quantity module + qrf updates

.gitignore

@@ -1,3 +1,6 @@
+polymer_names.tsv.bkup
+quantity_module/data/copy-data.sh
+qrf/copy-data.sh
 __pycache__/*
 .idea/*
 .DS_Store

ChemID.py

@@ -15,10 +15,10 @@ import json
 
 ORGANIC_ATOM_SET = {5, 6, 7, 8, 9, 15, 16, 17, 35, 53}
 METAL_ATOM_SET = set([3,4,11,12,13] + list(range(19,31+1)) + list(range(37,50+1)) + list(range(55,84+1)) + list(range(87,114+1)) + [116])
-with open('ceramics_list.txt', 'r') as fp:
+with open('data/ceramics_list.txt', 'r') as fp:
     lines = fp.readlines()
 CERAMICS_SET = {line.strip() for line in lines}
-with open('salt_list.txt', 'r') as fp:
+with open('data/salt_list.txt', 'r') as fp:
     lines = fp.readlines()
 SALT_SET = {line.strip() for line in lines}
 
@@ -53,13 +53,13 @@ from rdkit.Chem import Descriptors,Draw,Crippen
 
 ## add custom chemical definitions (i.e., to correct confusion between methane and carbon)
 db = chemicals.identifiers.get_pubchem_db()
-db.load('custom_chemicals_db.tsv')
+db.load('data/custom_chemicals_db.tsv')
 ## load experimental and predicted properties
 #dfmp_expt = pd.read_excel('PHYSPROP_MP_data.xlsx')
-dfmp_expt = pd.read_csv('PHYSPROP_MP_data.tsv', sep='\t')
+dfmp_expt = pd.read_csv('data/PHYSPROP_MP_data.tsv', sep='\t')
 #dfmp_pred = pd.read_excel('DSSTOX_MP_pred_data.xlsx')
 #df_pred = pd.read_excel('Comptox_pred_data.xlsx')
-df_pred = pd.read_csv('Comptox_pred_data.tsv', sep='\t')
+df_pred = pd.read_csv('data/Comptox_pred_data.tsv', sep='\t')
 
 ## OPERA melting point model
 import dill as pickle
@@ -249,7 +249,7 @@ def ImageFromSmiles(smiles):
     if type(smiles) is str:
         try:
             if smiles == 'C1=CC=C2C(=C1)C3=NC4=NC(=NC5=C6C=CC=CC6=C([N-]5)N=C7C8=CC=CC=C8C(=N7)N=C2[N-]3)C9=CC=CC=C94.[Mn+2]':
-                mol = next(Chem.SDMolSupplier('MnPC.sdf', removeHs=False))
+                mol = next(Chem.SDMolSupplier('data/MnPC.sdf', removeHs=False))
                 image = Draw.MolToImage(mol, size=(350, 350))
             else:
                 image = Draw.MolToImage(Chem.MolFromSmiles(smiles), size=(350, 350))

color3_module/colors.py

@@ -4,7 +4,7 @@ import numpy as np
 import pandas as pd
 from functions import SigFigs, Piringer, WilkeChang, SheetRelease, SheetRates, RatePlot
 from functions import Piecewise, PowerLaw
-from qrf_functions import QRF_Apply, QRF_Ceramic
+from qrf.functions import QRF_Apply, QRF_Ceramic
 from . import blueprint
 from polymers import Polymers, Polymers3
 from ChemID import *

exposure3_module/exposure.py

@@ -4,7 +4,7 @@ import pandas as pd
 from flask import render_template, request
 from functions import SigFigs, Piringer, WilkeChang, SheetRelease, SheetRates, RatePlot
 from functions import Piecewise, PowerLaw
-from qrf_functions import QRF_Apply, QRF_Ceramic
+from qrf.functions import QRF_Apply, QRF_Ceramic
 from . import blueprint
 from polymers import Polymers, Polymers3
 from ChemID import *

qrf/db-D-interp-allT-semiclean.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5c4399929d0bb5f72e3fee3896058e7accfbf68d63df155e409a4c2b6b87a2
+size 13087796

qrf_functions.py → qrf/functions.py

@@ -9,11 +9,23 @@ import mordred.descriptors
 import rdkit
 from rdkit import Chem
 
