I am doing a homework assignment and I've been stomped for hours and hours looking up how to set the dimensions correctly for random number generated weights for a neural network. No matter how many articles I read or Google search's I do, I can't find a solution. Every time I change the dimensions, based off of the dimensions of the incoming X_train set, the program ends up having a "ValueError: operands could not be broadcast together with shapes (X,X) (y,y)". The major problem is the convoluted way in which dot product does it's math with 2d arrays. I don't know where else to turn so here I am. I will post cost and sample output to give as much information as possible, and check back every hour to see if anyone could figure this problem out. What I really need is a cookie cutter way to say...if you are pushing a n-dimensional array, weight one should be these dimensions, and weight two these dimensions, and weight three, and so on...so there are not compatibility errors in the calculations.
I've tried looking and looking on the internet for a way to decipher weights based off incoming dimensionality of data structure(s). I.E. rows and columns.
THIS IS THE CODE BELOW IN IT'S ENTIRETY SO FAR:
import numpy as np
import pandas as pd
from numpy import tanh
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
class NeuralNetwork():
def __init__(self):
print('constructor working...')
self.inputsize = 4
self.outputsize = 4
self.hiddensize = 1
self.W1 = np.random.randn(self.inputsize, self.hiddensize)
self.W2 = np.random.randn(self.hiddensize, self.outputsize)
def forward(self, X):
#print('forward - X:\n', X)
self.z = np.dot(X, self.W1)
#print('forward - self.z:\n', self.z)
self.z2 = self.sigmoid(self.z)
#print('forward - self.z2:\n', self.z2)
self.z3 = np.dot(self.z2, self.W2)
#print('forward - self.z3:\n', self.z3)
o = self.sigmoid(self.z3)
print('forward - o:\n', o)
print('forward shape of o:\n', o.shape)
print('forward shape of X:\n', X.shape)
return o
def sigmoid(self, s):
#print('sigmoid:\n', (1/(1+np.exp(-s))))
return(1/(1+np.exp(-s)))
def sigmoidPrime(self, s):
return(s * (1 - s))
def backward(self, X, y, o):
print('backward - X:\n',X,'\ny:\n',y,'\no:\n',o)
self.o_error = y - o
print('backward - o_error:\n', self.o_error)
self.o_delta = self.o_error * self.sigmoidPrime(o)
print('backward - o_delta:\n', self.o_delta)
self.z2_error = self.o_delta.dot(self.W2.T)
print('backward - z2_error:\n', self.z2_error)
self.z2_delta = self.z2_error * self.sigmoidPrime(self.z2)
print('backward - z2_delta:\n', self.z2_delta)
self.W1 += X.T.dot(self.z2_delta)
print('backward - W1:\n', self.W1)
self.W2 += self.z2.T.dot(self.o_delta)
print('backward - W2:\n', self.W2)
def train(self, X, y):
o = self.forward(X)
self.backward(X, y, o)
def saveWeights(self):
np.savetxt('w1.txt', self.W1, fmt='%s')
np.savetxt('w2.txt', self.W2, fmt='%s')
def predict(self):
print("Predicted data based on trained weights: ")
print("Input (scaled): \n" + str(X_test))
print("Output: \n" + str(self.forward(X_test)))
if __name__ == "__main__":
nn = NeuralNetwork()
titanic_original_df = pd.read_csv(r'./titanic_data.csv')
titanic_df = titanic_original_df.copy()
print('titanic data shape:', titanic_df.shape)
#print('titanic data head:\n', titanic_df.head(3))
'''
for col in titanic_df:
print(col,': ',titanic_df[col].dtypes)
for col in titanic_df:
print(col,'- value counts:\n', titanic_df[col].value_counts())
for col in titanic_df:
print(col,'- null data:', titanic_df[col].isnull().sum())
'''
titanic_df['Age'] = titanic_df['Age'].interpolate().round()
#print('after interpolation, Age null counts:\n', titanic_df['Age'].isnull().sum())
titanic_df['Sex'] = pd.get_dummies(titanic_df['Sex'])
#print('after dummy encoding Sex:\n', titanic_df['Sex'].value_counts())
for col in titanic_df:
print(col,'- null data:', titanic_df[col].dtypes)
titanic_df[['Pclass','Sex']] = titanic_df[['Pclass','Sex']].astype(np.float64)
sc = StandardScaler()
#scaled_data = sc.fit(titanic_df[['Age','Fare']])
#titanic_df[['Age','Fare']] = sc.transform(titanic_df[['Age','Fare']])
#print('after scaling, Age column:\n', titanic_df['Age'].value_counts())
#print('after scaling, Fare column:\n', titanic_df['Fare'].value_counts())
y = titanic_df.Survived
X = titanic_df.drop(['PassengerId','Survived','Name','SibSp','Parch','Ticket','Cabin','Embarked'], axis=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=124)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)
#print('X_train:\n', X_train['Sex'].value_counts())
for i in range(1):
print('# '+str(i)+'\n')
#print('Input (scaled):\n'+str(X_train))
#print('Actual output:\n'+str(y_train))
print('Predicted output:\n'+str(nn.forward(X_train)))
print('shape of X_train:',X_train.shape)
print('shape of y_train:',y_train.shape)
print('Loss:\n'+str(np.mean(np.square(y_train - nn.forward(X_train)))))
print('\n')
nn.train(X_train, y_train)
nn.saveWeights()
nn.predict()
In [55]: runfile('C:/Users/John/.spyder-py3/ProgrammingAssignment#9.py', wdir='C:/Users/John/.spyder-py3')
constructor working...
