No show appointments Data Analysis Project

Overveiw

This dataset is about medical appointments in Brazil, a sample over 100k the information of this dataset is collected from. the questions of this dataset strongly focus on Why do 30% (approximately) of patients miss their scheduled appointments?

The Original problem and data set can be found in the following link:
https://www.kaggle.com/code/minaanis/no-show-appointment-data-set

Questions for Analysis

• What is the probability (in percent) that the reason of causing patients to miss their appointments is that the patients have: Scholarships, Hipertension, Diabetes, Alcoholism or at least one Handcap.
• What is the effectivness of the SMS on patients? Or does the SMS reduce the percentage of those who missed their appointment?
• What is the Neighbourhood that has the biggest no show patients?
• What is the average ages who missed their appointments? and what is the most no show age?
• Who misses their appointments more, men or women?
• Is there a relationship between age and waiting days?

Conclusions

• 1. Patients who have scholarships is more likely to miss their appointments with probability of %23.7 than the other reasons! and the reason that came after that is Alcoholism with probaility of %20.1.
• 2. The result of comparason between who received SMS and who didn't, to see if the SMS is an effective way to reduce the miss of appointment.

The percentage of patients who missed and who didn't miss their appointment in the first bar char (Received SMS) :

• who missed their appointment: %27.6.
• who did not miss their appointment: %72.4.
  

In the second bar chart (Did not receive SMS):

• who missed their appointment: %16.7.
• who did not miss their appointment: %83.3.

• 3. the neighbourhood that has the biggest no show patients is JARDIM CAMBURI.
• 4. the Avarage ages that missed their appointments is about 34 with a standard diviation 21.965. And the 17th age is the age that missed the appointment too much.
• 5. Females is slightly missing their appointment more than men (with %0.8 difference).
• 6. the waiting days increase approximatley at the age 20 to 80 years.

Statistical Analysis Scope

• Data Wrangling
• Exploratory Data Analysis
• Data Visualization

Tools&Libraries

• Python Libraries
  • numby
  • pandas
  • matplotlib
  • seaborn
• Jupyter notebook