pages/5_research_hotspots.py

import os
import datetime
import faiss
import streamlit as st
import feedparser
import urllib
import cloudpickle as cp
import pickle
from urllib.request import urlopen
from summa import summarizer
import numpy as np
import matplotlib.pyplot as plt
import requests
import json
from scipy import ndimage

from langchain_openai import AzureOpenAIEmbeddings
from langchain.llms import OpenAI
from langchain_openai import AzureChatOpenAI

os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["AZURE_ENDPOINT"] = st.secrets["endpoint1"]
os.environ["OPENAI_API_KEY"] = st.secrets["key1"]
os.environ["OPENAI_API_VERSION"] = "2023-05-15"

embeddings = AzureOpenAIEmbeddings(
    deployment="embedding",
    model="text-embedding-ada-002",
    azure_endpoint=st.secrets["endpoint1"],
)

llm = AzureChatOpenAI(
        deployment_name="gpt4_small",
        openai_api_version="2023-12-01-preview",
        azure_endpoint=st.secrets["endpoint2"],
        openai_api_key=st.secrets["key2"],
        openai_api_type="azure",
        temperature=0.
    )


@st.cache_data
def get_feeds_data(url):
    # data = cp.load(urlopen(url))
    with open(url, "rb") as fp:
        data = pickle.load(fp)
    st.sidebar.success("Loaded data")
    return data

# feeds_link = "https://drive.google.com/uc?export=download&id=1-IPk1voyUM9VqnghwyVrM1dY6rFnn1S_"
# embed_link = "https://dl.dropboxusercontent.com/s/ob2betm29qrtb8v/astro_ph_ga_feeds_ada_embedding_18-Apr-2023.pkl?dl=0"
dateval = "27-Jun-2023"
feeds_link = "local_files/astro_ph_ga_feeds_upto_"+dateval+".pkl"
embed_link = "local_files/astro_ph_ga_feeds_ada_embedding_"+dateval+".pkl"
gal_feeds = get_feeds_data(feeds_link)
arxiv_ada_embeddings = get_feeds_data(embed_link)

@st.cache_data
def get_embedding_data(url):
    # data = cp.load(urlopen(url))
    with open(url, "rb") as fp:
        data = pickle.load(fp)
    st.sidebar.success("Fetched data from API!")
    return data

# url = "https://drive.google.com/uc?export=download&id=1133tynMwsfdR1wxbkFLhbES3FwDWTPjP"
url = "local_files/astro_ph_ga_embedding_"+dateval+".pkl"
e2d = get_embedding_data(url)
# e2d, _, _, _, _ = get_embedding_data(url)

ctr = -1
num_chunks = len(gal_feeds)
ctr = -1
num_chunks = len(gal_feeds)
all_text, all_titles, all_arxivid, all_links, all_authors, all_pubdates, all_old = [], [], [], [], [], [], []

for nc in range(num_chunks):

    for i in range(len(gal_feeds[nc].entries)):
        text = gal_feeds[nc].entries[i].summary
        text = text.replace('\n', ' ')
        text = text.replace('\\', '')
        all_text.append(text)
        all_titles.append(gal_feeds[nc].entries[i].title)
        all_arxivid.append(gal_feeds[nc].entries[i].id.split('/')[-1][0:-2])
        all_links.append(gal_feeds[nc].entries[i].links[1].href)
        all_authors.append(gal_feeds[nc].entries[i].authors)
        temp = gal_feeds[nc].entries[i].published
        datetime_object = datetime.datetime.strptime(temp[0:10]+' '+temp[11:-1], '%Y-%m-%d %H:%M:%S')
        all_pubdates.append(datetime_object)
        all_old.append((datetime.datetime.now() - datetime_object).days)

def make_time_excess_plot(midage = 0, tolage = 1, onlyolder = False):

    bw = 0.05
    sigma = 4.0
    mask = (np.abs(np.array(all_old) - midage*365) < tolage*365)

    if onlyolder == True:
        mask2 = (np.array(all_old) > midage*365 + tolage*365/2)
        a = np.histogram2d(e2d[0:,0][mask2], e2d[0:,1][mask2], bins=(np.arange(0,17,bw)), density=True)
    else:
        a = np.histogram2d(e2d[0:,0], e2d[0:,1], bins=(np.arange(0,17,bw)), density=True)
    b = np.histogram2d(e2d[0:,0][mask], e2d[0:,1][mask], bins=(np.arange(0,17,bw)), density=True)
    temp = b[0].T - a[0].T
    temp = ndimage.gaussian_filter(temp, sigma, mode='nearest')
    vscale = (np.nanpercentile(temp,99.5) - np.nanpercentile(temp,0.5))/2

    fig = plt.figure(figsize=(11,9))
    plt.pcolor(a[1][0:-1] + (a[1][1]-a[1][0])/2, a[2][0:-1] + (a[2][1]-a[2][0])/2,
               temp,cmap='bwr',
               vmin=-vscale,vmax=vscale); plt.colorbar()
    # plt.scatter(e2d[0:,0], e2d[0:,1],s=2,color='k',alpha=0.1)
    plt.title('excess research over the last %.1f yrs centered at %.1f yrs' %(tolage, midage))
    plt.axis([0,14,1,15])
    plt.axis('off')
    st.pyplot(fig)
    return

st.title('Research hotspots')
st.markdown('[Includes papers up to: `'+dateval+'`]')

midage = st.slider('Age', 0., 10., 0.)
tolage = st.slider('Period width', 0., 10., 1.)

st.markdown('Compare the research in a given time period to the full manifold.')
make_time_excess_plot(midage, tolage, onlyolder = False)

st.markdown('Compare the research in a given time period to research older than that.')
make_time_excess_plot(midage, tolage, onlyolder = True)