add model

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,6 @@
+This respository contains trained neural networks that can be used to predict the steady-state temperature profile.
+
+Step 1: Define the simulation parameters 
+Step 2: The output is as follows  
+        - the depth profile (first column) and the temperature profile (second column)  
+        - corresonding plot of the temperature profile  

.ipynb_checkpoints/app-checkpoint.py

@@ -0,0 +1,59 @@
+import streamlit as st
+
+from matplotlib import pyplot as plt
+from utils import * 
+import warnings
+
+raq_ra = st.number_input("# raq/ra ", value=None, placeholder="betweel 0 and 10")
+st.write("raq/ra = ", raq_ra)
+
+fkt = st.number_input("# FKT ", value=None, placeholder="betweel 1e+6 and 1e+10")
+st.write("FKT = ", fkt)
+
+fkv = st.number_input("# FKV ", value=None, placeholder="betweel 0 and 100")
+st.write("FKV = ", fkv)
+
+num_points = st.number_input("# number of profile points ", value=None, placeholder=" e.g. 128")
+st.write("number of profile points = ", num_points)
+
+with open('numpy_networks/mlp_[256, 256, 256, 256].pkl', 'rb') as file: 
+    mlp = pickle.load(file) 
+
+r_list = [raq_ra]
+t_list = [fkt]
+v_list = [fkv]
+
+for i in range(len(r_list)):
+    if r_list[i]<0 or  r_list[i]>9.5:
+        warnings.warn('RaQ/Ra is outside the range of the training dataset') 
+    if t_list[i]<1e+6 or  t_list[i]>5e+9:
+        warnings.warn('FKT is outside the range of the training dataset')
+    if v_list[i]<1 or  v_list[i]>95:
+        warnings.warn('FKV is outside the range of the training dataset')
+
+y_prof = np.linspace(0,1,num_points)[::-1]
+
+### calculates temperature profile ###
+x_in = get_input(r_list, t_list, v_list, y_prof)
+y_pred_nn_pointwise = get_profile(x_in, mlp, num_sims=len(r_list)) 
+### calculates temperature profile ###
+
+### writes out temperature profile ###
+st.write("Depth", "Temperature")
+for i in range(len(r_list)):
+    for j in range(len(y_prof)):
+        st.write(str(y_prof[j]) ,"   ", str(y_pred_nn_pointwise[i,j]), "\n")
+### writes out temperature profile ###
+
+
+### plots temperature profile ###
+for i in range(len(r_list)):
+    plt.figure()
+    plt.plot(y_pred_nn_pointwise[i,:], y_prof, 'k-', linewidth=3.0, label="pointwise neural network")
+    plt.ylim([1,0])
+    plt.xlabel("Temperature")
+    plt.ylabel("Depth")
+    plt.legend()
+    plt.grid()
+    st.pyplot(fig)
+### plots temperature profile ###

.ipynb_checkpoints/calculate_profiles-checkpoint.py

@@ -0,0 +1,80 @@
+from matplotlib import pyplot as plt
+from utils import * 
+import warnings
+
+#### Define outputs ####
+write_file   = True
+plot_profile = True
+#### Define outputs ####
+
+with open('numpy_networks/mlp_[256, 256, 256, 256].pkl', 'rb') as file: 
+    mlp = pickle.load(file) 
+
+f_nn = "my_simulation_parameters.txt"    
+with open(f_nn) as fw:
+    lines = fw.readlines()
+
+for line in lines:
+    l = line.rstrip()
+    if "r_list" in l:
+        if not l[-1] == ",":
+            raise Exception("Ensure there is a comma after last parameter value in " + f_nn)
+        r_list = [float(p) for p in l.split("=")[1].split(",")[:-1]]
+    elif "t_list" in line:
+        if not l[-1] == ",":
+            raise Exception("Ensure there is a comma after last parameter value in " + f_nn)
+        t_list = [float(p) for p in l.split("=")[1].split(",")[:-1]]
+    elif "v_list" in line:
+        if not l[-1] == ",":
+            raise Exception("Ensure there is a comma after last parameter value in " + f_nn)
+        v_list = [float(p) for p in l.split("=")[1].split(",")[:-1]]
+
+if not len(r_list) == len(v_list) and len(r_list) == len(t_list):
+    raise Exception("Ensure equal number of values for all parameters in " + f_nn)
+
+for i in range(len(r_list)):
+    if r_list[i]<0 or  r_list[i]>9.5:
+        warnings.warn('RaQ/Ra is outside the range of the training dataset') 
+    if t_list[i]<1e+6 or  t_list[i]>5e+9:
+        warnings.warn('FKT is outside the range of the training dataset')
+    if v_list[i]<1 or  v_list[i]>95:
+        warnings.warn('FKV is outside the range of the training dataset')
+
+### calculates y points ###
+num_points = 128
+y_prof = np.linspace(0,1,num_points)[::-1]
+### calculates y points ###
+
+
+### calculates temperature profile ###
+x_in = get_input(r_list, t_list, v_list, y_prof)
+y_pred_nn_pointwise = get_profile(x_in, mlp, num_sims=len(r_list)) 
+### calculates temperature profile ###
+
+
+### writes out temperature profile ###
+if write_file:
+    for i in range(len(r_list)):
+        fname = "outputs/profile_raq_ra" + str(r_list[i]) + "_fkt" + str(t_list[i]) + "_fkv" + str(v_list[i])
+        f = open(fname + ".txt", "wb")
+        for j in range(len(y_prof)):
+            f.writelines([str(y_prof[j]).encode('ascii'), 
+                          "   ".encode('ascii'), 
+                          str(y_pred_nn_pointwise[i,j]).encode('ascii'), 
+                          "\n".encode('ascii')])
+        f.close()
+### writes out temperature profile ###
+
+
+### plots temperature profile ###
+for i in range(len(r_list)):
+    fname = "outputs/profile_raq_ra" + str(r_list[i]) + "_fkt" + str(t_list[i]) + "_fkv" + str(v_list[i])
+    plt.figure()
+    plt.plot(y_pred_nn_pointwise[i,:], y_prof, 'k-', linewidth=3.0, label="pointwise neural network")
+    plt.ylim([1,0])
+    plt.xlabel("Temperature")
+    plt.ylabel("Depth")
+    plt.legend()
+    plt.grid()
+    plt.savefig(fname + ".png")
+### plots temperature profile ###

