From 5889978f1d4cad42b8325bf10622edd082e88ebd Mon Sep 17 00:00:00 2001
From: ltcptgeneral <35508619+ltcptgeneral@users.noreply.github.com>
Date: Fri, 1 Mar 2019 12:18:38 -0600
Subject: [PATCH] dumb

---
 .../__pycache__/titanlearn.cpython-37.pyc     | Bin 4864 -> 5554 bytes
 data analysis/superscript.py                  |   2 +
 data analysis/titanlearn.py                   |  42 ++++++++++++++----
 3 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/data analysis/__pycache__/titanlearn.cpython-37.pyc b/data analysis/__pycache__/titanlearn.cpython-37.pyc
index 534544d2aa385ef5f79ac87e816fa44a91ae641c..18fa10d52f2f52bc0d5d14fd4cd87b4cebee0726 100644
GIT binary patch
delta 2156
zcmah~O>7fK6rR~1$6o)$|2B|<6QU-D5(1^=uOi_mg%T;G1rbUE#&|Z)5@+qsuC2t{
z$VleEp%l=HTMzcJr%LpWkgE2;q33GU-l|Hu_0U_@s_(6B8dYk$tNr%d_h#OE^WMDK
z`)@u!7&#XXYXq)8?`|$X9DN$e(l4G)G!E`!5hg#NHxq0(OE48!lI>w>rT|N^49h+s
zH`8qBD#?#Lefhhpm{n8%`WyPAG$&NMXs%8Rxnh{x6fBD&%P6l`4JH&Ipa2vK*DH0Q
zB2G88ie6mX%y}ZE!u4t4{;bST!o=!|y<XhNOG2*JZJq*aJb;h}$V=XfN8D@bceBE0
zm<4963vJb4Oz-g_nAH=S_4PteA$-M>U05-NteZ^GH9?Ip37>Lr`kq}4W4Q9VrI$j$
z@IsfEpY!louOvbo(jhkO(yfpq^_k?zeI`2!BWp6Bc9gzEahF4%x1P|AU+jqEYtswl
z3BC2hR?LYx{xo5MHR*}OS8Ta6+y%|!4N4p^+@@P`hcXSclxOW|Ck8I!UD8Q(i4z~N
zuC$eaQ9*Ci85ouPmr<>R6Yiv(M3+)xr|parYf~1=5MYTm&5$<Av-ft{yE}XA2n#qd
z7S0gI-<G=+Wlp$DVLuE%k|8{Ag%I=w2vos9?X*MD!s~#4^8!};!9vI_FVe{C5dP0q
zwCBoP?5_@-d8^xD5-cViw3zf3_1_j-l*Rhd2e3X6{j#0yj5q-n&k!`QL>T#yd_-;#
zD8(CH@^~876YcEn5_k^^GVH`1xh-u4onU95r-^oQ`2KtLr>~ZXqxF5f09&IlTT68%
zOmJtcXAYVsvA~bI=L1e!NX44axL)SEWf@hoDV@sku={Ob--M6pjojSzrZQDyEBXCG
zva14RMoH%x*p57lu*;RT6TUH|``xqJ2pw^6YX^?=A&>|awta0=Wc7_&rD&KsD>RDS
zD4Hd`V3n#|hhC`Funp82H%y!FbvxQpG$mwHw}oGC6f4&@Yr6Y~_VDl_wC96<szD<j
z#}7$w@G11`!C_=Fz&t$Gs{2*&&}fMIsYXZoPnJ#s^P@~k0y{u8w;M}64~@&=qd5C*
zfIQ{L+#|yY<sJBND}l=k{9V*308QWA;+6B4a!n<7<$cH!iXdH0FHvU~Vd_Z~_3|~r
zPvN}N2s^WNJDMHuWeYX42xk$_A&ekgLfGq$L`SDC0u`!d7fWj#PXO*ixPUN+@BzYQ
z1YEWIGCJAH@8;J~a2;U@;ReFT07BJk)zYd6+%4LrRm*7V{1enIBiur`jZi?igHS}c
zi%>#f03u-6Ixki0P%W<{L!L3+67(J#J^_|l(JqRhCogjt$@p71T}Qym{j+Kk$R4<t
zV~rNN@h&W65FT8#)da9fhce0}CgW39nZi`&V?)djJmB3j8v^bJ?q?d4faCZejDqoH
z6^_iFl@JT#VZuV5jM@^5LVLzpqTN!qBwKbQmUQqmNwM@J6`CcpP=*NL`gNvH$ZVe^
z2jujC<OU=<AlU&KACSobIW{1EkF>zYR9|#|en2h`2F=fIt1x04{|Dag+s4fC69DD!
zYx0?y&lYE36JkyCir1aOXX~a_<sAQmUU%f>9XsO=N_Vsn`WIoY+ne>OQLC@8&H4)v
zSy2EYMQO;p<1|Sllw(!k7wCtV_fO3G7Z&(5ejP!;?f?NcRz3g(6UJ8&JT<a`IwOLG
zLPO`4I~+gY^G=m9cP2jW^Y-|>YsB{jy`660^wX{zpO{4NJ3@bb1PK3o>s3~-=w~oX
O)|mTKd`v#6o%##x>;3Qm

