Storytelling-Data-and-Hypotesis-Testing

URl Heroku is https://hillidatul-ftds-001-p0m1.herokuapp.com/

Dasbord Heroku

Assignment Problems

The CEO of the online store "The Look" suspects that there is something wrong with the sales system in his shop, in terms of product sales performance, delivery of goods, etc. Please help reveal whether or not there is a problem with the sales system on the platform. Use thelook_ecommerce dataset on Google Cloud Platform BigQuery.

Dataset Information

The dataset used is from Google Cloud Platform BigQuery. Then identify and describe the problem based on the dataset that will be used, in order to make it easier for you to carry out the analysis. Can use any method such as SWOT analysis, Fish bone diagram, 5W+1H, etc

Storytelling and visualization

• Central Tendency

One of the most important aspects to describe the distribution of data is the value of the center of observation. There are four types of measures of central tendency used, namely Mean, Median and Mode.

• Dispersion

The size of the spread of data as a measure that states how big the deviation of the data values from the central value is. There are three types of spread measures that will be used, namely Range, Variance and Standard Deviation.

• Storytelling

Will be displayed in the form of a bar chart, pie chart, scatterplot which will explain the storytelling of the case based on the visualization results.

Hypotesis Testing

Hypothesis testing is a decision-making method based on data analysis, both from controlled experiments, and from observations (uncontrolled). After all the data is clean of missing values and oulier, the next stage of analysis can be carried out. The testing hypothesis that I use in solving the case of order items & products is One Sample T-Test One Tailed and Independent Sample T-Test.

Process Concept Completion

• Identification of problems. This chapter must include the topic of the problem and the description of the problem to be analyzed using statistical methods and data visualization.
• Data Loading & Queries. This section contains the process of data loading and simple data exploration. Include the SQL query for each data that is loaded.
• Data Cleaning. This section contains the process of preparing data in the form of data cleaning before further data exploration is carried out. The cleaning process can be in the form of giving a new name for each column, filling in missing values, deleting unused columns, and so on.
• Analysis and calculation. This section contains the process of analysis, explanation, calculation of descriptive statistics, inferential, and the creation of data visualization. For data visualization, it is mandatory to provide insight in each visualization.
  1. For Visualization layout:
     • There are at least 4 figures/data visualizations displayed on the Visualization page that match the ones made on the Notebook.
     • There must be at least 1 streamlit interactivity
  2. For the Statistical Analysis layout:
     • Write the process of descriptive and inferential statistical analysis carried out in a notebook from the problems raised to the conclusions of the results of statistical analysis.
• Conclusion. In this last chapter, it must contain conclusions that reflect solutions/recommendations/answers to the problems raised and draw common threads from all analyzes and calculations in a concise, clear, and concise manner.

Reference

• https://docs.streamlit.io/
• https://www.smartstat.info/materi/statistika/statistik-deskriptif/statistika-deskriptif.html#:~:text=Terdapat%20dua%20metode%20dasar%20dalam%20statistik%20deskriptif%2C%20yaitu%20numerik%20dan%20grafis.
• https://medium.com/geekculture/how-to-run-your-streamlit-apps-in-vscode-3417da669fc