def test_here(tmp_path):
# create dummy project
f1 = tmp_path / "proj" / "src"
f1.mkdir(parents=True, exist_ok=True)
f2 = tmp_path / "proj" / "data"
f2.mkdir(parents=True, exist_ok=True)
# create a .here file at the project root
tmp_path.joinpath("proj").joinpath(".here").touch()
# create a fake data file
f2.joinpath("data.csv").touch()
# set working dir to the src directory
if sys.version_info[0] == 2:
chdir(str(f1))
else:
chdir(f1)
herepath = here("data", "data.csv")
assert herepath.resolve() == f2.joinpath("data.csv").resolve()
import pandas as pd
import requests
import urllib.request
from pyhere import here
dataset = pd.read_csv(here('data', 'Uniprot', 'ZambeziensisUniprot.csv'), skiprows=[0], header=None, index_col=False)
print(len(dataset))
obsolete = []
row = 0
for i in dataset.itertuples():
## retrieve the sequences using Uniprot IDs from the Uniprot website
uniprotID = dataset.iloc(axis=0)[row, 0]
url = 'https://www.uniprot.org/uniprot/'+ uniprotID +'.fasta'
row = row + 1\
try:
with urllib.request.urlopen(url) as url:
## read the content from the url and decode it
page = url.read()
seq = page.decode('utf8')
## open and write a new fasta file with all the sequences corresponding to the Uniprot IDs stored in the csv file
with open(here('data', 'fasta', 'Rhipicephalus_zambeziensis.fasta'), 'a') as ffasta:
ffasta.write(seq)
if len(seq) == 0:
obsolete.append(row)
except:
def dir_path(*args) -> PosixPath:
if isinstance(dirname, str):
return here(dirname, *args)
else:
return here(*dirname, *args)
# # columns = ['tum_lymfklieren_positief_atl']
# X = X.loc[:, columns]
# print(X.head(20))
#
# gen_cont = GeneralizeContinuous(n_bins=10, strategy='quantile', labeled_missing=[999])
# # X = X.dropna()
#
# gen_cont.fit(X)
# X_cat = gen_cont.transform(X)
# print(X_cat)
#
# X_inv = gen_cont.inverse_transform(X_cat)
# print(X_inv)
# print(gen_cont.bin_edges_)
data_path = here("examples/data/input/adult_9c.csv")
df = pd.read_csv(data_path, delimiter=', ').astype(str)
print(df.head())
df_s = df[['native-country', 'occupation']]
# epsilon = float(np.inf)
epsilon = 0.1
gen_cat = GeneralizeCategorical(epsilon=epsilon, n_bins=5)
gen_cat.fit(df_s)
df_sT = gen_cat.transform(df_s)
df_sT = pd.DataFrame(df_sT, columns=df_s.columns)
df_sI = pd.DataFrame(gen_cat.inverse_transform(df_sT),
columns=df_s.columns)
visual.compare_value_counts(df_s, df_sI)
import pandas as pd
import requests
import urllib.request
from pyhere import here
from Bio import Entrez
dataset = pd.read_csv(here('data', 'Uniprot', 'ScapularisNCBI.csv'),
skiprows=[0],
header=None,
index_col=False)
outFile = here('data', 'fasta', 'Ixodes_scapularis.fasta')
print(len(dataset))
obsolete = []
row = 0
for i in dataset.itertuples():
## retrieve the sequences using Uniprot IDs from the Uniprot website
uniprotID = dataset.iloc(axis=0)[row, 0]
row = row + 1\
try:
with Entrez.efetch(db='protein', id=uniprotID,
rettype='fasta') as handle:
## read the content from the Entrez database
seq = handle.read()
## open and write a new fasta file with all the sequences corresponding to the Uniprot IDs stored in the csv file
with open(outFile, 'a') as ffasta:
def dir_path(*args) -> PosixPath:
if type(dirname) == str:
return here(dirname, *args)
else:
return here(*dirname, *args)
import pandas as pd
import requests
import urllib.request
from pyhere import here
from Bio import Entrez
dataset = pd.read_csv(here('data', 'Uniprot', 'moubataUniprot.csv'),
skiprows=[0],
header=None,
index_col=False)
outFile = here('data', 'fasta', 'Ornithodoros_moubata2.fasta')
print(len(dataset))
obsolete = []
row = 0
for i in dataset.itertuples():
## retrieve the sequences using Uniprot IDs from the Uniprot website
uniprotID = dataset.iloc(axis=0)[row, 0]
url = 'https://www.uniprot.org/uniprot/' + uniprotID + '.fasta'
row = row + 1\
try:
with urllib.request.urlopen(url) as url:
## read the content from the url and decode it
page = url.read()
seq = page.decode('utf8')
## open and write a new fasta file with all the sequences corresponding to the Uniprot IDs stored in the csv file