def test_getEcotypeInfo(self): from common import getEcotypeInfo import StockDB, Stock_250kDB #StockDB has to be setup otherwise, StockDB.Ecotype.table is None in getEcotypeInfo() hostname='papaya.usc.edu' dbname='stock_250k' db_user='******' db_passwd = '' drivername='mysql' schema = None db = Stock_250kDB.Stock_250kDB(drivername=drivername, username=db_user, password=db_passwd, hostname=hostname, database=dbname, schema=schema) #doesn't matter which database to connect as far as StockDB is imported #db = StockDB.StockDB(drivername=drivername, username=db_user, # password=db_passwd, hostname=hostname, database=dbname, schema=schema) db.setup(create_tables=False) import pdb pdb.set_trace() getEcotypeInfo(db)
def test_getEcotypeInfo(self):
from common import getEcotypeInfo
import StockDB, Stock_250kDB #StockDB has to be setup otherwise, StockDB.Ecotype.table is None in getEcotypeInfo()
hostname = 'papaya.usc.edu'
dbname = 'stock_250k'
db_user = '******'
db_passwd = ''
drivername = 'mysql'
schema = None
db = Stock_250kDB.Stock_250kDB(drivername=drivername,
username=db_user,
password=db_passwd,
hostname=hostname,
database=dbname,
schema=schema)
#doesn't matter which database to connect as far as StockDB is imported
#db = StockDB.StockDB(drivername=drivername, username=db_user,
# password=db_passwd, hostname=hostname, database=dbname, schema=schema)
db.setup(create_tables=False)
import pdb
pdb.set_trace()
getEcotypeInfo(db)
def run(self):
if self.debug:
import pdb
pdb.set_trace()
db = Stock_250kDB.Stock_250kDB(drivername=self.drivername, username=self.db_user,
password=self.db_passwd, hostname=self.hostname, database=self.dbname, schema=self.schema)
db.setup(create_tables=False)
session = db.session
snpData = SNPData(input_fname=self.input_fname, turn_into_integer=1, turn_into_array=1, ignore_2nd_column=1)
if self.eigen_vector_fname and self.eigen_value_fname:
eigen_value_ls = self.getEigenValueFromFile(self.eigen_value_fname)
eigen_value_ls = numpy.array(eigen_value_ls)
explained_var = eigen_value_ls/numpy.sum(eigen_value_ls)
PC_data = self.getPCFromFile(self.eigen_vector_fname)
PC_matrix = PC_data.PC_matrix
else:
max_no_of_snps = 10000
if len(snpData.col_id_ls)>max_no_of_snps: #2008-12-01 randomly pick max_no_of_snps SNPs
picked_col_index_ls = random.sample(range(len(snpData.col_id_ls)), max_no_of_snps)
new_col_id_ls = [snpData.col_id_ls[i] for i in picked_col_index_ls]
newSnpData = SNPData(row_id_ls=snpData.row_id_ls, col_id_ls=new_col_id_ls, strain_acc_list=snpData.strain_acc_list,\
category_list=snpData.category_list)
newSnpData.data_matrix = snpData.data_matrix[:, picked_col_index_ls]
snpData = newSnpData
snpData, allele_index2allele_ls = snpData.convertSNPAllele2Index()
explained_var = None
PC_matrix = None
header_phen, strain_acc_list_phen, category_list_phen, data_matrix_phen = read_data(self.phenotype_fname, turn_into_integer=0)
phenData = SNPData(header=header_phen, strain_acc_list=snpData.strain_acc_list, data_matrix=data_matrix_phen) #row label is that of the SNP matrix, because the phenotype matrix is gonna be re-ordered in that way
phenData.data_matrix = Kruskal_Wallis.get_phenotype_matrix_in_data_matrix_order(snpData.row_id_ls, strain_acc_list_phen, phenData.data_matrix) #tricky, using strain_acc_list_phen
phenotype_col_index = self.findOutWhichPhenotypeColumn(phenData, Set([self.phenotype_method_id]))[0]
ecotype_info = getEcotypeInfo(db, self.country_order_type)
#the offset below decides where the label of strains/snps should start in axe_snp_matrix
#2008-11-14 only for PlotGroupOfSNPs.py. you can set it to 1 cuz we dont' draw axe_snp_matrix here.
