First commit

.gitignore

@@ -0,0 +1,140 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+.vscode

app.py

@@ -0,0 +1,99 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+
+class TwitterEmotionClassifier:
+    def __init__(self, model_name: str, model_type: str):
+        self.is_gpu = False
+        self.model_type = model_type
+        device = torch.device("cuda") if self.is_gpu else torch.device("cpu")
+        model = AutoModelForSequenceClassification.from_pretrained(model_name)
+        tokenizer = AutoTokenizer.from_pretrained(model_name)
+        model.to(device)
+        model.eval()
+        self.bertweet = pipeline(
+            "text-classification",
+            model=model,
+            tokenizer=tokenizer,
+            device=self.is_gpu - 1,
+        )
+        self.deberta = None
+        self.emotions = {
+            "LABEL_0": "sadness",
+            "LABEL_1": "joy",
+            "LABEL_2": "love",
+            "LABEL_3": "anger",
+            "LABEL_4": "fear",
+            "LABEL_5": "surprise",
+        }
+
+    def get_model(self, model_type: str):
+        if self.model_type == "bertweet" and model_type == self.model_type:
+            return self.bertweet
+        elif model_type == "deberta":
+            if self.deberta:
+                return self.deberta
+            model = AutoModelForSequenceClassification.from_pretrained(
+                "Emanuel/twitter-emotion-deberta-v3-base"
+            )
+            tokenizer = AutoTokenizer.from_pretrained(
+                "Emanuel/twitter-emotion-deberta-v3-base"
+            )
+            self.deberta = pipeline(
+                "text-classification",
+                model=model,
+                tokenizer=tokenizer,
+                device=self.is_gpu - 1,
+            )
+            return self.deberta
+
+    def predict(self, twitter: str, model_type: str):
+        classifier = self.get_model(model_type)
+        preds = classifier(twitter, return_all_scores=True)
+        if preds:
+            pred = preds[0]
+            res = {
+                "Sadness 😢": pred[0]["score"],
+                "Joy 😂": pred[1]["score"],
+                "Love 💛": pred[2]["score"],
+                "Anger 😠": pred[3]["score"],
+                "Fear 😱": pred[4]["score"],
+                "Surprise 😮": pred[5]["score"],
+            }
+            return res
+        return None
+
+
+def main():
+
+    model = TwitterEmotionClassifier("Emanuel/bertweet-emotion-base", "bertweet")
+    interFace = gr.Interface(
+        fn=model.predict,
+        inputs=[
+            gr.inputs.Textbox(
+                placeholder="What's happenning?", label="Tweet content", lines=5
+            ),
+            gr.inputs.Radio(["bertweet", "deberta"], label="Model"),
+        ],
+        outputs=gr.outputs.Label(num_top_classes=6, label="Emotions of this tweet is "),
+        verbose=True,
+        examples=[
+            ["This GOT show just remember LOTR times!", "bertweet"],
+            ["Man, that my 30 days of training just got a NaN loss!!!", "bertweet"],
+            ["I couldn't see 3 Tom Hollands coming...", "bertweet"],
+            [
+                "There is nothing better than a soul-warming coffee in the morning",
+                "bertweet",
+            ],
+            ["I fear the vanishing gradient a lot", "deberta"],
+        ],
+        title="Emotion classification with DeBERTa-v3 🤖",
+        description="",
+        theme="huggingface",
+    )
+    interFace.launch()
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,66 @@
+analytics-python==1.4.0
+backoff==1.10.0
+bcrypt==3.2.0
+black==21.11b1
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.7
+click==8.0.3
+cryptography==36.0.0
+cycler==0.11.0
+emoji==1.6.1
+ffmpy==0.3.0
+filelock==3.4.0
+flake8==4.0.1
+Flask==2.0.2
+Flask-CacheBuster==1.0.0
+Flask-Cors==3.0.10
+Flask-Login==0.5.0
+fonttools==4.28.1
+gradio==2.4.5
+huggingface-hub==0.1.2
+idna==3.3
+isort==5.10.1
+itsdangerous==2.0.1
+Jinja2==3.0.3
+joblib==1.1.0
+kiwisolver==1.3.2
+markdown2==2.4.1
+MarkupSafe==2.0.1
+matplotlib==3.5.0
+mccabe==0.6.1
+monotonic==1.6
+mypy-extensions==0.4.3
+numpy==1.21.4
+packaging==21.3
+pandas==1.3.4
+paramiko==2.8.0
+pathspec==0.9.0
+Pillow==8.4.0
+platformdirs==2.4.0
+pycodestyle==2.8.0
+pycparser==2.21
+pycryptodome==3.11.0
+pydub==0.25.1
+pyflakes==2.4.0
+PyNaCl==1.4.0
+pyparsing==3.0.6
+python-dateutil==2.8.2
+pytz==2021.3
+PyYAML==6.0
+regex==2021.11.10
+requests==2.26.0
+sacremoses==0.0.46
+sentencepiece==0.1.96
+setuptools-scm==6.3.2
+six==1.16.0
+tokenizers==0.10.3
+tomli==1.2.2
+torch==1.10.0+cpu
+torchaudio==0.10.0+cpu
+torchvision==0.11.1+cpu
+tqdm==4.62.3
+transformers==4.12.5
+typing-extensions==4.0.0
+urllib3==1.26.7
+Werkzeug==2.0.2

setup.cfg

@@ -0,0 +1,17 @@
+[isort]
+default_section = FIRSTPARTY
+ensure_newline_before_comments = True
+force_grid_wrap = 0
+include_trailing_comma = True
+
+line_length = 119
+lines_after_imports = 2
+multi_line_output = 3
+use_parentheses = True
+
+[flake8]
+ignore = E203, E501, E741, W503, W605
+max-line-length = 119
+
+[tool:pytest]
+doctest_optionflags=NUMBER NORMALIZE_WHITESPACE ELLIPSIS