+QRF_T_list = np.array([25,30,35,37,40,45,50,55,60,65,70,75])
+QRF_T_cut = 2.5
+df_QRF = pd.read_excel('qrf/db-D-interp-allT-semiclean.xlsx')
+df_desc =  pd.read_excel('qrf/mordred-descriptors.xlsx')
+calc = mordred.Calculator(mordred.descriptors)
+colnames_mordred = [str(d) for d in calc.descriptors]
+df_QRF = pd.merge(df_QRF, df_desc[['Solute_InChIKey',*colnames_mordred]], how='left', on='Solute_InChIKey', suffixes=('', '_dupe'))
+
 def QRF_Ceramic(density, polytg, quantiles=[0.03,0.5,0.97], T=37, worstcase='hi'):
-    with open(f'qrf_model_bundle_{int(T)}.pkl','rb') as f:
+    nearest_T = QRF_T_list[np.abs(T-QRF_T_list).argmin()]
+    with open(f'qrf/qrf_model_bundle_{int(nearest_T)}.pkl','rb') as f:
         reg, imp, scaler_X, sub_desc_list = pickle.load(f)
-    df_X = pd.read_excel('qrf_x.xlsx')
-    df_y = pd.read_excel('qrf_y.xlsx')
+    #df_X = pd.read_excel('qrf/qrf_x.xlsx')
+    #df_y = pd.read_excel('qrf/qrf_y.xlsx')
+    mask_T = (df_QRF['T']>nearest_T-QRF_T_cut) & (df_QRF['T']<nearest_T+QRF_T_cut)
+    df_X = df_QRF.loc[mask_T, sub_desc_list]
+    df_y = df_QRF.loc[mask_T, 'LogD']
     X_all = imp.transform(df_X)
     X_all_scale = scaler_X.transform(X_all)
     ## use "worst-case" solute values
@@ -39,7 +51,8 @@ def QRF_Ceramic(density, polytg, quantiles=[0.03,0.5,0.97], T=37, worstcase='hi'
 
 
 def QRF_Apply(density, polytg, smiles, quantiles=[0.03,0.5,0.97], T=37):
-    with open(f'qrf_model_bundle_{int(T)}.pkl','rb') as f:
+    nearest_T = QRF_T_list[np.abs(T-QRF_T_list).argmin()]
+    with open(f'qrf/qrf_model_bundle_{int(nearest_T)}.pkl','rb') as f:
         reg, imp, scaler_X, sub_desc_list = pickle.load(f)
     # get list of descriptors to calculate
     solute_desc_list = sub_desc_list.copy()
@@ -67,7 +80,9 @@ def QRF_Apply(density, polytg, smiles, quantiles=[0.03,0.5,0.97], T=37):
         # return 1D array regardless of quantiles setting
         D_pred = D_pred[0]
     ## domain extrapolation check
-    df_X = pd.read_excel('qrf_x.xlsx')
+    #df_X = pd.read_excel('qrf/qrf_x.xlsx')
+    mask_T = (df_QRF['T']>nearest_T-QRF_T_cut) & (df_QRF['T']<nearest_T+QRF_T_cut)
+    df_X = df_QRF.loc[mask_T, sub_desc_list]
     X_all = imp.transform(df_X)
     X_all_scale = scaler_X.transform(X_all)
     dij = QRF_DomainExtrap(reg, X_all_scale, descs_scale)

qrf/mordred-descriptors.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121f72b88fa46a0f16af6a1244af761ee6b9d679af7ab2e32d545538f8b5c5b5
+size 10251595

