and makes a #[strong prediction]. It then
|
||
| consults the annotations provided on the #[code GoldParse] instance,
|
||
| to see whether it was right. If it was wrong, it adjusts its weights
|
||
| so that the correct prediction will score higher next time.
|
||
|
||
+item
|
||
| Optionally, you can also #[strong evaluate the text classifier] on
|
||
| each iteration, by checking how it performs on the development data
|
||
| held back from the dataset. This lets you print the
|
||
| #[strong precision], #[strong recall] and #[strong F-score].
|
||
|
||
+item
|
||
| #[strong Save] the trained model using
|
||
| #[+api("language#to_disk") #[code nlp.to_disk]].
|
||
|
||
+item
|
||
| #[strong Test] the model to make sure the text classifier works as
|
||
| expected.
|