.ipynb_checkpoints/utils-checkpoint.py

@@ -0,0 +1,69 @@
+import numpy as np
+import pickle
+
+def selu(x):
+    alpha = 1.6732632423543772848170429916717 
+    scale = 1.0507009873554804934193349852946
+    return scale*( np.maximum(0,x) + np.minimum(alpha*(np.exp(x)-1), 0) )
+
+def non_dimensionalize_raq(x):
+    return (x-0.12624371)/(9.70723344-0.12624371)
+
+def non_dimensionalize_fkt(x):
+    return (np.log10(x)-6.00352841978384)/(9.888820429862925-6.00352841978384)
+
+def non_dimensionalize_fkv(x):
+    return (np.log10(x)-0.005251646002323797)/(1.9927988938926755-0.005251646002323797)
+
+def dimensionalize_raq(x):
+    return x*(9.70723344-0.12624371) + 0.12624371
+
+def dimensionalize_fkt(x):
+    return 10**(x*(9.888820429862925-6.00352841978384)+6.00352841978384)
+
+def dimensionalize_fkv(x):
+    return 10**(x*(1.9927988938926755-0.005251646002323797)+0.005251646002323797)
+
+def get_input(raq_ra, fkt, fkp, y_prof):
+    
+    x = np.zeros((len(raq_ra)*len(y_prof), 4))
+
+    cntr = 0
+    for i in range(len(raq_ra)):
+        for j in range(len(y_prof)):
+            x[cntr,0] = non_dimensionalize_raq(raq_ra[i])
+            x[cntr,1] = non_dimensionalize_fkt(fkt[i])
+            x[cntr,2] = non_dimensionalize_fkv(fkp[i])
+            x[cntr,3] = y_prof[j]
+            cntr += 1    
+            
+    return x
+
+def get_profile(inp, mlp, num_sims=1, num_points=128):
+    
+    num_layers = len(mlp)-1
+    y_pred = inp
+    res = []
+    for l in range(num_layers+1):
+        
+        y_pred = y_pred @ mlp[l][0].T + mlp[l][1]
+
+        if l in [num_layers-1]:
+            y_pred = np.concatenate((inp,y_pred), axis=-1)
+            
+        if l != num_layers:
+            for r in res:
+                y_pred += r
+                
+            y_pred = selu(y_pred)
+            res.append(y_pred)
+                
+    y_pred = y_pred.reshape(num_sims, num_points)
+    y_pred[:,0]  = 1.
+    y_pred[:,-1] = 0.
+
+    return y_pred
+
+
+
+

README.md

@@ -1,13 +1,6 @@
----
-title: Steadystate Mantle
-emoji: 🐠
-colorFrom: red
-colorTo: purple
-sdk: streamlit
-sdk_version: 1.35.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+This respository contains trained neural networks that can be used to predict the steady-state temperature profile.
+
+Step 1: Define the simulation parameters 
+Step 2: The output is as follows  
+        - the depth profile (first column) and the temperature profile (second column)  
+        - corresonding plot of the temperature profile  

app.py

@@ -1,10 +1,59 @@
 import streamlit as st
 
-number = st.number_input("# raq/ra ", value=None, placeholder="betweel 0 and 10")
-st.write("raq/ra = ", number)
+from matplotlib import pyplot as plt
+from utils import * 
+import warnings
 
-number = st.number_input("# FKT ", value=None, placeholder="betweel 1e+6 and 1e+10")
-st.write("FKT = ", number)
+raq_ra = st.number_input("# raq/ra ", value=None, placeholder="betweel 0 and 10")
+st.write("raq/ra = ", raq_ra)
 
-number = st.number_input("# FKV ", value=None, placeholder="betweel 0 and 100")
-st.write("FKV = ", number)
+fkt = st.number_input("# FKT ", value=None, placeholder="betweel 1e+6 and 1e+10")
+st.write("FKT = ", fkt)
+
+fkv = st.number_input("# FKV ", value=None, placeholder="betweel 0 and 100")
+st.write("FKV = ", fkv)
+
+num_points = st.number_input("# number of profile points ", value=None, placeholder=" e.g. 128")
+st.write("number of profile points = ", num_points)
+
+with open('numpy_networks/mlp_[256, 256, 256, 256].pkl', 'rb') as file: 
+    mlp = pickle.load(file) 
+
+r_list = [raq_ra]
+t_list = [fkt]
+v_list = [fkv]
+
+for i in range(len(r_list)):
+    if r_list[i]<0 or  r_list[i]>9.5:
+        warnings.warn('RaQ/Ra is outside the range of the training dataset') 
+    if t_list[i]<1e+6 or  t_list[i]>5e+9:
+        warnings.warn('FKT is outside the range of the training dataset')
+    if v_list[i]<1 or  v_list[i]>95:
+        warnings.warn('FKV is outside the range of the training dataset')
+
+y_prof = np.linspace(0,1,num_points)[::-1]
+
+### calculates temperature profile ###
+x_in = get_input(r_list, t_list, v_list, y_prof)
+y_pred_nn_pointwise = get_profile(x_in, mlp, num_sims=len(r_list)) 
+### calculates temperature profile ###
+
+### writes out temperature profile ###
+st.write("Depth", "Temperature")
+for i in range(len(r_list)):
+    for j in range(len(y_prof)):
+        st.write(str(y_prof[j]) ,"   ", str(y_pred_nn_pointwise[i,j]), "\n")
+### writes out temperature profile ###
+
+
+### plots temperature profile ###
+for i in range(len(r_list)):
+    plt.figure()
+    plt.plot(y_pred_nn_pointwise[i,:], y_prof, 'k-', linewidth=3.0, label="pointwise neural network")
+    plt.ylim([1,0])
+    plt.xlabel("Temperature")
+    plt.ylabel("Depth")
+    plt.legend()
+    plt.grid()
+    st.pyplot(fig)
+### plots temperature profile ###

