medical_data_visualizer.py

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

# 1
df = pd.read_csv('medical_examination.csv')

# 2
df['overweight'] = np.where((df['weight'] / ((df['height'] / 100) ** 2) > 25), 1, 0)

# 3
df['cholesterol'] = np.where(df['cholesterol'] <= 1, 0, 1)
df['gluc'] = np.where(df['gluc'] <= 1, 0, 1)

# 4
def draw_cat_plot():
    # 5
    df_cat = pd.melt(
        df, 
        ['cardio'], 
        ['active', 'alco', 'cholesterol', 'gluc', 'overweight', 'smoke'], 
        ['variable'], 
        'value'
    )
    #print(df_cat)

    # 6
    df_cat = df_cat.groupby(['cardio', 'variable', 'value'])['value'].count().reset_index(name='total')
    #print(df_cat)

    # 7



    # 8
    fig = sns.catplot(df_cat, kind='bar', x='variable', y='total', col='cardio', hue='value')


    # 9
    fig.savefig('catplot.png')
    return fig


# 10
def draw_heat_map():
    # 11
    df_heat = df[
        (df['ap_lo'] <= df['ap_hi']) &
        (df['height'] >= df['height'].quantile(0.025)) &
        (df['height'] <= df['height'].quantile(0.975)) &
        (df['weight'] >= df['weight'].quantile(0.025)) &
        (df['weight'] <= df['weight'].quantile(0.975))]
    
    # print(df_heat)

    # 12
    corr = df_heat.corr()
    corr = corr.round(1)

    # 13

    # Generate a mask for the upper triangle
    mask = np.triu(np.ones_like(corr, dtype=bool))

    # mask = df_heat.mask()

    # 14
    fig, ax = plt.subplots(figsize=(12, 12))

    # 15
    ax = sns.heatmap(corr, mask=mask, ax=ax, annot=True,
                     robust=True,  fmt='.1f', linewidths=0.5, center=0, square=True)
    fig = ax.get_figure()

    # 16
    fig.savefig('heatmap.png')
    return fig