import pickle
import numpy as np
import pandas as pd
import tensorflow as tf
from tensorflow.keras.layers.experimental.preprocessing import TextVectorization
import tensorflow_hub as hub
from sklearn.preprocessing import LabelEncoder
from spacy.lang.en import English
import streamlit as st


file7 = open('pub_text_vectorizer.pkl', 'rb')
pre = pickle.load(file7)
new_v = TextVectorization.from_config(pre['config'])
new_v.set_weights(pre['weights'])
file7.close()

file8 = open('pub_label_encoder.pkl', 'rb')
label_encoder = pickle.load(file8)
file8.close()

new_model = tf.keras.models.load_model('pubmed_model.h5',
                                       custom_objects={'KerasLayer': hub.KerasLayer})

st.title('Medical Abstract Reader')


text = st.text_area('Classify medical abstract into various categories.', height=600, key='text')

submit = st.button('Predict')

def clear_text():
    st.session_state["text"] = ""

clear = st.button("Clear text input", on_click=clear_text)

if submit:
    if text is not None:
        df = []
        df = pd.DataFrame(df, columns=['abstract'])
        df.loc[0] = [text]
        nlp = English()
        sentencizer = nlp.add_pipe("sentencizer")
        doc = nlp(df['abstract'][0])
        abstract_lines = [str(sent) for sent in list(doc.sents)]
        total_lines_in_sample = len(abstract_lines)
        sample_lines = []
        for i, line in enumerate(abstract_lines):
            sample_dict = {}
            sample_dict["text"] = str(line)
            sample_dict["line_number"] = i
            sample_dict["total_lines"] = total_lines_in_sample - 1
            sample_lines.append(sample_dict)

        test = pd.DataFrame(sample_lines)
        testing_sentences = test['text'].tolist()
        new_v.adapt(testing_sentences)
        testing_dataset = tf.data.Dataset.from_tensor_slices((testing_sentences))
        testing_dataset = testing_dataset.batch(32).prefetch(tf.data.AUTOTUNE)
        new_model_probs = new_model.predict(testing_dataset)
        new_model_preds = tf.argmax(new_model_probs, axis=1)
        test_pred_classes = [label_encoder.classes_[pred] for pred in new_model_preds]
        test["prediction"] = test_pred_classes  # create column with test prediction class names
        test["pred_prob"] = tf.reduce_max(new_model_probs, axis=1).numpy()
        dict_abstract = enumerate(abstract_lines)

        for i, line in dict_abstract:
            st.write(f'{test_pred_classes[i]} : {line}')