def heritability( self ): """ compute the regression coefficient (need to get the p-value) """ x = R.FloatVector( self.mid_parent ) y = R.FloatVector( self.offspring ) formula = R.Formula( 'y ~ x' ) env = formula.environment env['x'] = x env['y'] = y results = stats.lm( formula ) print summary( results )[3][1], summary( results )[3][7] r = results[0][1] self.h_sqrd = 2*r**2
def linear_model(data, Input, Output, Condition):
try:
stats = importr('stats')
base = importr('base')
pandas2ri.activate()
r_df = pandas2ri.py2rpy(data)
pandas2ri.deactivate()
formula = '{y}~{x}*{condition}'.format(y=Output,
x=Input,
condition=Condition)
lm = stats.lm(formula, r_df)
summary = (base.summary(lm))
results = summary.rx2('coefficients')
results_df = base.as_data_frame_matrix(results)
py_results_df = pd.DataFrame(results_df).transpose()
py_results_df.columns = results_df.colnames
py_results_df.index = results_df.rownames
return (py_results_df)
except:
return (pd.DataFrame({}))
reanalysis_subset, ilat=lat_i, ilon=lon_i)
observations_data, observations_months = collect_monthly_data(
observations_subset, ilat=lat_i, ilon=lon_i)
for month_i, month in enumerate(range(1, 13)):
#print('month: '+str(month))
reanalysis = reanalysis_data[reanalysis_months ==
month].copy()
observations = observations_data[observations_months ==
month].copy()
# The ranking step of the downscaling model
reanalysis.sort()
observations.sort()
slope, intercept, *_ = lm(x=reanalysis, y=observations)
#print(slope)
#print(intercept)
full_array_lat_i = np.where(
land_mask.lat.values ==
land_mask_subset.lat.values[lat_i])[0][0]
full_array_lon_i = np.where(
land_mask.lon.values ==
land_mask_subset.lon.values[lon_i])[0][0]
model_coef['slope'][month_i, full_array_lat_i,
full_array_lon_i] = slope
model_coef['intercept'][month_i, full_array_lat_i,
full_array_lon_i] = intercept
progress += 1
def calc_mefs_helper(data):
x = data[XCOL].values
y = data[LABELS]
# Run regression for each column and store results
results = y.apply(lambda v: lm(x,v))
return results
ccallengths.append(allobs[cspcevent].length[j])
ccalHgs.append(allobs[cspcevent].Hg[j])
else:
cHg_obs = allobs[cspcevent].Hg[j]
clen = allobs[cspcevent].length[j]
dat_ofp.close()
# perform a linear regression to obtain initial parameters
x = np.array(ccallengths)
x = np.log(x+1.0)
y = np.array(ccalHgs)
y = np.log((y*1000.0)+1.0)
# check to be sure of uniqueness in both length and Hg
if (len(np.unique((x))) >= 1):
if (len(np.unique((y))) >= 1):
cspclm, ceventlm, r_value, p_value, cstderrlm = lm(x,y)
sigma_calc = np.std(y)
# ## sigma value, using STD of Hg
sig_ofp = open('Hgsigma.dat','w')
sig_ofp.write('%f\n' %(sigma_calc))
sig_ofp.close()
# ## SpC parameter value
spc_ofp = open('Hgspc.srt','w')
spc_ofp.write('%d %f\n' %(allobs[cspcevent].SpC,cspclm))
spc_ofp.close()
# ## Event parameter value
event_ofp = open('Hgevents.srt','w')
event_ofp.write('%d %f\n' %(allobs[cspcevent].Event,ceventlm))
event_ofp.close()
# ## Write the index file
ndx_ofp = open('Hgdata.ndx','w')
indat = np.genfromtxt(infile,delimiter = ',', dtype=None,names=True)
Hg = indat['Hg']
lens = indat['length']
DL = ['DL']
SpC_Event = indat['SpC_EVENT']
# set NDs as hald detection limit for linear regressions
NDs = np.nonzero(DL==1)[0]
for cind in NDs:
Hg[cind] = 0.5*Hg[cind]
# perform the log transformations
Hg = np.log((Hg*1000.0)+1)
lens = np.log(lens+1.0)
# now perform all the linear regressions, writing the results to a file
ofp = open(outfile,'w')
ofp.write('%20s'*6 %('SpC_EVENT','SpC_par','Event_par','sigma','r_squared','N') + '\n')
allSpC_Events = np.unique(SpC_Event)
k=0
allK = len(allSpC_Events)
for cspcev in allSpC_Events:
k+=1
print "rockin' " + cspcev + '-->%d of %d' %(k,allK)
cind = np.nonzero(SpC_Event == cspcev)[0]
y = Hg[cind]
x = lens[cind]
slope, intercept, r_value, p_value, std_err = lm(x,y)
sigma_calc = np.std(y)
ofp.write('%19s %19f %19f %19f %19f %19d\n' %(cspcev,slope,intercept,sigma_calc,r_value**2,len(x)))
ofp.close()
forecasts = collect_forecast_data(historic_forecasts,
month=month,
lead_time=lead_time,
ilat=lat_i,
ilon=lon_i)
obs = collect_obs_data(historic_observations,
month=month,
ilat=lat_i,
ilon=lon_i)
forecasts, obs = reconcile_forecasts_and_obs(
forecasts, obs)
# The ranking step of the downscaling model
forecasts['data'].sort()
obs['data'].sort()
slope, intercept, *_ = lm(x=forecasts['data'],
y=obs['data'])
model_coef['slope'][lead_time_i, month_i, lat_i,
lon_i] = slope
model_coef['intercept'][lead_time_i, month_i, lat_i,
lon_i] = intercept
pixel_processing_times.append(
round(time.time() - pixel_start_time, 1))
print(
str(progress) + '/' + str(total_pixels) + ' pixels, ' +
str(pixel_processing_times[-1]) + ' sec')
print('avg: ' + str(np.mean(pixel_processing_times)))
warnings.warn(x, RRuntimeWarning)
RRuntimeWarning: Error in eval(expr, envir, enclos) : object 'y' not found
Traceback (most recent call last):
File "<pyshell#140>", line 1, in <module>
M=R.lm('y~x')
File "/usr/local/lib/python2.7/dist-packages/rpy2/robjects/functions.py", line 178, in __call__
return super(SignatureTranslatedFunction, self).__call__(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/rpy2/robjects/functions.py", line 106, in __call__
res = super(Function, self).__call__(*new_args, **new_kwargs)
RRuntimeError: Error in eval(expr, envir, enclos) : object 'y' not found
>>> M=stats.lm(y~x)
SyntaxError: invalid syntax
>>> M=stats.lm('y~x')
Traceback (most recent call last):
File "<pyshell#142>", line 1, in <module>
M=stats.lm('y~x')
File "/usr/local/lib/python2.7/dist-packages/rpy2/robjects/functions.py", line 178, in __call__
return super(SignatureTranslatedFunction, self).__call__(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/rpy2/robjects/functions.py", line 106, in __call__
res = super(Function, self).__call__(*new_args, **new_kwargs)
RRuntimeError: Error in eval(expr, envir, enclos) : object 'y' not found
>>> M=stats.lm('y~x', data=(y,x))
Traceback (most recent call last):
File "<pyshell#143>", line 1, in <module>
M=stats.lm('y~x', data=(y,x))
