APPLIED DATA SCIENCE CAPSTONE RPOJECT

OPERATION SPACEX OUTCOME PREDICTION(A Machine Learning

Approach)

SETHU S
22 JULY 2023
 OUTLINE

⁂ EXECUTIVE SUMMARY

⁂ INTRODUCTION

⁂ METHODOLOGY

⁂ RESULTS

⁂ CONCLUSION

⁂ APPENDIX

GITHUB URL:

https://github.com/itsmesethus/courserac10assignments/tree/main/applied%20data%20science%20capstone%20project%20works
 EXECUTIVE SUMMARY

SUMMARIES OF METHODOLOGY:

1) Collecting the SpaceX history data using API ,

SUMMARIES OF RESULTS:
Web scrapping from Wikipedia source.
2) Data Preprocessing (handling missing values,
1) Data Visualizations
data integrity checking, data quality and etc.) 2) Best Machine Learning Model for Prediction of
SpaceX landing
3) EDA with Structured Query Language
4) EDA with Pandas and Matplotlib libraries(Python)
5) Interactive and Visualizing Dashboard( Folium, Plotly and
Dash)
6) Predictive Analytics with Machine Learning for SpaceX rockets
landing.
 INTRODUCTION

"As long as there are dreams, rockets will forever carry the hope of mankind beyond the horizon."

SpaceX advertises Falcon 9 rocket launches on its website, with a cost of

62 million dollars; other providers cost upward of 165 million dollars each, much
of the savings is because SpaceX can reuse the first stage. Therefore if we can
determine if the first stage will land, we can determine the cost of a launch. This
information can be used if an alternate company wants to bid against SpaceX for a
rocket launch.

We, hereby going to travel with the process of our Data Science Team
and how they have worked to solve this problem of SpaceX Organisation before
their next launch of rockets into the orbit whether it will be succeful or loss for
them based on their previous history launches. So, okay let’s dive into the
presentation of the Team.
 METHODOLOGY
❖ DATA COLLECTION ----- (Rest API, Web Scrapping):

* Using the Rest API we extract the data from the source in the form of JSON and later we can easily turn that format
to data frame using the help of Pandas library of Python.

* For Web Scrapping we can use the BeautifulSoup and request libraries to scrap out the data from the Wikipedia
source.

https://github.com/itsmesethus/coursera-c10-
assignments/blob/main/applied%20data%20science%20capstone%20project%20works/Week1%20SpaceX%20Falcon%20Data
%20Collection-Wrangling.ipynb
 ❖ DATA PREPROCESSING :

* Here in this section we need to look for the data integrity, data quality and handling the missing values will be
considered.

* Because if data is n’t in correct format or any other possibilities the results may mislead to wrong predictions.

https://github.com/itsmesethus/coursera-c10-
assignments/blob/main/applied%20data%20science%20capstone%20project%20works/Week1%20SpaceX%20Falcon%20Data
%20Collection-Wrangling.ipynb
❖ EDA WITH STRUCTURED QUERY LANGUAGE:

* SQL is the best programming language when handling in terms of huge volumes of data. Using this we have done the
EDA for the Falcon 9 rockets. And some results are,
❖ EDA WITH MATPLOTLIB AND PANDAS:

* Matplotlib and Pandas are the most versatile libraries in Python for handling the visualizations and data frames.

Scatter Graphs : Line Graph:

• Flight Number vs. Payload Mass • Success rate vs. Year

• Flight Number vs. Launch Site
• Payload vs. Launch Site
• Orbit vs. Flight Number Bar Graph :
• Payload vs. Orbit Type
• Orbit vs. Payload Mass • Success rate vs. Orbit
❖ EDA REASULTS:
YEAR 2019 have the high no of rocket success rates than other years.
❖ VISUALIZATIONS (FOLIUM MAPS)

Launch Sites

Red : faliures
Green: Success
❖ PLOTLY:

KSC LC-39A has the best success rate of launches.

KSC LC-39A has achieved a 76.9% success rate while

getting a 23.1% failure rate.
Low weighted payloads have a better success rate than the heavy weighted payloads.
❖ PREDICTIVE ANALYSIS:

For accuracy test,

all methods
performed similar.
We could get more
test data to decide
between them. But
if we really need to
choose one right
now, we would take
the decision tree.
❖ CONCLUSION:

*The success of a mission can be explained by several factors such as the launch site, the orbit and especially the number of
previous launches. Indeed, we can assume that there has been a gain in knowledge between launches that allowed to go from a
launch failure to a success.

• The orbits with the best success rates are GEO, HEO, SSO, ES-L1.

• Depending on the orbits, the payload mass can be a criterion to take into account for the success of a mission. Some orbits
require a light or heavy payload mass. But generally low weighted payloads perform better than the heavy weighted payloads.

• With the current data, we cannot explain why some launch sites are better than others (KSC LC-39A is the best launch site).
To get an answer to this problem, we could obtain atmospheric or other relevant data.

• For this dataset, we choose the Decision Tree Algorithm as the best model even if the test accuracy between all the models
used is identical. We choose Decision Tree Algorithm because it has a better train accuracy.
THANK YOU!