eric-czech

playerID,yearID,stint,teamID,lgID,G,AB,R,H,2B,3B,HR,RBI,SB,CS,BB,SO,IBB,HBP,SH,SF,GIDP
abercda01,1871,1,TRO,NA,1,4,0,0,0,0,0,0,0,0,0,0,,,,,0
addybo01,1871,1,RC1,NA,25,118,30,32,6,0,0,13,8,1,4,0,,,,,0
allisar01,1871,1,CL1,NA,29,137,28,40,4,5,0,19,3,1,2,5,,,,,1
allisdo01,1871,1,WS3,NA,27,133,28,44,10,2,2,27,1,1,0,2,,,,,0
ansonca01,1871,1,RC1,NA,25,120,29,39,11,3,0,16,6,2,2,1,,,,,0
armstbo01,1871,1,FW1,NA,12,49,9,11,2,1,0,5,0,1,0,1,,,,,0
barkeal01,1871,1,RC1,NA,1,4,0,1,0,0,0,2,0,0,1,0,,,,,0
barnero01,1871,1,BS1,NA,31,157,66,63,10,9,0,34,11,6,13,1,,,,,1
barrebi01,1871,1,FW1,NA,1,5,1,1,1,0,0,1,0,0,0,0,,,,,0

eric-czech

eric-czech

def get_clustered_order(df: pd.DataFrame, metric: str='euclidean', method: str='average') -> pd.DataFrame:
    from scipy.cluster.hierarchy import linkage, leaves_list
    return leaves_list(linkage(df, metric=metric, method=method))

def get_clustered_dataframe(df: pd.DataFrame, fill_value: Any=None, **kwargs)  -> pd.DataFrame:
    dfs = df if fill_value is None else df.fillna(fill_value)
    return df.iloc[get_clustered_order(dfs, **kwargs), get_clustered_order(dfs.T, **kwargs)]

import plotly.express as px
px.imshow(get_clustered_dataframe(df))

eric-czech

taxon_id,gene_id,gene_symbol
9606,109951028,A-GAMMA3'E
9606,1,A1BG
9606,503538,A1BG-AS1
9606,29974,A1CF
9606,2,A2M
9606,144571,A2M-AS1
9606,144568,A2ML1
9606,100874108,A2ML1-AS1
9606,106478979,A2ML1-AS2

eric-czech

eric-czech

import requests
from urllib.parse import quote_plus

def get_info(disease):
    url_fmt = 'http://www.ebi.ac.uk/spot/zooma/v2/api/services/annotate?propertyValue={disease}&propertyType=disease&filter=ontologies:[efo]'
    url = url_fmt.format(disease=quote_plus(disease))
    print(url)
    res = requests.get(url).json()
    if len(res) == 0:
        return None

eric-czech

def search_efo(disease):
    import requests
    from urllib.parse import quote_plus
    res = requests.get(f"https://www.ebi.ac.uk/ols/api/select?q={quote_plus(disease)}&ontology=efo")
    res = res.json()
    docs = res['response']['docs']
    if len(docs) == 0:
        return None
    return docs[0]

eric-czech

eric-czech

library(ggplot2)

# For figure 2 of paper https://www.semanticscholar.org/paper/Dealing-with-Logs-and-Zeros-in-Regression-Models-Bellégo-Pape/546a6f45433b413721f9a60f0be8e3e2b69fe103
set.seed(1)
beta <- 1
x_max <- 1
x <- x_max * runif(10000)
y <- sapply(x, function(x) rpois(1, lambda=exp(beta * x + 1)))
df <- do.call(rbind, lapply(seq(.01, 1, by=.01), function(delta){
  beta_hat <- unname(lm(log(y + delta) ~ x)$coefficients['x'])

eric-czech

def get_ols(term):
    import requests
    url = 'http://www.ebi.ac.uk/ols/api/ontologies/efo/terms?obo_id=' + term
    res = requests.get(url)
    terms = res.json()['_embedded']['terms']
    assert len(terms) == 1
    return terms[0]