---
title: Virgil - Descriptive Statistics - S41 Correlation Heatmap
tags: Virgil, LearnWorld, DescriptiveStatistics
---
<a target="_blank" href="https://colab.research.google.com/drive/1Yn86m2WWdwos15Na42LhKFW6WMjibEh8"><img src="https://www.tensorflow.org/images/colab_logo_32px.png" />Run in Google Colab</a>

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

# CORRELATION: Scatter Plot & Heatmap

df = pd.read_csv('https://raw.githubusercontent.com/dhminh1024/practice_datasets/master/titanic.csv')
df.head()

<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

.dataframe tbody tr th {
vertical-align: top;
}

.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>PassengerId</th>
<th>Survived</th>
<th>Pclass</th>
<th>Name</th>
<th>Sex</th>
<th>Age</th>
<th>SibSp</th>
<th>Parch</th>
<th>Ticket</th>
<th>Fare</th>
<th>Cabin</th>
<th>Embarked</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>1</td>
<td>0</td>
<td>3</td>
<td>Braund, Mr. Owen Harris</td>
<td>male</td>
<td>22.0</td>
<td>1</td>
<td>0</td>
<td>A/5 21171</td>
<td>7.2500</td>
<td>NaN</td>
<td>S</td>
</tr>
<tr>
<th>1</th>
<td>2</td>
<td>1</td>
<td>1</td>
<td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>
<td>female</td>
<td>38.0</td>
<td>1</td>
<td>0</td>
<td>PC 17599</td>
<td>71.2833</td>
<td>C85</td>
<td>C</td>
</tr>
<tr>
<th>2</th>
<td>3</td>
<td>1</td>
<td>3</td>
<td>Heikkinen, Miss. Laina</td>
<td>female</td>
<td>26.0</td>
<td>0</td>
<td>0</td>
<td>STON/O2. 3101282</td>
<td>7.9250</td>
<td>NaN</td>
<td>S</td>
</tr>
<tr>
<th>3</th>
<td>4</td>
<td>1</td>
<td>1</td>
<td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>
<td>female</td>
<td>35.0</td>
<td>1</td>
<td>0</td>
<td>113803</td>
<td>53.1000</td>
<td>C123</td>
<td>S</td>
</tr>
<tr>
<th>4</th>
<td>5</td>
<td>0</td>
<td>3</td>
<td>Allen, Mr. William Henry</td>
<td>male</td>
<td>35.0</td>
<td>0</td>
<td>0</td>
<td>373450</td>
<td>8.0500</td>
<td>NaN</td>
<td>S</td>
</tr>
</tbody>
</table>
</div>

num = df[['Survived', 'Pclass', 'Age', 'SibSp', 'Parch', 'Fare']]
num.corr()

<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

.dataframe tbody tr th {
vertical-align: top;
}

.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>Survived</th>
<th>Pclass</th>
<th>Age</th>
<th>SibSp</th>
<th>Parch</th>
<th>Fare</th>
</tr>
</thead>
<tbody>
<tr>
<th>Survived</th>
<td>1.000000</td>
<td>-0.338481</td>
<td>-0.077221</td>
<td>-0.035322</td>
<td>0.081629</td>
<td>0.257307</td>
</tr>
<tr>
<th>Pclass</th>
<td>-0.338481</td>
<td>1.000000</td>
<td>-0.369226</td>
<td>0.083081</td>
<td>0.018443</td>
<td>-0.549500</td>
</tr>
<tr>
<th>Age</th>
<td>-0.077221</td>
<td>-0.369226</td>
<td>1.000000</td>
<td>-0.308247</td>
<td>-0.189119</td>
<td>0.096067</td>
</tr>
<tr>
<th>SibSp</th>
<td>-0.035322</td>
<td>0.083081</td>
<td>-0.308247</td>
<td>1.000000</td>
<td>0.414838</td>
<td>0.159651</td>
</tr>
<tr>
<th>Parch</th>
<td>0.081629</td>
<td>0.018443</td>
<td>-0.189119</td>
<td>0.414838</td>
<td>1.000000</td>
<td>0.216225</td>
</tr>
<tr>
<th>Fare</th>
<td>0.257307</td>
<td>-0.549500</td>
<td>0.096067</td>
<td>0.159651</td>
<td>0.216225</td>
<td>1.000000</td>
</tr>
</tbody>
</table>
</div>

# Heatmap using Pandas style module
num.corr().style.background_gradient(cmap='Reds')

sns.pairplot(data=num, corner=True);

[MORE AMAZING EXAMPLE USING .STYLE](https://pandas.pydata.org/pandas-docs/stable/user_guide/style.html)

# Heatmap using Seaborn 
sns.heatmap(data=num.corr(), annot=True, fmt='.2f');