delta 1601
zcmZvcOK;p%6vywi$Da2)nVE!yOqw*wq)j@M0wsm2ZTd)yNCPcNv5KO}Tqkkn$(=h<
zGk6rF>4F7O6B$;p@NAISwtFNtDB>en6)QI7D<A>qc!ma5Sn|(*|IfYW_*`H6>6tI5
zBG<y<0D&XD!XAD-dKAgfZ;qySC(<m!<i}J?vJ6Wy1=Ii=VkzbUHORd8NN)J(_)nj=
zQQH)i!lP%$^tp6fQ$(S<o!8{DQGG!nspD-JTa}u@G!KZpBLf`|*UL>!LFQY5vR)|d
zWnIft<~mO1y0xwhTV7@EH1|W6oaD&0rf{|6sn)7GkGi&d;UVjx^2-%XHLB~(sAz$0
zgE76Qy)dn3R-2XeUO-a|MX|nFb!5HD99nXy@gw0A)`t4+To9jGt~B%_Dm;>K;`%JY
z**Gf^ViKDO+NJHFbs?PF4{ecl*bLZGmoQqA_<bSocy<&fG5LVDBh}S@%mcA9#%#4q
zz`xx074RRszSs4q`o0SO_pa}A{fO|}0p{&eN*K9EAQIdOnZbQK+$E;Ud<RlHdPpBF
ziHNCm=yh^PKU-+W%$Vs-5#}#Rhm;=+*^YL}ljoF}L6df9J1$~&+?4DD<cK4?QafRW
z?4+5%LSjG+nz0ULfiwY?=+HFjpr6`Fi;O)aB5dDp##k^-Om9c-QZ&s_m$DEGAIMNf
zW~3xT=^vn={Ia0um4e}y1y2(Hf8Izxudko?r+tyKhfN=grU^dr8Z6F7<YV#x7RY`L
zdd<T_MD39-IqBJqn9y@aY6oDcN8L!&ejTqTvp@fJjhKG7h{UsyYYZCjcO~rI&i1mw
zClFhf__X!HZ>lY6A<Ki-7lE-c&wQP2=EfaK)Et%RyGBvxao9aPfk;|E2QI23C`YZo
z10ytLjRa>ijshFBzUQcgdL6f=Qs+ih@Ql?CuBk~!uIj@2J^0n^DVXS}u&e7$;Yfu#
zpTJBmCQ-?N58!O9S|28I(FBdq0QJ!UV1~|E-zA2g{S}&&$ER`d3?N5&4lb>5k=GiH
ztPVwM^*ugoEykAj&)_HzhSeJ@cNdqkEl>9DO=uJ?=(vUbWv{M4lCx;_TA$`~IBy>D
zpT_a_93qc+192YFTMJZgA}%1_LZtA!;|qw4H5?xwe;1^qG(@3T;%}p^BHlq<L|n3d
zi)HRyL3tH%4S^pnzmB*8$PM$GsBa;b5VsL`0FI*9YsGENzflmy?S|3PEh9d&!SCaM
zPXL<V5IQf`ny^Ohd+@p=^@c-t`m<O;6ttjgZ*dsN_&Cm9MXVuSd0p^7AuVeuv3n~g
zaUTwF|98ISWqum(rVzN=VBjmu`9VBD^HYQyM)hwvWj!4@ueuv;#QI}kGViX-`!K?Z
zR|=wDu8Fd-F<;+9<*2<Yzl6Co#JqKRaC+k8Azg(V%kjNesj+5Rzl<-Xk+lv6PtkM#
E04nB*AOHXW

diff --git a/data analysis/superscript.py b/data analysis/superscript.py
index 3eaad286..b9ca508b 100644
--- a/data analysis/superscript.py	
+++ b/data analysis/superscript.py	
@@ -134,6 +134,8 @@ def service():
 
     while True:
 
