Duplicate from daniel-de-leon/streamlit-docker-poc

.gitignore

@@ -0,0 +1,134 @@
+venv/
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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/
+
+.vscode/
+
+data/audio/

.streamlit/config.toml

@@ -0,0 +1,5 @@
+[theme]
+base='light'
+
+[server]
+maxUploadSize = 200

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.9
+
+WORKDIR /app
+
+COPY ./requirements.txt /app/requirements.txt
+COPY ./packages.txt /app/packages.txt
+
+RUN apt-get update && xargs -r -a /app/packages.txt apt-get install -y && rm -rf /var/lib/apt/lists/*
+RUN pip3 install --no-cache-dir -r /app/requirements.txt
+
+# User
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME /home/user
+ENV PATH $HOME/.local/bin:$PATH
+
+WORKDIR $HOME
+RUN mkdir app
+WORKDIR $HOME/app
+COPY . $HOME/app
+
+EXPOSE 8501
+CMD streamlit run app.py \
+    --server.headless true \
+    --server.enableCORS false \
+    --server.enableXsrfProtection false \
+    --server.fileWatcherType none

README.md

@@ -0,0 +1,16 @@
+---
+title: Streamlit Docker Template
+emoji: 📉
+colorFrom: blue
+colorTo: green
+sdk: docker
+app_port: 8501
+pinned: false
+duplicated_from: daniel-de-leon/streamlit-docker-poc
+---
+
+## 🧠 Streamlit Docker Template 🔎
+
+Streamlit Docker Template is a template for creating a Streamlit app with Docker and Hugging Face Spaces.
+
+Code from https://docs.streamlit.io/library/get-started/create-an-app

app.py

@@ -0,0 +1,61 @@
+import streamlit as st
+import streamlit.components.v1 as components
+from transformers import (AutoModelForSequenceClassification, AutoTokenizer,
+                          pipeline)
+import shap
+from PIL import Image
+
+st.set_option('deprecation.showPyplotGlobalUse', False)
+output_width = 800
+output_height = 300
+rescale_logits = False
+
+
+
+st.set_page_config(page_title='Text Classification with Shap')
+st.title('Interpreting HF Pipeline Text Classification with Shap')
+
+form = st.sidebar.form("Model Selection")
+form.header('Model Selection')
+
+model_name = form.text_input("Enter the name of the text classification LLM (note: model must be fine-tuned on a text classification task)", value = "Hate-speech-CNERG/bert-base-uncased-hatexplain")
+form.form_submit_button("Submit")
+
+
+@st.cache_data()
+def load_model(model_name):
+    tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+    return tokenizer, model
+
+tokenizer, model = load_model(model_name)
+pred = pipeline("text-classification", model=model, tokenizer=tokenizer, top_k=None)
+explainer = shap.Explainer(pred, rescale_to_logits = rescale_logits)
+
+col1, col2 = st.columns(2)
+text = col1.text_area("Enter text input", value = "Classify me.")
+
+result = pred(text)
+top_pred = result[0][0]['label']
+col2.write('')
+for label in result[0]:
+    col2.write(f'**{label["label"]}**: {label["score"]: .2f}')
+
+shap_values = explainer([text])
+
+force_plot = shap.plots.text(shap_values, display=False)
+bar_plot = shap.plots.bar(shap_values[0, :, top_pred], order=shap.Explanation.argsort.flip, show=False)
+
+st.markdown("""
+<style>
+.big-font {
+    font-size:35px !important;
+}
+</style>
+""", unsafe_allow_html=True)
+st.markdown(f'<center><p class="big-font">Shap Bar Plot for <i>{top_pred}</i> Prediction</p></center>', unsafe_allow_html=True)
+st.pyplot(bar_plot, clear_figure=True)
+
+st.markdown('<center><p class="big-font">Shap Interactive Force Plot</p></center>', unsafe_allow_html=True)
+components.html(force_plot, height=output_height, width=output_width, scrolling=True)

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+transformers
+shap
+torch
+matplotlib
+numpy