# Having erros when loading my own data

**URL:** <https://support.prodi.gy/t/having-erros-when-loading-my-own-data/61>\
**Category:** Uncategorized\
**Tags:** usage, textcat\
**Created:** [October 23, 2017, 9:04am UTC](https://support.prodi.gy/t/having-erros-when-loading-my-own-data/61 "2017-10-23T09:04:52Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![ilhami123](https://avatars.discourse-cdn.com/v4/letter/i/e36b37/32.png) [@ilhami123](https://support.prodi.gy/u/ilhami123)\
**Post date:** [October 23, 2017, 9:04am UTC](https://support.prodi.gy/t/having-erros-when-loading-my-own-data/61/1 "2017-10-23T09:04:52Z")

</div>

I am really enjoying using prodigy. I tried the Github Issues dataset. It works perfectly fine 🙂

```
prodigy dataset gh_issues "Classify issues on GitHub"
prodigy textcat.teach gh_issues en_core_web_sm "docs" --api github --label DOCUMENTATION

```

I tried to make a different dataset by following the example in [here](https://prodi.gy/docs/workflow-first-steps).

```
MY_DATA.TXT

Pinterest Hires Its First Head of Diversity
Airbnb and Others Set Terms for Employees to Cash Out

prodigy textcat.teach my_set path/to/my_data.txt --label POLITICS

```

However, I received the following error.

```
Traceback (most recent call last):
  File "/home/pacmann/anaconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    " __main__", mod_spec)
  File "/home/pacmann/anaconda3/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/prodigy/ __main__.py", line 235, in <module>
    controller = recipe(*args, use_plac=True)
  File "cython_src/prodigy/core.pyx", line 130, in prodigy.core.recipe.recipe_decorator.recipe_proxy
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/plac_core.py", line 328, in call
    cmd, result = parser.consume(arglist)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/plac_core.py", line 207, in consume
    return cmd, self.func(*(args + varargs + extraopts), **kwargs)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/prodigy/recipes/textcat.py", line 42, in teach
    nlp = spacy.load(spacy_model)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/spacy/ __init__.py", line 15, in load
    return util.load_model(name, **overrides)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/spacy/util.py", line 108, in load_model
    return load_model_from_path(Path(name), **overrides)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/spacy/util.py", line 136, in load_model_from_path
    meta = get_model_meta(model_path)
  File "/home/pacmann/anaconda3/lib/python3.6/site-packages/spacy/util.py", line 181, in get_model_meta
    raise IOError("Could not read meta.json from %s" % meta_path)
OSError: Could not read meta.json from my_data.jsonl/meta.json

```

I would to know if there are an suggestions. I’ve been stuck with this error for weeks now and need some help.

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [October 23, 2017, 9:39am UTC](https://support.prodi.gy/t/having-erros-when-loading-my-own-data/61/2 "2017-10-23T09:39:12Z")

</div>

Thanks, glad you like Prodigy!

I think the problem here has nothing to do with your data and is much simpler: The second argument on `textcat.teach`, after your data set, is the base model you want to start off with – for example, spaCy’s `en_core_web_sm`. The model is used for basic text processing and tokenization, and will be updated with your annotations. Then, the _third_ argument is the data you want to load in. So what happened here is that Prodigy thought `path/to/my_data.txt` was a model, tried to load it, and failed.

You can see the command signature and available arguments [here](https://prodi.gy/docs/recipes#textcat-teach), or by typing:

```bash
prodigy textcat.teach --help

```

---

<div class="post-metadata">

**Author:** ![beckerfuffle](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/beckerfuffle/32/159_2.png) [@beckerfuffle](https://support.prodi.gy/u/beckerfuffle)\
**Post date:** [March 6, 2018, 4:01pm UTC](https://support.prodi.gy/t/having-erros-when-loading-my-own-data/61/3 "2018-03-06T16:01:24Z")

</div>

FYI I ran into the same issue above using the example [from the documentation](https://prodi.gy/docs/workflow-first-steps#load-data):

```bash
$ prodigy textcat.teach my_set path/to/my_data.txt --label POLITICS

```

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [March 6, 2018, 4:03pm UTC](https://support.prodi.gy/t/having-erros-when-loading-my-own-data/61/4 "2018-03-06T16:03:20Z")

</div>

@beckerfuffle Ah damn, so there’s a bug in the example! I totally missed that. Fixing, thanks! 👍