Merge pull request #1 from dbleek/milestone-2

.flake8

@@ -0,0 +1,2 @@
+[flake8]
+max-line-length=90

.github/workflows/deploy.yaml

@@ -0,0 +1,20 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://dbleek:$HF_TOKEN@huggingface.co/spaces/dbleek/cs-gy-6613-project-final main

README.md

@@ -1,8 +1,25 @@
+---
+title: CS-GY-6613 Project Milestone 2
+colorFrom: blue
+colorTo: red
+sdk: streamlit
+app_file: app.py
+pinned: false
+---
+
 # cs-gy-6613-project
 Project for CS-GY-6613 Spring 2023
 
+# Milestone 2
+
+Sentiment Analysis App: https://huggingface.co/spaces/dbleek/cs-gy-6613-project
+
+# Milestone 1
 For milestone 1, I used the quick start instructions from VS code to connect to a remote Ubuntu container:
 
 https://code.visualstudio.com/docs/devcontainers/containers#_quick-start-open-an-existing-folder-in-a-container
 
-![Alt text](milestone-1.jpg "Screenshot for Milestone 1")
+![Alt text](milestone-1.jpg "Screenshot for Milestone 1")
+
+
+

app.py

@@ -0,0 +1,26 @@
+import streamlit as st
+from transformers import (AutoTokenizer, TFAutoModelForSequenceClassification,
+                          pipeline)
+
+st.title("CS-GY-6613 Project Milestone 2")
+model_choices = (
+    "distilbert-base-uncased-finetuned-sst-2-english",
+    "j-hartmann/emotion-english-distilroberta-base",
+    "joeddav/distilbert-base-uncased-go-emotions-student",
+)
+
+with st.form("Input Form"):
+    text = st.text_area("Write your text here:", "CS-GY-6613 is a great course!")
+    model_name = st.selectbox("Select a model:", model_choices)
+    submitted = st.form_submit_button("Submit")
+
+if submitted:
+    model = TFAutoModelForSequenceClassification.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
+    res = classifier(text)
+    label = res[0]["label"].upper()
+    score = res[0]["score"]
+    st.markdown(
+        f"This text was classified as **{label}** with a confidence score of **{score}**."
+    )

requirements.txt

@@ -0,0 +1,87 @@
+absl-py==1.4.0
+altair==4.2.2
+astunparse==1.6.3
+attrs==22.2.0
+blinker==1.6.1
+cachetools==5.3.0
+certifi==2022.12.7
+charset-normalizer==3.1.0
+click==8.1.3
+decorator==5.1.1
+entrypoints==0.4
+filelock==3.10.7
+flatbuffers==23.3.3
+gast==0.4.0
+gitdb==4.0.10
+GitPython==3.1.31
+google-auth==2.17.1
+google-auth-oauthlib==1.0.0
+google-pasta==0.2.0
+grpcio==1.53.0
+h5py==3.8.0
+huggingface-hub==0.13.3
+idna==3.4
+importlib-metadata==6.2.1
+inquirerpy==0.3.4
+jax==0.4.8
+Jinja2==3.1.2
+jsonschema==4.17.3
+keras==2.12.0
+libclang==16.0.0
+Markdown==3.4.3
+markdown-it-py==2.2.0
+MarkupSafe==2.1.2
+mdurl==0.1.2
+ml-dtypes==0.0.4
+numpy==1.23.5
+oauthlib==3.2.2
+opt-einsum==3.3.0
+packaging==23.0
+pandas==1.5.3
+pfzy==0.3.4
+Pillow==9.5.0
+prompt-toolkit==3.0.38
+protobuf==3.20.3
+pyarrow==11.0.0
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pydeck==0.8.0
+Pygments==2.14.0
+Pympler==1.0.1
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0
+regex==2023.3.23
+requests==2.28.2
+requests-oauthlib==1.3.1
+rich==13.3.3
+rsa==4.9
+scipy==1.10.1
+six==1.16.0
+smmap==5.0.0
+streamlit==1.21.0
+tensorboard==2.12.1
+tensorboard-data-server==0.7.0
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.12.0
+tensorflow-estimator==2.12.0
+tensorflow-io-gcs-filesystem==0.32.0
+termcolor==2.2.0
+tokenizers==0.13.3
+toml==0.10.2
+toolz==0.12.0
+tornado==6.2
+tqdm==4.65.0
+transformers==4.27.4
+typing_extensions==4.5.0
+tzdata==2023.3
+tzlocal==4.3
+urllib3==1.26.15
+validators==0.20.0
+watchdog==3.0.0
+wcwidth==0.2.6
+Werkzeug==2.2.3
+wrapt==1.14.1
+zipp==3.15.0