Update app.py

app.py

@@ -1,14 +1,118 @@
 import streamlit as st
+import pandas as pd
 from transformers import pipeline
+
+from pprint import pprint
+from datasets import load_dataset
+from torch.utils.data import DataLoader
+
 st.title("CS634 - milestone2 - Tedi Pano")
 
-sentiment_model = pipeline("sentiment-analysis")
+@st.cache_resource
+def load_data():
+    dataset_dict = load_dataset('HUPD/hupd',
+        name='sample',
+        data_files="https://huggingface.co/datasets/HUPD/hupd/blob/main/hupd_metadata_2022-02-22.feather", 
+        icpr_label=None,
+        train_filing_start_date='2016-01-01',
+        train_filing_end_date='2016-01-21',
+        val_filing_start_date='2016-01-22',
+        val_filing_end_date='2016-01-31',
+    )
+
+    st.write('Loading is done!')
+    return dataset_dict
+
+@st.cache_resource
+def training_computation(_dataset_dict):
+    df = pd.DataFrame(_dataset_dict['train'])
+    vf = pd.DataFrame(_dataset_dict['validation'])
+    
+    accepted_rejected = ['ACCEPTED', 'REJECTED']
+    df = df[df['decision'].isin(accepted_rejected)]
+    df['patentability_score'] = df['decision'].map({'ACCEPTED': 1, 'REJECTED': 0})
+    vf = vf[vf['decision'].isin(accepted_rejected)]
+    vf['patentability_score'] = vf['decision'].map({'ACCEPTED': 1, 'REJECTED': 0})
+    
+    st.write("Processed the data")
+    
+    
+    from sklearn.model_selection import train_test_split
+    dftrain, dftest = train_test_split(df, test_size = 0.90, random_state = 0)
+    
+    from transformers import DistilBertTokenizerFast
+    tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')
+    
+    X_dtrain = dftrain['abstract'].tolist()
+    y_dtrain = dftrain['patentability_score'].tolist()
+    
+    X_vtrain = vf['abstract'].tolist()
+    y_vtrain = vf['patentability_score'].tolist()
+    
+    X_dtest = dftest['abstract'].tolist()
+    y_dtest = dftest['patentability_score'].tolist()
+    
+    train_encodings = tokenizer(X_dtrain, truncation=True, padding=True)
+    val_encodings = tokenizer(X_vtrain, truncation=True, padding=True)
+    test_encodings = tokenizer(X_dtest, truncation=True, padding=True)
+    
+    st.write("tokenizing completed!")
+    
+    import tensorflow as tf
+    
+    train_dataset = tf.data.Dataset.from_tensor_slices((
+        dict(train_encodings),
+        y_dtrain
+    ))
+    
+    val_dataset = tf.data.Dataset.from_tensor_slices((
+        dict(val_encodings),
+        y_vtrain
+    ))
+    
+    test_dataset = tf.data.Dataset.from_tensor_slices((
+        dict(test_encodings),
+        y_dtest
+    ))
+    
+    st.write("back to dataset!")
+    
+    from transformers import TFDistilBertForSequenceClassification, TFTrainer, TFTrainingArguments
+    
+    training_args = TFTrainingArguments(
+        output_dir='./results',          
+        num_train_epochs=2,              
+        per_device_train_batch_size=16, 
+        per_device_eval_batch_size=16,   
+        warmup_steps=500,
+        eval_steps=500, 
+        weight_decay=0.01               
+    )
+    
+    
+    with training_args.strategy.scope():
+        model = TFDistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")
+    
+    trainer = TFTrainer(
+        model=model,                         
+        args=training_args,                  
+        train_dataset=train_dataset,         
+        eval_dataset=val_dataset             
+    )
 
-with st.form("my_form"):
-    text_input = st.text_input("Enter in a sentence for sentiment analysis" , "I love you so much it hurts sometimes.")
-    submitted = st.form_submit_button("Submit")
+    trainer.train()
 
+    st.write("training completed")
+    return trainer
     
-    if submitted:
-        output = sentiment_model(text_input)
-        st.write("The sentiment analysis for '" + text_input+ "' is " + output[0]['label'] + " with a certainty score of " + str(output[0]['score']))
+
+dataset_dict = load_data()
+trainer = training_computation(dataset_dict)
+
+
+patents = pd.DataFrame(dataset_dict['train'])
+patent_selection = st.selectbox("Select Patent",patents['patent_number'])
+
+patent = patents.loc[patents['patent_number'] == patent_selection]
+st.write(patent['abstract'])
+st.write(patent['claims'])