calculate_profiles.py

@@ -0,0 +1,80 @@
+from matplotlib import pyplot as plt
+from utils import * 
+import warnings
+
+#### Define outputs ####
+write_file   = True
+plot_profile = True
+#### Define outputs ####
+
+with open('numpy_networks/mlp_[256, 256, 256, 256].pkl', 'rb') as file: 
+    mlp = pickle.load(file) 
+
+f_nn = "my_simulation_parameters.txt"    
+with open(f_nn) as fw:
+    lines = fw.readlines()
+
+for line in lines:
+    l = line.rstrip()
+    if "r_list" in l:
+        if not l[-1] == ",":
+            raise Exception("Ensure there is a comma after last parameter value in " + f_nn)
+        r_list = [float(p) for p in l.split("=")[1].split(",")[:-1]]
+    elif "t_list" in line:
+        if not l[-1] == ",":
+            raise Exception("Ensure there is a comma after last parameter value in " + f_nn)
+        t_list = [float(p) for p in l.split("=")[1].split(",")[:-1]]
+    elif "v_list" in line:
+        if not l[-1] == ",":
+            raise Exception("Ensure there is a comma after last parameter value in " + f_nn)
+        v_list = [float(p) for p in l.split("=")[1].split(",")[:-1]]
+
+if not len(r_list) == len(v_list) and len(r_list) == len(t_list):
+    raise Exception("Ensure equal number of values for all parameters in " + f_nn)
+
+for i in range(len(r_list)):
+    if r_list[i]<0 or  r_list[i]>9.5:
+        warnings.warn('RaQ/Ra is outside the range of the training dataset') 
+    if t_list[i]<1e+6 or  t_list[i]>5e+9:
+        warnings.warn('FKT is outside the range of the training dataset')
+    if v_list[i]<1 or  v_list[i]>95:
+        warnings.warn('FKV is outside the range of the training dataset')
+
+### calculates y points ###
+num_points = 128
+y_prof = np.linspace(0,1,num_points)[::-1]
+### calculates y points ###
+
+
+### calculates temperature profile ###
+x_in = get_input(r_list, t_list, v_list, y_prof)
+y_pred_nn_pointwise = get_profile(x_in, mlp, num_sims=len(r_list)) 
+### calculates temperature profile ###
+
+
+### writes out temperature profile ###
+if write_file:
+    for i in range(len(r_list)):
+        fname = "outputs/profile_raq_ra" + str(r_list[i]) + "_fkt" + str(t_list[i]) + "_fkv" + str(v_list[i])
+        f = open(fname + ".txt", "wb")
+        for j in range(len(y_prof)):
+            f.writelines([str(y_prof[j]).encode('ascii'), 
+                          "   ".encode('ascii'), 
+                          str(y_pred_nn_pointwise[i,j]).encode('ascii'), 
+                          "\n".encode('ascii')])
+        f.close()
+### writes out temperature profile ###
+
+
+### plots temperature profile ###
+for i in range(len(r_list)):
+    fname = "outputs/profile_raq_ra" + str(r_list[i]) + "_fkt" + str(t_list[i]) + "_fkv" + str(v_list[i])
+    plt.figure()
+    plt.plot(y_pred_nn_pointwise[i,:], y_prof, 'k-', linewidth=3.0, label="pointwise neural network")
+    plt.ylim([1,0])
+    plt.xlabel("Temperature")
+    plt.ylabel("Depth")
+    plt.legend()
+    plt.grid()
+    plt.savefig(fname + ".png")
+### plots temperature profile ###

inputs/.ipynb_checkpoints/simulations-checkpoint.txt

@@ -0,0 +1,133 @@
+----------  -------  ----------  -----------  ------------
+Simulation  Dataset  RaQ/Ra      FKT          FKV
+0           train    4.21479129  3.01635241   86422511.6
+1           test     9.51640694  94.18089723  4821329.69
+2           cv       6.271087    42.76214789  4941931.78
+3           train    0.44977861  10.12215385  94829681.7
+4           train    8.36560001  35.73834584  1455479.5
+5           train    5.67467946  1.64110011   6367690.4
+6           train    0.70579799  5.84651349   1187881210.0
+7           train    7.52290158  53.86099519  12388219.2
+8           train    0.12624371  24.95454721  1318547.97
+9           train    2.2359818   1.05720485   199740515.0
+10          train    3.02242373  11.01921145  1640799310.0
+11          train    6.26027711  4.53218755   366333588.0
+12          train    4.62259524  11.02248583  427407621.0
+13          train    1.43277485  24.85716255  12376736.0
+14          train    7.5645277   4.35148281   401681704.0
+15          test     6.70361149  73.08858228  6558027490.0
+16          train    0.40661271  52.21228433  90006820.6
+17          cv       8.63392765  2.64317264   2187883890.0
+18          train    3.41552419  53.31843207  73876163.5
+19          train    8.36636851  1.2217876    20837722.4
+20          train    3.12477618  1.09223116   804157796.0
+21          train    6.15233896  45.71924975  106800064.0
+22          train    2.68648417  25.01160266  452572724.0
+23          train    5.62854856  16.83603314  55118347.0
+24          train    1.99522057  50.38927796  11793606.7
+25          train    8.43504053  1.74586381   72241124.0
+26          train    0.15682868  3.01303633   48187633.5
+27          train    5.23937284  18.24324448  232584444.0
+28          train    6.31543445  10.52630296  14606584.6
+29          train    1.73038798  2.83393888   16181068.4
+30          train    8.68359761  16.95695456  378170888.0
+31          train    3.57184556  11.05039248  1719860.91
+32          cv       5.76158491  4.53324069   2126761.12
+33          train    1.70166218  38.34916682  228426072.0
+34          train    3.30432282  2.89257812   17507664.5
+35          train    4.5068189   17.86232579  27437525.3
+36          train    6.23026526  2.72393805   7692784.95
+37          train    5.51926251  34.72353772  81760879.4