qrf/qrf_model_bundle_25.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e7f3f4acd41d0548897c8d00cd41ba9129b4ab39e4d6d03bb9924a56bae417
+size 8024827

qrf/qrf_model_bundle_30.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de06c8cfff7b657ed755fd6b3dab6d2a09c742b3a1134d5bec4dc224135bba90
+size 6488642

qrf/qrf_model_bundle_35.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb21d88ccb961223607c258be1b14f45fa67c0dd6fb6a3de41d2ade394b092e
+size 13733182

qrf_model_bundle_37.pkl → qrf/qrf_model_bundle_37.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c2b2899461c3597863a6271f0bb37658f053daf1d0cba509b98b445fb45698
-size 15583438
+oid sha256:b6df089e005123321d21b33506ccf0fc4df4dafb4d953e1bd5931b92bd2445d7
+size 14843969

qrf/qrf_model_bundle_40.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e99f5b40d4c460c174e90fa44f82d10f1a54f024d961499fb08c8d18d3835e5
+size 2773504

qrf/qrf_model_bundle_45.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db0082b872c4ce725e9ebfb54ea2dcd5fd1621e4de13a2020d4842ba18f5753
+size 7288402

qrf/qrf_model_bundle_50.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38bef3650a1adb76ee07c4e9fa09058e16ffe3fc64ff18b31511f94d78a0d29
+size 7743347

qrf/qrf_model_bundle_55.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07aaf56f2d7dbeac952097146544c8ffef0a48f05a67b5b9961aca2a5c1c1127
+size 6981710

qrf/qrf_model_bundle_60.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022eba72bc51d42134229f6a9757f07ddafb763a9ae3176dc4a3c08760e3494b
+size 2651150

qrf/qrf_model_bundle_65.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c04563ec96989bd0ba4f44d09070cc543546326ca4b9aba8ef6000b8e27894d
+size 15893003

qrf/qrf_model_bundle_70.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4e7d02658d5b048d5a5d8d1de63e1bd892b561f0d0dbba95cf35a9280f48c7
+size 6673668

qrf/qrf_model_bundle_75.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36653c20dcb9c7cdcb72f32bd1121cc83d98a174e3969ba0c6dec719d93cac67
+size 2548133

qrf/qrf_parameters_allT.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8d83fd6f4f5efd9352cb33e9a4c48d05d94c4aee1b64b2a3134d847856ae52
+size 5755

