Document is here. https://www.ncbi.nlm.nih.gov/books/NBK25501/
https://www.nlm.nih.gov/databases/download/terms_and_conditions.html
outputimage
import math
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import numpy as np
import pandas as pd
import plotly
import plotly.express as px
import requests
import urllib.parse
import uuid
import xml.etree.ElementTree as ET
from collections import OrderedDict
from sklearn.cluster import MiniBatchKMeans
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from tqdm import tqdm_notebook as tqdm
plotly.offline.init_notebook_mode(connected=False)