Created streamlit app

README.md

@@ -1,6 +1,13 @@
 # Datamining Project
 
-Milestone 1
+Milestone 2
+
+```yaml
+title: Toxic Tweets
+sdk: streamlit
+app_file: app/main.py
+pinned: false
+```
 
 ## Requirements
 

app/main.py

@@ -1,4 +1,34 @@
-print("Hello, world!")
+import streamlit as st
+from transformers import AutoTokenizer
+from transformers import (
+    TFAutoModelForSequenceClassification as AutoModelForSequenceClassification,
+)
+from transformers import pipeline
 
-while 1:
-    continue
+st.title("Toxic Tweets")
+
+text = st.text_area("Input text", "", height=275)
+
+model_name = st.selectbox(
+    "Select the model you want to use below.",
+    (
+        "distilbert-base-uncased-finetuned-sst-2-english",
+        "cardiffnlp/twitter-roberta-base-sentiment",
+        "finiteautomata/bertweet-base-sentiment-analysis",
+        "ProsusAI/finbert",
+    ),
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+clf = pipeline(
+    "sentiment-analysis", model=model, tokenizer=tokenizer, return_all_scores=True
+)
+
+input = tokenizer(text, return_tensors="tf")
+
+if st.button("Submit", type="primary"):
+    results = clf(text)[0]
+    classes = dict(d.values() for d in results)
+    # st.write(f"The sentiment is {results}.")
+    st.bar_chart(classes)

app/requirements.txt

@@ -0,0 +1,88 @@
+absl-py==1.4.0
+altair==4.2.2
+astunparse==1.6.3
+attrs==22.2.0
+blinker==1.6
+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==2.0.7
+gast==0.4.0
+gitdb==4.0.10
+GitPython==3.1.31
+google-auth==2.17.2
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+grpcio==1.53.0
+h5py==3.8.0
+huggingface-hub==0.13.3
+idna==3.4
+importlib-metadata==6.1.0
+Jinja2==3.1.2
+jsonschema==4.17.3
+keras==2.11.0
+keras-nlp==0.4.1
+libclang==16.0.0
+Markdown==3.4.3
+markdown-it-py==2.2.0
+MarkupSafe==2.1.2
+mdurl==0.1.2
+numpy==1.24.2
+oauthlib==3.2.2
+onnx==1.12.0
+onnxconverter-common==1.13.0
+opt-einsum==3.3.0
+packaging==23.0
+pandas==1.5.3
+Pillow==9.5.0
+protobuf==3.19.6
+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
+semver==3.0.0
+six==1.16.0
+smmap==5.0.0
+streamlit==1.20.0
+tensorboard==2.11.2
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.11.1
+tensorflow-cpu==2.11.1
+tensorflow-estimator==2.11.0
+tensorflow-hub==0.13.0
+tensorflow-io-gcs-filesystem==0.32.0
+tensorflow-text==2.11.0
+termcolor==2.2.0
+tf2onnx==1.14.0
+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
+Werkzeug==2.2.3
+wrapt==1.15.0
+zipp==3.15.0