#!/usr/bin/env python
# coding: utf-8

# ---   
#  <img align="left" width="75" height="75"  src="https://upload.wikimedia.org/wikipedia/en/c/c8/University_of_the_Punjab_logo.png"> 
# 
# <h1 align="center">Department of Data Science</h1>
# <h1 align="center">Course: Tools and Techniques for Data Science</h1>
# 
# ---
# <h3><div align="right">Instructor: Muhammad Arif Butt, Ph.D.</div></h3>    

# <h1 align="center">Lecture 3.25 (Data Visualization-V)</h1>

# <a href="https://colab.research.google.com/github/arifpucit/data-science/blob/master/Section-3-Python-for-Data-Scientists/Lec-3.25(Data-Visualization-V).ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

# ## _Data Visualization with Seaborn_
# 
# **Read Documentation for details:** 
# https://seaborn.pydata.org

# <img align="left" width="500" height="500"  src="images/intromatlab.png"  >
# <img align="right" width="400" height="500"  src="images/matplotlibadvantages.png"  >

# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ## Learning agenda of this notebook
# 1. Overview of Seaborn Library
# 2. Download and Install Seaborn
# 3. Built-in Datasets of Seaborn Library
# 4. Plotting with Seaborn
#     - The `relplot()` method
#     - The `displot()` method
#     - The `catplot()` method

# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ## 2. Download and Install Seaborn Library

# In[ ]:


# To install this library in Jupyter notebook
import sys
#!{sys.executable} -m pip install --upgrade pip
get_ipython().system('{sys.executable} -m pip install seaborn --quiet')


# In[1]:


import seaborn as sns
sns.__version__ , sns.__path__


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ## 3. Built-in Sets of Seaborn Library

# In[4]:


# To handle URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] ... unable to get local issuer certificate>
import ssl
ssl._create_default_https_context = ssl._create_unverified_context

print(sns.get_dataset_names())


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### a. CAR_CRASHES Dataset

# In[6]:


import seaborn as sns
df_cc = sns.load_dataset('car_crashes')
df_cc.head()


# In[7]:


df_cc.shape


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### b. FLIGHTS Dataset

# In[8]:


df_flights = sns.load_dataset('flights')
df_flights


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### c. TIPS Dataset

# In[9]:


df_tips = sns.load_dataset('tips')
df_tips


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### d. IRIS Dataset
# <img align="center" width="700" height="500"  src="images/iris.png"  >

# In[ ]:





# In[10]:


df_iris = sns.load_dataset('iris')
df_iris


# In[11]:


df_iris['species'].value_counts()


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### e. TITANIC Dataset
# <img align="center" width="600" height="300"  src="images/titanic_sinking.jpeg"  >

# In[14]:


df_titanic = sns.load_dataset('titanic')
df_titanic.head()


# In[13]:


df_titanic.shape


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ## Programming with Seaborn

# #### Option 1: (Use Axes-Level Functions)

# In[15]:


import seaborn as sns
from matplotlib import pyplot as plt
fig, ax = plt.subplots()
sns.boxplot(x='sex', y='age', data=df_titanic, ax=ax);


# #### Option 2: (Use Figure-Level Functions)

# In[16]:


import seaborn as sns
sns.catplot(x ='sex', y='age', kind='box', data = df_titanic);


# In[ ]:


sns.set_context(context='paper')


# In[ ]:





# In[ ]:





# ## 4. Plotting Graphs with Seaborn
# <img align="center" width="600" height="300"  src="images/seaborn_functions.png"  >

# In[17]:


import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
#plt.style.use('fivethirtyeight')  
import warnings
warnings.filterwarnings('ignore') 


# In[18]:


sns.set_style(style='white') # 'dark', 'darkgrid' white', 'whitegrid'
sns.set_context(context='paper', font_scale=1.5) # talk', 'poster'


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### a. The `sns.relplot()` Method
# - Line Plot
# - Scatter Plot

# **Example: Line Plot**

# In[19]:


df_iris.head()


# In[20]:


df_iris.describe()


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[21]:


sns.relplot(x="sepal_width", y="sepal_length", data=df_iris,  kind='line');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[22]:


sns.relplot(x="sepal_width", y="sepal_length", data=df_iris,  kind='line', hue='species');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[23]:


sns.relplot(x="sepal_width", y="sepal_length", data=df_iris,  kind='line', hue='species', style='species');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Scatter Plot**

# In[24]:


df_tips.head()


# In[26]:


df_tips.shape


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[25]:


sns.relplot(x='total_bill', y='tip', data=df_tips, kind='scatter');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[27]:


sns.relplot(x='total_bill', y='tip', data=df_tips, kind='scatter', hue='sex');


# In[28]:


sns.relplot(x='total_bill', y='tip', data=df_tips, kind='scatter', hue='sex', style='sex');


# In[ ]:





# In[ ]:





# In[29]:


sns.relplot(x='total_bill', y='tip', data=df_tips, kind='scatter', hue='sex', style='sex', col='sex');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Sub-Plots using FacetGrid**

# In[31]:


sns.relplot(x='total_bill', y='tip', data=df_tips, kind='scatter', hue='day',col='day', col_wrap=2);


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### b. The `sns.catplot()` Method
# - Categorical estimate plots:
#     - `pointplot` (with ``kind="point"``)
#     - `barplot` (with ``kind="bar"``)
#     - `countplot` (with ``kind="count"``)
#     
# - Categorical distribution plots:
#     - `boxplot` (with ``kind="box"``)
#     - `violinplot` (with ``kind="violin"``)
#     - `boxenplot` (with ``kind="boxen"``)
# 
# - Categorical scatterplots:
#     - `stripplot` (with ``kind="strip"``; the default)
#     - `swarmplot` (with ``kind="swarm"``)