+38          cv       5.61895019  13.79164313  967450922.0
+39          cv       1.09103611  91.31624922  1517951.65
+40          cv       3.54175058  39.71096834  1008157.58
+41          train    1.92594717  37.01010991  9772036.92
+42          test     9.70723344  56.28276492  1015330.41
+43          train    3.08975856  4.57055172   17770265.0
+44          train    1.38024964  22.65176318  10395536.1
+45          train    3.75282062  19.97972718  104595781.0
+46          train    1.22269777  14.27630401  1679205170.0
+47          train    2.80488044  2.29915349   3593013.29
+48          train    5.13189578  13.2442949   136549073.0
+49          train    4.9460591   10.7995829   24287525.2
+50          train    4.99909724  22.46165834  52737683.8
+51          train    7.31775345  7.73718569   1020606.79
+52          train    7.06258578  86.12572482  2224833.68
+53          train    0.6899426   59.64510385  1932628.07
+54          train    3.386145    3.55017896   21014570.1
+55          test     7.38284445  11.66799278  7538933640.0
+56          train    4.08423546  1.74922806   725904067.0
+57          cv       2.67362452  26.28214014  51821221.6
+58          test     2.24712439  98.26613159  129667315.0
+59          cv       4.44838147  4.03057782   2805039520.0
+60          cv       2.80942173  10.34159997  284317229.0
+61          train    7.79341449  2.02389494   698171693.0
+62          train    2.14158405  1.09767463   214437223.0
+63          train    1.00672028  1.77203701   2146927190.0
+64          train    2.75896303  1.01216577   1629808.7
+65          train    2.31856541  16.92198257  3258621.07
+66          train    0.51313958  76.60516337  16316079.4
+67          train    6.91868053  2.29281923   2581835.05
+68          test     3.19785433  38.51330949  7741416430.0
+69          test     9.70176645  66.88205995  6742721.02
+70          train    4.5807426   19.59110792  4389885.79
+71          train    0.74078406  2.52622848   511362006.0
+72          train    5.08755399  7.40943107   19058749.0
+73          train    4.99394988  1.27436515   6085204.83
+74          train    0.45521012  20.65980997  40770664.9
+75          train    3.97347544  10.76777553  1610519.78
+76          cv       6.9980184   85.15026443  85457763.4
+77          test     9.68233821  2.24352405   9101478.03
+78          train    3.5983924   59.08511032  513989594.0
+79          train    1.71516547  5.28981365   2021804.21
+80          train    8.90619866  92.87866715  842798515.0
+81          train    2.15518657  34.53441385  142408852.0
+82          train    4.18290969  40.8230102   5667779.62
+83          cv       4.40076342  2.60998341   86553821.3
+84          train    7.923791    2.00903448   7847389.6
+85          test     9.49745122  96.2027838   64145832.8
+86          test     3.00577213  1.77607573   6848799970.0
+87          test     6.43144786  2.80081331   5133341820.0
+88          train    3.23268188  7.33454372   683657849.0
+89          train    1.45449431  66.14228054  12661236.2
+90          train    7.55357502  47.56032424  840358151.0
+91          train    0.8745516   19.03683004  1348280.14
+92          cv       2.48944593  64.96293189  1453255.63
+93          test     3.29462875  23.07376101  7301730590.0
+94          test     3.08732987  98.35555512  14813542.7
+95          cv       2.27394372  55.85930328  3949869450.0
+96          train    2.16161172  11.81239082  465455593.0
+97          train    7.00771735  4.13900522   1880711.48
+98          cv       0.526931    16.34974624  24964307.0
+99          train    1.07206555  2.98839101   211956460.0
+100         train    6.79733173  2.58574662   475523342.0
+101         train    5.10030487  4.03819673   1664087320.0
+102         train    7.46133626  5.88239496   109443847.0
+103         train    1.31598953  29.4046416   20509114.1
+104         train    7.67114992  1.7810773    3772943.1
+105         cv       5.79324631  6.49745687   2011480.87
+106         train    6.94242801  1.06855549   8393763.9
+107         train    7.87136172  10.88264954  169155714.0
+108         train    0.53522819  83.44910045  3944779.68
+109         train    4.35426606  4.52555225   100728730.0
+110         train    0.32364009  9.14243349   322819020.0
+111         train    3.66563052  10.08158087  168383022.0
+112         test     7.87992683  5.70103793   5860425410.0
+113         train    0.26710223  3.57980514   3636478.69
+114         train    2.22284414  1.08850972   10277545.5
+115         train    0.97760298  1.86846107   103097759.0
+116         train    2.38140612  32.34044506  3319135.1
+117         train    9.32155776  9.07025187   231431645.0
+118         test     9.98475203  20.79358182  5235741.91
+119         train    8.75081696  28.82373853  1686046950.0
+120         train    0.80523448  6.37660281   3296282.95
+121         train    5.3432885   73.14491846  2298401.12
+122         cv       9.17743012  7.49928359   179784166.0
+123         train    3.00500403  16.42289134  4046947.23
+124         train    2.45033082  13.06101342  3027412.85
+125         train    5.47610781  70.54556374  1311680.04
+126         train    7.10811033  2.59864226   4812900.22
+127         test     9.46423039  1.90577479   7513000020.0
+128         train    2.7278834   5.33062584   495559360.0
+129         train    7.66466625  3.97436225   8300665.59
+----------  -------  ----------  -----------  ------------

