Data Science
Content
1. About Us
2. Instructions
3. Submission
4. Task List
About Us
Welcome to Codveda Technology, where innovation meets
excellence. Founded with a vision to empower businesses
through cutting-edge IT solutions, we specialize in delivering
tailored services that drive success in the digital era.
At Codveda, we offer a diverse range of services, including web
development, app development, digital marketing, SEO
optimization, AI/ML automation, and data analysis.
Our team of skilled professionals is committed to helping
businesses unlock their full potential by providing innovative,
scalable, and reliable solutions.
INSTRUCTIONS
Update your LinkedIn profile with your achievements,
including the offer letter and completion certificate. Mention
and tag @Codveda in your posts.
Use hashtags like #CodvedaJourney, #CodvedaExperience,
and #FutureWithCodveda to showcase your progress and
experiences.
Share your project completion updates on LinkedIn,
accompanied by a video explanation and the GitHub project
repository link.
You will be provided with four tasks. Select and complete any
three tasks within your domain to fulfill the internship
requirements.
Submit your completed tasks via the Codveda submission
form. Ensure all tasks are submitted within the allocated 15-
day period.
SUBMISSION
Create a professional video showcasing your internship
projects and achievements.
Host the video on LinkedIn to provide proof of your work and
establish credibility among your peers. Consider tagging
Codveda Technology in your posts to ensure they are notified
of your work using hashtags like #CodvedaAchievements and
#CodvedaProjects.
A SUBMISSION FORM will be shared later. Till then, please
continue your tasks and maintain a separate file for each level.
When posting the video on LinkedIn, include engaging content
that highlights your contributions and skills. Tailor the post to
your specific internship domain to maximize impact and
visibility.
Level 1 Task 1: Data Collection and Web
(Basic) Scraping
Description: Collect data from a website using web
scraping techniques.
Objectives:
Identify a target website and inspect its structure.
Use BeautifulSoup and requests libraries to scrape data
from web pages.
Store the scraped data in a structured format (e.g., CSV,
JSON).
Handle common challenges such as pagination and
dynamic content.
Tools: Python, BeautifulSoup, requests, pandas.
Level 1 Task 2: Data Cleaning and
(Basic) Preprocessing
Description: Clean and preprocess a raw dataset to
make it suitable for analysis.
Objectives:
Handle missing data (e.g., imputation, removal).
Detect and remove outliers.
Convert categorical variables into numerical format
using one-hot encoding or label encoding.
Normalize or standardize numerical data.
Tools: Python, pandas, scikit-learn
Level 1 Task 3: Exploratory Data
(Basic) Analysis (EDA)
Description: Perform exploratory data analysis to
understand the underlying structure and trends in the
data.
Objectives:
Compute summary statistics (mean, median, variance,
etc.).
Visualize the data using histograms, scatter plots, and
box plots.
Identify correlations between numerical features using
a correlation matrix.
Generate a report summarizing insights from the EDA.
Tools: Python, pandas, matplotlib, seaborn.
Level 2 Task 1: Predictive Modeling
(Intermediate) (Regression)
Description: Build and evaluate a regression model to
predict a continuous variable (e.g., house prices).
Objectives:
Split the dataset into training and testing sets.
Train a linear regression model using scikit-learn.
Evaluate the model using performance metrics like
mean squared error (MSE) and R-squared.
Experiment with multiple models (e.g., Decision Trees,
Random Forest) and compare performance.
Tools: Python, scikit-learn, pandas, matplotlib.
Level 2 Task 2: Classification with Logistic
(Intermediate) Regression
Description: Build a decision tree classifier to predict
a categorical outcome (e.g., predict species of
flowers).
Objectives:
Preprocess the data (e.g., handling categorical features,
feature scaling).
Train and evaluate the logistic regression model.
Use metrics such as accuracy, precision, recall, and the
ROC curve for evaluation.
Compare logistic regression with other classifiers like
Random Forest or SVM.
Tools: Python, scikit-learn, pandas, matplotlib.
Level 2 Task 3: Clustering (Unsupervised
(Intermediate) Learning)
Description: Implement K-Means clustering to group
data points into clusters without labels (e.g.,
customer segmentation).
Objectives:
Apply K-Means clustering to the dataset.
Use the elbow method or silhouette score to determine
the optimal number of clusters.
Visualize the clusters in 2D space using PCA or t-SNE for
dimensionality reduction.
Interpret the clustering results and summarize key
findings.
Tools: Python, scikit-learn, matplotlib, seaborn.
Level 3 Task 1: Time Series Analysis
(Advanced)
Description: Analyze and model time-series data to
forecast future values (e.g., stock prices, sales).
Objectives:
Plot and decompose the time series into trend,
seasonality, and residual components.
Implement moving average and exponential smoothing
techniques.
Build an ARIMA or SARIMA model for forecasting.
Evaluate the model using metrics such as RMSE and
visualize the forecast.
Tools: Python, pandas, statsmodels, matplotlib.
Level 3 Task 2: Natural Language
(Advanced) Processing (NLP) - Text
Classification
Description: Classify text data into categories (e.g.,
spam vs. non-spam, sentiment analysis).
Objectives:
Preprocess text data (tokenization, removing
stopwords, stemming/lemmatization).
Convert text into numerical representation using TF-IDF
or Word2Vec.
Train a classification model (e.g., Naive Bayes, Logistic
Regression) on the processed text.
Evaluate the model using precision, recall, and F1-score.
Tools: Python, nltk, scikit-learn, pandas.
Level 3 Task 3: Neural Networks with
(Advanced) TensorFlow/Keras
Description: Build and train a simple feed-forward
neural network to classify images or structured data.
Objectives:
Load a dataset (e.g., MNIST digits or a structured
dataset) and preprocess it.
Design a neural network architecture using TensorFlow
or Keras.
Train the model using backpropagation and evaluate it
using accuracy and loss curves.
Tune hyperparameters (e.g., learning rate, batch size) to
improve performance.
Tools: Python, TensorFlow, Keras, pandas, matplotlib.
How to
Contact Us?
For additional information, kindly
get in touch with our team.
@codveda
[email protected]
www.codveda.com