snp_id_label_y_offset = 0.95
StrainID2PCAPosInfo = self.getStrainID2PCAPosInfo(snpData, pca_range=[0,1], snp_id_label_y_offset=snp_id_label_y_offset, explained_var=explained_var, T=PC_matrix)
axe_y_offset1 = 0.03
axe_height1 = 0.45 #height of axe_chromosome, twice height of axe_map_phenotype_legend
axe_y_offset2 = axe_y_offset1+axe_height1
axe_height2 = 0.5 #height of axe_strain_pca, axe_snp_matrix, axe_map
axe_y_offset3 = axe_y_offset2+axe_height2
axe_x_offset1 = 0.05
axe_width1 = 0.8 #width of axe_strain_pca
axe_x_offset2 = axe_x_offset1 + 0.02 + axe_width1
axe_width2 = 0.05 #width of axe_chromosome, axe_snp_matrix, axe_snp_pca
axe_x_offset3 = axe_x_offset2 + axe_width2
axe_width3 = 0.02 #width of axe_phenotype
phenotype_method = Stock_250kDB.PhenotypeMethod.get(self.phenotype_method_id)
phenotype_cmap = mpl.cm.jet
max_phenotype = numpy.nanmax(phenData.data_matrix[:,phenotype_col_index]) #nanmax ignores the nan elements
min_phenotype = numpy.nanmin(phenData.data_matrix[:,phenotype_col_index]) #nanmin ignores the nan elements
phenotype_gap = max_phenotype - min_phenotype
phenotype_jitter = phenotype_gap/10.
phenotype_norm = mpl.colors.Normalize(vmin=min_phenotype-phenotype_jitter, vmax=max_phenotype+phenotype_jitter)
axe_map_phenotype_legend = pylab.axes([axe_x_offset2, axe_y_offset1, axe_width2, 0.3], frameon=False)
cb = mpl.colorbar.ColorbarBase(axe_map_phenotype_legend, cmap=phenotype_cmap,
norm=phenotype_norm,
orientation='vertical')
cb.set_label('Legend Of Phenotype %s %s'%(phenotype_method.id, phenotype_method.short_name))
axe_strain_map = pylab.axes([axe_x_offset1, axe_y_offset2, axe_width1, axe_height2], frameon=False)
axe_strain_pca = pylab.axes([axe_x_offset1, axe_y_offset1, axe_width1, axe_height1], frameon=False)
axe_strain_map_pca_cover = pylab.axes([axe_x_offset1, axe_y_offset1, axe_width1, axe_height1+axe_height2], frameon=False, \
sharex=axe_strain_pca) #cover both axe_strain_map and axe_strain_pca
axe_strain_map_pca_cover.set_yticks([])
axe_strain_pca_xlim = [-0.05,1.05]
axe_strain_pca_ylim = [0, 1.05]
axe_strain_pca.set_xlim(axe_strain_pca_xlim)
axe_strain_pca.set_ylim(axe_strain_pca_ylim)
axe_strain_map_pca_cover_ylim = [0, (axe_height1+axe_height2)/axe_height1] #set it accordingly
axe_strain_map_pca_cover.set_ylim(axe_strain_map_pca_cover_ylim)
axe_strain_pca.grid(True, alpha=0.3)
axe_strain_pca.set_xticks([])
axe_strain_pca.set_yticks([])
axe_strain_pca_legend = None #no pca legend
self.drawStrainPCA(axe_strain_pca, axe_strain_map, axe_strain_map_pca_cover, axe_strain_pca_legend, StrainID2PCAPosInfo, \
ecotype_info, phenData, \
phenotype_col_index, phenotype_cmap, phenotype_norm, rightmost_x_value=axe_strain_pca_xlim[1],\
strain_color_type=2, pca2map_line_color=None, ecotype_width_on_map=10,\
draw_lines_to_axe_snp_matrix = False, strain_size_on_axe_strain_pca=14, pic_area=self.pic_area,\
map_pca_line_alpha=0.2, map_pca_linewidth=0.2) #customize a couple of things
axe_strain_pca.set_xlim(axe_strain_pca_xlim)
axe_strain_pca.set_ylim(axe_strain_pca_ylim)
axe_strain_map_pca_cover.set_ylim(axe_strain_map_pca_cover_ylim)
png_output_fname = '%s.png'%self.output_fname_prefix
pylab.savefig(png_output_fname, dpi=400)
pylab.savefig('%s.svg'%self.output_fname_prefix)
self.plotLatLonPhenVsPC(ecotype_info, StrainID2PCAPosInfo, phenData, phenotype_col_index, phenotype_cmap, phenotype_norm,