inputs/simulations.txt

@@ -0,0 +1,133 @@
+----------  -------  ----------  ------------  -----------
+Simulation  Dataset  RaQ/Ra      FKT           FKV
+0           train    4.21479129  86422511.6    3.01635241
+1           test     9.51640694  4821329.69    94.18089723
+2           cv       6.271087    4941931.78    42.76214789
+3           train    0.44977861  94829681.7    10.12215385
+4           train    8.36560001  1455479.5     35.73834584
+5           train    5.67467946  6367690.4     1.64110011
+6           train    0.70579799  1187881210.0  5.84651349
+7           train    7.52290158  12388219.2    53.86099519
+8           train    0.12624371  1318547.97    24.95454721
+9           train    2.2359818   199740515.0   1.05720485
+10          train    3.02242373  1640799310.0  11.01921145
+11          train    6.26027711  366333588.0   4.53218755
+12          train    4.62259524  427407621.0   11.02248583
+13          train    1.43277485  12376736.0    24.85716255
+14          train    7.5645277   401681704.0   4.35148281
+15          test     6.70361149  6558027490.0  73.08858228
+16          train    0.40661271  90006820.6    52.21228433
+17          cv       8.63392765  2187883890.0  2.64317264
+18          train    3.41552419  73876163.5    53.31843207
+19          train    8.36636851  20837722.4    1.2217876
+20          train    3.12477618  804157796.0   1.09223116
+21          train    6.15233896  106800064.0   45.71924975
+22          train    2.68648417  452572724.0   25.01160266
+23          train    5.62854856  55118347.0    16.83603314
+24          train    1.99522057  11793606.7    50.38927796
+25          train    8.43504053  72241124.0    1.74586381
+26          train    0.15682868  48187633.5    3.01303633
+27          train    5.23937284  232584444.0   18.24324448
+28          train    6.31543445  14606584.6    10.52630296
+29          train    1.73038798  16181068.4    2.83393888
+30          train    8.68359761  378170888.0   16.95695456
+31          train    3.57184556  1719860.91    11.05039248
+32          cv       5.76158491  2126761.12    4.53324069
+33          train    1.70166218  228426072.0   38.34916682
+34          train    3.30432282  17507664.5    2.89257812
+35          train    4.5068189   27437525.3    17.86232579
+36          train    6.23026526  7692784.95    2.72393805
+37          train    5.51926251  81760879.4    34.72353772
+38          cv       5.61895019  967450922.0   13.79164313
+39          cv       1.09103611  1517951.65    91.31624922
+40          cv       3.54175058  1008157.58    39.71096834
+41          train    1.92594717  9772036.92    37.01010991
+42          test     9.70723344  1015330.41    56.28276492
+43          train    3.08975856  17770265.0    4.57055172
+44          train    1.38024964  10395536.1    22.65176318
+45          train    3.75282062  104595781.0   19.97972718
+46          train    1.22269777  1679205170.0  14.27630401
+47          train    2.80488044  3593013.29    2.29915349
+48          train    5.13189578  136549073.0   13.2442949
+49          train    4.9460591   24287525.2    10.7995829
+50          train    4.99909724  52737683.8    22.46165834
+51          train    7.31775345  1020606.79    7.73718569
+52          train    7.06258578  2224833.68    86.12572482
+53          train    0.6899426   1932628.07    59.64510385
+54          train    3.386145    21014570.1    3.55017896
+55          test     7.38284445  7538933640.0  11.66799278
+56          train    4.08423546  725904067.0   1.74922806
+57          cv       2.67362452  51821221.6    26.28214014
+58          test     2.24712439  129667315.0   98.26613159
+59          cv       4.44838147  2805039520.0  4.03057782
+60          cv       2.80942173  284317229.0   10.34159997
+61          train    7.79341449  698171693.0   2.02389494
+62          train    2.14158405  214437223.0   1.09767463
+63          train    1.00672028  2146927190.0  1.77203701
+64          train    2.75896303  1629808.7     1.01216577
+65          train    2.31856541  3258621.07    16.92198257
+66          train    0.51313958  16316079.4    76.60516337
+67          train    6.91868053  2581835.05    2.29281923
+68          test     3.19785433  7741416430.0  38.51330949
+69          test     9.70176645  6742721.02    66.88205995
+70          train    4.5807426   4389885.79    19.59110792
+71          train    0.74078406  511362006.0   2.52622848
+72          train    5.08755399  19058749.0    7.40943107
+73          train    4.99394988  6085204.83    1.27436515
+74          train    0.45521012  40770664.9    20.65980997
+75          train    3.97347544  1610519.78    10.76777553
+76          cv       6.9980184   85457763.4    85.15026443
+77          test     9.68233821  9101478.03    2.24352405
+78          train    3.5983924   513989594.0   59.08511032
+79          train    1.71516547  2021804.21    5.28981365
+80          train    8.90619866  842798515.0   92.87866715
+81          train    2.15518657  142408852.0   34.53441385
+82          train    4.18290969  5667779.62    40.8230102
+83          cv       4.40076342  86553821.3    2.60998341
+84          train    7.923791    7847389.6     2.00903448
+85          test     9.49745122  64145832.8    96.2027838
+86          test     3.00577213  6848799970.0  1.77607573
+87          test     6.43144786  5133341820.0  2.80081331
+88          train    3.23268188  683657849.0   7.33454372
+89          train    1.45449431  12661236.2    66.14228054
+90          train    7.55357502  840358151.0   47.56032424
+91          train    0.8745516   1348280.14    19.03683004
+92          cv       2.48944593  1453255.63    64.96293189
+93          test     3.29462875  7301730590.0  23.07376101
+94          test     3.08732987  14813542.7    98.35555512
+95          cv       2.27394372  3949869450.0  55.85930328
+96          train    2.16161172  465455593.0   11.81239082
+97          train    7.00771735  1880711.48    4.13900522
+98          cv       0.526931    24964307.0    16.34974624
+99          train    1.07206555  211956460.0   2.98839101
+100         train    6.79733173  475523342.0   2.58574662
+101         train    5.10030487  1664087320.0  4.03819673
+102         train    7.46133626  109443847.0   5.88239496
+103         train    1.31598953  20509114.1    29.4046416
+104         train    7.67114992  3772943.1     1.7810773
+105         cv       5.79324631  2011480.87    6.49745687
+106         train    6.94242801  8393763.9     1.06855549
+107         train    7.87136172  169155714.0   10.88264954
+108         train    0.53522819  3944779.68    83.44910045
+109         train    4.35426606  100728730.0   4.52555225
+110         train    0.32364009  322819020.0   9.14243349
+111         train    3.66563052  168383022.0   10.08158087
+112         test     7.87992683  5860425410.0  5.70103793
+113         train    0.26710223  3636478.69    3.57980514
+114         train    2.22284414  10277545.5    1.08850972
+115         train    0.97760298  103097759.0   1.86846107
+116         train    2.38140612  3319135.1     32.34044506
+117         train    9.32155776  231431645.0   9.07025187
+118         test     9.98475203  5235741.91    20.79358182
+119         train    8.75081696  1686046950.0  28.82373853
+120         train    0.80523448  3296282.95    6.37660281
+121         train    5.3432885   2298401.12    73.14491846
+122         cv       9.17743012  179784166.0   7.49928359
+123         train    3.00500403  4046947.23    16.42289134
+124         train    2.45033082  3027412.85    13.06101342
+125         train    5.47610781  1311680.04    70.54556374
+126         train    7.10811033  4812900.22    2.59864226
+127         test     9.46423039  7513000020.0  1.90577479
+128         train    2.7278834   495559360.0   5.33062584
+129         train    7.66466625  8300665.59    3.97436225
+----------  -------  ----------  ------------  -----------

numpy_networks/mlp_[256, 256, 256, 256].pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655be8aae8c72cf27ff9de99522941f5d9b3bb8055c79f3d252b99b2995ff1fb
+size 1583595

outputs/.ipynb_checkpoints/profile_raq_ra5.0_fkt100000.0_fkv10.0-checkpoint.txt

@@ -0,0 +1,128 @@
+1.0   1.0
+0.9921259842519685   1.0178024589432006
+0.984251968503937   1.02419132486311
+0.9763779527559056   1.0321625073297056
+0.968503937007874   1.0421713204767553
+0.9606299212598425   1.0516163062641521
+0.952755905511811   1.0614091699716657
+0.9448818897637795   1.0715877577625534
+0.937007874015748   1.0810735731530021
+0.9291338582677166   1.089926726337548
+0.9212598425196851   1.0982001155465002
+0.9133858267716535   1.1058568867629859
+0.905511811023622   1.1129892549680713
+0.8976377952755905   1.1198585877833815
+0.889763779527559   1.1264196723670623
+0.8818897637795275   1.132586150591497
+0.8740157480314961   1.1384566274167192
+0.8661417322834646   1.1456330495711229
+0.8582677165354331   1.1523635015752953
+0.8503937007874016   1.1586039897141758
+0.84251968503937   1.164203314751497
+0.8346456692913385   1.1694048936942336
+0.8267716535433071   1.1742405969709162
+0.8188976377952756   1.17876629362649
+0.8110236220472441   1.18299415999214
+0.8031496062992126   1.1869087505503264
+0.7952755905511811   1.1905182923886117
+0.7874015748031495   1.1938298366132871
+0.7795275590551181   1.1968493236227868
+0.7716535433070866   1.199608124481236
+0.7637795275590551   1.2020144235173167
+0.7559055118110236   1.204030577737787
+0.7480314960629921   1.2057678448470486
+0.7401574803149606   1.2072262272213867
+0.7322834645669292   1.2084063445380056
+0.7244094488188977   1.2093082547736647
+0.7165354330708661   1.2099303424100876
+0.7086614173228346   1.2102700794433012
+0.7007874015748031   1.2103917008171063
+0.6929133858267716   1.210251464896192
+0.6850393700787402   1.2098211885199128
+0.6771653543307087   1.2089267084950532
+0.6692913385826772   1.2076845685485764
+0.6614173228346456   1.206129355332681
+0.6535433070866141   1.205371680302955
+0.6456692913385826   1.2049806974748283
+0.6377952755905512   1.2043954210198335
+0.6299212598425197   1.2036106204337338
+0.6220472440944882   1.2026201242791477
+0.6141732283464567   1.201416745705292
+0.6062992125984252   1.1999648008867543
+0.5984251968503937   1.1978809672582558
+0.5905511811023622   1.1958229061601988
+0.5826771653543307   1.19378547840869
+0.5748031496062992   1.1911429438142505
+0.5669291338582677   1.1881662557479544
+0.5590551181102362   1.1854410463378466
+0.5511811023622047   1.1823048964210143
+0.5433070866141733   1.178876982518623
+0.5354330708661417   1.1751299194641118
+0.5275590551181102   1.1710321065675582
+0.5196850393700787   1.1665436813486774
+0.5118110236220472   1.1616333192854635
+0.5039370078740157   1.1562582478198198
+0.49606299212598426   1.1503703986482516
+0.4881889763779528   1.1439156304548939
+0.48031496062992124   1.1368328201979288
+0.47244094488188976   1.129052797880398
+0.4645669291338583   1.1205223636539805
+0.45669291338582674   1.1117314823669315
+0.44881889763779526   1.102807930274322
+0.4409448818897638   1.0928255734605004
+0.4330708661417323   1.0816474431805874
+0.4251968503937008   1.0708782919973383
+0.41732283464566927   1.0605856578751718
+0.4094488188976378   1.049296390847412
+0.4015748031496063   1.0369421605031424
+0.39370078740157477   1.0255553010327565
+0.3858267716535433   1.0128340315070852
+0.3779527559055118   1.0019086718619157
+0.3700787401574803   0.9901977470956335
+0.36220472440944884   0.9766690777548703
+0.3543307086614173   0.9609864831395294
+0.3464566929133858   0.9427593339272101
+0.33858267716535434   0.9216423392280653
+0.3307086614173228   0.9017482646476044
+0.3228346456692913   0.8842250257427756
+0.31496062992125984   0.8691045183639151
+0.30708661417322836   0.8534496543474743
+0.2992125984251969   0.8371339522358304
+0.29133858267716534   0.8201284700467455
+0.28346456692913385   0.806397780911551
+0.2755905511811024   0.7931112166023593
+0.26771653543307083   0.7794296062844782
+0.25984251968503935   0.7653047810449107
+0.25196850393700787   0.7506458827692618
+0.2440944881889764   0.7354059250507149
+0.23622047244094488   0.7207409819202417
+0.22834645669291337   0.7064884218371179
+0.2204724409448819   0.6914737948523322
+0.2125984251968504   0.6742529297594405
+0.2047244094488189   0.6543064551474167
+0.19685039370078738   0.6327049937642623
+0.1889763779527559   0.6106332087469254
+0.18110236220472442   0.5903256804560127
+0.1732283464566929   0.5679499052457502
+0.1653543307086614   0.5440168042704815
+0.15748031496062992   0.5181675076528582
+0.14960629921259844   0.49097526265094993
+0.14173228346456693   0.4690522939899713
+0.13385826771653542   0.4467834165720918
+0.12598425196850394   0.4241461376614992
+0.11811023622047244   0.401149626112448
+0.11023622047244094   0.377774600216698
+0.10236220472440945   0.35399309283800373
+0.09448818897637795   0.3296930391700775
+0.08661417322834646   0.304730824684046
+0.07874015748031496   0.2792811035876094
+0.07086614173228346   0.2532962702159859
+0.06299212598425197   0.22674011680482922
+0.05511811023622047   0.20052832043844745
+0.047244094488188976   0.176698559684727
+0.03937007874015748   0.1523331129226084
+0.031496062992125984   0.1273659753191407
+0.023622047244094488   0.10175475262612885
+0.015748031496062992   0.07538511274619461
+0.007874015748031496   0.04814103197609307
+0.0   0.0

outputs/.ipynb_checkpoints/profile_raq_ra7.5_fkt1000000000.0_fkv25.0-checkpoint.txt