titanic data shape: (891, 12)
PassengerId - null data: int64
Survived - null data: int64
Pclass - null data: int64
Name - null data: object
Sex - null data: uint8
Age - null data: float64
SibSp - null data: int64
Parch - null data: int64
Ticket - null data: object
Fare - null data: float64
Cabin - null data: object
Embarked - null data: object
X_train shape: (623, 4)
X_test shape: (268, 4)
y_train shape: (623,)
y_test shape: (268,)
# 0
forward - o:
[[0.50384373 0.4961504 0.50183024 0.49790133]
[0.5001908 0.49980891 0.50009085 0.49989583]
[0.51753819 0.48243502 0.50835355 0.49042155]
...
[0.51554828 0.48442797 0.50740524 0.49150886]
[0.50025489 0.49974472 0.50012137 0.49986083]
[0.50000075 0.49999925 0.50000036 0.49999959]]
forward shape of o:
(623, 4)
forward shape of X:
(623, 4)
Predicted output:
[[0.50384373 0.4961504 0.50183024 0.49790133]
[0.5001908 0.49980891 0.50009085 0.49989583]
[0.51753819 0.48243502 0.50835355 0.49042155]
...
[0.51554828 0.48442797 0.50740524 0.49150886]
[0.50025489 0.49974472 0.50012137 0.49986083]
[0.50000075 0.49999925 0.50000036 0.49999959]]
shape of X_train: (623, 4)
shape of y_train: (623,)
forward - o:
[[0.50384373 0.4961504 0.50183024 0.49790133]
[0.5001908 0.49980891 0.50009085 0.49989583]
[0.51753819 0.48243502 0.50835355 0.49042155]
...
[0.51554828 0.48442797 0.50740524 0.49150886]
[0.50025489 0.49974472 0.50012137 0.49986083]
[0.50000075 0.49999925 0.50000036 0.49999959]]
forward shape of o:
(623, 4)
forward shape of X:
(623, 4)
Traceback (most recent call last):
File "<ipython-input-55-52d7c067a2dd>", line 1, in <module>
runfile('C:/Users/John/.spyder-py3/ProgrammingAssignment#9.py', wdir='C:/Users/John/.spyder-py3')
File "C:\Users\John\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 786, in runfile
execfile(filename, namespace)
File "C:\Users\John\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 110, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/John/.spyder-py3/ProgrammingAssignment#9.py", line 117, in <module>
print('Loss:\n'+str(np.mean(np.square(y_train - nn.forward(X_train)))))
File "C:\Users\John\Anaconda3\lib\site-packages\pandas\core\ops.py", line 1583, in wrapper
result = safe_na_op(lvalues, rvalues)
File "C:\Users\John\Anaconda3\lib\site-packages\pandas\core\ops.py", line 1529, in safe_na_op
return na_op(lvalues, rvalues)
File "C:\Users\John\Anaconda3\lib\site-packages\pandas\core\ops.py", line 1505, in na_op
result = expressions.evaluate(op, str_rep, x, y, **eval_kwargs)
File "C:\Users\John\Anaconda3\lib\site-packages\pandas\core\computation\expressions.py", line 208, in evaluate
return _evaluate(op, op_str, a, b, **eval_kwargs)
File "C:\Users\John\Anaconda3\lib\site-packages\pandas\core\computation\expressions.py", line 123, in _evaluate_numexpr
result = _evaluate_standard(op, op_str, a, b)
File "C:\Users\John\Anaconda3\lib\site-packages\pandas\core\computation\expressions.py", line 68, in _evaluate_standard
return op(a, b)
ValueError: operands could not be broadcast together with shapes (623,) (623,4)