qrf/qrf_train.py

@@ -0,0 +1,72 @@
+import pickle
+import numpy as np
+import pandas as pd
+import sklearn
+import sklearn.impute
+import sklearn.metrics
+from quantile_forest import RandomForestQuantileRegressor
+import mordred
+from mordred import Calculator, descriptors
+
+#T_target = 37
+#T_cut = 2.5
+qhiv, qlov = 0.97, 0.03
+state = 12345
+
+QRF_T_list = np.array([25,30,35,37,40,45,50,55,60,65,70,75])
+QRF_T_cut = 2.5
+df_QRF = pd.read_excel('db-D-interp-allT-semiclean.xlsx')
+df_desc =  pd.read_excel('mordred-descriptors.xlsx')
+calc = mordred.Calculator(mordred.descriptors)
+colnames_mordred = [str(d) for d in calc.descriptors]
+df_QRF = pd.merge(df_QRF, df_desc[['Solute_InChIKey',*colnames_mordred]], how='left', on='Solute_InChIKey', suffixes=('', '_dupe'))
+
+df_params = pd.read_excel('qrf_parameters_allT.xlsx')
+
+for T_target in QRF_T_list:
+    print(T_target)
+    if 1:
+        if T_target == 37:
+            sub_desc_list = ['MW', 'Polymer_Tg', 'Polymer_Density', 'VR2_A', 'ATS0Z', 'AATS5d', 'BCUTv-1h', 'BCUTse-1l', 'Xch-7dv', 'Mp', 'Mi', 'SaasC', 'ETA_epsilon_5', 'fragCpx', 'JGI5', 'JGI8']
+            params = {'bootstrap': True, 'max_depth': 7, 'max_features': 0.4, 'max_samples': 1.0, 'min_samples_leaf': 2, 'min_samples_split': 2, 'n_estimators': 1000} # best from -18-2.py w fout<0.040 (and 0.045)
+        elif T_target == 50:
+            sub_desc_list = ['MW', 'Polymer_Tg', 'Polymer_Density', 'ATS0m', 'ATSC2dv', 'ATSC6dv', 'ATSC0m', 'ATSC6i', 'BCUTse-1l', 'BCUTp-1h', 'Mp', 'Mi', 'SaasC']
+            params = {'bootstrap': True, 'max_depth': 6, 'max_features': 0.4, 'max_samples': 1.0, 'min_samples_leaf': 6, 'min_samples_split': 2, 'n_estimators': 1000} # best from -19.py and -19-2.py with fout<0.040
+        else:
+            mask_T = df_params['T']==T_target
+            sub_desc_list = df_params.loc[mask_T, 'sub_desc_list'].iloc[0].split('|')
+            params = df_params.loc[mask_T, ['bootstrap', 'max_depth', 'max_features', 'max_samples', 'min_samples_leaf', 'min_samples_split', 'n_estimators']].iloc[0].to_dict()
+            params['max_samples'] = float(params['max_samples'])
+    if 0:
+        sub_desc_list = ['MW', 'Polymer_Tg', 'Polymer_Density', 'VR2_A', 'ATS0Z', 'AATS5d', 'BCUTv-1h', 'BCUTse-1l', 'Xch-7dv', 'Mp', 'Mi', 'SaasC', 'ETA_epsilon_5', 'fragCpx', 'JGI5', 'JGI8']
+        params = {'bootstrap': True, 'max_depth': 7, 'max_features': 0.4, 'max_samples': 1.0, 'min_samples_leaf': 2, 'min_samples_split': 2, 'n_estimators': 1000} # best from -18-2.py w fout<0.040 (and 0.045)
+
+    ## read data
+    #df_X = pd.read_excel('qrf_x.xlsx')
+    #df_y = pd.read_excel('qrf_y.xlsx')
+    mask_T = (df_QRF['T']>T_target-QRF_T_cut) & (df_QRF['T']<T_target+QRF_T_cut)
+    df_X = df_QRF.loc[mask_T, sub_desc_list]
+    df_y = df_QRF.loc[mask_T, 'LogD']
+    #sub_desc_list = list(df_X.columns)
+
+    ## fit transforms
+    imp = sklearn.impute.SimpleImputer(missing_values=np.nan, strategy='mean')
+    imp.fit(df_X)
+    X_all = imp.transform(df_X)
+    y_all = np.array(df_y)
+    scaler_X = sklearn.preprocessing.StandardScaler().fit(X_all)
+    X_all_scale = scaler_X.transform(X_all)
+
+    reg_all = RandomForestQuantileRegressor(random_state=state, n_jobs=-1, **params)
+    reg_all.fit(X_all_scale,y_all)
+
+    with open(f'qrf_model_bundle_{T_target}.pkl','wb') as f:
+        pickle.dump([reg_all,imp,scaler_X,sub_desc_list],f)
+
+    print(sub_desc_list)
+    print(params)
+    print(mask_T.sum())
+    y_pred = reg_all.predict(X_all_scale)
+    print(y_pred.mean(),y_pred.std())
+    print()
+

