app.py

import streamlit as st
from streamlit_option_menu import option_menu
from word2vec import *
import pandas as pd
from autocomplete import *
from vector_graph import *
from plots import *
from lsj_dict import *
import json
from streamlit_tags import st_tags, st_tags_sidebar


st.set_page_config(page_title="Ancient Greek Word2Vec", layout="centered")

# Cache data
@st.cache_data
def load_lsj_dict():
    return json.load(open('lsj_dict.json', 'r'))

@st.cache_data
def load_all_models_words():
    return sorted(load_compressed_word_list('corpora/compass_filtered.pkl.gz'), key=custom_sort)

@st.cache_data
def load_models_for_word_dict():
    return word_in_models_dict('corpora/compass_filtered.pkl.gz')


@st.cache_data
def load_all_lemmas():
    return load_compressed_word_list('all_lemmas.pkl.gz')

# Load compressed word list
all_models_words = load_all_models_words()


# Prepare lsj dictionary
lemma_dict = load_lsj_dict()

# Load dictionary with words as keys and eligible models as values
models_for_word_dict = load_models_for_word_dict()


# Set styles for menu
styles = {
    "container": {"display": "flex", "justify-content": "center"},
    "nav": {"display": "flex", "gap": "2px", "margin": "5px"},
    "nav-item": {"flex": "1", "font-family": "Sans-serif"},
    "nav-link": {
        "background-color": "#f0f0f0",
        "border": "1px solid #ccc",
        "border-radius": "5px",
        "padding": "10px",
        "width": "100px",  
        "height": "60px",  
        "display": "flex",
        "align-items": "center",
        "justify-content": "center",
        "transition": "background-color 0.3s, color 0.3s",
        "color": "black",
        "text-decoration": "none"
    },
    "nav-link:hover": {
        "background-color": "rgb(238, 238, 238)",
        "color": "#000"
    },
    "nav-link-selected": {
        "background-color": "rgb(254, 74, 75)",
        "color": "white",
        "font-weight": "bold"
    },
    "icon": {"display": "None"}
}

# Horizontal menu
active_tab = option_menu(None, ["Nearest neighbours", "Cosine similarity", "3D graph", 'Dictionary', 'About', 'FAQ'], 
    menu_icon="cast", default_index=0, orientation="horizontal", styles=styles)


# Adding CSS style to remove list-style-type
st.markdown("""
<style>
/* Define a class to remove list-style-type */
.no-list-style {
    list-style-type: none;
}
</style>
""", unsafe_allow_html=True)



# Nearest neighbours tab
if active_tab == "Nearest neighbours":
    
    # All models in a list
    eligible_models = ["Archaic", "Classical", "Hellenistic", "Early Roman", "Late Roman"]
    all_models_words = load_all_models_words()
    
    with st.container():
        st.markdown("## Nearest Neighbours")
        st.markdown('###### Here you can extract the nearest neighbours to a chosen lemma. Please select one or more time slices and the preferred number of nearest neighbours.')
        target_word = st.multiselect("Enter a word", options=all_models_words, max_selections=1)
        if len(target_word) > 0:
            target_word = target_word[0]
            
            eligible_models = models_for_word_dict[target_word]
        
        models = st.multiselect(
            "Select models to search for neighbours",
            eligible_models
            )
        n = st.slider("Number of neighbours", 1, 50, 15)
        
        nearest_neighbours_button = st.button("Find nearest neighbours")

    if nearest_neighbours_button:
        if validate_nearest_neighbours(target_word, n, models) == False:
            st.error('Please fill in all fields')
        else:
            # Rewrite models to list of all loaded models
            models = load_selected_models(models)
            
            nearest_neighbours = get_nearest_neighbours(target_word, n, models)
            
            all_dfs = []
                            
            # Create dataframes
            for model in nearest_neighbours.keys():
                st.write(f"### {model}")
                df = pd.DataFrame(
                    nearest_neighbours[model],
                    columns = ['Word', 'Cosine Similarity']
                )

                all_dfs.append((model, df))
                st.table(df)        
            
            
            # Store content in a temporary file
            tmp_file = store_df_in_temp_file(all_dfs)
            
            # Open the temporary file and read its content
            with open(tmp_file, "rb") as file:
                file_byte = file.read()
                
                # Create download button
                st.download_button(
                    "Download results",
                    data=file_byte,
                    file_name = f'nearest_neighbours_{target_word}_TEST.xlsx',
                    mime='application/octet-stream'
                    )
                
   
# Cosine similarity tab
elif active_tab == "Cosine similarity":
    all_models_words = load_all_models_words()
    
    with st.container():
        eligible_models_1 = []
        eligible_models_2 = []
        st.markdown("## Cosine similarity")
        st.markdown('###### Here you can extract the cosine similarity between two lemmas. Please select a time slice for each lemma. You can also calculate the cosine similarity between two vectors of the same lemma in different time slices.')
        col1, col2 = st.columns(2)
        col3, col4 = st.columns(2)
        with col1:
            word_1 = st.multiselect("Enter a word", placeholder="πατήρ", max_selections=1, options=all_models_words)
            if len(word_1) > 0:
                word_1 = word_1[0]
                eligible_models_1 = models_for_word_dict[word_1]
                
        with col2:
            time_slice_1 = st.selectbox("Time slice word 1", options = eligible_models_1)


        with st.container():
            with col3:
                word_2 = st.multiselect("Enter a word", placeholder="μήτηρ", max_selections=1, options=all_models_words)
                if len(word_2) > 0:
                    word_2 = word_2[0]
                    eligible_models_2 = models_for_word_dict[word_2]
                
            with col4:
                time_slice_2 = st.selectbox("Time slice word 2", eligible_models_2)
    
