Post Job Free
Sign in

Python Data

Location:
Chennai, Tamil Nadu, India
Posted:
February 15, 2021

Contact this candidate

Resume:

Anandaselvi.S

Plot No:***E, Senthil Rail Nagar,

6th Street, Iyyenchery, Urapakkam

Kanchipuram District- 603210

Email: adj6k4@r.postjobfree.com

Mobile:+91-741*******

OBJECTIVE

To be a dynamic professional, upgrade my knowledge and skills and achieve the objectives of the company with dedication.

TECHNICAL SKILLS:

SKill

Technology known

Programming /Scripting

Python

Database

SQL,MongoDB

Tools /IDE

Pycharm,Pyspyder,Jupyter Notebook

Data Science

Web scrapping,Machine learning,Statistical modelling,Natural language Processing,pandas,scikit-learn,keras,matplotlib

Operating system

Windows

MACHINE LEARNING ALGORITHM:

Linear Regression

Logistic regression

Ridgo and lasso regression

SVM

Naïve bayes

Random forest

Decision tree

KNN

Kmeans

Xgboost

PCA

PROFESSIONAL EXPERIENCE

Organisation

Nanoyotta Technology Perungudi Chennai

Nanoyotta, a subsidiary Global Sports Commerce, is an advanced technology and analytical firm in the business of real-time deep data analytics on text, image, video empowered with advanced data science and content overlay platform specialised in Big Data, Machine Learning and Computer Vision domain.

Duration

8 months(Augest-2018-March 2019)

Tasks:

INDIAN PREMIUM LEAGUE,PROKABBADI-Learned to prepare Brand catalogue based on the Brand representation Document

Annotated the branding present in the dataset for Machine learning and brand modelling

ACADEMIC PROFILE

Qualifications

Year of passing

Institution Name

Percentage

M-tech(CSE)

2019

VIT

68.9

B. E(CSE)

2017

Peri Institute of Technology

70.6

12th

2013

Kings Matriculation Higher Sec School

89.3

PROJECTS DONE

Flight price prediction:

Build a regression model to predict flight price based on training data

Here Random forest algorithm are passed with the best parameters derived from GridSearch.

oWe calculate the Rsquared scores or Adjusted Rsquared score for both models and select the model with the best score.

oDeployment-Flask

Python packages-numpy,scikit-learn,pandas,matplot

oCloud service – Heraku

Heart disease prediction:

oBuild classification model to predict heart disease for that the person has, based on training data

oHere, KNN and RANDOM FOREST algorithms are passed with the best parameters derived from GridSearch.

oWe calculate the AUC scores for both models and select the model with the best score.

Python packages-numpy,scikit-learn,pandas,matplot

Movie Review Sentiment Analysis

Build the classification algorithm,which classify data into positive or negative

Algorithm:Naïve bayes

Data: https://www.kaggle.com/c/word2vec-nlp-tutorial

Technology:nltk,scikit-learn,pandas,matplot

CERTIFICATION

INEURON -Affordable MachineLearning course

Certificate course Core Python at UDEMY.

PERSONAL DETAILS

Languages known : Tamil,English

DECLARATION

I declare that all the information furnished above is true to the best of my knowledge.

Place: Kanchipuram (S.Anandaselvi)

Date:



Contact this candidate