Naraharisetti SaiTeja — Associate Consultant

Seeking opportunity for position in Data Science .Carrying 3 years of experience in Python , Data Annotation , Model Validation , Data Annotation Quality Check, Data Analysis (PANDAS & NUMPY) . Worked in Agile methodology and Used Jira tool for updating every day Task . Tasks involved by me are : ->Understanding the business requirement and business requirement and plan my work flow accordingly ->Worked on libraries Numpy, Pandas, Openpyxl,Pillow,cv2,Beautiful Soup,request,PyPDF2,Docx, ->Training dataset Preperations(CSV,JSON,XML formats) -> Handling outliers by performing box plotiing, z scores, Interquartile range ) -> Collecting raw data from database team and checking whether the requirements which we need are present in the data or not. ->Performing Statistical analysis to check how the independent variable are performing with target class variable and find out the deviation ->Checking the missing values any present in the data if any try to fill the null values with mean or median or mode what ever required and check the data by again plotting. ->Performing multiple quality checks on the training data to check all the required labels are given correctly or not . ->Plotting the training data to check how it is representing the data any inconsistency is there or not . ->Working on different NLP(spacy,nltk,textblob) packages using python to compare and understand the outputs from the libraries used . ->Checking any special characters present in the text raw data and eleminating them so that they will not cause issues while model training and testing . ->Tackling and handling challenges faces while working on text data by having a meet with my colleagues to see how to handle them with out disturbing the other data which is appropriate . ->Worked on webscraping scrapped tabular data, text data from web pages using beautiful soup. ->Worked on OCR as well extracting the data from PDF, Documents, using pytesract library . ->Worked on Open Cv for detection of all the features of face by using Haarcascade Classifiers . ->Validating the results which are obtained from the validation data set preparing the report on the results occurred like (100% detected , partially detected, wrong detection , missed detection ) and sent the report to the data scietist so that he can take steps in the future to avoid this issues to not be repeated again .

Stackforce AI infers this person is a Data Science professional with strong capabilities in Python and machine learning.

Location: Hyderabad, Telangana, India

Experience: 5 yrs 10 mos