MY DATA SCIENCE

INTERNSHIP
Rohit Bihade
DATASMITH AI SOLUTIONS PVT. LTD

Our mission is to become a distinguished AI company providing

data science solutions in the fields of Oil and Gas, Healthcare, &
Earth Data Science by 2025.
We aim to build 3 TechSquads consisting of minimum 10 AI Engineers
each for providing solutions in Oil & Gas | Health Care and Earth Data
Science.
INTRODUCTION
My name is Rohit Bihade, and I am delighted
to be standing before you today as an intern at
Data Smith AI. Over the past two months, I
have had the incredible opportunity to dive
into the world of data analytics and contribute
to the innovative projects at Data Smith AI.
Throughout my internship, I have been
exposed to a wealth of knowledge, practical
experiences, and invaluable mentorship that
has shaped my understanding of this
fascinating field. Allow me to share some of
my key learnings and experiences during my
time at Data Smith AI."
MY LEARNING
• Throughout my internship at Data Smith AI, I had the opportunity to dive deep into the
world of data analytics and gain valuable insights into the data science life cycle, all
while utilizing Python as a powerful tool for analysis. This experience has been
transformative, allowing me to develop a solid foundation in data analytics and apply it
to real-world scenarios.
• Through hands-on projects, I learned various Python libraries, such as Pandas, NumPy,
and Matplotlib, which enabled me to efficiently handle and preprocess large datasets. I
acquired skills in data cleaning, transformation, and exploratory data analysis, allowing
me to uncover patterns, trends, and anomalies within the data.
• Furthermore, I delved into the data science life cycle, understanding the step-by-step
process of solving real-world problems. From defining objectives and formulating
questions to data collection, model development and evaluation, I gained a holistic
understanding of the iterative nature of data science projects. I grasped the importance
of data visualization in effectively communicating insights and conclusions to the client.
DATA SCIENCE LIFE CYCLE
Data Science Lifecycle contains Seven Major
Steps

1. Business Understanding

2. Data Mining

3. Data Cleaning

4. Data Exploration

5. Feature Engineering

6. Predictive Modeling

7. Data Visualization
BUSINESS UNDERSTANDING

Business Understanding is basically

understanding problems which includes
1. What the actual business is about
2. What is the product of the company
3. What is the problem company is
facing
4. What outcome is required
5. What analyst can do for tackling the
problem
DATA MINING

• Gathering the data necessary for the

project.
• Data can be collected from CSV files,
Excels sheets, Images, SQL servers etc.
• Crawling & Scraping may require when
data is not provided
• Crawling- Mining data from different
websource
• Scrapping- Importing data from website
into files or spreadsheet
DATA CLEANING

• We need to filter data according to our

needs.
• We need to handle missing data values
from the data.
• We need to rearrange the data several
times.
• We need to remove all the null and
duplicate values from data.
• We need to replace some of the values
in the data.
 DATA EXPLORATION
• Exploring the data by converting into the
simplest.
• To check whether data is clean.
• To check whether data has no faulty points.
• To understand data statistically using plots,
graphs etc.
• Raw data is typically reviewed with a
combination of manual workflows and
automated data-exploration techniques to
visually explore data sets.
• Look for similarities, patterns and outliers
and to identify the relationships between
different variables.
FEATURE ENGINEERING
Feature engineering is the process of
transforming raw data into meaningful
features that can improve the performance
of machine learning models
• It involves selecting and extracting
relevant information from raw data to
create new features.
• It focuses on choosing the most
informative features that have a
significant impact on the target variable.
• By performing effective feature
engineering, data scientists can enhance
the predictive power of their models,
improve interpretability and extract
valuable insights from the available data.
PREDICTIVE MODELING
Training your machine learning models by feeding
data to evaluate the performance to make prediction
• Clean up data by treating missing data and
eliminating outliers
• Determine whether parametric or nonparametric
predictive modeling is most effective
• Reprocess the data into a format appropriate for
the modeling algorithm
• Specify a subset of data to be used for training
the model
• Train model parameters from the training dataset
• Conduct predictive model performance monitoring
tests to assess model efficacy
• Validate predictive modeling accuracy on data not
used for calibrating the model
• Deploy the model for prediction
DATA VISUALIZATION

Representing data into the simplest form but

it should be effective and visually pleasing,
types of data visualization are
• Bar charts
• Line charts
• Pie charts
• Scatter plots
• Heat maps
• Tree maps
• Network diagrams
MY EXPERIENCE IN DATA SMITH AI
During my internship at Data Smith AI, I had the privilege of being a part of a
vibrant and knowledgeable team in the field of data analytics. As a fresher, I
embarked on this journey with excitement and an eagerness to learn. From day
one, I was warmly welcomed into the company and throughout my internship, I
experienced incredible support from my mentors and colleagues. The work
environment was conducive to growth, with everyone being approachable and
willing to lend a helping hand. I truly appreciated the collaborative atmosphere,
where ideas were encouraged, and I had the opportunity to contribute to
meaningful projects. The quality time spent with my colleagues not only allowed
me to learn from their expertise but also fostered strong professional
relationships. My experience at Data Smith AI has been enriching, and I am
grateful for the knowledge and skills I have acquired during this valuable
internship.
MEMORIES TO TAKE WITH
THANK YOU SO MUCH