You are on page 1of 7

ABSTRACT

The proposed project is smart appointment booking system that provides patients or any user and
easy way of booking a doctor’s appointment online. This is a web based application that
overcomes the issue of managing and booking appointments according to user’s choice or
demands. The task sometime become very tedious for the compounder or doctor himself in
manually allotting appointments for the users as per their availability. Hence this project offers
an effective solution where user can view various booking slots available select the preferred
date and time. The already booked space will be marked yellow and will not be available for
anyone else for the specified time. This system also allows users to cancel their booking anytime.
The system provides an additional feature of calculating monthly earnings of doctor. Doctor has
to just feed the system regularly with daily earnings and the system automatically generates a
report of total amount earned at the end of the month. The application uses Asp.net as a frontend
and sql database as the back-end.

i
Acknowledgement
“Machine Learning With Python” is responsible for keeping all the records of doctor
appointments that are taken by users. This system helps the patient take an appointment online
and save time.
The main objective of the “Machine Learning With Python” project is to provide easier doctor
appointment and gets appointment online which save lots of time.
I like to express our sincere thanks to Mr. G Venkata Ratnam, Head of the Department of CSE
for his valuable suggestions at the time need.
My heartfelt thanks to Dr. S.H.V. PRASADA RAO, Professor and Principal, V.K.R., V.N.B. &
A.G.K.College of Engineering, Gudivada for giving us this opportunity for the successful
completion of our degree.
I will be quite lost without the guidance of the B. Tech Teaching staff of V.K.R., V.N.B. &
A.G.K.College of Engineering, and Gudivada. We also thank other teaching and non-teaching
staff for their assistance and help. I thank the Management favour college for providing
necessary arrangements to carry out this task.
Above all, we thank our parents. I feel deep sense of gratitude for my family who formed part of
my vision. Finally, thank one and all that have contributed directly or indirectly to this project.

PASUPULETI TEJA KUMAR

20NH1A0585

B.Tech 4th Year

1st semester

ii
TABLE OF CONTENTS

Title Page No.

Abstract i

Acknowledgement ii

Table of contents iii -


v

1. Introduction 1–2
1.0 Simple Regression 1
1.1 Multivariable Regression 1
1.2 Simple Regression 1
1.3 Making Predictions 1
1.4 Weight 1
1.5 Radio 1
1.6 Bias 1
1.7 Cost Function 1
1.8 Gradient Descent 2
2
2

2. TRAINING 3–4
2.0 Code 3
2.1 Def 3
2.2 Model Evaluation 3
2.3 Logging 3
2.4 Visualizing 3
2.5 Cost History 3
2.6 Error Rate 3
2.7 Traning Iterations 4
2.8 Mean Squared Error 4

iii
3. SUMMARY 5-6
3.0 MultiVaria Regressionble 5
3.1 Growing Complexity 5
3.2 Normalization 5
3.3 Code 5
3.4 Def 6
3.5 Making Predictions 6
3.6 Initialize 6

3.7 Simplifying with Matrices 6

4. Math 7–8
4.1Code 7
4.0 Bias 7
4.2 Code 7
4.3 Model evaluation 7 -8

5. LOGISTICS REGRESSION INTRODUCTION 9 – 10


5.0 Comprassion to linear regresssion 9
5.1 Linear regression 9
5.2 Logistics regression 9
5.3 Functions 9
5.4 Control Flow 9
5.5 DOM Manipulation 9
5.6 Events 10

6. TYPES OF LOGISTIC REGRESSION 11 – 12


6.0 Binary(Pass/Fail) 11
6.1 multi 11
6.2 ordinal 11

iv
7. BINARY LOGISTIC REGRESSION 13 – 14
7.0 Sigmoid activation 13
7.1 graph 13
7.2 code 13
7.3 def 13
7.4 sigmoid 13
7.5 Making Predictions 14
7.6 Code 14
7.7 Group By 14
7.8 Indexes 14
7.9 Transactions 14

8. COST FUNCTION 15 – 16
8.0 Math 15
8.1 Gradient descent 15
8.2 Multiclass logistic 15
8.3 Glossary 15
8.4 Alogirthm 15
8.5 Attribute 15
8.6 Bias metric 15
8.7 Epoch 15
8.8 Universal 15
8.9 Laravel Mix 16
8.10 Authentication and Authorization 16
8.11 Task Scheduling and Cron Jobs 16
8.12 Testing 16

TYPE 1 ERROR 17 – 35
17
1. Underfitting 18
2. Universal Approximation Theroem 19
3. Unsupervised Learning 20
21
4. VALIDATION SET 21-22
22
4.0 Low variance 22-23
4.1 High variance 23-24
24

OUTPUT 24
CONCLUSION 25

v
vi
7

You might also like