Here is my code it does create the 2 maps as requested but I do get the following error and not sure where or what it means can someone help.
here is the error.
python main.py
Matplotlib created a temporary config/cache directory at /tmp/matplotlib-09zxtysk because the default path (/config/matplotlib) is not a writable directory; it is highly recommended to set the MPLCONFIGDIR environment variable to a writable directory, in particular to speed up the import of Matplotlib and to better support multiprocessing.
Traceback (most recent call last):
File “main.py”, line 6, in
medical_data_visualizer.draw_cat_plot()
TypeError: draw_cat_plot() missing 1 required positional argument: ‘df’
exit status 1
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
def bmi(df):
weight = df['weight']
height = df['height']/100
bmi = weight/(height**2)
if bmi > 25:
return 1
else:
return 0
df['overweight'] = df.apply(bmi,axis=1)
# 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.
def cholestrol(df):
if df['cholesterol'] > 1:
return 1
else:
return 0
df["cholesterol"] = df.apply(cholestrol, axis=1)
def gluc(df):
if df["gluc"] >1:
return 1
else:
return 0
df['gluc'] = df.apply(gluc, axis=1)
# Draw Categorical Plot
def draw_cat_plot(df):
print(df.head())
# Create DataFrame for cat plot using `pd.melt` using just the values from 'cholesterol', 'gluc', 'smoke', 'alco', 'active', and 'overweight'.
df_cat = df[['cholesterol', 'gluc', 'smoke', 'alco', 'active','overweight', 'cardio']]
melt_new = pd.melt(df_cat, id_vars='cardio').value_counts()
# 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_melt = melt_new.groupby(['cardio', 'variable', 'value']).sum().reset_index(name='total')
#fig, ax = plt.subplots(figsize=(9,9))
# Draw the catplot with 'sns.catplot()'
fig = sns.catplot(x='variable', y= 'total', hue='value', col='cardio', aspect=0.4, data=df_melt, kind='bar')
# Do not modify the next two lines
fig.savefig('catplot.png')
return fig
# Draw Heat Map
def draw_heat_map(df):
# Clean the data
df= df[df['ap_lo']<=df['ap_hi']]
height_0025 = df['height'].quantile(0.025)
height_0975 = df['height'].quantile(0.975)
weight_0025 = df['weight'].quantile(0.025)
weight_0975 = df['weight'].quantile(0.975)
df_heat = df[((df['height'] >=height_0025) & (df['height']<= height_0975)&(df['weight'] >=weight_0025) & (df['weight']<= weight_0975))]
# Calculate the correlation matrix
corr = df_heat.corr()
# Generate a mask for the upper triangle
mask = np.zeros_like(corr)
mask[np.triu_indices_from(mask)] = True
# Set up the matplotlib figure
fig,ax = plt.subplots()
#plt.figure(figsize=(15,15))
# Draw the heatmap with 'sns.heatmap()'
ax = sns.heatmap(corr, mask=mask, annot=True, annot_kws={'size':10},fmt='.1f')
# Do not modify the next two lines
fig.savefig('heatmap.png')
return fig
draw_cat_plot(df)
draw_heat_map(df)