我使用spaCy从事文本分类项目。我非常仔细地遵循spaCy代码示例。唯一重要的区别是,我在示例中使用的是两个类别,而不是一个类别。我不知道出什么问题了,因为我检查了一下,并且正在加载的数据与原始示例中的格式相同。这是相关的代码(下面附有完整的代码):
def load_data(limit=0, split=0.8):
"""Load the patents data."""
# Partition off part of the train data for evaluation
temp=pd.read_csv(excel + 'patents_text_class.csv',header = None)
new_cols = ['id' , 'class' , 'patent_text']
temp.columns = new_cols
print(temp)
train_data = list(zip(temp["patent_text"], temp["class"]))
random.shuffle(train_data)
train_data = train_data[-limit:]
texts, labels = zip(*train_data)
cats = [{"A01D": bool(y) , "A01B": operator.not_(bool(y))} for y in labels]
split = int(len(train_data) * split)
return (texts[:split], cats[:split]), (texts[split:], cats[split:])
这是日志:
Loaded model 'en_core_web_lg'
Loading patents data...
id class patent_text
0 1317 0 Improvement n revolving harrows <div itemprop=...
1 2476 1 Machine for cutting meat and other substances ...
2 2650 0 Improvement in cultivators fob vines <div item...
3 3311 0 Improvement in plows <div itemprop="content" h...
4 4544 0 Improvement in plow-clevises <div itemprop="co...
5 7277 1 Improvement in machines for raking and loading...
6 8721 0 Improvement in shovel-plows <div itemprop="con...
7 8844 0 Improvement in gang-plows <div itemprop="conte...
8 9069 0 Improvement in potato-diggers and stone-gather...
9 10624 0 Improvement in rotary cultivators <div itempro...
10 12057 0 Improvement in hoes <div itemprop="content" ht...
[70000 rows x 3 columns]
Using 10000 examples (8000 training, 2000 evaluation)
Training the model...
LOSS P R F
Traceback (most recent call last):
File "process/task_classification.py", line 150, in <module>
plac.call(main)
File "/anaconda/lib/python3.6/site-packages/plac_core.py", line 328, in call
cmd, result = parser.consume(arglist)
File "/anaconda/lib/python3.6/site-packages/plac_core.py", line 207, in consume
return cmd, self.func(*(args + varargs + extraopts), **kwargs)
File "process/task_classification.py", line 78, in main
losses=losses)
File "/anaconda/lib/python3.6/site-packages/spacy/language.py", line 405, in update
gold = GoldParse(doc, **gold)
File "gold.pyx", line 409, in spacy.gold.GoldParse.__init__
TypeError: 'float' object is not iterable
有什么主意为什么会出现此错误?
完整代码供参考:
#!/usr/bin/env python
# coding: utf8
"""Train a convolutional neural network text classifier on the
IMDB dataset, using the TextCategorizer component. The dataset will be loaded
automatically via Thinc's built-in dataset loader. The model is added to
spacy.pipeline, and predictions are available via `doc.cats`. For more details,
see the documentation:
* Training: https://spacy.io/usage/training
Compatible with: spaCy v2.0.0+
"""
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import thinc.extra.datasets
import os
import pandas as pd
import operator
import spacy
from spacy.util import minibatch, compounding
root = 'path/to/folder'
output = root + 'output/'
process = root + 'process/'
excel = root + 'excel/'
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
n_texts=("Number of texts to train from", "option", "t", int),
n_iter=("Number of training iterations", "option", "n", int))
def main(model='en_core_web_lg', output_dir=output, n_iter=5, n_texts=10000):
if output_dir is not None:
output_dir = Path(output_dir)
if not output_dir.exists():
output_dir.mkdir()
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank('en') # create blank Language class
print("Created blank 'en' model")
# add the text classifier to the pipeline if it doesn't exist
# nlp.create_pipe works for built-ins that are registered with spaCy
if 'textcat' not in nlp.pipe_names:
textcat = nlp.create_pipe('textcat')
nlp.add_pipe(textcat, last=True)
# otherwise, get it, so we can add labels to it
else:
textcat = nlp.get_pipe('textcat')
# add label to text classifier
textcat.add_label("A01B")
textcat.add_label("A01D")
# load the patents dataset
print("Loading patents data...")
