The following steps will serve as a guideline to extract numerical measures statistics from the previous data frame:

Load the notebook with commands developed in step 2.2. (click on the link):

https://colab.research.google.com/drive/1nBs9HfaD2l3BxVTUB48OT-9ZhqMRlnh6?usp=sharing

Use the command describe() for all columns in data frame df1: 

df1.describe()

To obtain statistics from the column 'January 2022' is necessary to convert all values to float and then apply the command describe(). Additionally, the result could be stored in a variable called statistics:

statistics = df1['January 2022'].astype(float).describe()

count 9.700000e+01 

mean 2.374360e+05 

std 4.922685e+05 

min 6.420000e+02 

25% 1.558200e+04 

50% 7.375400e+04 

75% 2.266370e+05 

max 3.212252e+06 

Name: January 2022, dtype: float64 

The command round(2) applied in the variable statistics helps to visualize the statistical values with two decimals:

statistics.round(2)

count 97.00 

mean 237435.99 

std 492268.52 

min 642.00 

25% 15582.00 

50% 73754.00 

75% 226637.00 

max 3212252.00 

Name: January 2022, dtype: float64 

Another interesting result could be achieved by selecting the product categories with the top ten highest values in column 'January 2022' stored in the variable df1_descendent_order (created in section 2.2). Select the first ten rows, and the second and third columns using the command iloc[list(range(0,10)),[1, 2]]. The complete command is as follows:

top_ten_products = df1_descendent_order.iloc[list(range(0,10)),[1, 2]]