1. Web Scraping Housing Data

Web scraping used to obtain huge data from websites & extracting/parsing required info from it which usually in unstructured form (HTML format) and then its converted into structured data in a spreadsheet or database so it can be used in various applications.

• Used requests and BeautifulSoup libraries to perform the web scraping.
• All Important parameters related to housing such house price, total sqft area, project by, location, BHK and so on are scraped from website makaan.com
• Objective is to know Price of house for differents location in mumbai city.
• Data from 250 pages scarpped, store in single dataframe & export to csv file.
• Clean Scrapped data and Visualize to know important features & their correlation with house price.
• Compare Price rate for different location BHK wise to understand location with higher rate.
• Tech stack used:Python,requests,BeautifulSoup,pandas.
  
• 👉Web Scraping 💝
• 👉Scraped Data Analysis 💝

2. Predict Price of Old Car

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 & visualization
• Train model with multiple regression algorithms then Analysed & compare performance of differents models based of accuracy and complexity
• Got well accuracy by RandomForestRegressor(cross validation-around 90%)
• Build Web App using streamlit and deploy model
• Tech Tools:Python,Numpy,Pandas,sklearn,matplotllib,seaborn,html,css.
• • View on kaggle 💝
  • Web App 💝

3. Bank Marketing Campaign

Marketing campaigns are sets of strategic activities that promote a business’s goal or objective also can be used to promote a product, service, or any brand as a whole. The project is focus on analysis of Bank Marketing dataset which contains data of customers details (Personal + Banking) and aims to get useful insights from data. By understanding important features and patterns of target customers which can help to get best strategies to improve for the next marketing campaign

• Build Model which predict either a new customer will accept a deposit offer or not
• Done EDA & Data Correction and Handle outliers
• Visualize data to know pattern of target customers by their previuos campaign deatils includes contact duration,type,no of contact perform, also banking details & so on..
• RandomForest & XG boost Perform best (R2score 86%) after Train and Evaluate model performance based on accuracy, R2 score & complexity
• Build Pipeline for deployment session & Deploy the model
• Tech stack used:Python,pandas,matplotlib,seaborn,numpy,html,css.
• • View on kaggle 💝
  • Web App 💝

4. G-Play Apps Visualization

Google Play Store team is about to launch a new feature wherein, certain apps with higher priority in recommendations sections (“Similar apps”,“New and updated games”) that are promising, are boosted in visibility also 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 on raw data
• Done visualizationby various plots to draw useful insight from data and which will help for decision making like
  1. Total No of apps of all category (like games,sports,medical,education,beauty..etc)
  2. Which category has highest demand, rating, installation or reviews?
  3. Total percentages of free and paid apps available in glapy store
  4. Is there is any relation of apps rating and reviews with their installation?
• Tech stack used : Python,numpy,pandas,matplotlib,seaborn.
• • View on kaggle 💝
  • View on Github 💝

5. Bank Management Web App

Python | Flask | SQL | HTML | CSS

I have made Flask Project of Bank Management Web Application System designed for customer/bank holder to get all basic bank services

• Front end was created by HTML and CSS without use of bootstrap
• Connect python with SQL database to manage all information by CRUD operation
• First customer has to open their bank account by filling basic bank details such as Name, Password, DOB, mob no, Initial Deposit & register their bank account
• Now user can login account by entering user ID and password
• User can view and modify their personal details & change password also can logout acccount with login session
• User can withdraw, credit money into their account and check current balance
• Tech stack used:Python,Flask,MySql Database,XAMPP,html,CSS
  
• • View Project Report
  • View on Github

6. Movie Rating Sentiment Analysis

Sentiment Analysis, also referred to as opinion mining, is an approach to Natural Language Processing (NLP) that identifies the emotional tone behind a body of text. IMDB Dataset contains 50k movie which taken from kaggle.

• Perfrom text cleaning using nltk library and convert word to vector form
• Trained model with various algorithms and compared the performance models on the basis of f1_score.
• The best performing model on the bases of f1-score was LSTM RNN with f1_score of 0.96.
• Deployed a web app using streamlit
• Tech stack used : Python,numpy,pandas,nltk,sklearn,tensorflow,streamlit
• • View Web App 💝
  • View on Github 💝

7. Personal Web PortFolio

HTML | CSS | BOOTSTRAP

• I have made Personal web Portfolio to showcase my skills, technical knowledge and personal projects
• 👉Click to View My Personal Web Porfolio 💝

💝To view my more projects