self.output_fname_prefix, commit=self.commit)
def test_drawMap(self):
sys.stderr.write("Drawing graph on a map ...\n")
#import pdb
#pdb.set_trace()
import StockDB, Stock_250kDB #StockDB has to be setup otherwise, StockDB.Ecotype.table is None in getEcotypeInfo()
hostname = 'papaya.usc.edu'
dbname = 'stock_250k'
db_user = '******'
db_passwd = ''
drivername = 'mysql'
schema = None
db = Stock_250kDB.Stock_250kDB(drivername=drivername,
username=db_user,
password=db_passwd,
hostname=hostname,
database=dbname,
schema=schema)
#doesn't matter which database to connect as far as StockDB is imported
#db = StockDB.StockDB(drivername=drivername, username=db_user,
# password=db_passwd, hostname=hostname, database=dbname, schema=schema)
db.setup(create_tables=False)
from common import getEcotypeInfo
ecotype_info = getEcotypeInfo(db)
from matplotlib.toolkits.basemap import Basemap
#from mpl_toolkits.basemap import Basemap
import pylab
from matplotlib import rcParams
rcParams['font.size'] = 6
rcParams['legend.fontsize'] = 6
#rcParams['text.fontsize'] = 6 #deprecated. use font.size instead
rcParams['axes.labelsize'] = 4
rcParams['axes.titlesize'] = 8
rcParams['xtick.labelsize'] = 4
rcParams['ytick.labelsize'] = 4
pylab.clf()
#fig = pylab.figure()
#fig.add_axes([0.05,0.05,0.9,0.9]) #[left, bottom, width, height]
axe_map = pylab.axes([0.5, 0.02, 0.4, 0.8], frameon=False)
axe_map.set_title("Global Arabidopsis Ecotype Distribution")
axe_map.set_xlabel('ecotype is drawn as circles.')
axe_map.set_ylabel('strains')
pic_area = [-140, -40, 140, 70]
m = Basemap(llcrnrlon=pic_area[0],llcrnrlat=pic_area[1],urcrnrlon=pic_area[2],urcrnrlat=pic_area[3],\
resolution='l',projection='mill', ax=axe_map)
"""
llcrnrx = -self.rmajor
llcrnry = -self.rmajor
urcrnrx = -llcrnrx
urcrnry = -llcrnry
"""
#m.drawcoastlines()
#m.bluemarble()
m.drawparallels(pylab.arange(-90, 90, 30),
labels=[1, 1, 0, 1],
size=4,
linewidth=0.1)
m.drawmeridians(pylab.arange(-180, 180, 30),
labels=[1, 1, 0, 1],
size=4,
linewidth=0.1)
m.fillcontinents()
m.drawcountries(linewidth=0.1)
#m.drawstates()
#m.drawlsmask((0,255,0,255), (0,0,255,255), lakes=True)
#m.drawlsmask('coral','aqua',lakes=True)
print "xlim:", axe_map.get_xlim()
print "ylim:", axe_map.get_ylim()
xlim = axe_map.get_xlim()
ylim = axe_map.get_ylim()
"""
for strain_id in StrainID2PCAPosInfo.strain_id_ls:
img_y_pos = StrainID2PCAPosInfo.strain_id2img_y_pos[strain_id]
phenotype_row_index = phenData.row_id2row_index[strain_id]
phenotype = phenData.data_matrix[phenotype_row_index][phenotype_col_index]
ecotype_id = int(strain_id)
ecotype_obj = ecotype_info.ecotype_id2ecotype_obj.get(ecotype_id)
if ecotype_obj:
lat, lon = ecotype_obj.latitude, ecotype_obj.longitude
else:
sys.stderr.write("Warning: Ecotype %s not in ecotype_info (fetched from stock db).\n"%ecotype_id)
continue
if lat and lon:
x, y = m(lon, lat)
color = cmap(norm(phenotype))
ax.plot([0, x], [img_y_pos, y], linestyle='--', alpha=0.2, linewidth=0.2)
ax.scatter([x],[y], s=10, linewidth=0, facecolor=color) #, zorder=10)
"""
#pylab.title("Global Arabidopsis Ecotype Distribution")
output_fname_prefix = '/tmp/map'
print "ylim:", axe_map.get_ylim()
axe_map.set_xlim(xlim)
axe_map.set_ylim(ylim)
axe_chromosome = pylab.axes([0.05, 0.02, 0.8, 0.8], frameon=False)
