def calc_site_pwp(sitedf, sitephreeqc, returnPCO2=False):
have_data = False
if ('Stream flow, mean. daily' in sitedf.columns) and (
'Temperature, water' in sitedf.columns) and (
'CO2_Molality' in sitephreeqc.columns) and (
'Ca+2_Activity' in sitephreeqc.columns) and (
'CO2_Activity' in sitephreeqc.columns) and (
'H+_Activity' in sitephreeqc.columns) and (
'HCO3-_Activity' in sitephreeqc.columns):
have_data = True
if have_data:
#create dataframe subset
subdf = DataFrame({
'Q': sitedf['Stream flow, mean. daily'],
'T_C': sitedf['Temperature, water'],
'CO2': sitephreeqc.CO2_Molality,
'a_Ca': sitephreeqc['Ca+2_Activity'],
'a_H2CO3s': sitephreeqc['CO2_Activity'],
'a_H': sitephreeqc['H+_Activity'],
'a_HCO3': sitephreeqc['HCO3-_Activity']
})
#Clear out NaN values
subdf = subdf.dropna()
if subdf.size > 0:
#Average any duplicate indicies
g = subdf.groupby(level=0) #group by duplicate indicies
subdf = g.mean() #average duplicate indicies
#Calculate PCO2
T_K = CtoK(subdf.T_C)
K_H = calc_K_H(T_K)
PCO2 = subdf.CO2 / K_H
pwp_rates = pwpRateTheory(a_Ca=subdf.a_Ca,
a_H2CO3s=subdf.a_H2CO3s,
a_H=subdf.a_H,
a_HCO3=subdf.a_HCO3,
T_K=T_K,
PCO2=PCO2)
if returnPCO2:
return [pwp_rates, PCO2]
else:
return pwp_rates
else:
if returnPCO2:
return [None, None]
else:
return None
#Data were missing
else:
if returnPCO2:
return [None, None]
else:
return None
def calc_site_pwp(sitedf, sitephreeqc, returnPCO2=False):
have_data = False
if ('Stream flow, mean. daily' in sitedf.columns) and ( 'Temperature, water' in sitedf.columns) and ('CO2_Molality' in sitephreeqc.columns) and ('Ca+2_Activity' in sitephreeqc.columns) and ('CO2_Activity' in sitephreeqc.columns) and ('H+_Activity' in sitephreeqc.columns) and ('HCO3-_Activity' in sitephreeqc.columns):
have_data = True
if have_data:
#create dataframe subset
subdf = DataFrame({
'Q':sitedf['Stream flow, mean. daily'],
'T_C':sitedf['Temperature, water'],
'CO2':sitephreeqc.CO2_Molality,
'a_Ca':sitephreeqc['Ca+2_Activity'],
'a_H2CO3s':sitephreeqc['CO2_Activity'],
'a_H':sitephreeqc['H+_Activity'],
'a_HCO3':sitephreeqc['HCO3-_Activity']
})
#Clear out NaN values
subdf = subdf.dropna()
if subdf.size>0:
#Average any duplicate indicies
g = subdf.groupby(level=0)#group by duplicate indicies
subdf = g.mean()#average duplicate indicies
#Calculate PCO2
T_K = CtoK(subdf.T_C)
K_H = calc_K_H(T_K)
PCO2 = subdf.CO2/K_H
pwp_rates = pwpRateTheory(a_Ca=subdf.a_Ca, a_H2CO3s=subdf.a_H2CO3s, a_H=subdf.a_H, a_HCO3=subdf.a_HCO3, T_K=T_K, PCO2=PCO2)
if returnPCO2:
return [pwp_rates, PCO2]
else:
return pwp_rates
else:
if returnPCO2:
return [None,None]
else:
return None
#Data were missing
else:
if returnPCO2:
return [None,None]
else:
return None
def make_pwp_vs_T_plots(sitesDir, siteList=None, siteFile=None, makeHistograms=True, classFile=''):
sitePanelDict, sitePhreeqcDict = loadSiteListData(processedSitesDir=sitesDir, loadPhreeqc=True)
if classFile != '':
class_xls = read_excel(classFile, 'Sheet1',index_col=1, names=['name','site', 'recharge', 'age'])
rs = []
ps = []
slopes = []
plotsDir = os.path.join(sitesDir, 'plots/')
for site in list(sitePanelDict.keys()):
if classFile !='':
#read in classification for this site
this_class = class_xls['recharge'][site]
this_color=class_colors[this_class]
else:
this_color='black'
print(("Making plot for: "+site))
#Read out data into shorter variable names
Q = sitePanelDict[site].data['Stream flow, mean. daily']
T_C = sitePanelDict[site].data['Temperature, water']
CO2 = sitePhreeqcDict[site].CO2_Molality
Ca = sitePhreeqcDict[site]['Ca']
a_Ca = sitePhreeqcDict[site]['Ca+2_Activity']
a_H2CO3s = sitePhreeqcDict[site]['CO2_Activity']
a_HCO3 = sitePhreeqcDict[site]['HCO3-_Activity']
a_H = sitePhreeqcDict[site]['H+_Activity']
#Filter out nan values
#good_values = ~(Q+T_C+CO2+Ca).isnull()#Addition will create Nans if any of the series contains a NaN
good_values = get_good_indicies([Q,T_C,CO2,Ca,a_Ca,a_H2CO3s,a_H, a_HCO3])
Q = Q[good_values]
T_C = T_C[good_values]
CO2 = CO2[good_values]
