alod83 / data-science

Data Science for Beginners

A collection of Jupyter Notebooks, HTML and JS code for Data Scientists.

Comments on the single scripts can be found on my Medium blog as well as on my Web site.

Programming Languages

• Python 3.X
• HTML5
• Javascript, with a focus on D3.JS
• CSS

Other interesting tutorials can be found on my Observable Profile.

Authors

• @alod83

Documentation

The Project is organised in different folders, one covered topic:

• Data Collection - data extraction from HTML, Twitter, PDF ...
• Preprocessing - missing data, duplicates, normalisation, binning ...
• Data Analysis - full workflow in scikit-learn and PyCaret, as well as overfitting, Auto ML, ...
• Text Analysis - sentiment analysis, ...
• Data Visualisation - examples in Altair, Plotly, D3.js, ...
• Data Narrative - how to improve data visualisations.

data-science's Issues

about the Twitter user profile input

Hi I have a question about the input "from:" in the file get_tweets.ipynb.
I wonder what the right form of this variable is? Since when I type " from:" + " elonmusk", it didn't give me any tweets.
I am a new beginner of python, sorry if this question sound stupid.

tourist_arrivals.csv missing

In https://github.com/alod83/data-science/blob/master/DataVisualization/Altair/AltairAnimation.py, line 9:

df = pd.read_csv('../sources/tourist_arrivals.csv')

I get an error when running. I tried to find this file the site mentioned in the article https://towardsdatascience.com/how-to-run-animations-in-altair-and-streamlit-2a0624789ad, but I could not find it.

I then tried the dataset https://github.com/alod83/data-science/blob/master/DataVisualization/presenza_negli_alberghi.csv, but it failed on the column named 'Dato'

I then renamed it to 'Date', and it ran without errors, but clicking the Start button produced no output.

I like the concepts in the Streamlit program, and would like to get it running. Please advise

questions about the configuration file

Sorry I cannot find the configuration file config.py in the DataCollection/Twitter file. How can I find it? Thanks!

Twitter API object response updated

Hi Angelica

In cell 13, line 3 text = tweet._json["full_text"] will now return a keyword error as Twitter API response object has updated the text response dictionary key as text and not full_text. Kindly update your notebook. I could also submit a PR if don't mind