axe_chromosome.set_title("chromosome")
#fix the two transformations before doing cross-axe drawings
axe_map.transData.freeze() # eval the lazy objects
axe_map.transAxes.freeze()
axe_chromosome.transData.freeze() # eval the lazy objects
axe_chromosome.transAxes.freeze()
no_of_ecotypes = 200
ecotype_id_ls = ecotype_info.ecotype_id2ecotype_obj.keys(
)[:no_of_ecotypes]
no_of_ecotypes_drawn = 0
for i in range(no_of_ecotypes):
ecotype_id = ecotype_id_ls[i]
y_pos = i / float(no_of_ecotypes)
#y_pos = i/float(no_of_ecotypes)*ylim[1]
ecotype_obj = ecotype_info.ecotype_id2ecotype_obj.get(ecotype_id)
if ecotype_obj:
lat, lon = ecotype_obj.latitude, ecotype_obj.longitude
else:
sys.stderr.write(
"Warning: Ecotype %s not in ecotype_info (fetched from stock db).\n"
% ecotype_id)
continue
if lat and lon:
x, y = m(lon, lat)
#axe_map.plot([0, x], [y_pos, y], linestyle='--', alpha=0.2, linewidth=0.2)
axe_map.set_xlim(xlim)
axe_map.set_ylim(ylim)
axe_map.scatter([x], [y],
s=5,
linewidth=0,
facecolor='r',
alpha=0.2,
zorder=10)
canvas_x, canvas_y = axe_map.transData.xy_tup((x, y))
axe_chromosome_xy = axe_chromosome.transData.inverse_xy_tup(
(canvas_x, canvas_y))
axe_chromosome.plot([0, axe_chromosome_xy[0]],
[y_pos, axe_chromosome_xy[1]],
linestyle='--',
alpha=0.2,
linewidth=0.2)
no_of_ecotypes_drawn += 1
#release two transformations
axe_map.transData.thaw() # eval the lazy objects
axe_map.transAxes.thaw()
axe_chromosome.transData.thaw() # eval the lazy objects
axe_chromosome.transAxes.thaw()
#set to the same x/y_lim before cross-axe drawing
axe_map.set_xlim(xlim)
axe_map.set_ylim(ylim)
axe_chromosome.set_xlim([0, 1])
axe_chromosome.set_ylim([0, 1])
if output_fname_prefix:
pylab.savefig('%s.png' % output_fname_prefix, dpi=600)
pylab.savefig('%s.svg' % output_fname_prefix)
sys.stderr.write("%s ecotypes drawn. Done.\n" % (no_of_ecotypes_drawn))
def test_drawMap(self):
sys.stderr.write("Drawing graph on a map ...\n")
#import pdb
#pdb.set_trace()
import StockDB, Stock_250kDB #StockDB has to be setup otherwise, StockDB.Ecotype.table is None in getEcotypeInfo()
hostname='papaya.usc.edu'
dbname='stock_250k'
db_user='******'
db_passwd = ''
drivername='mysql'
schema = None
db = Stock_250kDB.Stock_250kDB(drivername=drivername, username=db_user,
password=db_passwd, hostname=hostname, database=dbname, schema=schema)
#doesn't matter which database to connect as far as StockDB is imported
#db = StockDB.StockDB(drivername=drivername, username=db_user,
# password=db_passwd, hostname=hostname, database=dbname, schema=schema)
db.setup(create_tables=False)
from common import getEcotypeInfo
ecotype_info = getEcotypeInfo(db)
from matplotlib.toolkits.basemap import Basemap
#from mpl_toolkits.basemap import Basemap
import pylab
from matplotlib import rcParams
rcParams['font.size'] = 6
rcParams['legend.fontsize'] = 6
#rcParams['text.fontsize'] = 6 #deprecated. use font.size instead
rcParams['axes.labelsize'] = 4
rcParams['axes.titlesize'] = 8
rcParams['xtick.labelsize'] = 4
rcParams['ytick.labelsize'] = 4
pylab.clf()
#fig = pylab.figure()
#fig.add_axes([0.05,0.05,0.9,0.9]) #[left, bottom, width, height]
axe_map = pylab.axes([0.5, 0.02, 0.4, 0.8], frameon=False)
axe_map.set_title("Global Arabidopsis Ecotype Distribution")
axe_map.set_xlabel('ecotype is drawn as circles.')
axe_map.set_ylabel('strains')
pic_area=[-140,-40,140,70]
m = Basemap(llcrnrlon=pic_area[0],llcrnrlat=pic_area[1],urcrnrlon=pic_area[2],urcrnrlat=pic_area[3],\
resolution='l',projection='mill', ax=axe_map)
"""
llcrnrx = -self.rmajor
llcrnry = -self.rmajor
urcrnrx = -llcrnrx
urcrnry = -llcrnry
"""
#m.drawcoastlines()
#m.bluemarble()
m.drawparallels(pylab.arange(-90,90,30), labels=[1,1,0,1], size=4, linewidth=0.1)
m.drawmeridians(pylab.arange(-180,180,30), labels=[1,1,0,1], size=4, linewidth=0.1)
m.fillcontinents()
m.drawcountries(linewidth=0.1)
#m.drawstates()
#m.drawlsmask((0,255,0,255), (0,0,255,255), lakes=True)
#m.drawlsmask('coral','aqua',lakes=True)
print "xlim:", axe_map.get_xlim()
print "ylim:", axe_map.get_ylim()
xlim = axe_map.get_xlim()
ylim = axe_map.get_ylim()
"""
for strain_id in StrainID2PCAPosInfo.strain_id_ls:
img_y_pos = StrainID2PCAPosInfo.strain_id2img_y_pos[strain_id]
phenotype_row_index = phenData.row_id2row_index[strain_id]
phenotype = phenData.data_matrix[phenotype_row_index][phenotype_col_index]
ecotype_id = int(strain_id)
ecotype_obj = ecotype_info.ecotype_id2ecotype_obj.get(ecotype_id)
if ecotype_obj:
lat, lon = ecotype_obj.latitude, ecotype_obj.longitude
else:
sys.stderr.write("Warning: Ecotype %s not in ecotype_info (fetched from stock db).\n"%ecotype_id)
continue
if lat and lon:
x, y = m(lon, lat)
color = cmap(norm(phenotype))
ax.plot([0, x], [img_y_pos, y], linestyle='--', alpha=0.2, linewidth=0.2)
ax.scatter([x],[y], s=10, linewidth=0, facecolor=color) #, zorder=10)
"""
#pylab.title("Global Arabidopsis Ecotype Distribution")
output_fname_prefix = '/tmp/map'
print "ylim:", axe_map.get_ylim()
axe_map.set_xlim(xlim)
axe_map.set_ylim(ylim)
axe_chromosome = pylab.axes([0.05, 0.02, 0.8, 0.8], frameon=False)
axe_chromosome.set_title("chromosome")
#fix the two transformations before doing cross-axe drawings
axe_map.transData.freeze() # eval the lazy objects
axe_map.transAxes.freeze()
axe_chromosome.transData.freeze() # eval the lazy objects
axe_chromosome.transAxes.freeze()
no_of_ecotypes = 200
ecotype_id_ls = ecotype_info.ecotype_id2ecotype_obj.keys()[:no_of_ecotypes]
no_of_ecotypes_drawn = 0
for i in range(no_of_ecotypes):
ecotype_id = ecotype_id_ls[i]
y_pos = i/float(no_of_ecotypes)
#y_pos = i/float(no_of_ecotypes)*ylim[1]
ecotype_obj = ecotype_info.ecotype_id2ecotype_obj.get(ecotype_id)
if ecotype_obj:
lat, lon = ecotype_obj.latitude, ecotype_obj.longitude
else:
sys.stderr.write("Warning: Ecotype %s not in ecotype_info (fetched from stock db).\n"%ecotype_id)
continue
if lat and lon:
x, y = m(lon, lat)
#axe_map.plot([0, x], [y_pos, y], linestyle='--', alpha=0.2, linewidth=0.2)
axe_map.set_xlim(xlim)
axe_map.set_ylim(ylim)
axe_map.scatter([x],[y], s=5, linewidth=0, facecolor='r', alpha=0.2, zorder=10)
canvas_x, canvas_y = axe_map.transData.xy_tup((x,y))
axe_chromosome_xy = axe_chromosome.transData.inverse_xy_tup((canvas_x,canvas_y))
axe_chromosome.plot([0,axe_chromosome_xy[0]], [y_pos, axe_chromosome_xy[1]], linestyle='--', alpha=0.2, linewidth=0.2)
no_of_ecotypes_drawn += 1
#release two transformations
axe_map.transData.thaw() # eval the lazy objects
axe_map.transAxes.thaw()
axe_chromosome.transData.thaw() # eval the lazy objects
axe_chromosome.transAxes.thaw()
#set to the same x/y_lim before cross-axe drawing
axe_map.set_xlim(xlim)
axe_map.set_ylim(ylim)
axe_chromosome.set_xlim([0,1])
axe_chromosome.set_ylim([0,1])
if output_fname_prefix:
pylab.savefig('%s.png'%output_fname_prefix, dpi=600)
pylab.savefig('%s.svg'%output_fname_prefix)
sys.stderr.write("%s ecotypes drawn. Done.\n"%(no_of_ecotypes_drawn))
