removed old model file

model.py

-#! /usr/bin/env python3
-import sys
-import os
-import csv
-from random import seed, random
-from pprint import pprint as pp
-from math import log, exp
-import numpy as np
-
-params = {"layers":[57, int(57/2), 1], "test":"TestX.csv", "train":"Train.csv"}
-
-def doNormalize(X):
-    #do 0 mean 1 std normalization
-    x1 = np.array(X,dtype=float)
-    for i in range(len(X[0])):
-        col = x1[:,i]
-        mean,std = col.mean(),col.std()
-        std = std if std!=0.0 else 1.0
-        x1[:,i] = (x1[:,i]-mean)/std
-    return x1.tolist()
-
-def getData(srcF, isTrain=True, addBias=True, normalize=True):
-    X,y=[],[]
-    with open(srcF) as src:
-        reader = csv.reader(src, delimiter=',')
-        for i,row in enumerate(reader):
-            temp = []
-            if addBias:
-                temp.append(1)
-            end = -1 if isTrain else len(row)
-            temp.extend(row[:end])
-            
-            #correct data type
-            X.append([x for x in map(float, temp)])
-
-            if isTrain:
-                y.append(int(row[-1]))
-
-    if normalize:
-        X = doNormalize(X)
-    #print(X[0])
-    return (X,y)
-
-def sigmoid(v):
-    return 1.0/(1+exp(-v))
-
-def sigmoidGradient(v):
-    return [a*b for a,b in zip([sigmoid(x) for x in v], [1-sigmoid(x) for x in v])]
-
-def regularization(cost, w1, w2, lamb, m):
-    reg = sum(w1*w1)+sum(w2*w2)
-    reg = reg*lamb/(2*m)
-    return cost+reg
-
-def gradient(del1, del2, w1, w2, lamb, m):
-    del1,del2 = del1/m, del2/m    
-    tgrad1 = del1[:,1:] + lamb*w1[:,1:]/m
-    tgrad2 = del2[:,1:] + lamb*w2[:,1:]/m
-
-    w1[:,1:] = np.copy(tgrad1)
-    w2[:,1:] = np.copy(tgrad2)
-
-    return np.append(w1.reshape(w1.size), w2.reshape(w2.size))
-
-def cost(li, lh, lo, weights, X, y, lamb):
-    w1 = weights[:(li+1)*lh]    #28x58
-    w2 = weights[(li+1)*lh:]    #1x29
-    #28x58, 1x29
-    tdel1,tdel2 = np.zeros((lh,li+1),dtype=float), np.zeros((lo,lh+1),dtype=float)
-
-    #w1,w2 = getMatrix(lh, li+1, w1t), getMatrix(lo, lh+1, w2t)
-    # w1 = np.array(w1t)
-    # w2 = np.array(w2t)
-    #cost
-    m = len(X)
-    J = 0.0
-    for i in range(m):
-        a1 = X[i]   #1x58
-        z2 = np.dot(w1.reshape((lh,li+1)), a1) #28x58 * 58x1 = 28x1        
-        a2 = [1.0]  #bias for hidden
-        a2.extend([sigmoid(x) for x  in z2])    #29x1
-        z3 = np.dot(w2.reshape((lo,lh+1)), a2) #1x29 *29x1 = 1x1
-        z3 = z3[0]
-        h = sigmoid(z3)
-        # J += -y[i]*log(fw) - (1-y[i])*log(1-fw)
-        #backpropagation
-        del3 = h-y[i]   #1x1
-        z2 = [1]+z2.tolist()      #29x1
-        del2 = w2.reshape((lo,lh+1))*del3*np.array(sigmoidGradient(z2)).reshape((1,29))  #1x29 x 1x1 x 1x29 = 1x29
-
-        del2 = del2.reshape(lh+1,lo).tolist()
-        del(del2[0])        #28x1
-        tdel1 = np.dot(np.array(del2).reshape(lh,lo),np.array(a1).reshape(lo,li+1))+tdel1 #28x1 x 1x58
-        tdel2 = np.multiply(np.array(a2).reshape((lo,lh+1)), del3)+tdel2   #1x29 * 1x1 + 1x29 = 1x29
-        J += y[i]*log(h) + (1-y[i])*log(1-h)
-
-    J = -J/m
-
-    #regularization
-    J = regularization(J, w1, w2, lamb, m)
-
-    #calculate gradient
-    grad = gradient(tdel1, tdel2, w1.reshape((lh,li+1)), w2.reshape((lo,lh+1)), lamb, m)    
-
-    return J,grad
-
-def fit(X, y, li, lh, lo, weight, lamb, eta, passes=1000, verbose=True):
-    weights = np.copy(weight)
-    for i in range(1,passes+1):
-        J, dw = cost(li, lh, lo, weights, X, y, lamb)
-        #print(weights.shape, dw.shape)
-        weights += -eta*dw
-        print(i,"\r", end='')
-        if verbose and i%(passes/10) == 0:
-            print()
-            print(J)
-    return weights
-
-def predict(x, w1, w2):
-    #x=[1]+x    #58x1    
-    x = np.array(x)
-    h1 = [sigmoid(z) for z in np.dot(w1,x).tolist()]    #28x58 * 58x1 = 28x1
-    h1 = [1]+h1
-    h2 = sigmoid(np.dot(w2,h1).tolist()[0])    #1x29 * 29x1 = 1x1
-    return h2
-
-def setWeightsFromFile(weights):
-    if os.path.isfile("weights"):
-        with open("weights","rb") as wfile:
-            weights = np.load(wfile)
-            return True
-    return False
-
-    
-if __name__ == "__main__":
-    np.random.rand(47)
-    X,y = getData(params["train"])
-    tX,ty = getData(params["test"], isTrain=False)
-    # print(len(X), len(X[0]), len(y), X[0])
-    # print(len(tX), len(ty), tX[0])
-    li,lh,lo = tuple(params["layers"])
-    weights = np.random.rand(lh*(li+1)+lo*(lh+1))
-    lamb,eta = 0.1,0.1
-    if not setWeightsFromFile(weights):
-        weights = fit(X, y, li, lh, lo, weights, lamb, eta, passes=300)
-        with open("weights","wb") as wfile:
-            np.save(wfile, weights)
-    w1 = weights[:(li+1)*lh].reshape(lh,li+1)    #28x58
-    w2 = weights[(li+1)*lh:].reshape(lo,lh+1)    #1x29
-    py = []
-    for x in X:
-        py.append(predict(x,w1,w2))
-    print(py)
-    # print("train accuracy", len(list(filter(lambda z:z==0,[a-b for a,b in zip(py,y)])))*1.0/len(y))
-
-    # pty = []
-    # for x in tX:
-    #     pty.append(predict(x,w1,w2))
-
-    # with open("answer.txt","w") as dest:
-    #     writer = csv.writer(dest)
-    #     for i,ans in enumerate(pty):
-    #         writer.writerow([i,ans])
-
-
-
-    # J,grad = cost(li, lh, lo, weights, X, y, 0.1)
-    # print(J,grad)
-    #print(len(w1), len(w1[0]), len(w2), len(w2[0]))
\ No newline at end of file