add initial app

app.py

@@ -0,0 +1,43 @@
+import streamlit as st
+import transformers
+import matplotlib.pyplot as plt
+
+@st.cache(allow_output_mutation=True)
+def get_pipe():
+    model_name = "joeddav/distilbert-base-uncased-go-emotions-student"
+    model = transformers.AutoModelForSequenceClassification.from_pretrained(model_name)
+    tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+    pipe = transformers.pipeline('text-classification', model=model, tokenizer=tokenizer, return_all_scores=True, truncation=True)
+    return pipe
+
+def sort_predictions(predictions):
+    return sorted(predictions, key=lambda x: x['score'], reverse=True)
+
+st.set_page_config(page_title="Emotion Prediction")
+st.title("Emotion Prediction")
+st.write("Type text into the text box and then press 'Predict' to get the predicted emotion.")
+
+with st.spinner("Loading model..."):
+    pipe = get_pipe()
+
+text = st.text_area('Enter text here:')
+submit = st.button('Predict')
+
+if submit:
+    
+    prediction = pipe(text)[0]
+    prediction = sort_predictions(prediction)
+
+    fig, ax = plt.subplots()
+    ax.bar(x=[i for i, _ in enumerate(prediction)],
+           height=[p['score'] for p in prediction],
+           tick_label=[p['label'] for p in prediction])
+    ax.tick_params(rotation=90)
+    ax.set_ylim(0, 1)
+    
+    st.header('Prediction:')
+    st.pyplot(fig)
+
+    prediction = dict([(p['label'], p['score']) for p in prediction])
+    st.header('Raw values:')
+    st.json(prediction)