Simple data analysis project based on Netflix records, which provides a wealth of information on the Netflix situation.
The goal is to demonstrate and compare the most popular models available today.
With the help of libraries such as numpy, pandas, seaborn, and matplotlib, the visualization becomes pretty simple and intuitive. Which were useful for doing a large number of operations in order to provide precise and accurate results.
This programme takes Netflix's previous to present records as an input and analyses and constrains the data records to produce precise and accurate findings that conclude a lot of information that will be useful for the company's and other's growth.
This resolves a lot of question which will be beneficial for all kind of genre.
We can quickly visualize, understand, and compare data (such as the number of movies that have increased or decreased, and the number of TV series that have increased or decreased and much more) throughout the globe with the use of graphs, bar and pie plots, Tree Maps, and Heatmaps as an output.
This project is written in Python using the Anaconda distribution platform, which includes support for Jupyter notebook.
- NumPy : 1.18.5
- Pandas : 1.18.5
- Seaborn : 1.18.5
- Matplotlib : 1.18.5
After installation, download the above files present in the repository to our system and open the EDA.ipynb file in Anaconda or another text editor and run individual block of code to see the results.
- Compare countries data with simple and easy-to-understand plots that show results over year added through time.
- Why has Netflix's Video Count Increased So Much?
Netflix has clearly established itself as the largest company in the film/drama industry. Let's take a look at how Netflix has grown and what it means in terms of data.
- Using wiki data Netflix(wiki).
- Timeline of Netflix
- Now let's see Which country is the most productive in terms of content creation?
We can also utilise TreeMap mosaic graphs, etc., which are suitable for structural tree data and can be used for huge comparisons.
- Finding a link between the months we can relate highest count in a particular month
The graph shows that November 2019 saw a high number of Netflix content updates.
Contributions for pull requests are welcomed. Please first start an issue to discuss what you'd like to change before making any big modifications.
Please ensure that tests are updated as needed.
To sum up our analysis, we have gathered a lot of data that will be valuable in the future for improving our strategies our relationships applied on data sets or methodologies for company growth.
Referenced from link