aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--wqflask/wqflask/my_pylmm/pyLMM/genotype.py2
-rw-r--r--wqflask/wqflask/my_pylmm/pyLMM/kinship.py4
-rw-r--r--wqflask/wqflask/my_pylmm/pyLMM/lmm.py4
-rw-r--r--wqflask/wqflask/my_pylmm/pyLMM/runlmm.py23
4 files changed, 18 insertions, 15 deletions
diff --git a/wqflask/wqflask/my_pylmm/pyLMM/genotype.py b/wqflask/wqflask/my_pylmm/pyLMM/genotype.py
index f5d9ee8c..315fd824 100644
--- a/wqflask/wqflask/my_pylmm/pyLMM/genotype.py
+++ b/wqflask/wqflask/my_pylmm/pyLMM/genotype.py
@@ -23,7 +23,7 @@ import operator
def replace_missing_with_MAF(snp_g):
"""
Replace the missing genotype with the minor allele frequency (MAF)
- in the snp row
+ in the snp row. It is rather slow!
"""
cnt = Counter(snp_g)
tuples = sorted(cnt.items(), key=operator.itemgetter(1))
diff --git a/wqflask/wqflask/my_pylmm/pyLMM/kinship.py b/wqflask/wqflask/my_pylmm/pyLMM/kinship.py
index 61da68fc..c1750e1d 100644
--- a/wqflask/wqflask/my_pylmm/pyLMM/kinship.py
+++ b/wqflask/wqflask/my_pylmm/pyLMM/kinship.py
@@ -61,6 +61,10 @@ def f_init(q):
def kinship_full(G,options):
print G.shape
+ m = G.shape[0] # snps
+ n = G.shape[1] # inds
+ sys.stderr.write(str(m)+" SNPs\n")
+ assert m>n, "n should be larger than m (snps>inds)"
m = np.dot(G.T,G)
m = m/G.shape[0]
return m
diff --git a/wqflask/wqflask/my_pylmm/pyLMM/lmm.py b/wqflask/wqflask/my_pylmm/pyLMM/lmm.py
index 36c3602f..7bf77be5 100644
--- a/wqflask/wqflask/my_pylmm/pyLMM/lmm.py
+++ b/wqflask/wqflask/my_pylmm/pyLMM/lmm.py
@@ -340,8 +340,8 @@ def calculate_kinship(genotype_matrix, temp_data=None, is_testing=False):
print("genotype 2D matrix m (snps) is:", m)
keep = []
for counter in range(m):
- if is_testing and counter>8:
- break
+ # if is_testing and counter>8:
+ # break
#print("type of genotype_matrix[:,counter]:", pf(genotype_matrix[:,counter]))
#Checks if any values in column are not numbers
not_number = np.isnan(genotype_matrix[:,counter])
diff --git a/wqflask/wqflask/my_pylmm/pyLMM/runlmm.py b/wqflask/wqflask/my_pylmm/pyLMM/runlmm.py
index 0b8830d4..80478368 100644
--- a/wqflask/wqflask/my_pylmm/pyLMM/runlmm.py
+++ b/wqflask/wqflask/my_pylmm/pyLMM/runlmm.py
@@ -116,28 +116,27 @@ if cmd == 'redis':
elif cmd == 'kinship':
G = g
print "Original G",G.shape, "\n", G
+ if y:
+ gnt = np.array(gn).T
+ Y,g = phenotype.remove_missing(y,g.T,options.verbose)
+ G = g.T
+ print "Removed missing phenotypes",G.shape, "\n", G
if options.maf_normalization:
G = np.apply_along_axis( genotype.replace_missing_with_MAF, axis=0, arr=g )
print "MAF replacements: \n",G
if not options.skip_genotype_normalization:
G = np.apply_along_axis( genotype.normalize, axis=1, arr=G)
- print G.shape, "\n", G
K = kinship_full(G,options)
+ print "Genotype",G.shape, "\n", G
print "first Kinship method",K.shape,"\n",K
- K2 = calculate_kinship(np.copy(G.T),None,options)
+ K2 = calculate_kinship(np.copy(G.T),temp_data=None,is_testing=options.testing)
+ print "Genotype",G.shape, "\n", G
print "GN2 Kinship method",K2.shape,"\n",K2
- K3 = kinship(G,options)
+
+ print "Genotype",G.shape, "\n", G
+ K3 = kinship(np.copy(G),options)
print "third Kinship method",K3.shape,"\n",K3
- sys.exit(1)
- gnt = np.array(gn).T
- Y,g = remove_missing_phenotypes(y,gnt,options.verbose)
- G = g
- print G.shape,G
- K = calculate_kinship(np.copy(G),temp_data=None,is_testing=options.testing)
- print G.shape,G
- print "first Kinship method",K.shape,K
- K = kinship(G.T,options)
assert(K[0][0]==1.28)
else:
print "Doing nothing"