Python Dash: Final Project

In this app, there is some statistical analysis about the Craiglist vehicles data set and the Bank Churners data set. We will find the following pages:

1. Introduction: There are an introduction for both problems and the description of the variables we are going to use.


2. Vehicles: Data description: There is the data frame description of the vehicles data set, where we can show a different number of entries, search any value or sort the variables.


3. Vehicles: Descriptive analysis: In the following panel, we are able to observe two tabs, one for the numerical variables where we can see their histogram, and the other one for the categorical ones, where we can see their barplots to see the relationship between our target variable and the rest of predictors.


4. Vehicles: Statistical models: In this page, we can perform some statistical and machine learning models, selecting the partition of the data that goes in the training set, the variables that will be employed, and the model, which can be logistic regression (glm), k nearest neighbors (knn) or random forest (rf).


5. Bank Churners: Data description: There is the data frame description of the bank churners data set, where we can show a different number of entries, search any value or sort the variables.


6. Bank Churners: Visual plots: In this panel, you can select the numerical variable according to the most relevant categorical variables. Moreover, as the response variable in this case is income, it is important to have this reference as well. Besides, you are able to display the proportion of customer according some categorical variables


7. Bank Churners: Regression model: In this panel, you are able to plot the account in relation to the amount, so in this panel you can see the customers and label them by card type. Finally, you can see the information of the customer you will choose


8. References

Amalia Jiménez Toledano and Roberto Jesús Alcaraz Molina.