Skip to content
View Harsh071202's full-sized avatar

Block or report Harsh071202

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 250 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Harsh071202/README.md

Hello, I am Harsh 👋

📍 Pune, Maharashtra, India
📧 Email: harshnagrale03@gmail.com
🔗 LinkedIn: https://www.linkedin.com/in/harsh-nagrale-61ab4820a
💻 GitHub: https://github.com/harshnagrale

👨‍💻 About Me

Aspiring Data Analyst with a strong foundation in Python, SQL, and Machine Learning. I enjoy working on real-world data projects and building solutions that drive insights. I'm passionate about data visualization, model deployment, and constantly learning new tools and techniques to grow in the data domain.

💼 Projects

📌 Insurance Fraud Detection

Built a machine learning pipeline using XGBoost to detect fraudulent insurance claims. Deployed the model using Streamlit for real-time prediction. Focused on feature engineering, data imbalance handling, and pipeline deployment.

📌 Sentiment Analysis on E-Commerce Reviews

Scraped product reviews from Flipkart using BeautifulSoup and performed sentiment analysis using TF-IDF and logistic regression. Created a word cloud and sentiment score dashboard.

📌 Retinal Diabetic Detection (CNN)

Developed a deep learning model using Convolutional Neural Networks (CNN) to classify retinal fundus images into diabetic or non-diabetic categories. Worked with real medical image datasets and used TensorFlow/Keras for model training and evaluation.

📌 Placement Prediction Using ML

Created a predictive model to determine the likelihood of a student's placement based on academic scores, skills, and certifications. Utilized logistic regression and decision tree algorithms with proper data preprocessing and visualization.

🧰 Tech Toolbox

  • Languages: Python, SQL, HTML/CSS
  • Libraries & Frameworks: Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, XGBoost
  • Tools: Jupyter Notebook, VS Code, Git, GitHub, Streamlit, MySQL, Excel , Adv Excel
  • Concepts: Data Cleaning, EDA, Supervised & Unsupervised Learning, NLP, Model Evaluation , Deep Learning , CNN , ANN , RNN

🎓 Education

Bachelor of Technology (B.Tech) in Computer Science and Engineering
Government College of Engineering, Amravati
Graduated: 2024

Post Graduate Program in Data Science and Analytics Certification
Imarticus Learning – End-to-End training in Python, ML, Deep Learning, NLP, SQL, and project deployment

📜 Certifications

  • Data Science and Machine Learning – Imarticus Learning
  • Career Essentials in Data Analysis by Microsoft and LinkedIn

Thanks for visiting my profile! 😊
Feel free to connect or collaborate on data-driven projects.

Pinned Loading

  1. Insurance_Fraud_Detection Insurance_Fraud_Detection Public

    Detecting fraudulent insurance claims using machine learning techniques like XGBoost and SMOTE on real-world data to enhance claim verification accuracy.

    Python

  2. Flipkart_Product_Sentiment_Analysis Flipkart_Product_Sentiment_Analysis Public

    Web scraped Flipkart product reviews using BeautifulSoup and performed sentiment analysis with TF-IDF, polarity scores, and data visualizations to understand customer opinions.

    Jupyter Notebook

  3. Retino-Diabetic Retino-Diabetic Public

    A deep learning Model using CNN (ResNet50) to detect diabetic retinopathy stages from retinal images, deployed with Streamlit and enhanced with patient form input.

    Jupyter Notebook

  4. Placement_Prediction Placement_Prediction Public

    A Streamlit web app that predicts student placement chances using an AdaBoost classifier, based on academic scores, certifications, and soft skills. Integrated with MySQL for result logging.

    Python

  5. Customer_Churn_Prediction_App Customer_Churn_Prediction_App Public

    A Streamlit-based churn prediction app using a trained Random Forest model to analyze customer behavior and predict churn based on demographics, spending, interaction history, and service usage.

    Python

  6. Car_MPG_Prediction_App Car_MPG_Prediction_App Public

    A Streamlit web app to predict a car’s fuel efficiency (MPG) based on specifications like horsepower, weight, and model year using a trained machine learning regression model.

    Python