@@ -0,0 +1,128 @@
+1.0   1.0
+0.9921259842519685   0.9950688346403253
+0.984251968503937   0.9958109333720785
+0.9763779527559056   0.9962344373154483
+0.968503937007874   0.9963438127157567
+0.9606299212598425   0.9961419425701642
+0.952755905511811   0.9956301997182383
+0.9448818897637795   0.9948085046842855
+0.937007874015748   0.9940939520613497
+0.9291338582677166   0.9946201323314715
+0.9212598425196851   0.9950150370927474
+0.9133858267716535   0.9952845790823276
+0.905511811023622   0.9954341277024014
+0.8976377952755905   0.9954685574336534
+0.889763779527559   0.9953230018455609
+0.8818897637795275   0.9949449242563548
+0.8740157480314961   0.99448569940869
+0.8661417322834646   0.9939459441547048
+0.8582677165354331   0.9933258014056847
+0.8503937007874016   0.9926260108279151
+0.84251968503937   0.9918474918186793
+0.8346456692913385   0.9909907871995196
+0.8267716535433071   0.9906878114843723
+0.8188976377952756   0.9906106350029152
+0.8110236220472441   0.9904939840805035
+0.8031496062992126   0.9903390537912615
+0.7952755905511811   0.990146453812062
+0.7874015748031495   0.9899171435791735
+0.7795275590551181   0.9896528927122547
+0.7716535433070866   0.9893547314976728
+0.7637795275590551   0.9890612122526262
+0.7559055118110236   0.9893196595812495
+0.7480314960629921   0.9895564211609327
+0.7401574803149606   0.989772442085792
+0.7322834645669292   0.9899686248562548
+0.7244094488188977   0.9901458299221866
+0.7165354330708661   0.9903048761979846
+0.7086614173228346   0.990446541534676
+0.7007874015748031   0.9905715631213701
+0.6929133858267716   0.9906806328494628
+0.6850393700787402   0.9907736704034982
+0.6771653543307087   0.9908520347002285
+0.6692913385826772   0.990916300999504
+0.6614173228346456   0.9909670048852377
+0.6535433070866141   0.9910046409314675
+0.6456692913385826   0.9910506796923337
+0.6377952755905512   0.9910935873624599
+0.6299212598425197   0.9911256000361585
+0.6220472440944882   0.9911424770684899
+0.6141732283464567   0.9911429480301582
+0.6062992125984252   0.991133661750414
+0.5984251968503937   0.9911148755527556
+0.5905511811023622   0.9910868001204874
+0.5826771653543307   0.9910482981983292
+0.5748031496062992   0.9909960481561243
+0.5669291338582677   0.9909313899110497
+0.5590551181102362   0.9908529573606984
+0.5511811023622047   0.990802994004299
+0.5433070866141733   0.9907689107593368
+0.5354330708661417   0.9907286385148512
+0.5275590551181102   0.9906821287132976
+0.5196850393700787   0.9906292710827063
+0.5118110236220472   0.9905698879237498
+0.5039370078740157   0.9905037276030212
+0.49606299212598426   0.9903512862004434
+0.4881889763779528   0.9901705111090647
+0.48031496062992124   0.990394105267406
+0.47244094488188976   0.9907094238367197
+0.4645669291338583   0.9910166209293753
+0.45669291338582674   0.9913148228031922
+0.44881889763779526   0.991603010351046
+0.4409448818897638   0.9918800018564412
+0.4330708661417323   0.9920970234152766
+0.4251968503937008   0.9926663730962876
+0.41732283464566927   0.9934669371102811
+0.4094488188976378   0.9942288729603758
+0.4015748031496063   0.9949423232342525
+0.39370078740157477   0.9956252947243415
+0.3858267716535433   0.9962590339323164
+0.3779527559055118   0.9967479593090736
+0.3700787401574803   0.9971294513207575
+0.36220472440944884   0.9974497813570239
+0.3543307086614173   0.9977023709739241
+0.3464566929133858   0.9978637868769807
+0.33858267716535434   0.9978957472618809
+0.3307086614173228   0.9978327829053294
+0.3228346456692913   0.9976642055670972
+0.31496062992125984   0.9973751632626285
+0.30708661417322836   0.9969521187285088
+0.2992125984251969   0.9967668271065058
+0.29133858267716534   0.996799932369035
+0.28346456692913385   0.99663553290747
+0.2755905511811024   0.9962471955509634
+0.26771653543307083   0.9957151691949947
+0.25984251968503935   0.9949376720774421
+0.25196850393700787   0.9948204261550649
+0.2440944881889764   0.9944991487665473
+0.23622047244094488   0.9939093942741223
+0.22834645669291337   0.9949612343773557
+0.2204724409448819   0.9958097897762018
+0.2125984251968504   0.9958570680839077
+0.2047244094488189   0.9950326535250745
+0.19685039370078738   0.993269657110815
+0.1889763779527559   0.9904943987782671
+0.18110236220472442   0.9866067651892468
+0.1732283464566929   0.9814501496109934
+0.1653543307086614   0.9725284162704944
+0.15748031496062992   0.960591955881983
+0.14960629921259844   0.9459049031998263
+0.14173228346456693   0.9274022536864276
+0.13385826771653542   0.9055608536874807
+0.12598425196850394   0.8794161299393387
+0.11811023622047244   0.8483762304671509
+0.11023622047244094   0.8119839698697441
+0.10236220472440945   0.7693537351714411
+0.09448818897637795   0.7193951419727576
+0.08661417322834646   0.6644998392322397
+0.07874015748031496   0.6072823940873321
+0.07086614173228346   0.5458252537723316
+0.06299212598425197   0.4825227176208522
+0.05511811023622047   0.419475266210097
+0.047244094488188976   0.3521553434788696
+0.03937007874015748   0.2945246014638161
+0.031496062992125984   0.23725826815687479
+0.023622047244094488   0.17699945091965216
+0.015748031496062992   0.11634573154412606
+0.007874015748031496   0.0546717664461345
+0.0   0.0

stats/.ipynb_checkpoints/MLP_stats-checkpoint.txt

@@ -0,0 +1,23 @@
+------------  ---------  -------  -------  ---------
+architecture  mae train  mae cv   diff     diff + cv
+[32, 2]       0.01158    0.01249  0.00091  0.01294
+[64, 2]       0.01077    0.01379  0.00302  0.0153
+[128, 2]      0.00997    0.01177  0.00179  0.01266
+[256, 2]      0.01       0.01226  0.00226  0.01339
+[32, 3]       0.00922    0.01167  0.00245  0.01289
+[64, 3]       0.00878    0.01149  0.00271  0.01284
+[128, 3]      0.00834    0.01009  0.00175  0.01097
+[256, 3]      0.0082     0.00927  0.00108  0.00981
+[32, 4]       0.00797    0.00915  0.00118  0.00974
+[64, 4]       0.00652    0.00821  0.00169  0.00905
+[128, 4]      0.00592    0.0083   0.00237  0.00948
+[256, 4]      0.00681    0.00794  0.00113  0.0085
+[32, 5]       0.00877    0.01209  0.00332  0.01375
+[64, 5]       0.00584    0.0084   0.00256  0.00968
+[128, 5]      0.00608    0.00857  0.00249  0.00981
+[256, 5]      0.00682    0.00814  0.00133  0.00881
+[32, 6]       0.00799    0.01453  0.00654  0.0178
+[64, 6]       0.0118     0.01206  0.00026  0.01219
+[128, 6]      0.00607    0.00949  0.00342  0.0112
+[256, 6]      0.00738    0.01015  0.00277  0.01153
+------------  ---------  -------  -------  ---------

stats/.ipynb_checkpoints/overall_stats-checkpoint.txt

@@ -0,0 +1,9 @@
+-----------------------  ------  ------  ------
+Mean Absolute Error
+
+Algorithm                train   cv      test
+Linear Regression        0.0385  0.0388  0.0676
+Kernel Ridge Regression  0.0148  0.0147  0.0371
+Neural Network           0.0071  0.0071  0.0187
+Nearest neighbor         0.0     0.0282  0.0495
+-----------------------  ------  ------  ------

