Hello!
I’m currently working on Medical Data Visualizer using Vscode, after trying to run the function, there’s some errors in the results :
Diff is 1966 characters long. Set self.maxDiff to None to see it. : Expected different values in heat map.
I’ve tried both filter out (drop) the incorrect data from dataframe, or reverse it by keeping the correct data, but it doesn’t seem to change.
I think the problem is on the data cleaning part, but i’m stuck and can’t for the life of me find where the issues is. I’m new to python so, the solution might be obvious 
Thanks!
Your code so far
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
# Import data
df = pd.read_csv('medical_examination.csv')
# Add 'overweight' column
df['overweight'] = df['weight'] / ((df['height'] /100) ** 2 )
df['overweight'] = np.where( df['weight'] / ((df['height'] /100) ** 2 ) > 25, 1, 0)
# Normalize data by making 0 always good and 1 always bad. If the value of 'cholesterol' or 'gluc' is 1, make the value 0. If the value is more than 1, make the value 1.
df['cholesterol'] = np.where( df['cholesterol'] == 1, 0, 1)
df['gluc'] = np.where( df['gluc'] == 1, 0, 1)
# Draw Categorical Plot
def draw_cat_plot():
# Create DataFrame for cat plot using `pd.melt` using just the values from 'cholesterol', 'gluc', 'smoke', 'alco', 'active', and 'overweight'.
df_cat = pd.melt(df, value_vars=['cholesterol','gluc', 'smoke', 'alco', 'active', 'overweight'])
# Group and reformat the data to split it by 'cardio'. Show the counts of each feature. You will have to rename one of the columns for the catplot to work correctly.
df_cat = pd.melt(df, id_vars=['cardio'], value_vars=['cholesterol','gluc', 'smoke', 'alco', 'active', 'overweight'])
df_cat = pd.melt(df, id_vars=['cardio'], value_vars=['cholesterol','gluc', 'smoke', 'alco', 'active', 'overweight']).value_counts().reset_index()
df_cat['value'] = df_cat['value'].astype(str) #To avoid errors on replit, Needs to change to strings, otherwise it'll results on error
df_cat.rename(columns={'count': 'total'}, inplace=True)
df_cat.sort_values(by='variable', inplace=True)
# Draw the catplot with 'sns.catplot()'
cat_plot = sns.catplot( data=df_cat, x='variable', y='total', kind='bar', col='cardio' , hue='value' , palette='Set1' )
cat_plot.set_axis_labels('variable', 'total')
# Get the figure for the output
fig = cat_plot.figure
# Do not modify the next two lines
fig.savefig('catplot.png')
return fig
# Draw Heat Map
def draw_heat_map():
# Clean the data
df_heat = df
drop_data = df_heat[ (df_heat['weight'] >= df_heat['weight'].quantile(0.975)) #5 weight is more than the 97.5th percentile
| (df_heat['weight'] <= df_heat['weight'].quantile(0.025)) #4 weight is less than the 2.5th percentile
| (df_heat['height'] >= df_heat['height'].quantile(0.975)) #3 height is more than the 97.5th percentile
| (df_heat['height'] <= df_heat['height'].quantile(0.025)) #2 height is less than the 2.5th percentile
| (df_heat['ap_lo'] >= df_heat['ap_hi'])].index #1 diastolic pressure is higher than systolic ap_lo > ap_hi
df_heat.drop(drop_data, inplace=True)
# Calculate the correlation matrix
corr = df_heat.corr().round(1)
# Generate a mask for the upper triangle
mask = np.triu(np.ones_like(corr))
# Set up the matplotlib figure
fig, ax = plt.subplots()
# Draw the heatmap with 'sns.heatmap()'
heatmap_fig = sns.heatmap(corr, annot=True, square=True, center=0, annot_kws={'fontsize':7 }, linewidths=0.5, mask=mask)
fig = heatmap_fig.figure
# Do not modify the next two lines
fig.savefig('heatmap.png')
return fig
Your browser information:
User Agent is: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36
Challenge: Data Analysis with Python Projects - Medical Data Visualizer
Link to the challenge:
