Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from datasets import load_dataset
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModel, Trainer, TrainingArguments, LineByLineTextDataset
+import json
+
+
+@st.cache()
+def get_model():
+    model = AutoModelForSequenceClassification.from_pretrained("siebert/sentiment-roberta-large-english", num_labels=2)
+    model.load_state_dict(torch.load('model'))
+    return model
+
+@st.cache()
+def get_tokenizer():
+    tokenizer = AutoTokenizer.from_pretrained("siebert/sentiment-roberta-large-english")
+    return tokenizer
+
+def make_prediction():
+    model = get_model()
+    tokenizer = tokenizer()
+    
+
+
+st.header("Sentiment analysis on twitter datasets")
+st.markdown("Here is a sentiment model further trained on a slice of a twitter dataset")
+st.markdown("""
+<img width=700px src='https://imagez.tmz.com/image/73/4by3/2020/10/05/735aaee2f6b9464ca220e62ef797dab0_md.jpg'> 
+""", unsafe_allow_html=True)
+
+text = st.text_area("Try typing something here! \n You will see how much better our model is compared to the base model! No kidding")
+# ^-- показать текстовое поле. В поле text лежит строка, которая находится там в данный момент
+
+### Loading and tokenizing data
+# data = load_dataset("carblacac/twitter-sentiment-analysis")
+# tokenizer = AutoTokenizer.from_pretrained("siebert/sentiment-roberta-large-english")
+# dataset = data.map(lambda xs: tokenizer(xs["text"], truncation=True, padding='max_length'))
+# dataset = dataset.rename_column("feeling", "labels")
+
+with st.form(key='input_form'):
+    to_analyze = st.text_input(label='Input text to be analyzed')
+    button = st.form_submit_button(label='Classify')
+if button:
+    if to_analyze:
+        make_prediction(to_analyze)
+    else:
+        st.markdown("Empty request. Please resubmit")
+
+# classifier = pipeline('sentiment-analysis', model="distilbert-base-uncased-finetuned-sst-2-english")
+# raw_predictions = classifier(text)
+# тут уже знакомый вам код с huggingface.transformers -- его можно заменить на что угодно от fairseq до catboost
+
+# st.markdown(f"{raw_predictions}")
+# выводим результаты модели в текстовое поле, на потеху пользователю