-Associate system Engineer with 1 year of experience as Data analyst in IBM.
-Actively writing kernel scripts in kaggle.
-Experience in writing python scripts to automate browser and web scraping.
-Understanding of Graphs including Barchart,Histograms,Pie-chart,Scatter plot,Box-plot.
-Understanding of Deep learning algorithms,including ANN,CNN and RNN.
-Actively writing kernels in Kaggle.
BTech(Information Technology,2013-2017),KIIT UNIVERSITY with 7.8 CGPA. HSCC Plus 2 (2013),DAV BSEB Patna with 78.2%
HSC (2011),DAV BSEB Patna with 9.2 CGPA
Role-Associate System Engineer-Sept 2017-Dec 2018
Tools:Pycharm,Anaconda,Jupyter Notebook,R Studio
Machine Learning Algorithms:
Automation/Web scraping projects:
Quora Automation-In this project I have created a python script that will extract information of particular user .User have to enter the name of a particular quoran and it will generate two files.One excel file having information of that user and other text file gives the all answers written by that user.
Technology used-Python,Selenium Webdriver,Beautifulsoup,Microsoft Excel. Cricketer_Data_Extraction-In this project I have extracted data from Cricbuzz.User have to type just the name of cricketer and script gives you all the details in excel sheet. Technology used-Python,Selenium Webdriver,Beautifulsoup,Microsoft Excel. Machine Learning Projects:
Boston Housing Dataset- In this dataset we have to predict the price of house in dataset.This is clearly a problem of linear regression.I have done the detailed analysis of data using pandas and numpy.Machine Learning algorithm used here Gradient Boosting Regressor which gives R-Square value of 0.935.
Iris Dataset- In this dataset we have to claasify data on the basis of its features.This is a problem of classification.Algorithm used here is DecisionTreeClassifier Which uses ginni value for prediction.The average F1-Score is 0.866 Titanic Dataset- In this dataset we have to predict whether the passenger has survived the accident or not.Algorithm used here is XGBoost.The F1 score is 0.875. NLP Projects:
In this project, I have written a python script that extract paragraph from Wikipedia using web scraping, Then created a weighted histogram.After that i have calculated scores of each sentance.After sorting the sentance with highest score can be used to give summary of the whole paragraph.
Deep Learning Projects:
In this Project,i have done data analysis on text data(basically review of the movie),based on that we have to predict.there are 5 classes and we have to predict one of them.The F1 score on test data is 0.79.
In this Dataset, i have applied CNN to recognise data based on the image.The accuracy is about 0.821.
In this project i have used haar cascade classifier and opencv to detect faces. Library used-Keras,Numpy.
Certifications and Trainings
1.Certified Linux System and Network Administrator from Linux Solution,Bhopal. 2.Complete Machine Learning course with Python from Udemy. Personal Profile
Date of Birth:28.06.1995
Father’s Name:Navin Kumar
I hereby declare that all the information furnished above is correct to my knowledge and belief. Hyderabad (Abhinav)