qrf_train.py

@@ -1,36 +0,0 @@
-import pickle
-import numpy as np
-import pandas as pd
-import sklearn
-import sklearn.impute
-from quantile_forest import RandomForestQuantileRegressor
-
-T_target = 37
-T_cut = 5
-qhiv, qlov = 0.97, 0.03
-state = 12345
-
-if T_target == 37:
-    params = {'bootstrap': True, 'max_depth': 7, 'max_features': 0.4, 'max_samples': 1.0, 'min_samples_leaf': 2, 'min_samples_split': 2, 'n_estimators': 1000} # best from -18-2.py w fout<0.040 (and 0.045)
-
-if T_target == 50:
-    params = {'bootstrap': True, 'max_depth': 6, 'max_features': 0.4, 'max_samples': 1.0, 'min_samples_leaf': 6, 'min_samples_split': 2, 'n_estimators': 1000} # best from -19.py and -19-2.py with fout<0.040
-
-## read data
-df_X = pd.read_excel('qrf_x.xlsx')
-df_y = pd.read_excel('qrf_y.xlsx')
-sub_desc_list = list(df_X.columns)
-
-## fit transforms
-imp = sklearn.impute.SimpleImputer(missing_values=np.nan, strategy='mean')
-imp.fit(df_X)
-X_all = imp.transform(df_X)
-y_all = np.array(df_y['LogD'])
-scaler_X = sklearn.preprocessing.StandardScaler().fit(X_all)
-X_all_scale = scaler_X.transform(X_all)
-
-reg_all = RandomForestQuantileRegressor(random_state=state, n_jobs=-1, **params)
-reg_all.fit(X_all_scale,y_all)
-
-with open(f'qrf_model_bundle_{T_target}.pkl','wb') as f:
-    pickle.dump([reg_all,imp,scaler_X,sub_desc_list],f)

quantity_module/quantity.py

@@ -4,11 +4,11 @@ import pandas as pd
 from flask import render_template, request
 from functions import SigFigs, HtmlNumber, Piringer, WilkeChang, CdfPlot
 #from functions import Piecewise, PowerLaw
-from qrf_functions import QRF_Apply, QRF_Ceramic
+from qrf.functions import QRF_Apply, QRF_Ceramic
 from . import blueprint
 from polymers import Polymers, Polymers3
 from ChemID import *
-from quantity_functions import *
+from quantity_module.functions import *
 import rdkit
 from rdkit.Chem import AllChem as Chem
 
@@ -104,17 +104,23 @@ def exp_post():
     Solvent_MW = Solvent_MWs[Solvent_Name]
     Solute_MW = MW
 
+    if units == 'mg':
+        mass_units = mass*1e3
+    elif units == 'µg':
+        mass_units = mass*1e6
+
     polymer = request.form['polymer']
     pIndex = np.argmax(polymers == polymer)
 
-    # QRF is only implemented for 37 and 50 C
-    if polymer == 'Other polymer' and round(T) in [310,323]:
+    # QRF is implemented for 25-75 C
+    if polymer == 'Other polymer':
         use_qrf = True
     else:
         use_qrf = False
 
     if use_qrf:
-        quantiles = list(np.linspace(0.05,0.95,181))
+        quantiles = list(np.linspace(0.0,1.0,201))
+        #quantiles = list(np.linspace(0.05,0.95,181))
         if is_ceramic:
             diff,domain_extrap = QRF_Ceramic(Polymer_Density, Polymer_Tg, quantiles=quantiles, T=T-273.15, worstcase='lo')
         else:
@@ -143,13 +149,18 @@ def exp_post():
         else:
             method = 'wc'
     if 1:
+        print('DEBUG')
         print('Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, CHRIS_category')
         print(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, CHRIS_category)
         print(np.nanquantile(D_dist_noswell, [0.05,0.5,0.95]))
         print(np.nanquantile(D_dist_swell, [0.05,0.5,0.95]))
-        print('M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt')
-        print(M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt)
+        print('M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt, method')
+        print(M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt, method)
         print(np.nanquantile(M0_pred, [0.05,0.5,0.95]))
+        V1,V2 = get_D_dists(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, 'G2', rng, return_DCs=False, N=N_sample)
+        V3 = get_M_dist(V2, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt)
+        print(np.nanquantile(V2, [0.05,0.5,0.95]))
+        print(np.nanquantile(V3, [0.05,0.5,0.95]))
 
