Skip to content

karanchinch10/My_Projects_Portfolio

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

82 Commits
 
 
 
 
 
 

Repository files navigation

Now a day many peoples prefer to buy second hand car instead of buying new one, as its better investment option where we get almost 30-40% discount. but main question here is how seller will know actual selling price of old car base on car features or which factors play major roles?? So to solve this complex problem, I have build ML model which predict estimated price of car base on given input features as brand,KM drive,Power,Year and so on..
  • Completed stepwise EDA (Exploratory Data Analysis) and visualization to get data insight & to know important features also their correlation with car price
  • Done Feature Engineering includes Features extraction & Features construction based on my domian knowledge and visualization
  • Train ML models with multiples regression algorithms then Analysed & compare performance of differents models based of accuracy and complexity
  • After comparing, got well accuracy by RandomForestRegressor(cross validation--around 90%)
  • Finally Build Web App using streamlit and deploy the model
  • Technical tools or library used -- Python,Numpy,Pandas,sklearn,matplotllib,seaborn,streamlit
Marketing campaigns are sets of strategic activities that promote a business’s goal or objective. A marketing campaign could be used to promote a product, a service, or the brand as a whole. To achieve the most effective results, campaigns are carefully planned and the activities are varied. Marketing campaigns are characterized by focusing on the customer needs and their overall satisfaction. The following project focus on the analysis of a dataset of Bank Marketing which contains data or information about customers and aims to get useful insights from the data and predict if a new customer will accept a deposit offer or not. By understanding important factors or features and patterns of target customers those subscribed for deposit so that company can improve this factors and improve business and also which will help to get best strategies to improve for the next marketing campaign
  • I have made ML model which will predict either new customer will accept offer deposit or not?
  • Completed stepwise EDA (Exploratory Data Analysis) then visualizatiion to get some idea about important features or correlation
  • Done Feature Engineering which includes features extraction & features construction based on domain knowledge and visualization followed by label encoding
  • Train ML models with multiples algorithms then Analysed & compare performance of differents models based of accuracy and complexity
  • after comparing with all, got well accuracy by RandomForest and XG boost
  • Finally after cross validation XG boost won (accuarcy of 85% and recall score 88%)
  • Build Pipeline for deployment session
  • Technical tools or library used -- Python,Numpy,Pandas,sklearn,matplotllib,XG boost
To determine class or cateogry of flower which its belong to base on their 4 features or parameters such as sepal length,sepal width, petal length and petal width. Dataset contains total 3 category of flowers of 50 instances each(setosa,virginica,versicolor), where each class refers to a type of iris plant. One class is linearly separable from the other 2; the latter are NOT linearly separable from each other. contents of Multiclass classification problem as below
  • EDA (Exploratory Data Analysis) and visualization to get data insight or important features
  • Train model with multiples classification algorithms
  • Analysed & compare performance of differents models based on F1 score
  • SVM and KNN had given best accuracy
  • Vary K value still accuracy was almost same 97.2 then after cross validation SVM accuracy was more than KNN
  • Finally Build web application using streamlit and deploy the model.
  • Web App👉 https://karanchinch10-streamlit-iris-app-0k57bb.streamlitapp.com// 💝
  • Technical tools or library used -- Python,Numpy,Pandas,sklearn,matplotllib,html,css,streamlit
Google Play Store team is about to launch a new feature wherein, certain apps that are promising, are boosted in visibility. The boost will manifest in multiple ways including higher priority in recommendations sections (“Similar apps”, “You might also like”, “New and updated games”). These will also get a boost in search results visibility. This feature will help bring more attention to newer apps that have the potential.
  • Perform EDA, Data cleaning and Data correction
  • Done details visualization on gplay store apps to get basic information or data insight and that will be helpful for decision making like
    • Total No of apps of all category (like games,sports,medical,education,beauty..etc) to understand whcih category has highest apps
    • Which category has highest demand, rating, installation & reviews
    • Total percentages of free and paid apps available in glapy store
    • Which category of apps are most installed or like to user
    • Average price of paid apps of each category and their demands
    • Is there is any relation of apps rating and reviews with insatllation?
  • Technical tools or library used -- Python,Numpy,Pandas,sklearn,matplotllib,seaborn,html,css

Python | Flask | SQL | HTML | CSS

  • I have made this flask project of bank management web application system
  • Front end was created by HTML and CSS without use of bootstrap
  • Project is specially designed for customer/bank holder to get all basic bank services
  • First customer has to open their bank account by filling basic bank details such as Name, Password, DOB, mob no, Initial Deposit and register their bank account
  • Once account has been created then they can login with their user ID and password
  • User can view and modify their personal details from profile section
  • User can withdraw, credit money into their account also can check current balance
  • Minimum credit and withdraw should be RS 200 and RS50 and minimum initial deposit should be min 1000 RS while opening account
  • User can also change their password by clicking on forgot password and set new password by confirming their name and email ID
  • User can Login and Logout their account anytime
  • Technical tools or library used -- Python,Flask,MySql Database,XAMPP,html,CSS

HTML | CSS | BOOTSTRAP