dhivyapriyar / basic-nn-model Goto Github PK

To develop a neural network regression model for the given dataset.

A neural network can be used to solve a problem by Data collection and Preprocessing,choosing a appropriate neural network architecture ,Train the neural network using the collected and preprocessed data,Assess the performance of the trained model using evaluation metrics,Depending on the performance of the model, you might need to fine-tune hyperparameters or adjust the architecture to achieve better results,Once you're satisfied with the model's performance, you can deploy it to production where it can be used to make predictions on new, unseen data

For the problem statement we have dealt with , we have developed a neural network with three hidden layers. First hidden layer consists of 4 neurons ,second hidden layer with 8 neurons , third layer with 5 neurons . The input and output layer contain 1 neuron . The Activation Function used is 'relu'.

Loading the dataset

Split the dataset into training and testing

Create MinMaxScalar objects ,fit the model and transform the data.

Build the Neural Network Model and compile the model.

Train the model with the training data.

Plot the performance plot

Evaluate the model with the testing data.

Name: Dhivyapriya.R

Register Number: 212222230032

import numpy as np

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import MinMaxScaler

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense

import gspread

from google.auth import default

import pandas as pd

auth.authenticate_user()

creds, _ = default()

gc = gspread.authorize(creds)

worksheet = gc.open('DL').sheet1

rows = worksheet.get_all_values()

df = pd.DataFrame(rows[1:], columns=rows[0])

df.head()

df['Input']=pd.to_numeric(df['Input'])

df['Output']=pd.to_numeric(df['Output'])

X = df[['Input']].values

y = df[['Output']].values

x_train,x_test,y_train,y_test = train_test_split(X,y,test_size = 0.33,random_state = 33)

Scaler = MinMaxScaler()

Scaler.fit(x_train)

x_train.shape

x_train1 = Scaler.transform(x_train)

x_train1.shape

model = Sequential([
Dense(units = 5,activation = 'relu',input_shape=[1]),
Dense(units = 2, activation = 'relu'),
Dense(units = 1)
])

model.compile(optimizer='rmsprop', loss = 'mae')

model.fit(x_train1,y_train,epochs = 2000)

model.summary()

x_test1 = Scaler.transform(x_test)

model.evaluate(x_test1,y_test)

x_n = [[21]]

x_n1 = Scaler.transform(x_n)

model.predict(x_n1)

Summarize the overall performance of the model based on the evaluation metrics obtained from testing data as a regressive neural network based prediction has been obtained.