Welcome to Rohit Bhimrao Jondhale Data Science Portfolio 😊 Information upload is in progress............!

Project 1: Diabetic Prediction

-Performed Discriptive Analysis. -Filled null values with respective the skweness and normally distributed values of the data with median and mean. -Histogram plotted for the data distrubution. -Skweness corrected with the logarithmic function. -Scatterplot created to understand the relationship between different variables. -Pair plot also created to see the relationship between variables at once. -Performed the correlation Analysis with Pearsons Correlation.

Spliting data into training and testing dataset.
Different ML model implimented such as Logistic Regression, Decision Tree, Random Forest classifier, XGBoost classifier, Gradient Boosting classifier, Support Vector Machine classifier, KNN classifier, Naive Bayes, XGBoost Random Forest Classifier. -Classification report printed for model validation also checked the AUC-ROC for the model evaluation.

-Also, stacked ensemble technique used to show these model at once with the accuracy score by gridsearch CV. -

Data Vizualisation in presented in Tableau

————————————🌹🌹🌹🌹🌹🌹🌹🌹🌹🌹🌹🌹————————

Project 2: Loan Prediction Analysis

Loan Prediction Analysis using Stack-ensemble Models -Data cleaning, Fitted different kinds of algorithms such as Logistic Regression, Decision Tree Classifier, Random Forest Classifier, -Checking model with Cross-Validation. -Tried StackEnsemble Models with Logistic Regression, Naive Bayes, Random Forest Classifier, Gradient Boosting Classifier, Quadratic Discriminant Analysis, Support Vector Machines Classifier, K-Neigherest Neighbors and Decision Tree Classifier, XGBoost Classifier and XGBoost Random Forest Classifier. -Checking model with K-fold Cross-validation as cv=10 with theirs mean as output.

————————————🌸🌸🌸🌸🌸🌸🌸🌸🌸🌸🌸🌸————————

Project 3: Advance Regression House Price

Advance Regression House Price Prediction -Cleaning the data. -Used Normalisation Technique. -Label Encoading. -Used Linear Regression, Decision Tree Regressor, Gradient boosting Regressor, Cross Validation.

————————————💙💙💙💙💙💙💙💙💙💙💙💙————————

Project 4: Mercedes Benz Greener Manufacturing

-Performed PCA -predicted values using XGBoost

————————————❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️———————-

Project 5: Black-Friday-Sale-Prediction

-Handling missing Values -Data cleaning, -Label Encoding,
-Linear Regression, Decision Tree Regressor, XGB Regressor.

————————————💚💚💚💚💚💚💚💚💚💚💚💚————————

Project 6: Retail Analysis with Walmart Data

————————————❄️❄️❄️❄️❄️❄️❄️❄️❄️❄️❄️❄️————————

Project 7: Chronic Kidney Disease Prediction

-Chronic Kidney Disease Prediction using Logistic regression, Support Vector Machines, Naive Bayes, etc. -Used Cross-validation for the model accuracy.

————————————🌻🌻🌻🌻🌻🌻🌻🌻🌻🌻🌻🌻————————

Project 8: Stroke Prediction

-Data Cleaning, missing values handling, -Checking for skweness and kurtosis -Label Encoding, -Logistic Regression, K-Nearest Neighbors, Gradient Boosting, Naive Bayes, -cross validation -classification report -pd.crosstab on (y_train, y_pred) to get type 1 and type 2 error.

————————————⭐⭐⭐⭐⭐⭐⭐⭐⭐⭐⭐⭐————————

Project 9: College Admission Prediction using R

-Predictive Analysis - Outlier treatement, EDA, Boxplot and QQ plot, Shapiro-Wilk test for normality, -Skweness and Kurtosis corrected with logrithmic and square root transformation, -Logistic Regression, Decision Tree, Naive Bayes, SVM, KNN, Descriptive Analysis, Point chart.