Clinic Survey

Part of the Statistics for ML section of Coddy's Machine Learning journey. Lesson 64 of 64.

A clinic asked 48 patients about their visit: age, visit type, minutes waited and satisfaction, from poor to excellent. It is all in clinic.csv.

What drives satisfaction? Two columns are text, so encode them first. Satisfaction has an order; visit types do not:

One patient's row before and after encoding: age 58, visit follow-up, wait 30, satisfaction good becomes age 58, wait 30, satisfaction 3, then 0, 1, 0 in three visit columns for checkup, follow-up and urgent

Then every column is a number, and one heatmap shows how everything relates. The manager also wants a report per visit type and the least satisfied age group.

Challenge

Hard

The program reads a visit type. Round to 2 decimals.

Map satisfaction to 1 to 4, one-hot visit into encoded (dtype=int), keep its correlations.
For the visit type: its visits, mean wait and satisfaction, and the share unhappy (2 or less) among them and overall.
Bin ages at 17, 34, 54, 85 as 18-34, 35-54, 55-85; print the least satisfied.
Draw the matrix: coolwarm from -1 to 1, a color bar, column names on both axes, title Clinic Survey.

For another clinic and urgent:

urgent: 16 visits, mean wait 30.44, mean satisfaction 2.44
Unhappy after urgent: 0.56 (overall 0.33)
Least satisfied: 35-54 (2.6)

A heatmap titled Clinic Survey with a color bar from -1 to 1 and the six column names on both axes: age, wait_min, satisfaction, visit_checkup, visit_follow-up, visit_urgent; red diagonal, wait_min and satisfaction a deep blue pair

After your lines, Coddy describes your heatmap.

Try it yourself

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

visit = input()
df = pd.read_csv("clinic.csv")

# Write your code below

Test yourself

This lesson includes a short quiz. Start the lesson to answer it and track your progress.

All lessons in Statistics for ML

3Probability by Simulation

Probability as Frequency The Law of Large Numbers Sums of Dice Expected Value Conditional Probability Recap: Dice Stall Odds

6Relationships

Reading Scatter Plots Correlation Correlation Matrix Correlation Heatmaps Correlation Is Not Cause Recap: Ice Cream and Sun

9Feature Scaling

Why Scale Features Min-Max Scaling Standardization StandardScaler Recap: Climbing Partners

12Final Challenges

Train Delays Air Quality Wine ChemistryClinic Survey

Practice on your own: Online Python compiler