Kuldeep 's repositories
Evaluation_Project-Global_Power_Plant_Database_test
Aim: Need To Predict Primary Fuel And Capacity_mw For Global Power Plant Dataset. Problem Statment: An affordable, reliable, and environmentally sustainable power sector is central to modern society. Governments, utilities, and companies make decisions that both affect and depend on the power sector. For example, if governments apply a carbon price to electricity generation, it changes how plants run and which plants are built over time. On the other hand, each new plant affects the electricity generation mix, the reliability of the system, and system emissions. Plants also have significant impact on climate change, through carbon dioxide (CO2) emissions; on water stress, through water withdrawal and consumption; and on air quality, through sulfur oxides (SOx), nitrogen oxides (NOx), and particulate matter (PM) emissions. The Global Power Plant Database is an open-source open-access dataset of grid-scale (1 MW and greater) electricity generating facilities operating across the world. The actual Database currently contains nearly 35000 power plants in 167 countries, representing about 72% of the world's capacity. Entries are at the facility level only, generally defined as a single transmission grid connection point. Generation unit-level information is not currently available. But in our study we will be working on the dataset only for INDIA. The data set contains only 908 rows and 25 columns. The data set provides information of all the power plant situated at diffrent loactions in india. Features of dataset: country: symbolic country Name country_long: Full country Name name : Name of the Power Plant gppd_idnr : 10-12 character type ID of the power plant capacity_mw : Electricity generating capacity in megawatts latitude : Geo location of plant in decimal degerees longitude : Geo location of plant in decimal degerees primary_fuel : Primary fuel used for electricity genrration. other_fuel1 : Energy source used in electricity generation or export other_fuel2 : Energy source used in electricity generation or export other_fuel3 : Energy source used in electricity generation or export commissioning_year: year of opertaion of power plant or when the power plant start. owner : Majority shareholder of the power plant source: Entity reporting the data url : Web document corresponding to the sourcefield geolocation_source :Attribution for geolocation information wepp_id : A reference to a unique plant identifier in the widely-used PLATTS-WEPP database. year_of_capacity_data: year the capacity information was reported generation_gwh_2013 : electricity generation in gigawatt-hours reported for the year 2013 generation_gwh_2014 : electricity generation in gigawatt-hours reported for the year 2014 generation_gwh_2015 : electricity generation in gigawatt-hours reported for the year 2015 generation_gwh_2016 : electricity generation in gigawatt-hours reported for the year 2016 generation_gwh_2017 : electricity generation in gigawatt-hours reported for the year 2017 generation_data_source : electricity generation in gigawatt-hours reported for the year 2014 estimated_generation_gwh : attribution for the reported generation information
Baseball-Win-Prediction
This dataset utilizes data from 2014 Major League Baseball seasons in order to develop an algorithm that predicts the number of wins for a given team in the 2015 season based on several different indicators of success. There are 16 different features that will be used as the inputs to the machine learning and the output will be a value that represents the number of wins.
Car_Price_Predication
CAR PRICE PREDICTION With the covid 19 impact in the market, we have seen lot of changes in the car market. Now some cars are in demand hence making them costly and some are not in demand hence cheaper. One of our clients works with small traders, who sell used cars. With the change in market due to covid 19 impact, our client is facing problems with their previous car price valuation machine learning models. So, they are looking for new machine learning models from new data. We have to make car price valuation model. This project contains two phase- Data Collection Phase You have to scrape at least 5000 used cars data. You can scrape more data as well, it’s up to you. more the data better the model In this section You need to scrape the data of used cars from websites (Olx, cardekho, Cars24 etc.) You need web scraping for this. You have to fetch data for different locations. The number of columns for data doesn’t have limit, it’s up to you and your creativity. Generally, these columns are Brand, model, variant, manufacturing year, driven kilometers, fuel, number of owners, location and at last target variable Price of the car. This data is to give you a hint about important variables in used car model. You can make changes to it, you can add or you can remove some columns, it completely depends on the website from which you are fetching the data. Try to include all types of cars in your data for example- SUV, Sedans, Coupe, minivan, Hatchback. Note – The data which you are collecting is important to us. Kindly don’t share it on any public platforms. Model Building Phase After collecting the data, you need to build a machine learning model. Before model building do all data pre-processing steps. Try different models with different hyper parameters and select the best model. Follow the complete life cycle of data science. Include all the steps like. 1. Data Cleaning 2. Exploratory Data Analysis 3. Data Pre-processing 4. Model Building 5. Model Evaluation 6. Selecting the best model
Customer_Review_Rating_Prediction
Rating Prediction for technical products from e-commerce website
Evaluation_Project--Census_Income_Project
Aim: The aim is to determine whether a person makes over $50K a year.
Evaluation_Project-_Temperature_Forecast_Project_using_ML
Aim:Temperature Forecast using Machine Learning.
Evaluation_Project_Customer_Churn_Analysis
Aim: Building and comparing several customer churn prediction models.
Evaluation_Project_Flight_Price_Prediction
Aim: Build a machine learning model to predict the price of the flight ticket.
Evaluation_Project_Insurance_Claims_Fraud_Detection
Aim: Predicting if an insurance claim is fraudulent or not
Evaluation_Project_Loan_Application_Status_Prediction
Aim: Loan Application Status Prediction using available dataset.
Flight_Price_Prediction
Analysis of the Flights price and prediction using machine learning model
Customers_Retention_Data_Analysis
Customer satisfaction has emerged as one of the most important factors that guarantee the success of online store; it has been posited as a key stimulant of purchase, repurchase intentions and customer loyalty. A comprehensive review of the literature, theories and models have been carried out to propose the models for customer activation and customer retention. Five major factors that contributed to the success of an e-commerce store have been identified as: service quality, system quality, information quality, trust and net benefit. The research furthermore investigated the factors that influence the online customers repeat purchase intention. The combination of both utilitarian value and hedonistic values are needed to affect the repeat purchase intention (loyalty) positively. The data is collected from the Indian online shoppers. Results indicate the e-retail success factors, which are very much critical for customer satisfaction.
KULDEEP220
Config files for my GitHub profile.
MALIGNANT_COMMENTS_CLASSIFICATION
MALIGNANT_COMMENTS_CLASSIFICATION
Practice_Project
Projects for Practice
Python-web-scraping
This Repo contains Assignments and Notes for Web Scraping