Guided projects details:
- Language: Python
- Anaconda.Navigator - Jupyter Notebook
- This project aims identify what are the more profitable app profiles for the App Store and Google Play markets.
- Python for Data Science: Fundamentals (Part I and II)
- This project aims to take some conclusions about which posts from Hacker News receive more comments.
- Python for Data Science: Intermediate
- This project aims to explore the data details of used cars sold in eBay.
- Pandas and NumPy Fundamentals
- Objective: Explore the dataset and tried to find some details about what kind of cars we have in this dataset.
- I propose myself to tried to reply to following questions in the point 4 of this project:
- 4.1 - What are the most commons brands?
- 4.2 - What are the relation between the most commons brands and its mean price?
- 4.3 - What are the relation between the most commons brands and its mean odometer?
- 4.4 - What are the most common brand/model combination?
- 4.5 - How much cheaper are cars with damage than their non-damaged counterparts?
- 4.6 - How much expensive are cars with automatic gearbox?
- 4.7 - How is the price evoluation according to the vehicle type?
- Created filters on data to find replies for these questions https://github.com/midlourenco/Dataquest.io/blob/main/project_3-%20used%20cars%20eBay/20210707_projecto3.ipynb
- This project aims to find heavy traffic indicators on I-94.
- Data Visualization Fundamentals
- Objective: Tried to identify the correlation between variables, to find what could be the factors that cause heavy traffic in the highway I-94. * during day time vs night time * during working days vs weekend
- Cleaning dataset and using groupby() function to manipulate the information and create the graphics
- Created exploratory graphics: histograms, line plot, horizontal bar plot, scatter plots and made a grid chart with small multiple graphics
- Reach the oportuniy to explore a little more about how to customise plots using Matplotlib (still without use the styles), adding grid with customised linestyle and Seaborn options. https://github.com/midlourenco/Dataquest.io/blob/main/project_4-%20heavy%20traffic%20indicators/20210719-%20project4%20-%20heavy%20traffic%20indicators.ipynb
- Evolution of Euro daily exchange rates
- Storytelling Data Visualization and Information Design
- Objective: In this project we focus on evolution of EUR/USD rate and related its evolution with some historical facts: * During financial crises (2008) * COVID-19 pandemic (2020)
- Cleaned the dataset and made few exploratory graphic to identify what kind of data we have on hands.
- Created explanatory graphics which should be enough to let audience easily understand the storyline just checking graphics
- Focus on remove excess ink and in gestalt principles
- Used style "fivethirtyeight" and customized each plot to reach this project goal; use verticial line/horizontal line, added span areas and used arrow to identify a specific point in graphics https://github.com/midlourenco/Dataquest.io/blob/main/project_5-%20euro%20daily%20exchange%20rates/20210817%20-%20Project%205%20-%20euro%20exchange%20rate.ipynb
- Clean and Analyze Employee Exit Surveys from 2 organization in Australia
- Objectives: To find the different factors that affect employee resignations and identify the relation between dissatisfaction and the lenght of period that employee worked at the institute.
- To reach this goal we applied following tools for data cleaning and analyze. * Vectorized string methods to clean string columns * The apply(), map(), and applymap() methods to transform data * The fillna(), dropna(), and drop() methods to drop missing or unnecessary values * The melt() function to reshape data * The concat() and merge() functions to combine data * Basic Regular Expressions * Create customized dataframe bins with specific label * Create pivot table, pie plots and bar plots to show the results
- https://github.com/midlourenco/Dataquest.io/blob/main/project_6%20-%20clean%20and%20analyze%20employee%20exit%20surveys/20210903%20-%20Project%20No.%206%20-%20%20Clean%20and%20Analyze%20Employee%20Exit%20Surveys.ipynb