# **Example: Bar Plot**

# In[32]:


df_titanic


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[33]:


sns.catplot(x ='sex', y ='survived',kind='bar', data = df_titanic);


# In[34]:


sns.catplot(x ='sex', y ='tip',kind='bar', data = df_tips);


# In[35]:


sns.catplot(x ='size', y ='tip',kind='bar', data = df_tips);


# In[36]:


sns.catplot(x ='day', y ='tip',kind='bar', data = df_tips);


# In[ ]:





# **Example: Count Plot**

# In[37]:


sns.catplot(x ='sex',kind='count', data = df_titanic);


# In[38]:


sns.catplot(x ='day',kind='count', data = df_tips);


# In[ ]:





# In[ ]:





# In[39]:


sns.catplot(x ='sex',kind='count', data = df_titanic, hue='survived');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Box Plot**

# In[40]:


sns.catplot(x ='sex', y='age', kind='box', data = df_titanic);


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[41]:


sns.catplot(x ='sex', y='age', kind='box', data = df_titanic, hue='survived');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Violin Plot**

# In[42]:


sns.catplot(x ='sex', y='age', kind='violin', data = df_titanic);


# In[ ]:





# In[ ]:





# In[ ]:





# In[43]:


sns.catplot(x ='sex', y='age', kind='violin', data = df_titanic, hue='survived'); 


# In[ ]:


sns.catplot(x ='sex', y='age', kind='violin', data = df_titanic, hue='survived', col='survived'); 


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Strip Plot**

# In[44]:


sns.catplot(y ='age', kind='strip', data = df_titanic);


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:


sns.catplot(x ='sex', y='age', kind='strip', data = df_titanic);


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[45]:


sns.catplot(x ='sex', y='age', kind='strip', data = df_titanic, hue='survived');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Swarm Plot**

# In[46]:


sns.catplot(x ='sex', y='age', kind='swarm', data = df_titanic, hue='survived');


# In[ ]:





# In[ ]:





# **Example: Sub-Plots using FacetGrid**

# In[47]:


sns.catplot(x ='sex', y='age', kind='box', data = df_titanic, hue='survived', col='survived');


# In[ ]:





# In[ ]:





# In[ ]:





# In[48]:


sns.catplot(x ='sex', y='age', kind='box', data = df_titanic, col='survived');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### c. The `sns.displot()` Method
# - Categorical estimate plots:
#     - `histplot` (with ``kind="hist"``)
#     - `kdeplot` (with ``kind="kde"``)
#     - `ecdfplot` (with ``kind="ecdf"``)
#     

# **Example: Histogram**

# In[49]:


df_tips


# In[ ]:


df_tips.total_bill.min()


# In[ ]:


df_tips.total_bill.max()


# In[ ]:


df_tips.total_bill.mode()


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[50]:


sns.displot(x= 'total_bill', data=df_tips);


# In[51]:


sns.displot(x= 'total_bill', data=df_tips, kind='hist');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[52]:


sns.displot(x= 'total_bill', data=df_tips, kind='hist', bins=30);


# In[ ]:





# In[53]:


sns.displot(x= 'total_bill', data=df_tips, kind='hist', bins=30, hue='day');


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: KDE**

# In[54]:


sns.displot(x= 'total_bill', data=df_tips, kind='kde');


# In[ ]:





# In[ ]:





# In[ ]:





# In[55]:


sns.displot(x= 'total_bill', data=df_tips, kind='kde', fill=True)


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Histogram + KDE**

# In[ ]:





# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, kind='hist', kde=True);


# In[ ]:





# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, hue='day');


# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, hue='day', col='day');


# In[ ]:





# **Example: Adding hue**

# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, kind='kde', fill=True, hue='day');


# In[ ]:





# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, kind='kde', fill=True, hue='day')


# In[ ]:





# In[ ]:





# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, kind='kde', fill=True, hue='day')


# In[ ]:


df_tips


# In[ ]:


sns.displot(x= 'tip', data=df_tips, kind='kde', fill=True)


# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, kind='kde', fill=True)


# In[ ]:





# **Example: ECDF**

# >**Binning Bias** is a pitfall of histograms where you will get different representations of the same data as you change the number of bins of a histogram plot. Note the values along the y-axis changes as you change the number of bins

# In[ ]:


fig,ax = plt.subplots(2,2)
ax[0][0].hist(df_tips['total_bill'],bins=5);
ax[0][1].hist(df_tips['total_bill'],bins=25);
ax[1][0].hist(df_tips['total_bill'],bins=50);
ax[1][1].hist(df_tips['total_bill'],bins=100);


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:


sns.displot(x='total_bill', data=df_tips, kind='ecdf');


# In[ ]:


sns.displot(x='tip', data=df_tips, kind='ecdf');


# In[ ]:





# In[ ]:





# In[ ]:


sns.displot(x='tip', data=df_tips, kind='ecdf', hue='time');


# In[ ]:


df_tips.tip.value_counts()


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Bivariate Analysis**

# In[ ]:


sns.displot(x='total_bill', y='tip', data=df_tips, kind='hist', cbar=True)


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:


sns.displot(x='total_bill', y='tip', data=df_tips, kind='kde')


# In[ ]:





# In[ ]:


sns.displot(x='total_bill', y='tip', data=df_tips, kind='hist', hue='day', col='day')


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# **Example: Sub-Plots using FacetGrid**

# In[ ]:


sns.displot(x= 'total_bill', data=df_tips, kind='hist', hue='day', col='day');


# In[ ]:





# In[ ]: