def login(self):
"""
login to the Dimensions API through their 'DSL'
"""
if not self.api_obj:
dimcli.login(
username=self.parent.config["DEFAULT"]["email"],
password=self.parent.config["DEFAULT"]["dimensions_password"])
self.api_obj = dimcli.Dsl(verbose=False)
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 15 11:10:11 2020
This script is for fetching dimensions data
@author: sahand
"""
import os
import gc
from tqdm import tqdm
import dimcli
import pandas as pd
import numpy as np
import json
dimcli.login(key="CC1FEFF8637149DBBA873831FCA4471F",endpoint="https://app.dimensions.ai")
# dimcli --init
# dimcli.login()
dsl = dimcli.Dsl()
# =============================================================================
# Query - get year by year
# =============================================================================
# data = dsl.query("""search publications for "black holes" return publications""")
# data = dsl.query("""search publications for "black holes" return publications""", verbose=False)
years = list(range(2018,2021))
for year in tqdm(years):
# year = 2016
# data = dsl.query_iterative(r"""search publications for "\"artificial intelligence\"" where year="""+str(year)+
# """ and (type="article" or type="proceeding") and times_cited > 0
#
# startup file for ipython
#
# used to generate a new version of the grammar_dsl.py file
#
import json
import dimcli
dimcli.login("test")
dsl = dimcli.Dsl()
data = dsl.query("describe schema").json
with open("dimcli/core/dsl_grammar_core_NEW.py", "w") as f:
f.write("GRAMMAR_DICT = " + str(data))
# Also, how to normalize the nested json data formats.
# Lastly, the script to concatenating several normalized datasets together
# import required libraries
import pandas as pd
import numpy as np
import json
import requests
!pip install dimcli -U
# I have created a local credential. Otherwise, can try log in with user name and password. Details in the Dimensions API lab: https://docs.dimensions.ai/dsl
import dimcli
dimcli.login()
dsl = dimcli.Dsl()
dimcli.login()
# create a list for researchers' ids
researcher_id = ['ur.01215450000.22','ur.011725645715.40','ur.01244272356.36','ur.01105074143.21','ur.01033403276.88',
'ur.015324333431.33','ur.0720260005.12','ur.0665714166.39']
# Use iterative to query all researchers within UR
data = dsl.query_iterative("""search researchers
where research_orgs in ["grid.461628.f", "grid.412750.5", "grid.414078.e", "grid.416663.0"]
and obsolete=0 return researchers""")
# There is a column called "id" which is the Dimensions id of the researchers.
import descartes
import networkx as nx
import plotly.express as px
import itertools
from tqdm.notebook import tqdm as pbar
if not 'google.colab' in sys.modules:
# make js dependecies local / needed by html exports
from plotly.offline import init_notebook_mode
init_notebook_mode(connected=True)
import getpass
USERNAME = getpass.getpass(prompt='*****@*****.**' )
PASSWORD = getpass.getpass(prompt='')
dimcli.login(username ="******" , password = "" )
else:
dimcli.login(username ="******" , password = "" )
dsl = dimcli.Dsl()
#------------------------------------------------------------
KEYWORD = "10.1080/20013078.2018.1535750"
q = f"""search publications
where research_orgs="grid.117476.2"
for "\\"{KEYWORD}\\""
return publications[id+title+times_cited+altmetric+concepts_scores]
"""