def R_inegration():
r.setwd("~/tuning/")
parameters = irace.readParameters("parameters-acotsp.txt")
scenario = irace.readScenario(filename="scenario.txt",
scenario=irace.defaultScenario())
ans = irace(scenario=scenario, parameters=parameters)
def ComBat(X, batch, covariate=None, parametric=False, empirical_bayes=True, save_dir=None):
# Check X
if not isinstance(X, (pd.DataFrame, pd.Series)):
if isinstance(X, (list, tuple, np.ndarray, Mapping)):
df = pd.DataFrame(X)
else:
raise TypeError('X must be an array-like object, dictionary or pandas Dataframe/Series')
else:
df = X
row_names = df.index
r_df = pandas2ri.py2ri(df)
# Check covariate
if covariate is None:
covariate = np.ones((len(batch), 1))
else:
if not isinstance(covariate, (list, tuple, np.ndarray)):
if isinstance(covariate, pd.DataFrame) or isinstance(covariate, pd.Series):
covariate = covariate.to_numpy()
else:
raise TypeError('covariate array must be an array like or pandas Dataframe/Series')
else:
covariate = np.array(covariate)
if len(covariate.shape) == 1:
covariate = covariate.reshape(-1, 1)
elif len(covariate.shape) > 2:
raise ValueError('covariate array must be 1D or 2D')
nr, nc = covariate.shape
r_covariate = r.matrix(covariate, nrow=nr, ncol=nc)
# Check batch
if not isinstance(batch, (list, tuple, np.ndarray)):
if isinstance(batch, pd.DataFrame) or isinstance(batch, pd.Series):
batch = batch.to_numpy()
else:
raise TypeError('batch array must be an array like or pandas Dataframe/Series')
else:
batch = np.array(batch)
if len(batch.shape) != 1:
if len(batch.shape) == 2 and batch.shape[1] == 1:
batch.reshape(-1)
else:
raise ValueError('batch array must be 1D or 2D with second dimension equal to 1')
if len(np.unique(batch)) <= 1:
raise ValueError('batch array must have at least 2 classes')
r_batch = Vector(batch)
# cwd = os.path.dirname(sys.argv[0])
cwd = os.path.dirname(os.path.abspath(__file__))
r.setwd(cwd)
# r.source('./Statistical_analysis/R_scripts/ComBat.R')
r.source('./R_scripts/ComBat.R')
r_dr_results = r.ComBat_harmonization(r_df, r_covariate, r_batch, parametric, empirical_bayes)
R_object_dict = {}
keys = r_dr_results.names
for i in range(len(keys)):
R_object_dict[keys[i]] = np.array(r_dr_results[i])
results = pd.DataFrame(R_object_dict)
results.index = row_names
if save_dir is not None:
results.to_excel(os.path.join(save_dir, 'Features_ComBat.xlsx'))
return results
def report(configDict):
r('.libPaths("/home/pilat/R/i686-pc-linux-gnu-library/2.15/")')
r.setwd('/home/pilat/workspace/web_fEPSPA/media/')
knitr=importr("knitr")
md=importr("markdown")
for i in configDict.keys():
tmpString='%s<-"%s"' % (i,configDict[i])
r(tmpString)
o = knitr.spin("/home/pilat/workspace/PostProcessing_v.2/control.R", knit = r('FALSE'))
out = knitr.knit(o, output="/home/pilat/workspace/web_fEPSPA/Rinterface/control.md")
md.markdownToHTML("/home/pilat/workspace/web_fEPSPA/Rinterface/control.md","/home/pilat/workspace/web_fEPSPA/media/Routput.html")
def hierarchical_clust_parmar(self, X, y=None):
"""
Consensus Clustering with hierarchical clustering as described in :
Radiomic feature clusters and Prognostic Signatures specific for Lung and Head & Neck cancer.