(train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts)
print("Using {} examples ({} training, {} evaluation)"
.format(n_texts, len(train_texts), len(dev_texts)))
train_data = list(zip(train_texts,
[{'cats': cats} for cats in train_cats]))
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'textcat']
with nlp.disable_pipes(*other_pipes): # only train textcat
optimizer = nlp.begin_training()
print("Training the model...")
print('{:^5}\t{:^5}\t{:^5}\t{:^5}'.format('LOSS', 'P', 'R', 'F'))
for i in range(n_iter):
losses = {}
# batch up the examples using spaCy's minibatch
batches = minibatch(train_data, size=compounding(4., 32., 1.001))
for batch in batches:
texts, annotations = zip(*batch)
nlp.update(texts, annotations, sgd=optimizer, drop=0.2,
losses=losses)
with textcat.model.use_params(optimizer.averages):
# evaluate on the dev data split off in load_data()
scores = evaluate(nlp.tokenizer, textcat, dev_texts, dev_cats)
print('{0:.3f}\t{1:.3f}\t{2:.3f}\t{3:.3f}' # print a simple table
.format(losses['textcat'], scores['textcat_p'],
scores['textcat_r'], scores['textcat_f']))
# test the trained model
test_text = "Harvesting"
doc = nlp(test_text)
print(test_text, doc.cats)
test_text = "Plowing"
doc = nlp(test_text)
print(test_text, doc.cats)
if output_dir is not None:
with nlp.use_params(optimizer.averages):
nlp.to_disk(output_dir)
print("Saved model to", output_dir)
# test the saved model
print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
doc2 = nlp2(test_text)
print(test_text, doc2.cats)
def load_data(limit=0, split=0.8):
"""Load the patents data."""
# Partition off part of the train data for evaluation
temp=pd.read_csv(excel + 'patents_text_class.csv',header = None)
new_cols = ['id' , 'class' , 'patent_text']
temp.columns = new_cols
train_data = list(zip(temp["patent_text"], temp["class"]))
random.shuffle(train_data)
train_data = train_data[-limit:]
texts, labels = zip(*train_data)
cats = [{"A01D": bool(y) , "A01B": operator.not_(bool(y))} for y in labels]
split = int(len(train_data) * split)
return (texts[:split], cats[:split]), (texts[split:], cats[split:])
def evaluate(tokenizer, textcat, texts, cats):
docs = (tokenizer(text) for text in texts)
tp = 0.0 # True positives
fp = 1e-8 # False positives
fn = 1e-8 # False negatives
tn = 0.0 # True negatives
for i, doc in enumerate(textcat.pipe(docs)):
gold = cats[i]
print(i)
for label, score in doc.cats.items():
if label not in gold:
continue
if score >= 0.5 and gold[label] >= 0.5:
tp += 1.
elif score >= 0.5 and gold[label] < 0.5:
fp += 1.
elif score < 0.5 and gold[label] < 0.5:
tn += 1
elif score < 0.5 and gold[label] >= 0.5:
fn += 1
precision = tp / (tp + fp)
recall = tp / (tp + fn)
f_score = 2 * (precision * recall) / (precision + recall)
return {'textcat_p': precision, 'textcat_r': recall, 'textcat_f': f_score}
if __name__ == '__main__':
plac.call(main)
答案 0 :(得分:2)
根据文档,Language.update
的第一个参数接受一批unicode
或Doc
。 Probalby texts
包含一些NaN
类型的float
值。相关代码:
batches = minibatch(train_data, size=compounding(4., 32., 1.001))
for batch in batches:
texts, annotations = zip(*batch) # check texts for NaN
nlp.update(texts, annotations, sgd=optimizer, drop=0.2,
losses=losses)
spacy
尝试迭代NaN
(浮动),并导致
...
TypeError: 'float' object is not iterable
-因此,您可以删除所有NaN
值或将其替换为空字符串。
此外,对于NLP(但不仅限于NLP)任务,这种错误非常常见。务必检出NaN
的文本数据并替换它们,尤其是当您收到类似的错误消息时。