IBM Data Science Professional Certificate

1. Python Webscraping

• Webscraping_finance_data.ipynb

  This notebook shows how a webscraping tool called beautifulsoup along with requests library in python can be used to extract netflix finance data from yahoo finance website.

• Webscraping_Tesla_GameStop_Stocks.ipynb

  This notebook shows uses webscraping to obtain GameStop and Tesla stocks and compare their trends over a few months.

2. Databases_and_SQL_for_DataScience

• DB0201EN-PeerAssign-v5_SQLite.ipynb.ipynb

  This notebook utilizes three datasets from the city of Chicago's Data Portal - Socioeconomic Indicators, Chicago Public Schools, and Chicago Crime Data - to load into SQLite database tables and execute SQL queries to analyze the data. The socioeconomic indicators cover public health metrics across Chicago communities from 2008-2012. The schools data provides performance indicators used for CPS reports in 2011-2012. Finally, the crimes dataset has incident reports from 2001 to present. By loading these datasets into a SQLite database and querying them with SQL, this notebook enables data analysis to answer key questions about socioeconomic, education, and crime trends and patterns in Chicago.

3. Data_Visualization_with_Python

   The multiple notebooks here use matplotlib, seaborn, plotly and dash to create visualizations for wildfire data.

4. Capstone Project - Space X Falcon 9 First Stage Landing Prediction

   SpaceX promotes Falcon 9 rocket launches on its website at a cost of 62 million dollars, while other providers charge upwards of 165 million dollars for each launch. A substantial part of these cost savings is attributed to SpaceX's ability to recycle the first stage of the rocket. Therefore, by predicting the first stage's landing success, we can estimate the overall cost of a launch. This information can be valuable for other companies looking to compete with SpaceX in the rocket launch industry. Here we will build a machine learning model to forecast whether the first stage will land given the data from the preceding labs.

   • This work includes data collection, cleaning, EDA as well as various model (Decision Trees, Random Forests, SVM, XGBoost, KNN and Linear Regression) applications for predictive analysis. The most significant model scores are shown below: