adilzouitine / pyfeel

Python package for emotion analysis in French

pyFeel

pyFeel is a python library, it will make your emotion analysis in french easier. pyFeel computes seven emotions: positivity, joy, fear, sadness, anger, surprise, disgust with a bag of word method.

Installation

If you want to install it :

Requirements

• Python 3
• numpy : run pip install numpy
• nltk : run pip install nltk
• Don't forget to download nltk data [punkt] !!

Let's play now !

• pyFeel : run pip install git+https://github.com/AdilZouitine/pyFeel --upgrade

PyPI

PyPI is coming ...

---

>>> from pyFeel import Feel
>>> test = Feel("Ma classe fonctionne bien, c'est sympathique non ?")
>>> test.emotions()
Out : {'positivity': 1.0, 'joy': 0.3333333333333333, 'fear': 0.0, 'sadness': 0.0, 'angry': 0.0, 'surprise': 0.0, 'disgust': 0.0}

For more information contact me: [email protected]

For the lexicon

Amine Abdaoui, Jérôme Azé, Sandra Bringay et Pascal Poncelet. FEEL: French Expanded Emotion Lexicon. Language Resources and Evaluation, LRE 2016, pp 1-23.

Bibliograpy

• Ekman, P., 1992. An argument for basic emotions. Cognition & emotion 6, 169–200.
• Mohammad, S.M., Turney, P.D., 2013. Crowdsourcing a Word-Emotion Association Lexicon. Computational Intelligence 29, 436–465.

pyfeel's Issues

Error : `Object arrays cannot be loaded when allow_pickle=False` when trying example

I ran the example in the repository description (given below)-

from pyFeel import Feel
test = Feel("Ma classe fonctionne bien, c'est sympathique non ?")
test.emotions()

And got this error (trace below) -

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-6-b6a3e1be6d31> in <module>
      1 from pyFeel import Feel
----> 2 test = Feel("Ma classe fonctionne bien, c'est sympathique non ?")
      3 test.emotions()

~/anaconda3/envs/py36/lib/python3.6/site-packages/pyFeel/pyFeel.py in __init__(self, text)
     33         dict_name = os.path.join(scriptpath, 'feel.npy')
     34 
---> 35         self.dict = np.load(dict_name).item()
     36         self.token = [word for word in word_tokenize(text.lower())]
     37         self.sentiment = {}

~/anaconda3/envs/py36/lib/python3.6/site-packages/numpy/lib/npyio.py in load(file, mmap_mode, allow_pickle, fix_imports, encoding)
    438             else:
    439                 return format.read_array(fid, allow_pickle=allow_pickle,
--> 440                                          pickle_kwargs=pickle_kwargs)
    441         else:
    442             # Try a pickle

~/anaconda3/envs/py36/lib/python3.6/site-packages/numpy/lib/format.py in read_array(fp, allow_pickle, pickle_kwargs)
    725         # The array contained Python objects. We need to unpickle the data.
    726         if not allow_pickle:
--> 727             raise ValueError("Object arrays cannot be loaded when "
    728                              "allow_pickle=False")
    729         if pickle_kwargs is None:

ValueError: Object arrays cannot be loaded when allow_pickle=False

Information about my environment-

python v3.6.12
nltk v3.5
numpy v1.19.1

Do you know what might be causing this?