     # Generate the rate plot using matplotlib
     #pngImageB64String = CdfPlot(M0_pred[~np.isnan(M0_pred)], units=units)
@@ -172,11 +183,12 @@ def exp_post():
 
     M0_out = SigFigs(np.nanquantile(M0_pred,0.5),6)
     tau_out = SigFigs(tau,6)
+    mass_units = SigFigs(mass_units,6)
 
     return render_template('quantity_report.html', show_properties=show_properties, polymers=polymers, pIndex=pIndex, 
                            area=Surface_Area, vol=Polymer_Volume, units=units, M=M_expt, M0=M0_out, time=Extraction_Time, 
                            solventvol=Solvent_Volume, solventname=Solvent_Name, swelling=Swelling_percent, K=K_expt, T=T, tau=tau_out,
                            chemName=chemName, MW=MW, LogP=LogP, rho=rho, mp=mp, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage, table=table,
-                           LogP_origin=LogP_origin, rho_origin=rho_origin, mp_origin=mp_origin, ceramic=is_ceramic, methods=[method,round(Polymer_Tg),Polymer_Density],
-                           mass=mass, density=Polymer_Density)
+                           LogP_origin=LogP_origin, rho_origin=rho_origin, mp_origin=mp_origin, ceramic=is_ceramic, methods=[method,round(Polymer_Tg-273.15),Polymer_Density],
+                           mass=mass, mass_units=mass_units, density=Polymer_Density)
 

quantity_module/templates/quantity_index.html

@@ -149,7 +149,7 @@ please see the <a href="{{url_for('.static', filename='RST.html')}}"> RST inform
   <tr><td colspan="2"><h4> Extraction parameters  <button type=button class="Info_btn" data-toggle="modal" data-target="#ExtractionModal">&#9432;</button></td></tr> </h4>
       <tr><th>Device surface area (cm<sup>2</sup>)</th><td> <input name="area" id="area" step="any" value="5.0" min="0.001" type="number" required></td></tr>
       <tr><th>Duration (hours)</th><td>                     <input name="time" id="time" step="any" value="24.0" min="0.001" type="number" required></td></tr>
-      <tr><th>Temperature (&deg;C)</th><td>                 <input name="T" id="T" step="any" value="50.0" min="20" max="75" type="number" required></td></tr>
+      <tr><th>Temperature (&deg;C)</th><td>                 <input name="T" id="T" step="any" value="50.0" min="25" max="75" type="number" required></td></tr>
       <tr><th>Solvent</th>
         <td> <select name="solventname" id="solventname">
         <option value="{{solvents[0]}}" selected>{{solvents[0]}}</option>

quantity_module/templates/quantity_report.html

@@ -119,6 +119,13 @@ Swelling = {{swelling}} wt% (used to estimate \( D \))<br>
 
 <p>The progress of the extraction can be expressed through the dimensionless time \( \tau \). For your extraction, \( \tau \) = {{tau}}. Extractions with \( \tau \) &geq; 0.1 result in more accurate estimates of the total quantity, and when \( \tau \) &geq; 1.0 the extracted amount may be used directly as the total quantity if the extraction is diffusion-controlled.</p>
 
+{% if M0>=mass_units %}
+<p>
+<font color="red">The predicted amount ({{M0}} {{units}}) is larger than the device mass ({{mass_units}} {{units}}) due to uncertainty and conservatism in the prediction. 
+In this case the device mass may be used as a conservative estimate of the total quantity of this extractable.</font>
+</p>
+{% endif  %}
+
 <p><button type="button" onclick="javascript:history.back()">Back</button></p>
 
 </body>