Parmar et al., Scientific Reports, 2015
"""
df = pd.DataFrame(X)
r_df = pandas2ri.py2ri(df)
cwd = os.path.dirname(sys.argv[0])
r.setwd(cwd)
r.source(
'./Statistical_analysis/R_scripts/hierarchical_clustering_Parmar.R'
)
if self.cluster_reduction in self.cluster_reduction_methods:
r_dr_results = r.hierarchical_clustering_parmar(
r_df,
max_k=20,
threshold=1 - self.threshold,
corr_metric=self.corr_metric,
cluster_reduction=self.cluster_reduction)
else:
raise ValueError(
'cluster_reduction must be one of : %s. '
'%s was passed' %
(self.cluster_reduction_methods, self.cluster_reduction))
R_object_dict = {}
keys = r_dr_results.names
for i in range(len(keys)):
R_object_dict[keys[i]] = np.array(r_dr_results[i])
dr_results = pd.DataFrame(R_object_dict).to_numpy()
self.cluster_labels = dr_results[:, 0]
nb_cluster = np.amax(dr_results[:, 0]).astype(int)
coefficient_matrix = np.zeros(
(dr_results.shape[0],
nb_cluster)) # Shape of (n_features, nb cluster)
for i in range(nb_cluster):
coefficient_matrix[:, i] = np.where(dr_results[:, 0] == i + 1,
dr_results[:, 1], 0)
coefficient_matrix = coefficient_matrix.T
return coefficient_matrix
def compute_prob(size_sample,
prior_pg,
r_read_file_name="20k_test_elbos.csv",
prob_result_file="20k_test_prob_result.csv",
working_folder="./"):
# save args in a txt file for R script yo read
# todo don't run compute_prob in parallel... filename.txt will be changed
# names_file = prob_result_file[:-4] + '.txt'
# save_path = 'filenames_for_r/'
# if not os.path.exists(save_path):
# os.makedirs(save_path)
text_file = open('filename.txt', "w")
text_file.write(r_read_file_name)
text_file.write('\n')
text_file.write(prob_result_file)
text_file.write('\n')
text_file.write(working_folder)
text_file.write('\n')
text_file.write(str(size_sample))
text_file.write('\n')
text_file.write(str(prior_pg))
text_file.write('\n')
text_file.close()
# kernel and local ELBOs
# training_results = "20k_test_elbos.pkl",
# with open(training_results, "rb") as fin:
# valid_ker = pickle.load(fin)
# elbos = pickle.load(fin)
# save as csv file
# "kernels" "L_i"
# data = {'kernels': valid_ker,
# 'L_i': np.array(elbos).reshape(-1)}
# print(data)
# df = pd.DataFrame(data)
# print(df)
# df.to_csv(r_read_file_name, index=None)
# compute probability
r.setwd('~/BKS/src/R_bks')
r.source('bks_run_global_python.R')
def univariate_analysis(X, y, adjusted_method='BH', save_dir=None):
if not isinstance(X, (pd.DataFrame, pd.Series)):
if isinstance(X, (list, tuple, np.ndarray, Mapping)):
if len(np.array(X).shape) != 2:
raise ValueError('X array must 2D')
X = pd.DataFrame(X)
else:
raise TypeError('X must be an array-like object, dictionary or pandas Dataframe/Series')
if not isinstance(y, (list, tuple, np.ndarray)):
if isinstance(y, pd.DataFrame) or isinstance(y, pd.Series):
y = y.to_numpy()
else:
raise TypeError('y array must be an array like or pandas Dataframe/Series')
else:
y = np.array(y)
if len(y.shape) != 1:
if len(y.shape) == 2 and y.shape[1] == 1:
y.reshape(-1)
else:
raise ValueError('y array must be 1D or 2D with second dimension equal to 1')
if len(np.unique(y)) <= 1:
raise ValueError('y array must have at least 2 classes')
r_X = pandas2ri.py2ri(X)
r_y = Vector(y)
cwd = os.path.dirname(sys.argv[0])
r.setwd(cwd)
r.source('./Statistical_analysis/R_scripts/univariate_analysis.R')
r_dr_results = r.univariate_analysis(r_X, r_y, adjusted_method=adjusted_method)
R_object_dict = {}
keys = r_dr_results.names
for i in range(len(keys)):
R_object_dict[keys[i]] = np.array(r_dr_results[i])
results = pd.DataFrame(R_object_dict)
if save_dir is not None:
results.to_excel(os.path.join(save_dir, 'univariate_stats_analysis.xlsx'))
return results
valores_python = list(valores)
he = IntVector([10, 2, 23, 11, 14, 35, 46, 32, 13, 51, 27, 49])
ha = he
print r.var(he)[0]
print r.cov(ha, he)[0]
print r.cor(ha, he)[0]
# funções
sqr = robjects.r('function(x) x^2')
print(sqr)
print(sqr(2))
print(sqr(IntVector([4])))
print(sqr(IntVector([4,4])))
eleva3 = robjects.r('function(a){ return(a*a*a); }')
print(eleva3)
print(eleva3(2))
print(eleva3(IntVector([4])))
print(eleva3(IntVector([4,4])))
# utilitários
r.getwd()
r.setwd("c:/docs/mydir") # lançam exceções de python
r.dir() # Lista arquivos do cwd.
import ipdb; ipdb.set_trace()
valores_python = list(valores)
he = IntVector([10, 2, 23, 11, 14, 35, 46, 32, 13, 51, 27, 49])
ha = he
print r.var(he)[0]
print r.cov(ha, he)[0]
print r.cor(ha, he)[0]
# funções
sqr = robjects.r('function(x) x^2')
print(sqr)
print(sqr(2))
print(sqr(IntVector([4])))
print(sqr(IntVector([4, 4])))
eleva3 = robjects.r('function(a){ return(a*a*a); }')
print(eleva3)
print(eleva3(2))
print(eleva3(IntVector([4])))
print(eleva3(IntVector([4, 4])))
# utilitários
r.getwd()
r.setwd("c:/docs/mydir") # lançam exceções de python
r.dir() # Lista arquivos do cwd.
import ipdb
ipdb.set_trace()
robjects.globalenv["surv_data"] = pandas2ri.py2rpy(surv_data)
robjects.globalenv["surv_diff"] = r(
f"survdiff(Surv({OS}, {Censored})~group,surv_data,rho = 0)")
Pvalue = r("1 - pchisq(surv_diff$chisq, length(surv_diff$n) -1)")[0]
if ggsave and Pvalue < pvalue:
r.ggsave(r(
f"autoplot(survfit(Surv({OS}, {Censored})~group,surv_data), xlab = 'Time', ylab = 'Survival')+ggtitle('Pvalue = {Pvalue}')"
),
file=f"{path}/{gene}.pdf")
return Pvalue
if __name__ == "__main__":
# 设置数据路径
path = "/install/git/Bioinformatics_paper/胶质母细胞瘤微环境预后相关基因的TCGA数据库挖掘/"
r.setwd(path)
# 读取处理好的数据
sample = pd.read_csv(f"{path}sample.txt", sep="\t", index_col=0)
sample_Group = sample["Stromal_Group"]
# 读取处理好的基因表达数据
HT_HG_U133A_sample = pd.read_csv(f"{path}HT_HG_U133A_sample.txt",
sep="\t").dropna()
################# 方差分析(ANOVA) GeneExp_Subtype #################
# https://www.bioinfo-scrounger.com/archives/588/
with localconverter(ro.default_converter + pandas2ri.converter):
ANOVA_data_R = ro.conversion.py2rpy(
sample[["Stromal_score", "GeneExp_Subtype"]])
print(
r.summary(
r.aov(r("Stromal_score~GeneExp_Subtype"), data=ANOVA_data_R)))
