plots.py

import streamlit as st
import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
import umap
import pandas as pd
from word2vec import *
from sklearn.preprocessing import StandardScaler
import plotly.express as px
from sklearn.manifold import TSNE


def make_3d_plot_tSNE(vectors_list, target_word, time_slice_model):
    """
        Turn list of 100D vectors into a 3D plot using t-SNE and Plotly.
        List structure: [(word, model_name, vector, cosine_sim)]
    """
    word = target_word
    
    # Load model
    model = load_word2vec_model(f'models/{time_slice_model}.model')
        
    # Extract vectors and names from ./3d_models/{time_slice_model}.model
    all_vectors = {}
    with open(f'./3d_models/{time_slice_model}.model', 'rb') as f:
        result_with_names = pickle.load(f)
        
    for word, vector in result_with_names:
        all_vectors[word] = vector
    
    
    
    # Only keep the vectors that are in vectors_list and their cosine similarities
    result_with_names = [(word, all_vectors[word], cosine_sim) for word, _, _, cosine_sim in vectors_list]

    
    
    # Create DataFrame from the transformed vectors
    df = pd.DataFrame(result_with_names, columns=['word', '3d_vector', 'cosine_sim'])
    
    # Sort dataframe by cosine_sim
    df = df.sort_values(by='cosine_sim', ascending=False)
    
    
    x = df['3d_vector'].apply(lambda v: v[0])
    y = df['3d_vector'].apply(lambda v: v[1])
    z = df['3d_vector'].apply(lambda v: v[2])
        
    # Plot
    fig = px.scatter_3d(df, x=x, y=y, z=z, text='word', color='cosine_sim', color_continuous_scale='Reds')
    fig.update_traces(marker=dict(size=5))
    fig.update_layout(title=f'3D plot of nearest neighbours to {target_word}')
    
    return fig, df