Outliers

Importing libraries and packages

# Mathematical operations and data manipulation
import pandas as pd

# Visualisation
import seaborn as sns
import matplotlib.pyplot as plt

# Warnings
import warnings

warnings.filterwarnings("ignore")

%matplotlib inline

Set paths

# Path to datasets directory
data_path = "./datasets"
# Path to assets directory (for saving results to)
assets_path = "./assets"

Loading dataset

# load data
dataset = pd.read_csv(f"{data_path}/preprocessed_heart.csv")
dataset.head().T

	0	1	2	3	4
age	63.0	37.0	41.0	56.0	57.0
sex	1.0	1.0	0.0	1.0	0.0
chest_pain	3.0	2.0	1.0	1.0	0.0
rest_bp	145.0	130.0	130.0	120.0	120.0
chol	233.0	250.0	204.0	236.0	354.0
fast_bld_sugar	1.0	0.0	0.0	0.0	0.0
rest_ecg	0.0	1.0	0.0	1.0	1.0
max_hr	150.0	187.0	172.0	178.0	163.0
ex_angina	0.0	0.0	0.0	0.0	1.0
st_depr	2.3	3.5	1.4	0.8	0.6
slope	0.0	0.0	2.0	2.0	2.0
colored_vessels	0.0	0.0	0.0	0.0	0.0
thalassemia	1.0	2.0	2.0	2.0	2.0
target	1.0	1.0	1.0	1.0	1.0

Checking for Outliers

sns.set(
    palette="pastel",
    rc={
        "figure.figsize": (12, 8),
        "axes.titlesize": 18,
        "axes.labelsize": 16,
        "xtick.labelsize": 16,
        "ytick.labelsize": 16,
    },
)

chol = sns.boxplot(dataset["chol"])
plt.show()

sd = sns.boxplot(dataset["st_depr"])
plt.show()

cv = sns.boxplot(dataset["colored_vessels"])
plt.show()

t = sns.boxplot(dataset["thalassemia"])
plt.show()