Improving Accuracy of prediction Algorithm - machine-learning

Question

I am new to machine learning and I am currently working on Prediction problem. I have provided the link for an excel spreadsheet that has few columns of data.
https://drive.google.com/file/d/1fWf6dX8kOCRB3GpX42AF6UvTmd0g9zXp/view?usp=sharing
I was trying to predict the column F values based column A to E values. The code for which is given below
import numpy as np
import pandas as pn
from keras.layers import Dense, Activation
from keras.models import Sequential
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import linear_model
import matplotlib.pyplot as plt
dataset = pn.read_excel(r"G:\Machine learning\data\database.xlsx", "Sheet5")
dataset.columns = ['A','B','C','D','E','F']
print (dataset)
#check= dataset.iloc[0:,3 :13]
X = dataset.iloc[0:,0 :5]
print(X)
Y = dataset.iloc[0:, 5 :6]
print(Y)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.15, random_state = 0)
print(X_test)
print(Y_test)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
#
model = Sequential()
##
### Adding the input layer and the first hidden layer
model.add(Dense(32, activation = 'relu', input_dim = 5, kernel_initializer='normal'))
##
### Adding the second hidden layer
model.add(Dense(units = 16, activation = 'relu'))
model.add(Dense(units = 64, activation = 'relu'))
model.add(Dense(units = 8, activation = 'relu'))
model.add(Dense(units = 16, activation = 'relu'))
#model.add(Dense(units = 8, activation = 'linear'))
###
#### Adding the third hidden layer
#model.add(Dense(units = 16, activation = 'relu'))
#model.add(Dense(units = 16, activation = 'relu'))
#model.add(Dense(units = 16, activation = 'relu'))
##
### Adding the output layer
model.add(Dense(units = 1))
##
model.add(Dense(units = 1))
##
model.add(Dense(1))
### Compiling the ANN
model.compile(optimizer = 'nadam', loss = 'mean_squared_error',metrics= ['accuracy'])
##
### Fitting the ANN to the Training set
history = model.fit(X_train, Y_train, epochs=125, batch_size=5, verbose=1, validation_split=0.1)
##
y_pred = model.predict(X_test)
##
y_pred1 = model.predict(X_train)
print (y_pred1)
Y_test.reset_index(drop= True, inplace= True)
print (Y_train)
Y_train.reset_index(drop= True, inplace= True)
plt.plot(y_pred1)
plt.plot(Y_train)
plt.show()
plt.plot(y_pred)
plt.plot(Y_test)
plt.show()
print (y_pred)
print (Y_test)
plt.plot((Y_test-y_pred)*100/Y_test)
plt.show()
The fit I get from this code is shown below.
Fit
Now when I predict, the error is huge in some cases as shown below
Prediction
Can anyone guide me on improvising the code so as to get a better prediction?


Answer 1

For a small dataset you have provided, it might be the case that your neural network model is too complicated (4 hidden layers and maximum 64 neurons).
What you can try is manually decreasing the amount of layers to see if the accuracy raises. But in the future, if you would like to more practically tune the hyperparameters or optimize your model parameters, you should consider using methods such as random/grid search, cross validation, and regularization.
Random Search: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html