Centrality and Dispersion¶

Exercise 1: Set up Python¶

Make sure you have a Python installation that allows you to create and execute Jupyter Notebooks. You find instructions on www.academis.eu/pandas_go_to_space/preparations/README.html

For the following exercises you will need a spreadsheet with student data that you created in class.

Put the spreadsheet into the same folder as your Python notebook. Execute the following piece of Python code:

import pandas as pd
from matplotlib import pyplot as plt

df = pd.read_excel("students.xlsx")
df.head()

If that works, also insert a column name in the next piece of code:

count = df["..."].value_counts()
count

Finally, create a plot with several bars:

count.plot.bar()

Now calculate the mean number of characters in our names. The following Python code contains 3 bugs. Find and fix them.

import pandas as pd

pd.read_excel("students.xlsx"

mean = df[chars_in_name].mean()
print(f"average number of characters : {mean:4.2f}")

Replace the mean() function by median() and mode(). To print the mode you need to leave away the :4.2f.

Examine the result.

Modify one the first entry to a very high number:

df.loc[0, "chars_in_name"] = 100
print(df.head())

Repeat the calculation of the mean and median. How do the metrics change?

Use the functions std(), min(), max() and describe() to examine the dispersion of the variable.

Examine the effect of adding the outlier on these numbers as well.

Draw a box plot showing the distribution of characters for different transportation modes.

df["chars_in_name"].plot.box()

If you have a local Python installation (with Anaconda), you can create a nicer plot with:

import seaborn as sns
import pandas as pd

df = pd.read_excel("students.xlsx")
sns.boxplot(data=df, y="chars_in_name", hue="transportation")

Draw a histogram using the previously loaded data and libraries:

df[“chars_in_name”].hist(bins=10)

If you have a local Python installation (with Anaconda), you can create a nicer plot with:

sns.histplot(
    data=df,
    x="chars_in_name",
    bins=10,
)

Try out different numbers for bins and see how the result changes. Also try setting kde=True.

Examine the student data further. Write a news headline summarizing your findings and post it in the course channel.

Examine the penguin data in the spreadsheet penguins.xlsx. Solve the following tasks to examine the beak length variable:

How would you interpret the result?