Welcome to my IBM—Data Science Repository 😄

• The aim of this repository is to practice the foundation of Data Science, such as asking the right questions, setting up the methodology, evaluate results, storytelling, presentation, data-driven decisions, and more 💡

• The folders in this repo are as follows,

01 - Introduction to Python with IBM

02 - Data Science Methodology

03 - SQL with Data Science

04 - Data Analysis

05 - Visualization

06 - Machine Learning

07 - Applied Data Science Capstone - Falcon 9 SpaceX First-Stage Landing Prediction – Data Science Project

• Aim: Predict the successfulness of Falcon 9 Landing.

• Procedure: Data collection using SpaceX open-source APIs and Web-scraping. Data wrangling using Pandas & SQL quires. EDA via Matplotlib & Seaborn. Launch sites locations analysis with Folium. Dashboard vis dash & plotly express. Benchmarking LR, SVM, DT, KNN.

• Findings: All models scored an accuracy of ~ 83%.

Hands-on Labs

A - Regression

• Fuel consumption — Linear Regression Analysis

• House Sales in King County, USA, Via Ridge Regression

• American Stocks data collection using API & Wep-scraping

B - Classification

• Customer churn with Logistic Regression

• Customer Category Classification Via K Nearest Neighbor

• Drug Classification Via Decision Tree

• Loan Classification - Benchmarking ML models

• Cancer Classification via Support Vector Machine

• Food Cuisine Classification Using Decision Trees - IBM Methodology

C - Clustering

• Customer Segmentation Via K-Means

• Vehicles Clustering Via Hierarchical Clustering

• Canada Weather Density Based Clustering

D - Recommendation

• Product Content-Based Recommendation

• Product Collaborative Filtering

E - EDA

• Chicago Census Selected Socioeconomic Indicator, Crime & School, SQL Analysis

• Hands-on SQL Queries from IBM-DB2

• Hands-on Data Visualization Using Matplotlip, Seaborn & Folium

• Hands-on Python Data types, Classes, Functions, API, HTTP-request, Pandas, Numpy & Wep-scraping