inzynieria-uczenia-maszynowego/dataset-stats/main.py
2023-04-19 19:17:01 +02:00

26 lines
656 B
Python

# Import dependencies
import pandas as pd
# Load data
train_data = pd.read_csv('spambase.data.train.csv')
val_data = pd.read_csv('spambase.data.val.csv')
test_data = pd.read_csv('spambase.data.test.csv')
# Inspect data
print('Train data shape:', train_data.shape)
print('Val data shape:', val_data.shape)
print('Test data shape:', test_data.shape)
print()
print('Train data head:', train_data.head())
print('Val data head:', val_data.head())
print('Test data head:', test_data.head())
print()
print('Train data describe:', train_data.describe())
print('Val data describe:', val_data.describe())
print('Test data describe:', test_data.describe())