Ca = Ca[good_values]
a_Ca = a_Ca[good_values]
a_H = a_H[good_values]
a_H2CO3s = a_H2CO3s[good_values]
a_HCO3 = a_HCO3[good_values]
#Calculate PCO2
T_K = CtoK(T_C)
K_H = calc_K_H(T_K)
PCO2 = CO2/K_H
#Calculate PWP rates
pwp_rates = []
for i, value in enumerate(Q):
# sol = solutionFromCaPCO2(Ca[i], PCO2[i], T_C = T_C[i])
# this_pwp = pwpFromSolution(sol)
this_pwp = pwpRateTheory(a_Ca=a_Ca[i], a_H2CO3s=a_H2CO3s[i], a_H=a_H[i], a_HCO3=a_HCO3[i], T_K=T_K[i], PCO2=PCO2[i])
this_rate_mm_yr = pwp_to_mm_yr(this_pwp)
pwp_rates.append(this_rate_mm_yr)
#Check for plots directory and make it if one doesn't exist
check_plots_dir(sitesDir)
#Make Discharge vs. Saturation Ratio Plot
figure()
plot(T_C, pwp_rates, 'o', color=this_color)
xlabel('Temperature ($^\circ C$)')
ylabel('PWP Dissolution Rate (mm/yr)')
savefig(os.path.join(plotsDir,site+'-T_vs_PWP.pdf'))
#Calculate correlation coefficient and regression
slope,intercept,r,p,stderr = linregress(T_C, pwp_rates)
rs.append(r)
ps.append(p)
slopes.append(slope)
if makeHistograms:
figure()
hist(pwp_rates, normed=True, color=this_color)
xlabel('PWP Rate mm/yr')
ylabel('Frequency')
savefig(os.path.join(plotsDir,site+'-PWPHist.pdf'))
#Make histogram of pearson r values
figure()
hist(rs,normed=True)
xlabel('Pearson R')
ylabel('Frequency')
savefig(os.path.join(plotsDir,'PearsonR_T_PWP.pdf'))
def make_pwp_vs_T_plots(sitesDir, siteList=None, siteFile=None, makeHistograms=True, classFile=''):
sitePanelDict, sitePhreeqcDict = loadSiteListData(processedSitesDir=sitesDir, loadPhreeqc=True)
if classFile != '':
class_xls = read_excel(classFile, 'Sheet1',index_col=1, names=['name','site', 'recharge', 'age'])
rs = []
ps = []
slopes = []
plotsDir = os.path.join(sitesDir, 'plots/')
for site in sitePanelDict.keys():
if classFile !='':
#read in classification for this site
this_class = class_xls['recharge'][site]
this_color=class_colors[this_class]
else:
this_color='black'
print("Making plot for: "+site)
#Read out data into shorter variable names
Q = sitePanelDict[site].data['Stream flow, mean. daily']
T_C = sitePanelDict[site].data['Temperature, water']
CO2 = sitePhreeqcDict[site].CO2_Molality
Ca = sitePhreeqcDict[site]['Ca']
a_Ca = sitePhreeqcDict[site]['Ca+2_Activity']
a_H2CO3s = sitePhreeqcDict[site]['CO2_Activity']
a_HCO3 = sitePhreeqcDict[site]['HCO3-_Activity']
a_H = sitePhreeqcDict[site]['H+_Activity']
#Filter out nan values
#good_values = ~(Q+T_C+CO2+Ca).isnull()#Addition will create Nans if any of the series contains a NaN
good_values = get_good_indicies([Q,T_C,CO2,Ca,a_Ca,a_H2CO3s,a_H, a_HCO3])
Q = Q[good_values]
T_C = T_C[good_values]
CO2 = CO2[good_values]
Ca = Ca[good_values]
a_Ca = a_Ca[good_values]
a_H = a_H[good_values]
a_H2CO3s = a_H2CO3s[good_values]
a_HCO3 = a_HCO3[good_values]
#Calculate PCO2
T_K = CtoK(T_C)
K_H = calc_K_H(T_K)
PCO2 = CO2/K_H
#Calculate PWP rates
pwp_rates = []
for i, value in enumerate(Q):
# sol = solutionFromCaPCO2(Ca[i], PCO2[i], T_C = T_C[i])
# this_pwp = pwpFromSolution(sol)
this_pwp = pwpRateTheory(a_Ca=a_Ca[i], a_H2CO3s=a_H2CO3s[i], a_H=a_H[i], a_HCO3=a_HCO3[i], T_K=T_K[i], PCO2=PCO2[i])
this_rate_mm_yr = pwp_to_mm_yr(this_pwp)
pwp_rates.append(this_rate_mm_yr)
#Check for plots directory and make it if one doesn't exist
check_plots_dir(sitesDir)
#Make Discharge vs. Saturation Ratio Plot
figure()
plot(T_C, pwp_rates, 'o', color=this_color)
xlabel('Temperature ($^\circ C$)')
ylabel('PWP Dissolution Rate (mm/yr)')
savefig(os.path.join(plotsDir,site+'-T_vs_PWP.pdf'))
#Calculate correlation coefficient and regression
slope,intercept,r,p,stderr = linregress(T_C, pwp_rates)
rs.append(r)
ps.append(p)
slopes.append(slope)
if makeHistograms:
figure()
hist(pwp_rates, normed=True, color=this_color)
xlabel('PWP Rate mm/yr')
ylabel('Frequency')
savefig(os.path.join(plotsDir,site+'-PWPHist.pdf'))
#Make histogram of pearson r values
figure()
hist(rs,normed=True)
xlabel('Pearson R')
ylabel('Frequency')
savefig(os.path.join(plotsDir,'PearsonR_T_PWP.pdf'))