+        pulldata()
+
         start = time.time()
 
         print("[OK] starting calculations")
diff --git a/data analysis/titanlearn.py b/data analysis/titanlearn.py
index 9fab3a11..2b895610 100644
--- a/data analysis/titanlearn.py	
+++ b/data analysis/titanlearn.py	
@@ -35,7 +35,7 @@ import math
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 #linear_nn: creates a fully connected network given params
-def linear_nn(in_dim, hidden_dim, out_dim, num_hidden, act_fn="tanh", end="softmax"):
+def linear_nn(in_dim, hidden_dim, out_dim, num_hidden, act_fn="tanh", end="none"):
     if act_fn.lower()=="tanh":
         k=OrderedDict([("in", torch.nn.Linear(in_dim,hidden_dim)), ('tanh0', torch.nn.Tanh())])
         for i in range(num_hidden):
@@ -72,7 +72,7 @@ def linear_nn(in_dim, hidden_dim, out_dim, num_hidden, act_fn="tanh", end="softm
     return torch.nn.Sequential(k)
 
 #train_sgd_simple: trains network using SGD
-def train_sgd_simple(net, data, ground, dev=None, devg=None, iters=1000, learnrate=1e-4, testevery=1, graphsaveloc=None, modelsaveloc=None, loss="mse"):
+def train_sgd_simple(net, evalType, data, ground, dev=None, devg=None, iters=1000, learnrate=1e-4, testevery=1, graphsaveloc=None, modelsaveloc=None, loss="mse"):
     model=net.to(device)
     data=data.to(device)
     ground=ground.to(device)
@@ -81,7 +81,7 @@ def train_sgd_simple(net, data, ground, dev=None, devg=None, iters=1000, learnra
     losses=[]
     dev_losses=[]
     if loss.lower()=="mse":
-        loss_fn = torch.nn.MSELoss(reduction='sum')
+        loss_fn = torch.nn.MSELoss()
     elif loss.lower()=="cross entropy":
         loss_fn = torch.nn.CrossEntropyLoss()
     elif loss.lower()=="nll":
@@ -96,21 +96,34 @@ def train_sgd_simple(net, data, ground, dev=None, devg=None, iters=1000, learnra
         if i%testevery==0:
             with torch.no_grad():
                 output = model(data)
-                ap = metrics.average_precision_score(ground.numpy(), output.numpy())
+                if evalType == "ap":
+                    ap = metrics.average_precision_score(ground.cpu().numpy(), output.cpu().numpy())
+                if evalType == "regression":
+                    ap = metrics.explained_variance_score(ground.cpu().numpy(), output.cpu().numpy())
                 losses.append(ap)
                 print(str(i)+": "+str(ap))
                 plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="train AP")
                 if dev != None:
                     output = model(dev)
-                    ap = metrics.average_precision_score(devg.numpy(), output.numpy())
-                    dev_losses.append(ap)
-                    plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev AP")
+                    print(evalType)
+                    if evalType == "ap":
+                        
+                        ap = metrics.average_precision_score(devg.numpy(), output.numpy())
+                        dev_losses.append(ap)
+                        plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev AP")
+                    elif evalType == "regression":
+                        ev = metrics.explained_variance_score(devg.numpy(), output.numpy())
+                        dev_losses.append(ev)
+                        plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev EV")
+
+                    
                 if graphsaveloc != None:
                     plt.savefig(graphsaveloc+".pdf")
         with torch.enable_grad():
             optimizer.zero_grad()
             output = model(data)
             loss = loss_fn(output, ground)
+            print(loss.item())
             loss.backward()
             optimizer.step()
     if modelsaveloc != None:
@@ -128,7 +141,7 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
     losses=[]
     dev_losses=[]
     if loss.lower()=="mse":
-        loss_fn = torch.nn.MSELoss(reduction='sum')
+        loss_fn = torch.nretyuoipufdyun.MSELoss(reduction='sum')
     elif loss.lower()=="cross entropy":
         loss_fn = torch.nn.CrossEntropyLoss()
     elif loss.lower()=="nll":
@@ -138,7 +151,7 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
     else: 
         warnings.warn("Did not specify a valid loss function. Returning nothing.")
         return None
-    optimizer=torch.optim.SGD(model.parameters(), lr=learnrate)
+    optimizer=torch.optim.LBFGS(model.parameters(), lr=learnrate)
     itercount=0
     for i in range(epoch):
         print("EPOCH "+str(i)+" OF "+str(epoch-1))
@@ -176,3 +189,14 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
         torch.save(model, modelsaveloc)
     plt.show()
     return model
+
+def retyuoipufdyu():
+    
+    data = torch.tensor([[ 1.,  2.,  5.,  2.,  5.],
+        [27.,  8.,  4.,  6., 10.],
+        [12., 12., 12.,  5.,  6.],
+        [10., 12., 10., 20.,  2.],
+        [ 1.,  2.,  3.,  4.,  5.]])
+    ground = torch.tensor([15., 55., 47., 54., 15.])
+    model = linear_nn(5, 10, 1, 3, act_fn = "relu")
+    return train_sgd_simple(model,"regression", data, ground, learnrate=1e-2)