Uploaded August 2023 | Updated November 2026, 3 hours ago
In this video I use a free LLM AI tool named Claude dot ai. You can find it at claude.ai
Claude dot AI work very much like ChatGPT. Instead of having to pay for ChatGPT Plus to get access to the code interprter, this built-in for free with Claude dot AI. This mean we can upload a CSV spreadsheet file and use prompts to analyze the data.
The data file that I use in this tutorial is heartLLM.csv and is availabe on GitHub.
The prompts that I use in the tutorial are given below.
The CSV file contains 7 columns. Age describes the age of participants in years, BinarySex describes the gender of each participant, with two classes, M for male and F for female. Cholesterol is the serum cholesterol in mg/dL. RestingECG is a multilevel variable with classes Normal for a normal ECG, ST for ST-segment elevation, and LVH for left-ventricular hypertrophy. MaxHR is a continuous variable measured in beats per minute describing the maximum heart rate reached during exercise. ExerciseAngina is a binary variable with two classes, N for no and Y for yes and describes whether angina was induced by exercise. HeartDisease is a binary response variable a with 0 for no heart disease and 1 for the presence of heart disease. There are 918 observations in the data file.
Calculate summary statistics of the Cholesterol column. Include the count, mean, median, variance, standard deviation, minimum, maximum, range, quartiles, and the interquartile range.
Create a histogram of the Cholesterol column.
Create R code to generate a histogram of the Cholesterol column. Add the title "Cholesterol distribution". Add the horizontal axis title "Cholesterol". Add the vertical axis label "Count".
Use the Python seaborn package to create a histogram with kernel density estimate of the Cholesterol column. Add the title "Cholesterol distribution". Add the horizontal axis title "Cholesterol". Add the vertical axis label "Count". Add a grid to the plot.
Create a contingency table of observed values using the HeartDisease and RestingECG columns.
Create a contingency table of expected values using the HeartDisease and RestingECG columns.
Perform a chi-square test for independence to determine if the HeartDisease variable is independent of the RestingECG variable. Use a 5% level of significance. Write a comment about the results.
In this video I use a free LLM AI tool named Claude dot ai. You can find it at claude.ai
Claude dot AI work very much like ChatGPT. Instead of having to pay for ChatGPT Plus to get access to the code interprter, this built-in for free with Claude dot AI. This mean we can upload a CSV spreadsheet file and use prompts to analyze the data.
The data file that I use in this tutorial is heartLLM.csv and is availabe on GitHub.
The prompts that I use in the tutorial are given below.
The CSV file contains 7 columns. Age describes the age of participants in years, BinarySex describes the gender of each participant, with two classes, M for male and F for female. Cholesterol is the serum cholesterol in mg/dL. RestingECG is a multilevel variable with classes Normal for a normal ECG, ST for ST-segment elevation, and LVH for left-ventricular hypertrophy. MaxHR is a continuous variable measured in beats per minute describing the maximum heart rate reached during exercise. ExerciseAngina is a binary variable with two classes, N for no and Y for yes and describes whether angina was induced by exercise. HeartDisease is a binary response variable a with 0 for no heart disease and 1 for the presence of heart disease. There are 918 observations in the data file.
Calculate summary statistics of the Cholesterol column. Include the count, mean, median, variance, standard deviation, minimum, maximum, range, quartiles, and the interquartile range.
Create a histogram of the Cholesterol column.
Create R code to generate a histogram of the Cholesterol column. Add the title "Cholesterol distribution". Add the horizontal axis title "Cholesterol". Add the vertical axis label "Count".
Use the Python seaborn package to create a histogram with kernel density estimate of the Cholesterol column. Add the title "Cholesterol distribution". Add the horizontal axis title "Cholesterol". Add the vertical axis label "Count". Add a grid to the plot.
Create a contingency table of observed values using the HeartDisease and RestingECG columns.
Create a contingency table of expected values using the HeartDisease and RestingECG columns.
Perform a chi-square test for independence to determine if the HeartDisease variable is independent of the RestingECG variable. Use a 5% level of significance. Write a comment about the results.