        # Create button for calculating cosine similarity
        cosine_similarity_button = st.button("Calculate cosine similarity")
    
    # If the button is clicked, execute calculation
    if cosine_similarity_button:
        cosine_simularity_score = get_cosine_similarity(word_1, time_slice_1, word_2, time_slice_2)
        st.write(cosine_simularity_score)

# 3D graph tab
elif active_tab == "3D graph":
    st.markdown("## 3D graph")
    st.markdown('###### Here you can generate a 3D representation of the semantic space surrounding a target lemma. Please choose the lemma and the time slice.')
    
    col1, col2 = st.columns(2)
    
    # Load compressed word list
    all_models_words = load_all_models_words()
    
    with st.container():
        with col1:
            word = st.multiselect("Enter a word", all_models_words, max_selections=1)
            if len(word) > 0:
                word = word[0]
            
        with col2:
            time_slice = st.selectbox("Time slice", ["Archaic", "Classical", "Hellenistic", "Early Roman", "Late Roman"])

        n = st.slider("Number of words", 1, 50, 15)

        graph_button = st.button("Create 3D graph")
        
        if graph_button:
            time_slice_model = convert_time_name_to_model(time_slice)
            nearest_neighbours_vectors = get_nearest_neighbours_vectors(word, time_slice_model, n)
            # nearest_neighbours_3d_vectors = create_3d_vectors(word, time_slice_model, nearest_neighbours_vectors)
            st.dataframe(nearest_neighbours_vectors)
            # new_3d_vectors = nearest_neighbours_to_pca_vectors(word, time_slice, nearest_neighbours_vectors)
            # st.dataframe(new_3d_vectors)
            
            
            fig, df = make_3d_plot4(nearest_neighbours_vectors, word, time_slice_model)
            
            st.dataframe(df)
            
            st.plotly_chart(fig) 
            
            
           
            
# Dictionary tab
elif active_tab == "Dictionary":
    
    with st.container():
        st.markdown('## Dictionary')
        st.markdown('###### Search a word in the Liddell-Scott-Jones dictionary (only Greek, no whitespaces).')


        all_lemmas = load_all_lemmas()
        
        # query_word = st.multiselect("Search a word in the LSJ dictionary", all_lemmas, max_selections=1)
        
        query_tag = st_tags(label='',
                            text = '',
                            value = [],
                            suggestions = all_lemmas,
                            maxtags = 1,
                            key = '1'
                            )
        
        # If a word has been selected by user
        if query_tag:
            st.write(f"### {query_tag[0]}")
            
            # Display word information
            if query_tag[0] in lemma_dict:
                data = lemma_dict[query_tag[0]]
            elif query_tag[0].capitalize() in lemma_dict: # Some words are capitalized in the dictionary
                data = lemma_dict[query_tag[0].capitalize()]
            else:
                st.error("Word not found in dictionary")
            
            # Put text in readable format
            text = format_text(data)
            
            
            st.markdown(format_text(data), unsafe_allow_html = True)
            
            
            
            st.markdown("""
                        <style>
                        .tab {
                            display: inline-block;
                            margin-left: 4em;
                        }
                        .tr {
                            font-weight: bold;
                        }
                        .list-class {
                            list-style-type: none;
                            margin-top: 1em;
                        }
                        .primary-indicator {
                            font-weight: bold;
                            font-size: x-large;
                        }
                        .secondary-indicator {
                            font-weight: bold;
                            font-size: large;
                        }
                        .tertiary-indicator {
                            font-weight: bold;
                            font-size: medium;
                        }
                        .quaternary-indicator {
                            font-weight: bold;
                            font-size: medium;
                        }
                        .primary-class {
                            padding-left: 2em;
                        }
                        .secondary-class {
                            padding-left: 4em;
                        }
                        .tertiary-class {
                            padding-left: 6em;
                        }
                        .quaternary-class {
                            padding-left: 8em;
                        }
                        </style>
                        """, unsafe_allow_html=True)
                    

# About tab
elif active_tab == "About":
    st.markdown("""
        ## About
        Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nullam nec purus nec nunc ultricies ultricies.
        """)


elif active_tab == "FAQ":
    st.markdown("""
        ## FAQ
        """)
    
    with st.expander("Which models is this interface based on?"):
        st.write(
                "This interface is based on five language models. \
                Language models are statistical models of language, \
                which store statistical information about word co-occurrence during the training phase. \
                During training they process a corpus of texts in the target language(s). \
                Once trained, models can be used to extract information about the language \
                (in this interface, we focus on the extraction of semantic information) or to perform specific linguistic tasks. \
                The models on which this interface is based are Word Embedding models."
                )
        
    with st.expander("Which corpus was used to train the models?"):
        st.write(
            "The five models on which this interface is based were trained on five slices of the Diorisis Ancient Greek Corpus (Vatri & McGillivray 2018)."
        )