File size: 2,157 Bytes
7b3478d f30d304 05fa263 f30d304 7b3478d 05fa263 7b3478d 05fa263 7b3478d 05fa263 7b3478d 05fa263 7b3478d 05fa263 7b3478d 05fa263 7b3478d 05fa263 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | 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, 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)]
"""
# Load model
model = load_word2vec_model(f'models/{time_slice_model}.model')
model_dict = model_dictionary(model)
# Extract vectors and names from model_dict
all_vector_names = list(model_dict.keys())
all_vectors = list(model_dict.values())
# Scale vectors
scaler = StandardScaler()
vectors_scaled = scaler.fit_transform(all_vectors)
# Make t-SNE model and fit it to the scaled vectors
tsne_model = TSNE(n_components=3, random_state=0)
tsne_result = tsne_model.fit_transform(vectors_scaled)
# Associate the names with the 3D representations
result_with_names = [(all_vector_names[i], tsne_result[i]) for i in range(len(all_vector_names))]
# Only keep the vectors that are in vectors_list and their cosine similarities
result_with_names = [r for r in result_with_names if r[0] in [v[0] for v in vectors_list]]
result_with_names = [(r[0], r[1], [v[3] for v in vectors_list if v[0] == r[0]][0]) for r in result_with_names]
# 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 {word}')
return fig, df
|