| import pandas as pd | |
| # Load the data | |
| df = pd.read_csv('data/adult.csv', na_values='?') | |
| # Dataset Overview | |
| df.head() # preview a sample | |
| df.shape # number of observations and features | |
| # (32561, 15) | |
| df.dtypes # data types | |
| #age int64 | |
| #workclass object | |
| #fnlwgt int64 | |
| #education object | |
| # (...) | |
| df[df.duplicated()] # check duplicated rows | |
| df.isna().sum() # missing values per feature | |
| #age 0 | |
| #workclass 1836 | |
| #fnlwgt 0 | |
| # (...) | |
| df.isna().sum().sum() # number of missing cells | |
| round(df.isna().sum().sum() / df.size * 100, 1) # percentage of missing cells |