Rohit Joseph's Projects
statistical technique used for reducing the dimensionality of data by transforming it into a new coordinate system to reveal underlying patterns and structure while minimizing information loss.
calculator using function
mean,median,mode,standerd deviation, variance, percentile, correlation
project is based on likelihood of developing diabetes based on glucose, bmi, insulin, age
Data Structure and methods
Employee management system using array of dictionary in python
employee management system using JSON
encrypting and decrypting a file using json librery methods
rendering a template using the render_template function provided by Flask's templating module.
Openpyxl-Python library allows work with Excel files
project based on basic multiple linear regression model data should be realtime ,and minimum 15 to 20 patient data should be there find out the normal Troponin , blood pressure,Cholesterol,range
using with a .json file (loading and dumping)
K-fold cross-validation divides data into K subsets. It trains the model K times, using K-1 subsets for training and one for validation. This helps assess model performance and prevent overfitting.
machine learning algorithm that partitions a dataset into 'k' distinct, non-overlapping clusters, where each data point belongs to the cluster with the nearest mean, serving as a prototype of the cluster.
machine learning algorithm for classification and regression tasks. It assigns a class label or value to a new data point based on the majority class or average value of its k nearest neighbors in the training set. It's simple, intuitive, but computationally expensive during prediction, and less effective in high-dimensional spaces.
Linear regression estimates the relationship between one independent variable and a dependent variable, while multilinear regression extends this to multiple independent variables.
list comprehension methods , ...etc
data visualizations using matplotlib python library
Gaussian Naive Bayes is a classification algorithm assuming features are independent and follow a Gaussian distribution. It predicts the class for a given sample by applying Bayes' theorem and selecting the class with the highest probability. Despite its simplicity, it's effective for many classification tasks with continuous features.
creating arrays with NumPy (1D,2D,3D)
dropna() and fillna() are methods used to handle missing data in a DataFrame.
File contains:- webscarping using requests,json,pandas,colorama,json ...etc
PYTORCH(tensorflow basics and others)
collecting grocery data through user input and dumping to json file
SVM is a versatile algorithm for classification and regression. It finds the best line or plane to separate data points of different classes, making it effective even in high-dimensional spaces.
Encryption and decryption using with file handling
string manipulation and file handliing
Train-test split divides data for model training and evaluation, while linear regression predicts continuous outcomes and logistic regression handles binary classification, both leveraging linear relationships between features and targets.
file contains:- webscraping with flask, request & json librery, workbook, iterrows() method, Dataframing,