registries_analysis/notebooks/01.4-exploration-fairsharing.ipynb

In [1]:

import ast
import csv
import json

import numpy as np
import pandas as pd

import plotly
from plotly.offline import iplot, init_notebook_mode
import plotly.graph_objs as go
import plotly.express as px

pd.set_option('display.max_columns', None)

Loading datasets¶

In [2]:

fairsharing_df = pd.read_csv('../data/raw/FAIRsharingDBrec_summary20210304.csv', 
                             delimiter='|', header=0,
                             names=['full_name', 'short_name', 'fs_url', 'url', 'countries', 'subjects'])
fairsharing_df.head()

Out[2]:

	full_name	short_name	fs_url	url	countries	subjects
0	GenBank	GenBank	https://fairsharing.org/10.25504/FAIRsharing.9...	https://www.ncbi.nlm.nih.gov/genbank/	European Union,Japan,United States	Bioinformatics,Data Management,Data Submission...
1	GlycoNAVI	GlycoNAVI	https://fairsharing.org/10.25504/FAIRsharing.w...	https://glyconavi.org/	Japan	Chemistry,Glycomics,Life Science,Organic Chemi...
2	ADHDgene	ADHDgene	https://fairsharing.org/10.25504/FAIRsharing.m...	http://adhd.psych.ac.cn/	China	Biomedical Science,Genetics
3	Allele frequency resource for research and tea...	ALFRED	https://fairsharing.org/10.25504/FAIRsharing.y...	http://alfred.med.yale.edu	United States	Life Science
4	Animal Transcription Factor Database	AnimalTFDB	https://fairsharing.org/10.25504/FAIRsharing.e...	http://bioinfo.life.hust.edu.cn/AnimalTFDB/	China	Life Science

In [3]:

fairsharing_df.describe(include='all')

Out[3]:

	full_name	short_name	fs_url	url	countries	subjects
count	1752	1752	1752	1752	1749	1690
unique	1752	1741	1752	1752	178	834
top	Brassica Information Portal	CGD	https://fairsharing.org/10.25504/FAIRsharing.e...	http://web.iodp.tamu.edu/LORE/	United States	Life Science
freq	1	3	1	1	588	367

In [4]:

fairsharing_df.isna().sum()

Out[4]:

full_name      0
short_name     0
fs_url         0
url            0
countries      3
subjects      62
dtype: int64