stats/MLP_stats.txt

@@ -0,0 +1,23 @@
+------------  ---------  -------  -------  ---------
+architecture  mae train  mae cv   diff     diff + cv
+[32, 2]       0.01158    0.01249  0.00091  0.01294
+[64, 2]       0.01077    0.01379  0.00302  0.0153
+[128, 2]      0.00997    0.01177  0.00179  0.01266
+[256, 2]      0.01       0.01226  0.00226  0.01339
+[32, 3]       0.00922    0.01167  0.00245  0.01289
+[64, 3]       0.00878    0.01149  0.00271  0.01284
+[128, 3]      0.00834    0.01009  0.00175  0.01097
+[256, 3]      0.0082     0.00927  0.00108  0.00981
+[32, 4]       0.00797    0.00915  0.00118  0.00974
+[64, 4]       0.00652    0.00821  0.00169  0.00905
+[128, 4]      0.00592    0.0083   0.00237  0.00948
+[256, 4]      0.00681    0.00794  0.00113  0.0085
+[32, 5]       0.00877    0.01209  0.00332  0.01375
+[64, 5]       0.00584    0.0084   0.00256  0.00968
+[128, 5]      0.00608    0.00857  0.00249  0.00981
+[256, 5]      0.00682    0.00814  0.00133  0.00881
+[32, 6]       0.00799    0.01453  0.00654  0.0178
+[64, 6]       0.0118     0.01206  0.00026  0.01219
+[128, 6]      0.00607    0.00949  0.00342  0.0112
+[256, 6]      0.00738    0.01015  0.00277  0.01153
+------------  ---------  -------  -------  ---------

stats/MLP_stats_modes.txt

@@ -0,0 +1,23 @@
+------------  ---------  -------  --------  ---------
+architecture  mae train  mae cv   diff      diff + cv
+[32, 2]       0.08696    0.06601  -0.02095  0.05554
+[64, 2]       0.08639    0.06642  -0.01996  0.05644
+[128, 2]      0.09331    0.06741  -0.02589  0.05447
+[256, 2]      0.08665    0.06687  -0.01978  0.05698
+[32, 3]       0.09488    0.06788  -0.02699  0.05439
+[64, 3]       0.07847    0.06889  -0.00958  0.06411
+[128, 3]      0.07296    0.07038  -0.00258  0.0691
+[256, 3]      0.07649    0.06953  -0.00696  0.06604
+[32, 4]       0.08799    0.06886  -0.01913  0.0593
+[64, 4]       0.08595    0.0706   -0.01535  0.06293
+[128, 4]      0.0852     0.07315  -0.01205  0.06713
+[256, 4]      0.09259    0.07169  -0.0209   0.06124
+[32, 5]       0.08676    0.06701  -0.01975  0.05713
+[64, 5]       0.07997    0.07123  -0.00874  0.06687
+[128, 5]      0.07262    0.07217  -0.00045  0.07195
+[256, 5]      0.08688    0.07142  -0.01546  0.0637
+[32, 6]       0.08931    0.069    -0.02031  0.05884
+[64, 6]       0.08923    0.07369  -0.01554  0.06592
+[128, 6]      0.09521    0.07428  -0.02094  0.06381
+[256, 6]      0.08294    0.07244  -0.01051  0.06718
+------------  ---------  -------  --------  ---------

stats/overall_stats.txt

@@ -0,0 +1,9 @@
+-----------------------  ------  ------  ------
+Mean Absolute Error
+
+Algorithm                train   cv      test
+Linear Regression        0.0385  0.0388  0.0676
+Kernel Ridge Regression  0.0148  0.0147  0.0371
+Neural Network           0.0071  0.0071  0.0187
+Nearest neighbor         0.0     0.0282  0.0495
+-----------------------  ------  ------  ------

stats/overall_stats_modes.txt

@@ -0,0 +1,9 @@
+-----------------------  ------  ------  ------
+Mean Absolute Error
+
+Algorithm                train   cv      test
+Linear Regression        0.1037  0.1048  0.1418
+Kernel Ridge Regression  0.0906  0.1138  0.1646
+Neural Network           0.0916  0.1036  0.1461
+Nearest neighbor         0.0     0.1304  0.1643
+-----------------------  ------  ------  ------

utils.py

@@ -0,0 +1,69 @@
+import numpy as np
+import pickle
+
+def selu(x):
+    alpha = 1.6732632423543772848170429916717 
+    scale = 1.0507009873554804934193349852946
+    return scale*( np.maximum(0,x) + np.minimum(alpha*(np.exp(x)-1), 0) )
+
+def non_dimensionalize_raq(x):
+    return (x-0.12624371)/(9.70723344-0.12624371)
+
+def non_dimensionalize_fkt(x):
+    return (np.log10(x)-6.00352841978384)/(9.888820429862925-6.00352841978384)
+
+def non_dimensionalize_fkv(x):
+    return (np.log10(x)-0.005251646002323797)/(1.9927988938926755-0.005251646002323797)
+
+def dimensionalize_raq(x):
+    return x*(9.70723344-0.12624371) + 0.12624371
+
+def dimensionalize_fkt(x):
+    return 10**(x*(9.888820429862925-6.00352841978384)+6.00352841978384)
+
+def dimensionalize_fkv(x):
+    return 10**(x*(1.9927988938926755-0.005251646002323797)+0.005251646002323797)
+
+def get_input(raq_ra, fkt, fkp, y_prof):
+    
+    x = np.zeros((len(raq_ra)*len(y_prof), 4))
+
+    cntr = 0
+    for i in range(len(raq_ra)):
+        for j in range(len(y_prof)):
+            x[cntr,0] = non_dimensionalize_raq(raq_ra[i])
+            x[cntr,1] = non_dimensionalize_fkt(fkt[i])
+            x[cntr,2] = non_dimensionalize_fkv(fkp[i])
+            x[cntr,3] = y_prof[j]
+            cntr += 1    
+            
+    return x
+
+def get_profile(inp, mlp, num_sims=1, num_points=128):
+    
+    num_layers = len(mlp)-1
+    y_pred = inp
+    res = []
+    for l in range(num_layers+1):
+        
+        y_pred = y_pred @ mlp[l][0].T + mlp[l][1]
+
+        if l in [num_layers-1]:
+            y_pred = np.concatenate((inp,y_pred), axis=-1)
+            
+        if l != num_layers:
+            for r in res:
+                y_pred += r
+                
+            y_pred = selu(y_pred)
+            res.append(y_pred)
+                
+    y_pred = y_pred.reshape(num_sims, num_points)
+    y_pred[:,0]  = 1.
+    y_pred[:,-1] = 0.
+
+    return y_pred
+
+
+
+