This is a study project using fictional data from Kaggle, available in http://kaggle.com/harlfoxem/housesalesprediction
Some examples available in the notebook:
- 1.1 Basic Operations Tasks:
- How many houses are available for purchase?
- What is the most expensive house?
- What is the average house price for homes with 2 bathrooms?
- From the houses that have living rooms over 300 square meters, how many have more than 2 bathrooms?
- 1.2 Data Manipulation Tasks:
- Create a new column called dormitory type
- Change the data type of 'yr_renovated' to DATE
- What is the earliest renovation in the dataset?
- How many houses are "good" and considered "new_houses"?
- 1.3 Data Structure Tasks:
- Create bars graph for the sum of prices by number of bedrooms
- Create line graph for average price by built year
- Create bars graph for average price by dormitory type
- Create a Dashboard with the previous 3 graphs.
- 1.4 Control Structures Tasks:
- Add information in the dataset using API requests.
- Create a Map view with filters.
- Create dashboard views with filters.
- jupyter notebook
- pandas
- numpy
- matplotlib
- seaborn
- geopy
- requests
- multiprocessing
- plotly
- ipywidgets
- Use the project data to find valuable business insights.
- Publish the findings using Streamlit and Heroku.
- Organize the code using functions.