37 lines
1.1 KiB
Python
37 lines
1.1 KiB
Python
import pandas as pd
|
|
from sklearn.model_selection import train_test_split
|
|
import os
|
|
|
|
dataset = pd.read_csv("heart_2020_cleaned.csv")
|
|
print(dataset.describe(include='all'))
|
|
dataset = dataset.dropna()
|
|
|
|
print(dataset.describe(include='all'))
|
|
|
|
dataset_train, dataset_test = train_test_split(dataset, test_size=.2, train_size=.8, random_state=1)
|
|
|
|
print(dataset_train.describe(include='all'))
|
|
|
|
print("Wielkości:")
|
|
|
|
print("Zbiór uczący:", dataset_train.shape[0])
|
|
print("Zbiór testowy:", dataset_test.shape[0])
|
|
print("Łącznie: ", dataset.shape[0])
|
|
|
|
print(dataset["GenHealth"].value_counts())
|
|
print(dataset_train["GenHealth"].value_counts())
|
|
print("Średnia BMI -łącznie: ", dataset["BMI"].mean())
|
|
print("Odchylenie standardowe BMI - uczący:", dataset_train["BMI"].std())
|
|
print("Odchylenie standardowe BMI - łącznie:", dataset["BMI"].std())
|
|
|
|
print("Mediana BMI:", dataset_test["BMI"].median())
|
|
|
|
max_bmi = dataset_train["BMI"].max()
|
|
|
|
print(max_bmi)
|
|
dataset_train["BMI"] = dataset_train["BMI"].apply(lambda x: x/max_bmi)
|
|
dataset_test["BMI"] = dataset_test["BMI"].apply(lambda x: x/max_bmi)
|
|
print(dataset_train["AgeCategory"].value_counts())
|
|
print(dataset_train["BMI"])
|
|
|