how to analysis the heatmap to find the correlation

+1 vote
Sep 28, 2019 in Machine Learning by Vikas
• 130 points

1 answer to this question.

0 votes

Hi @Vikas, there are 5 simple steps to analyze the heatmap correlation:

1. Import data

data = pd.read_csv('file_clean.csv')

2. Create correlation matrix. .corr() is used to create the correlation matrix. You'll have to make sure that all the elements in the matrix are of numeric type. If they are not of the numeric type you'll have to add or concat them explicitly.

corr = data.corr()

3. Create heatmap in seaborn:

ax = sns.heatmap(
    vmin=-1, vmax=1, center=0,
    cmap=sns.diverging_palette(20, 220, n=200),

You'll see something like this where the blue indicates positive and red indicates negative. 

Now to start analyzing the heatmap correlation, ask yourself this question:

What's the weakest and strongest correlation pair?

I am assuming its difficult to analyze right? 

Now according to your dataset, you need to create a scatter plot which makes it easier to analyze.

def heatmap(x, y, size):
    fig, ax = plt.subplots()
    # Mapping from column names to integer coordinates
    x_labels = [v for v in sorted(x.unique())]
    y_labels = [v for v in sorted(y.unique())]
    x_to_num = {p[1]:p[0] for p in enumerate(x_labels)} 
    y_to_num = {p[1]:p[0] for p in enumerate(y_labels)} 
    size_scale = 500
    ax.scatter(, # Use mapping for x, # Use mapping for y
        s=size * size_scale, # Vector of square sizes, proportional to size parameter
        marker='s' # Use square as scatterplot marker
    # Show column labels on the axes
    ax.set_xticks([x_to_num[v] for v in x_labels])
    ax.set_xticklabels(x_labels, rotation=45, horizontalalignment='right')
    ax.set_yticks([y_to_num[v] for v in y_labels])
data = pd.read_csv('')
columns = ['bore', 'stroke', 'compression-ratio', 'horsepower', 'city-mpg', 'price'] 
corr = data[columns].corr()
corr = pd.melt(corr.reset_index(), id_vars='index') # Unpivot the dataframe, so we can get pair of arrays for x and y
corr.columns = ['x', 'y', 'value']

You'll get something like this:

Make a few modifications(get the plots in between the grid)

ax.grid(False, 'major')
ax.grid(True, 'minor')
ax.set_xticks([t + 0.5 for t in ax.get_xticks()], minor=True)
ax.set_yticks([t + 0.5 for t in ax.get_yticks()], minor=True)

And you are good to go!
Have a look at this blog:

answered Sep 30, 2019 by Vishal
I tried the code sample you have given above. Everything seems fine except the graphs(both) not showing. Any idea? Thanks !
Are you trying to plot both the graph in a single window? Or explain your query a little bit.

Related Questions In Machine Learning

0 votes
1 answer

How to import the BatchNormalization function in Keras?

Hi@akhtar, The general use case is to use ...READ MORE

answered Jul 29, 2020 in Machine Learning by MD
• 95,320 points
0 votes
1 answer

How to determine the correct kernel function?

Hi@Ogun, It depends on your dataset. First thing ...READ MORE

answered Oct 12, 2020 in Machine Learning by MD
• 95,320 points
0 votes
1 answer
0 votes
1 answer

How to compare expected and predicted values?

The predict() function returns a plain numpy ...READ MORE

answered Jul 14, 2019 in Machine Learning by Tina
0 votes
0 answers

How to know if a problem is solvable by machine learning?

I have recently started learning the machine. ...READ MORE

Nov 21, 2019 in Machine Learning by Hannah
• 18,570 points
0 votes
1 answer

How to save machine learning model?

Hi@akhtar, To save your Machine Learning model, you ...READ MORE

answered Apr 13, 2020 in Machine Learning by MD
• 95,320 points
0 votes
1 answer

How to import one Machine Learning model?

Hi@akhtar, To import one pre-created ML model, you ...READ MORE

answered Apr 13, 2020 in Machine Learning by MD
• 95,320 points
0 votes
1 answer

How to add one new column in an existing dataset?

Hi@akhtar, You can do this task using numpy ...READ MORE

answered Apr 17, 2020 in Machine Learning by MD
• 95,320 points
0 votes
1 answer
+1 vote
1 answer