EDA_seaborn_part1.py

# create a histplot of age with hue stroke to check influence of age on class stroke
sns.histplot(data=df, x="age", hue="stroke", multiple="stack")

# create histplot of gender to check if there is any influence of gender on class stroke
sns.histplot(data=df, x="gender", hue="stroke", multiple="stack")

# create histplot of smoking_satus and check influence on class stroke 
sns.histplot(data=df, x="smoking_status", hue="stroke", multiple="stack")

# here: can be interesting to also print the percentage of stroke patients of each category
count_per_group_smoked_status = df.groupby("smoking_status").count()["stroke"]
count_stroke_per_group = df.loc[df["stroke"] == 1].groupby("smoking_status").count()["stroke"]
groups = count_per_group_smoked_status.index.to_list()
for idx, (count, group_count) in enumerate(zip(count_stroke_per_group, count_per_group_smoked_status)):
    print(f"Percentage of stroke cases in group {groups[idx]}: {100 * count / group_count}%")

# create histplot of ever_married and check influence on class stroke
sns.histplot(data=df, x="ever_married", hue="stroke", multiple="stack")

# again: check percentage of stroke patients being married and not being married 
# could be interesting for arguing for or against a wedding ;)
# get percentage of strokes per category
count_per_group_married_status = df.groupby("ever_married").count()["stroke"]
count_stroke_per_group = df.loc[df["stroke"] == 1].groupby("ever_married").count()["stroke"]
groups = count_per_group_married_status.index.to_list()
for idx, (count, group_count) in enumerate(zip(count_stroke_per_group, count_per_group_married_status)):
    print(f"Percentage of stroke cases in group {groups[idx]}: {100 * count / group_count}%")