- 👋 Hi, My name @Jitendra-Dash , I am a Data Scientist / NLP engineer!
- 👀 Interested in machine learning and data science stuff
- 📫 How to reach me you can email at jdash862@gmail.com
- Natural language processing
- Vectorization - TFIDF ,Count vectorizer , word2vec etc
- Data cleaning and preprocessing
- Sentiment classification , sentiment extraction, NER , Question-answering
- Machine learning
- KNN
- Niave Bayes
- Logistic regression
- Random Forest
- GBDT
- Decision Tree
- Linear Regression
- Deep learning
- MLP
- RNN
- CNN
- Encoder Decider
- Attention
- Bert
-
Exploratory Data Analysis
-
Model Deployment :- Flask and FastAPI
Projects That I have done :-
A detailed Explaination about this Case Study (A medium Blog on analytics vidhya Page)
The intrusion detector learning task is to build a predictive model (i.e. a classifier) capable of distinguishing between bad connections, called intrusions or attacks, and good normal connections.
!
- A detailed Exploratory Data Analysis
- Machine learning Model like (Naive Bayes , Logistic Regression , Randomforest , Decision Tree ,Xgboost)
- Feature engineering and many more things
A detailed Explaination about this Case Study (A medium Blog on analytics vidhya Page)
This case study is about capturing the sentiment or meaning behind a tweet .
With all of the tweets circulating every second it is hard to tell whether the sentiment behind a specific tweet will impact a company, or a person’s, brand for being viral (positive), or devastate profit because it strikes a negative tone. Capturing sentiment in language is important in these times where decisions and reactions are created and updated in seconds. But, which words actually lead to the sentiment description.
!
- A detailed EDA
- Deep Learning Algorithm Like : LSTM , Attention ,BERT
- Post Analysis of the Result (here we will see where our prediction making mistake or where it giving us great prediction)
A detailed Explaination about this project (in my youtube channel)
- get the data
- do some stats
- clean and preprocess
- convert to vectors
- build model
- save model
- deploy using fastAPI

